fbpx

Featured This month

  • Customisable OCT Reports: Enhancing Diagnostic Accuracy

    Сustomisable OCT reports for eye care practice enhancement
    Maria Martynova
    07.06. 2023
    8 min read

    The average OCT device is a significant investment, costing upwards of $40,000. As eye care specialists, we recognize the revolutionary power of OCT. However, patients often receive only a standard OCT report from this investment. Unfortunately, many patients are unaware of OCT’s true value and may not even know what it is. This raises a crucial question: are these standard reports truly reflecting the full diagnostic potential of such an expensive and sophisticated device? Are we, as professionals, maximizing the capabilities of this technology to ensure optimal patient care?

    This article explores how customisable OCT Reports address these shortcomings, enhancing diagnostic accuracy, treatment monitoring, referral efficiency, patient education, and audit readiness. 

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

    Common OCT reports and their limitations

    How does the standard report look?

    An example of a common OCT report

    OCT has become a golden standard for diagnosing and monitoring many ocular pathologies, thanks to its unparalleled level of detail in ophthalmic imaging.

    While retinal reports vary among OCT models, they typically include:

    • a foveally centered B-scan, 
    • a quantitative thickness map, 
    • and a semi-quantitative thickness map.

    The B-scan offers a visual snapshot of foveal architecture and confirms proper scan centering. The quantitative thickness map employs the ETDRS sector map to measure retinal thickness within a 6mm circle around the fovea, with specific measurements for the foveal sector (1mm), inner macular ring (3mm), and outer macular ring (6mm).

    Progression analytics enable comparison of serial macular scans, which is invaluable for managing vitreomacular interface disorders and macular edema. The semi-quantitative thickness map provides a broader overview of retinal thickness throughout the scan.

    Given this amount of data, it is challenging to identify subtle and localized retinal pathological changes. As a result, entire OCT datasets are represented by few aggregated values, and the standard OCT reports generated by most devices often rely on significant data reduction to simplify interpretation, which you can usually not customize. 

    Three standard methods exist for displaying OCT data

    Firstly, acquired 2D image slices are presented individually. This allows for detailed examination, but navigating through numerous images can be cumbersome, particularly with large datasets.

    Wet AMD on OCT, example provided by Altris AI platform

    Secondly, a fundus image is displayed with superimposed retinal layers. This facilitates linking layers to the fundus, but only one layer can be examined at a time, hindering the analysis of multiple layers simultaneously.

    OCT scan and fundus image on an example of OCR report

    Thirdly, the OCT tomogram is visualized in 3D, providing a comprehensive overview, but adjusting the visual representation often has limitations. Additionally, combined 3D visualizations of the tomogram and layers are typically unavailable, potentially obscuring spatial relationships.

    3d visualization of OCT scan results in OCT report

    While existing reports offer diverse approaches to managing, analyzing, and presenting OCT data, each solution focuses on specific aspects and lacks customization. The situation becomes even more complex if scans come from different OCT devices, as manufacturers only provide software for the data for proprietary OCT scanners. Consequently, no approved way of viewing, analyzing, or comparing data from different manufacturers exists.

    Furthermore, there are limited possibilities for implementing prototypes to perform such tasks since software libraries are provided with exclusive licenses and incomplete data specifications. Hence, managing and analyzing OCT data and relating them to other information are challenging and time-consuming tasks.

    Often, supplementary software is utilized to overcome these limitations by providing additional information, visualizing and emphasizing data differently, and enabling the selection of relevant subsets.

    How can customized reports for OCT help?

    Results of Altris AI survey for eye care specialists on What's the main purpose of OCT reports

    Altris AI’s recent survey has revealed that the key benefits of OCT technology for eye care specialists lie in treatment monitoring, patient education, and referral optimization.

    Dr.-Aswathi-Muraleedharan on OCT reports

    • Measuring treatment progress: biomarkers tracking, pathology progression

    Imaging biomarkers are a particularly attractive option for clinical practice due to their non-invasive and real-time nature. Quantitative measurements of retinal thickness, fluid volume, and other biomarkers relevant to diseases like diabetic retinopathy and age-related macular degeneration aid in treatment monitoring.

    Pathology Progression, part of Altris AI customisable OCT reports

     

    OCT reports with customized measurements and selected biomarkers, retinal layers, or segments allow for precise focus on treatment monitoring and patient response to therapy. This personalized approach enhances clinical decision-making by highlighting each case’s most relevant information. 

    Thickness comparison, part of ALtris AI customisable OCT reports

    In current clinical practice, macular damage assessment typically involves measuring the distance between the ILM and RPE layers, summarized in a post-scan report. 

     ILM and RPE layers on OCT report

    However, these reports often fall short of visualization best practices, employing ineffective or inconsistent color schemes. Additionally, they lack flexibility, with static visuals preventing in-depth examination of specific details. Despite these limitations, these reports remain valuable for many clinicians by distilling complex data into a manageable format. 

    Enhanced OCT data visualization offers a promising solution to these challenges. It enhances report clarity and comprehensibility while preserving the richness of the underlying data. 

    Let’s explore how this applies to a clinical case, such as monitoring a patient with Wet AMD during follow-up visits.

    Wet AMD on OCT scan, example provided by ALtris AI platform

    Data demonstrates that OCT findings can reveal the onset or progression of neovascular AMD before a patient reports new symptoms or changes in visual acuity. In fact, OCT images are reported to have the best diagnostic accuracy in monitoring nAMD disease states. This underscores the importance of key OCT findings or biomarkers in personalizing anti-VEGF treatment, achieving disease control, and reducing monitoring burdens.

    Jennifer O'Neill on OCT reports

    Central Retinal Thickness emerged as one of the earliest OCT biomarkers used as an outcome measure in clinical trials for nAMD.

    However, due to confounding factors, CRT’s use in outcome-based assessments of nAMD varies. Thus, it is essential to evaluate additional morphological changes alongside retinal thickness and their relationships with functional outcomes.

    It has been reported that OCT images have the best diagnostic accuracy in monitoring nAMD disease states.

    Another finding that is correlated with a worsening VA due to the associated photoreceptor defects is any damage to the four outer retina layers, including the RPE, interdigitation zone (IZ), ellipsoid zone (EZ), and external limiting membrane band (ELM). 

    Biomarkers measuring on Altris AI customisable OCT reports

    OCT is a valuable imaging tool for visualizing subretinal hyperreflective material (SHRM). It can automatically identify and quantify SHRM and fluid and pigment epithelial detachment to calculate the overall risk of worsening visual outcomes associated with SHRM.

    subretinal hyperreflective material calculated by AI with ALtris AI

    Subsequent follow-up visits will then display the most relevant picture, highlighting the most pertinent biomarkers for tracking a particular pathology (wet AMD in our example) and comparing their volume, progression, or regression through visits.

    Monitoring RPE disruption progression on OCT with Altris AI

    Another helpful option is retinal layer segmentation, which focuses solely on the retinal layers of interest for the specific case. 

    This level of customization empowers clinicians with a comprehensive yet targeted view of the patient’s condition. It saves time from manually detecting anomalies on scans and facilitates informed decision-making and personalized treatment plans.

    • Glaucoma risk evaluation

    Millions risk irreversible vision loss due to undiagnosed glaucoma, underscoring the need for improved early detection. Current tests often rely on observing changes over time, delaying treatment assessment and hindering early identification of rapid disease progression. OCT frequently detects microscopic damage to ganglion cells and thinning across these layers before changes are noticeable through other tests. However, the earliest signs on the scan can still be invisible to the human eye.

    AI algorithms offer insights into glaucoma detection by routinely analyzing the ganglion cell complex, measuring its thickness, and identifying any thinning or asymmetry to determine a patient’s glaucoma risk without additional clinician effort.

    Altris AI's Early glaucoma risk assessment module

    Another significant benefit of AI systems is that OCT for glaucoma usually utilizes a normative database to assess retinal normality. However, these databases are limited in size and represent an average of a select group of people, potentially missing early glaucoma development in those who deviate from the “norm.” Conversely, individuals may be unnecessarily referred for treatment due to not fitting the “normal” profile, even if their eyes are healthy.

    • Crafting effective referral

    In the UK, optometrists are crucial in initiating referrals to hospital eye services (HES), with 72% originating from primary care optometric examinations. While optometrists generally demonstrate proficiency in identifying conditions like cataracts and glaucoma, discrepancies in referral thresholds and unfamiliarity with less common pathologies can lead to unnecessary or delayed referrals.

    Arun-Balasegaram on OCT reports

    At the same time, an evaluation of incoming letters from optometrists in a glaucoma service found that 43% of the letters were considered “failures” because they did not convey the necessity and urgency of the referral.

     So, having an elaborate record of the entire clinical examination in addition to a referral letter is crucial.

    infographic on how customised OCT reports can enhance referrals

    Customized OCT reports solve this challenge by streamlining the referral process and improving communication between optometrists and ophthalmologists. These reports can significantly reduce delays and ensure patients receive timely care by providing comprehensive and relevant information upfront.

    • Patient Education

    Elderly patient is investigating his OCT report with color coded by Altris AI biomarkers

    Patient education and involvement in decision-making are vital for every medical field and crucial for ophthalmology, where insufficient patient engagement can lead to irreversible blindness.

    Omer-Salim on OCT reports

    Research specifically targeting the ophthalmology patient population, which often includes older and potentially visually impaired individuals, reveals a clear preference for materials their eye care provider endorsed.

    Infographic on patient education: 94% of patients want patient education content

    Providing explicit visual representations of diagnoses can significantly improve patient understanding and compliance. Seeing photos of their condition, like glaucoma progression, builds trust and reinforces the importance of treatment recommendations.

    Surveying eye care professionals specializing in dry eye disease revealed a strong emphasis on visual aids during patient education. 

    Photodocumentation is a favored tool for demonstrating the condition to asymptomatic patients, tracking progress, and highlighting treatment’s positive outcomes.

    The visual approach provides tangible evidence of the benefits of their treatment investment, allowing for a deeper understanding of the “why” behind treatment recommendations and paving the way for ongoing collaboration with the patient.

    Kaustubh-Parker on COT reports

    Color-coded OCT reports for pathologies and their signs, severity grading, and pathology progression over time within its OCT analysis highlight the littlest bits that a patient’s unprepared eye would miss otherwise. With follow-up visits, patients can see what’s happening within their eyes and track the progress of any conditions during treatment.

    Biomarkers detected by Altris AI on OCT

    • Updating EMR and Audit readiness

    OCT reports are crucial components of a patient’s medical history and are essential for accurate diagnosis, personalized treatment, and ongoing monitoring. The streamlined process of integrating OCT data into EMR ensures that every eye scan, with its corresponding measurements, biomarkers, and visualizations, becomes an easily accessible part of the patient’s medical history.

    This is crucial for continuity of care and simplifies the audit process, providing a clear and comprehensive record of the patient’s eye health over time. Just optometry chains alone can perform an imposing volume of OCT scans, with some reaching upwards of 40,000 per week. While this demonstrates the widespread adoption of this valuable diagnostic tool, it also presents a challenge: the increased risk of missing subtle or early-stage pathologies amidst the sheer volume of data.

    Enhanced OCT reports offer a solution by providing a crucial “second look” at scan results. While not foolproof, this double-check significantly reduces the risk of overlooking abnormalities, ultimately improving patient outcomes and safeguarding the clinic’s reputation.

    In audits, comprehensive OCT reports are critical in ensuring regulatory compliance. As the Fundamentals of Ophthalmic Coding states, “It is the responsibility of each physician to document the interpretations as promptly as possible and then communicate the findings with the patient… to develop a fail-safe way to ensure that your interpretations are completed promptly.”

    Auditors typically look for several key elements in OCT reports:

    • Physician’s Order: Document the test order, indicating which eye(s) and the medical necessity.
    • Interpretation and Report: The physician analyzes the scan results, including any identified abnormalities or concerns.
    • Timely Completion: Prompt documentation and communication of findings to the patient.

    Customisable OCT reports can streamline this process by generating comprehensive reports that meet these requirements. These reports include detailed measurements, biomarker analysis, and clear visualizations, making it easier for physicians to review, interpret, and document their findings efficiently.

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

     

    Summing up

    Standard OCT reports, while valuable, often need more customization due to data reduction and lack of customization. The inability to visualize multiple scans simultaneously or compare data from different devices hinders comprehensive analysis. Enhanced OCT reports address these limitations by offering detailed visualizations, customizable measurements, and biomarker tracking.

    Customisable OCT reports aid in the early detection and monitoring of diseases like wet AMD and glaucoma, empowering clinicians with accurate diagnoses and personalized treatment plans. Additionally, they streamline referrals by providing focused information and clear visualizations, reducing delays and improving communication between optometrists and ophthalmologists.

    These comprehensive reports also enhance patient education by offering clear visual representations of their conditions and treatment progress, fostering better understanding and compliance. Moreover, with detailed documentation and analysis, detailed reports ensure audit readiness for eye care professionals, mitigating the risk of missed pathologies and upholding regulatory compliance.

  • AI for Ophthalmic Drug Development: Fast and Accurate Biomarkers Detection

    AI for Ophthalmic Drug Development
    Maria Martynova
    20.05.2023
    8 min read

    Despite increased research and development spending, fewer novel drugs and biologics are reaching the market today.

    Large pharmaceutical companies invest an average of over $5 billion and 12+ years in research and development for each new drug approval.

    The high failure rate of drug candidates (only 15% of Phase I drugs reach approval) further exacerbates the issue. This risk often leads pharmaceutical companies to favor lower-risk investments like biosimilars or generic drugs over novel therapies. 

    Due to the eye’s specialized anatomy and physiology, ophthalmic drug development faces unique challenges. Ocular barriers like the tear film and blood-ocular barrier can hinder drug efficacy. Many therapeutic endpoints in ophthalmology are subjective, making controlled trials difficult. The imprecise nature of some measurements further complicates trial design. Rare ophthalmic diseases pose additional challenges, as clinical trials may group diverse conditions, like multiple types of uveitic, together despite their distinct underlying mechanisms and therapeutic needs.

    Here is where AI enters the game. With its ability to rapidly analyze vast amounts of data and detect subtle patterns, AI is revolutionizing how we approach clinical trials for ophthalmic drugs.

    In this article, we will explore how AI for ophthalmic drug development transforms the landscape by accelerating the identification of biomarkers for conditions like diabetic retinopathy and age-related macular degeneration, ensuring the right patients are enrolled in trials, and providing quantitative metrics for evaluating treatment efficacy.

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

    How AI for ophthalmic drug development can accelerate the search for biomarkers in clinical trials

    • Biomarkers for quantitative analysis before and after treatment

    A biomarker, as defined by the BEST Resource FDA-NIH Biomarker Working Group, is a characteristic that can be objectively measured and evaluated as an indicator of normal biological processes, disease processes, or responses to therapeutic intervention. Key characteristics of a useful biomarker include specificity, sensitivity, simplicity, reliability, reproducibility, multiplexing capability, and cost-effectiveness.

    Determining a biomarker’s performance involves assessing its:

    • analytical validity – how accurately it measures what it claims to measure;
    • clinical validity – how well it reflects a clinical feature or outcome;
    • clinical utility – how it improves patient outcomes or guides treatment decisions. 

    In the context of drug regulation, qualified biomarkers can serve as endpoints in clinical trials, potentially offering a more objective and less placebo-susceptible alternative to traditional patient-reported outcomes. 

    Imaging biomarkers are a particularly attractive option for clinical use due to their non-invasive, real-time, and cost-effective nature.

    In ophthalmology, AI-powered analysis of OCT scans can provide precise, quantitative measurements of retinal thickness, fluid volume, and other biomarkers relevant to diseases like diabetic retinopathy and age-related macular degeneration. These measurements can aid in diagnosis, disease staging, treatment monitoring, and prediction of treatment response.

    Systems like Altris AI for pathology detection and segmentation enabled automated disease characterization and longitudinal monitoring of therapeutic response in AMD. Multiple studies have demonstrated the value of volumetric fluid characterization, compartment-specific OCT feature evaluation, and subretinal fibrosis and hyperreflective material quantification.

    A study  has shown the potential of AI to predict conversion from early or intermediate non-neovascular AMD to the neovascular form, using quantitative imaging features like drusen shape and volume. 

    The extraction of quantitative fluid features and assessment of retinal multi-layer segmentation from OCT scans have offered valuable insights into disease prognosis and longitudinal dynamics of Diabetic Retinopathy.

    A recent study demonstrated that quantitative improvement in ellipsoid zone integrity following anti-VEGF therapy for DME significantly correlated with visual function recovery. Furthermore, novel imaging biomarkers, such as the retinal fluid index (RFI), are emerging as tools for precisely monitoring treatment response. Studies have shown that early RFI volatility can predict long-term instability in visual outcomes after treatment.

    Building on these advancements, researchers are now exploring the relationship between imaging biomarkers and underlying disease pathways. A recent study linked levels of various cytokines, including VEGF, MCP-1, and IL-6, with specific OCT-derived biomarkers like fluid parameters and outer retinal integrity.

    By automating the analysis of OCT scans, AI not only streamlines the process but also uncovers subtle details and patterns that might be missed by human observation. 

    Enhanced by AI precision enables more accurate identification and quantification of biomarkers, leading to better patient stratification, treatment monitoring, and prediction of therapeutic responses.

    •  Data Annotation for Clinical Trials

    An ophthalmologist’s report noting the presence of edema on an OCT scan is not the same as stating that its height and length are 411 and 3213 µm, accordingly.

    Imaging biomarkers can range from simple measurements of size or shape to complex computational models, providing valuable information to complement traditional diagnostic methods. They can also determine the presence and severity of a disorder, assess its progression, and evaluate treatment response.

    While biomarkers can be derived from various imaging modalities, OCT stands out in ophthalmology due to its high resolution and ability to visualize subtle retinal changes.

    How AI for OCT Revolutionizing clinical research and drug development trials

    Parametric images, which visually represent the spatial distribution of biomarker values, further enhance the analysis of OCT scans. This combination of quantitative data and visual representation empowers clinicians and researchers to make more informed decisions about diagnosis, treatment, and disease management.

    AI for OCT analyzing biomarkers

    Traditionally, medical image interpretation has relied heavily on visual assessment by experts, who recognize patterns and deviations from normal anatomy based on their accumulated knowledge. 

    While semi-quantitative scoring systems offer some level of objectivity, the field is rapidly evolving towards more quantitative and automated approaches. This shift is driven by advancements in standardization, sophisticated image analysis techniques, and the rise of machine and deep learning.

    In some clinical scenarios, automated image quantification can surpass manual assessment in objectivity and accuracy, interpreting subsequent changes with greater precision and clinical relevance by establishing thresholds for disease states. Unlike physical biomaterials, medical images are easily and rapidly shared for analysis, facilitating automated, reproducible, and blinded biomarker extraction.

    This transition to quantitative analysis is particularly evident in the study of AMD. For instance, non-neovascular (dry) AMD has been extensively evaluated using various imaging biomarkers, such as intraretinal hyper-reflective foci, complex drusenoid lesions, subretinal drusenoid deposits, and drusen burden. 

    While SD-OCT has traditionally described these features qualitatively, recent studies have demonstrated the predictive power of quantitative measures like ellipsoid zone integrity, sub-RPE compartment thickness, and automated drusen volume quantification.

    These quantitative biomarkers have shown stronger associations with disease progression than qualitative features, particularly in predicting the development of geographic atrophy. 

    This predictive power of AI extends to diabetic retinopathy as well. In DR, quantitative measures like central subfield retinal thickness and retinal nerve fiber layer thickness have been linked to disease severity. Disruption of retinal inner layers has been associated with worse visual acuity, and its presence is highly specific for macular nonperfusion. Both DRIL and outer retinal disruption are linked to visual acuity in DR and diabetic macular edema.

    Furthermore, morphological signs like hyperreflective foci, representing lipid extravasation and inflammatory cell aggregates, have emerged as potential biomarkers for monitoring inflammatory activity in diabetic eye disease. AI-powered segmentation and quantification of HRF can track changes in response to anti-VEGF and steroid injections.

    • Enrollment of the right patients

    Due to their complexity and scale, clinical trials, particularly Phase III trials, consume a significant portion of the budget required to bring a new drug to the market. However, the success rate for compounds entering clinical trials is dismal, with only about one in ten progressing to FDA approval. This high failure rate stems largely from ineffective patient recruitment, as each clinical trial has unique participant requirements, including eligibility criteria, disease stage, and specific sub-phenotypes. 

    Manual review of electronic medical records is time-consuming and prone to error, as staff must sift through vast amounts of data to identify eligible candidates.

    Infographic source

    AI can automate this process, rapidly analyzing medical imaging and extracting relevant information to determine patient eligibility. This reduces the burden on staff and allows for faster identification and enrollment of suitable participants, streamlining patient selection and ultimately leading to more efficient and successful clinical trials. 

    A targeted approach can dramatically improve recruitment efficiency by pinpointing ideal candidates and even revealing disease hotspots for geographically focused efforts.

    In later phases of clinical trials (Phase II and III), AI-powered image analysis can also play a pivotal role. In ophthalmology, AI can analyze OCT scans to precisely quantify disease biomarkers, ensuring that the trial participants are those most likely to benefit from the investigated drug. This improves the success rate of trials and minimizes potential harm to patients who might not be suitable candidates.

    AI-powered image analysis offers a crucial advantage: reducing variability in interpretation. 

    AI algorithms can standardize the imaging overview process by consistently identifying and quantifying key biomarkers, ensuring that different readers arrive at similar conclusions.

    • Real World Evidence

    Randomized controlled trials have long been the gold standard for evaluating the efficacy and safety of new therapies. However, controlled environments with strict inclusion and exclusion criteria may not fully reflect the diversity and complexity of real-world patient populations. 

    Real-world data (RWD) that is collected during routine clinical practice can provide critical insights into disease biomarkers and significantly impact the drug development process. This RWD can be transformed into real-world evidence (RWE) when appropriately analyzed.

    RWE is bridging the gap between clinical trials and real-world patient care, providing a more representative view of disease progression, treatment patterns, and long-term outcomes in everyday clinical settings.

    In ophthalmology, RWE already has played a crucial role in understanding the impact of anti-VEGF therapies for neovascular age-related macular degeneration. While RCTs demonstrated the initial efficacy of these treatments, RWE studies have shown variations in real-world outcomes and highlighted the need for continued and higher than previously provided treatment frequency and new treatment regimens such as treat-and-extend.

    Big data, encompassing a vast array of structured and unstructured information, is now an integral part of modern medicine, including ophthalmology.  By integrating RWE with traditional clinical trial data, researchers can better understand how a drug performs in the real world and conduct more pragmatic clinical trials designed to evaluate treatments in real-world settings with broader patient populations, ultimately accelerating the development of safer and more effective therapies.

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

     

    The future of ophthalmic drug trials

    The global AI-in-drug discovery market is poised for significant growth, driven by advancements in machine learning, natural language processing, and deep learning.

    Artificial intelligence has the potential to significantly impact drug discovery by enabling more creative and efficient experimentation. It can also reduce the cost and time associated with failures throughout the drug development process. By identifying promising leads earlier and eliminating less viable options, AI can streamline each stage, potentially halving the total cost of a single project. 

    Advanced simulation and modeling techniques powered by AI are also poised to revolutionize our understanding of disease mechanisms and accelerate the discovery of new drugs.

    The promising potential of AI in clinical trials extends to the proactive identification and mitigation of adverse events, enhancing patient safety and reducing trial risks. Data-driven AI tools are poised to revolutionize the entire clinical trial process, from design to execution. By streamlining patient recruitment, continuously monitoring participants, and facilitating comprehensive data analysis, AI can increase trial success rates, improve adherence, and yield more reliable endpoints.

    The future of ophthalmic drug trials is here, and it’s powered by AI. By embracing this technology, researchers and clinicians can unlock new possibilities for preventing blindness and preserving vision for future generations.

popular Posted

  • Customisable OCT Reports: Enhancing Diagnostic Accuracy

    Сustomisable OCT reports for eye care practice enhancement
    Maria Martynova
    07.06. 2023
    8 min read

    The average OCT device is a significant investment, costing upwards of $40,000. As eye care specialists, we recognize the revolutionary power of OCT. However, patients often receive only a standard OCT report from this investment. Unfortunately, many patients are unaware of OCT’s true value and may not even know what it is. This raises a crucial question: are these standard reports truly reflecting the full diagnostic potential of such an expensive and sophisticated device? Are we, as professionals, maximizing the capabilities of this technology to ensure optimal patient care?

    This article explores how customisable OCT Reports address these shortcomings, enhancing diagnostic accuracy, treatment monitoring, referral efficiency, patient education, and audit readiness. 

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

    Common OCT reports and their limitations

    How does the standard report look?

    An example of a common OCT report

    OCT has become a golden standard for diagnosing and monitoring many ocular pathologies, thanks to its unparalleled level of detail in ophthalmic imaging.

    While retinal reports vary among OCT models, they typically include:

    • a foveally centered B-scan, 
    • a quantitative thickness map, 
    • and a semi-quantitative thickness map.

    The B-scan offers a visual snapshot of foveal architecture and confirms proper scan centering. The quantitative thickness map employs the ETDRS sector map to measure retinal thickness within a 6mm circle around the fovea, with specific measurements for the foveal sector (1mm), inner macular ring (3mm), and outer macular ring (6mm).

    Progression analytics enable comparison of serial macular scans, which is invaluable for managing vitreomacular interface disorders and macular edema. The semi-quantitative thickness map provides a broader overview of retinal thickness throughout the scan.

    Given this amount of data, it is challenging to identify subtle and localized retinal pathological changes. As a result, entire OCT datasets are represented by few aggregated values, and the standard OCT reports generated by most devices often rely on significant data reduction to simplify interpretation, which you can usually not customize. 

    Three standard methods exist for displaying OCT data

    Firstly, acquired 2D image slices are presented individually. This allows for detailed examination, but navigating through numerous images can be cumbersome, particularly with large datasets.

    Wet AMD on OCT, example provided by Altris AI platform

    Secondly, a fundus image is displayed with superimposed retinal layers. This facilitates linking layers to the fundus, but only one layer can be examined at a time, hindering the analysis of multiple layers simultaneously.

    OCT scan and fundus image on an example of OCR report

    Thirdly, the OCT tomogram is visualized in 3D, providing a comprehensive overview, but adjusting the visual representation often has limitations. Additionally, combined 3D visualizations of the tomogram and layers are typically unavailable, potentially obscuring spatial relationships.

    3d visualization of OCT scan results in OCT report

    While existing reports offer diverse approaches to managing, analyzing, and presenting OCT data, each solution focuses on specific aspects and lacks customization. The situation becomes even more complex if scans come from different OCT devices, as manufacturers only provide software for the data for proprietary OCT scanners. Consequently, no approved way of viewing, analyzing, or comparing data from different manufacturers exists.

    Furthermore, there are limited possibilities for implementing prototypes to perform such tasks since software libraries are provided with exclusive licenses and incomplete data specifications. Hence, managing and analyzing OCT data and relating them to other information are challenging and time-consuming tasks.

    Often, supplementary software is utilized to overcome these limitations by providing additional information, visualizing and emphasizing data differently, and enabling the selection of relevant subsets.

    How can customized reports for OCT help?

    Results of Altris AI survey for eye care specialists on What's the main purpose of OCT reports

    Altris AI’s recent survey has revealed that the key benefits of OCT technology for eye care specialists lie in treatment monitoring, patient education, and referral optimization.

    Dr.-Aswathi-Muraleedharan on OCT reports

    • Measuring treatment progress: biomarkers tracking, pathology progression

    Imaging biomarkers are a particularly attractive option for clinical practice due to their non-invasive and real-time nature. Quantitative measurements of retinal thickness, fluid volume, and other biomarkers relevant to diseases like diabetic retinopathy and age-related macular degeneration aid in treatment monitoring.

    Pathology Progression, part of Altris AI customisable OCT reports

     

    OCT reports with customized measurements and selected biomarkers, retinal layers, or segments allow for precise focus on treatment monitoring and patient response to therapy. This personalized approach enhances clinical decision-making by highlighting each case’s most relevant information. 

    Thickness comparison, part of ALtris AI customisable OCT reports

    In current clinical practice, macular damage assessment typically involves measuring the distance between the ILM and RPE layers, summarized in a post-scan report. 

     ILM and RPE layers on OCT report

    However, these reports often fall short of visualization best practices, employing ineffective or inconsistent color schemes. Additionally, they lack flexibility, with static visuals preventing in-depth examination of specific details. Despite these limitations, these reports remain valuable for many clinicians by distilling complex data into a manageable format. 

    Enhanced OCT data visualization offers a promising solution to these challenges. It enhances report clarity and comprehensibility while preserving the richness of the underlying data. 

    Let’s explore how this applies to a clinical case, such as monitoring a patient with Wet AMD during follow-up visits.

    Wet AMD on OCT scan, example provided by ALtris AI platform

    Data demonstrates that OCT findings can reveal the onset or progression of neovascular AMD before a patient reports new symptoms or changes in visual acuity. In fact, OCT images are reported to have the best diagnostic accuracy in monitoring nAMD disease states. This underscores the importance of key OCT findings or biomarkers in personalizing anti-VEGF treatment, achieving disease control, and reducing monitoring burdens.

    Jennifer O'Neill on OCT reports

    Central Retinal Thickness emerged as one of the earliest OCT biomarkers used as an outcome measure in clinical trials for nAMD.

    However, due to confounding factors, CRT’s use in outcome-based assessments of nAMD varies. Thus, it is essential to evaluate additional morphological changes alongside retinal thickness and their relationships with functional outcomes.

    It has been reported that OCT images have the best diagnostic accuracy in monitoring nAMD disease states.

    Another finding that is correlated with a worsening VA due to the associated photoreceptor defects is any damage to the four outer retina layers, including the RPE, interdigitation zone (IZ), ellipsoid zone (EZ), and external limiting membrane band (ELM). 

    Biomarkers measuring on Altris AI customisable OCT reports

    OCT is a valuable imaging tool for visualizing subretinal hyperreflective material (SHRM). It can automatically identify and quantify SHRM and fluid and pigment epithelial detachment to calculate the overall risk of worsening visual outcomes associated with SHRM.

    subretinal hyperreflective material calculated by AI with ALtris AI

    Subsequent follow-up visits will then display the most relevant picture, highlighting the most pertinent biomarkers for tracking a particular pathology (wet AMD in our example) and comparing their volume, progression, or regression through visits.

    Monitoring RPE disruption progression on OCT with Altris AI

    Another helpful option is retinal layer segmentation, which focuses solely on the retinal layers of interest for the specific case. 

    This level of customization empowers clinicians with a comprehensive yet targeted view of the patient’s condition. It saves time from manually detecting anomalies on scans and facilitates informed decision-making and personalized treatment plans.

    • Glaucoma risk evaluation

    Millions risk irreversible vision loss due to undiagnosed glaucoma, underscoring the need for improved early detection. Current tests often rely on observing changes over time, delaying treatment assessment and hindering early identification of rapid disease progression. OCT frequently detects microscopic damage to ganglion cells and thinning across these layers before changes are noticeable through other tests. However, the earliest signs on the scan can still be invisible to the human eye.

    AI algorithms offer insights into glaucoma detection by routinely analyzing the ganglion cell complex, measuring its thickness, and identifying any thinning or asymmetry to determine a patient’s glaucoma risk without additional clinician effort.

    Altris AI's Early glaucoma risk assessment module

    Another significant benefit of AI systems is that OCT for glaucoma usually utilizes a normative database to assess retinal normality. However, these databases are limited in size and represent an average of a select group of people, potentially missing early glaucoma development in those who deviate from the “norm.” Conversely, individuals may be unnecessarily referred for treatment due to not fitting the “normal” profile, even if their eyes are healthy.

    • Crafting effective referral

    In the UK, optometrists are crucial in initiating referrals to hospital eye services (HES), with 72% originating from primary care optometric examinations. While optometrists generally demonstrate proficiency in identifying conditions like cataracts and glaucoma, discrepancies in referral thresholds and unfamiliarity with less common pathologies can lead to unnecessary or delayed referrals.

    Arun-Balasegaram on OCT reports

    At the same time, an evaluation of incoming letters from optometrists in a glaucoma service found that 43% of the letters were considered “failures” because they did not convey the necessity and urgency of the referral.

     So, having an elaborate record of the entire clinical examination in addition to a referral letter is crucial.

    infographic on how customised OCT reports can enhance referrals

    Customized OCT reports solve this challenge by streamlining the referral process and improving communication between optometrists and ophthalmologists. These reports can significantly reduce delays and ensure patients receive timely care by providing comprehensive and relevant information upfront.

    • Patient Education

    Elderly patient is investigating his OCT report with color coded by Altris AI biomarkers

    Patient education and involvement in decision-making are vital for every medical field and crucial for ophthalmology, where insufficient patient engagement can lead to irreversible blindness.

    Omer-Salim on OCT reports

    Research specifically targeting the ophthalmology patient population, which often includes older and potentially visually impaired individuals, reveals a clear preference for materials their eye care provider endorsed.

    Infographic on patient education: 94% of patients want patient education content

    Providing explicit visual representations of diagnoses can significantly improve patient understanding and compliance. Seeing photos of their condition, like glaucoma progression, builds trust and reinforces the importance of treatment recommendations.

    Surveying eye care professionals specializing in dry eye disease revealed a strong emphasis on visual aids during patient education. 

    Photodocumentation is a favored tool for demonstrating the condition to asymptomatic patients, tracking progress, and highlighting treatment’s positive outcomes.

    The visual approach provides tangible evidence of the benefits of their treatment investment, allowing for a deeper understanding of the “why” behind treatment recommendations and paving the way for ongoing collaboration with the patient.

    Kaustubh-Parker on COT reports

    Color-coded OCT reports for pathologies and their signs, severity grading, and pathology progression over time within its OCT analysis highlight the littlest bits that a patient’s unprepared eye would miss otherwise. With follow-up visits, patients can see what’s happening within their eyes and track the progress of any conditions during treatment.

    Biomarkers detected by Altris AI on OCT

    • Updating EMR and Audit readiness

    OCT reports are crucial components of a patient’s medical history and are essential for accurate diagnosis, personalized treatment, and ongoing monitoring. The streamlined process of integrating OCT data into EMR ensures that every eye scan, with its corresponding measurements, biomarkers, and visualizations, becomes an easily accessible part of the patient’s medical history.

    This is crucial for continuity of care and simplifies the audit process, providing a clear and comprehensive record of the patient’s eye health over time. Just optometry chains alone can perform an imposing volume of OCT scans, with some reaching upwards of 40,000 per week. While this demonstrates the widespread adoption of this valuable diagnostic tool, it also presents a challenge: the increased risk of missing subtle or early-stage pathologies amidst the sheer volume of data.

    Enhanced OCT reports offer a solution by providing a crucial “second look” at scan results. While not foolproof, this double-check significantly reduces the risk of overlooking abnormalities, ultimately improving patient outcomes and safeguarding the clinic’s reputation.

    In audits, comprehensive OCT reports are critical in ensuring regulatory compliance. As the Fundamentals of Ophthalmic Coding states, “It is the responsibility of each physician to document the interpretations as promptly as possible and then communicate the findings with the patient… to develop a fail-safe way to ensure that your interpretations are completed promptly.”

    Auditors typically look for several key elements in OCT reports:

    • Physician’s Order: Document the test order, indicating which eye(s) and the medical necessity.
    • Interpretation and Report: The physician analyzes the scan results, including any identified abnormalities or concerns.
    • Timely Completion: Prompt documentation and communication of findings to the patient.

    Customisable OCT reports can streamline this process by generating comprehensive reports that meet these requirements. These reports include detailed measurements, biomarker analysis, and clear visualizations, making it easier for physicians to review, interpret, and document their findings efficiently.

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

     

    Summing up

    Standard OCT reports, while valuable, often need more customization due to data reduction and lack of customization. The inability to visualize multiple scans simultaneously or compare data from different devices hinders comprehensive analysis. Enhanced OCT reports address these limitations by offering detailed visualizations, customizable measurements, and biomarker tracking.

    Customisable OCT reports aid in the early detection and monitoring of diseases like wet AMD and glaucoma, empowering clinicians with accurate diagnoses and personalized treatment plans. Additionally, they streamline referrals by providing focused information and clear visualizations, reducing delays and improving communication between optometrists and ophthalmologists.

    These comprehensive reports also enhance patient education by offering clear visual representations of their conditions and treatment progress, fostering better understanding and compliance. Moreover, with detailed documentation and analysis, detailed reports ensure audit readiness for eye care professionals, mitigating the risk of missed pathologies and upholding regulatory compliance.

  • AI for Ophthalmic Drug Development: Fast and Accurate Biomarkers Detection

    AI for Ophthalmic Drug Development
    Maria Martynova
    20.05.2023
    8 min read

    Despite increased research and development spending, fewer novel drugs and biologics are reaching the market today.

    Large pharmaceutical companies invest an average of over $5 billion and 12+ years in research and development for each new drug approval.

    The high failure rate of drug candidates (only 15% of Phase I drugs reach approval) further exacerbates the issue. This risk often leads pharmaceutical companies to favor lower-risk investments like biosimilars or generic drugs over novel therapies. 

    Due to the eye’s specialized anatomy and physiology, ophthalmic drug development faces unique challenges. Ocular barriers like the tear film and blood-ocular barrier can hinder drug efficacy. Many therapeutic endpoints in ophthalmology are subjective, making controlled trials difficult. The imprecise nature of some measurements further complicates trial design. Rare ophthalmic diseases pose additional challenges, as clinical trials may group diverse conditions, like multiple types of uveitic, together despite their distinct underlying mechanisms and therapeutic needs.

    Here is where AI enters the game. With its ability to rapidly analyze vast amounts of data and detect subtle patterns, AI is revolutionizing how we approach clinical trials for ophthalmic drugs.

    In this article, we will explore how AI for ophthalmic drug development transforms the landscape by accelerating the identification of biomarkers for conditions like diabetic retinopathy and age-related macular degeneration, ensuring the right patients are enrolled in trials, and providing quantitative metrics for evaluating treatment efficacy.

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

    How AI for ophthalmic drug development can accelerate the search for biomarkers in clinical trials

    • Biomarkers for quantitative analysis before and after treatment

    A biomarker, as defined by the BEST Resource FDA-NIH Biomarker Working Group, is a characteristic that can be objectively measured and evaluated as an indicator of normal biological processes, disease processes, or responses to therapeutic intervention. Key characteristics of a useful biomarker include specificity, sensitivity, simplicity, reliability, reproducibility, multiplexing capability, and cost-effectiveness.

    Determining a biomarker’s performance involves assessing its:

    • analytical validity – how accurately it measures what it claims to measure;
    • clinical validity – how well it reflects a clinical feature or outcome;
    • clinical utility – how it improves patient outcomes or guides treatment decisions. 

    In the context of drug regulation, qualified biomarkers can serve as endpoints in clinical trials, potentially offering a more objective and less placebo-susceptible alternative to traditional patient-reported outcomes. 

    Imaging biomarkers are a particularly attractive option for clinical use due to their non-invasive, real-time, and cost-effective nature.

    In ophthalmology, AI-powered analysis of OCT scans can provide precise, quantitative measurements of retinal thickness, fluid volume, and other biomarkers relevant to diseases like diabetic retinopathy and age-related macular degeneration. These measurements can aid in diagnosis, disease staging, treatment monitoring, and prediction of treatment response.

    Systems like Altris AI for pathology detection and segmentation enabled automated disease characterization and longitudinal monitoring of therapeutic response in AMD. Multiple studies have demonstrated the value of volumetric fluid characterization, compartment-specific OCT feature evaluation, and subretinal fibrosis and hyperreflective material quantification.

    A study  has shown the potential of AI to predict conversion from early or intermediate non-neovascular AMD to the neovascular form, using quantitative imaging features like drusen shape and volume. 

    The extraction of quantitative fluid features and assessment of retinal multi-layer segmentation from OCT scans have offered valuable insights into disease prognosis and longitudinal dynamics of Diabetic Retinopathy.

    A recent study demonstrated that quantitative improvement in ellipsoid zone integrity following anti-VEGF therapy for DME significantly correlated with visual function recovery. Furthermore, novel imaging biomarkers, such as the retinal fluid index (RFI), are emerging as tools for precisely monitoring treatment response. Studies have shown that early RFI volatility can predict long-term instability in visual outcomes after treatment.

    Building on these advancements, researchers are now exploring the relationship between imaging biomarkers and underlying disease pathways. A recent study linked levels of various cytokines, including VEGF, MCP-1, and IL-6, with specific OCT-derived biomarkers like fluid parameters and outer retinal integrity.

    By automating the analysis of OCT scans, AI not only streamlines the process but also uncovers subtle details and patterns that might be missed by human observation. 

    Enhanced by AI precision enables more accurate identification and quantification of biomarkers, leading to better patient stratification, treatment monitoring, and prediction of therapeutic responses.

    •  Data Annotation for Clinical Trials

    An ophthalmologist’s report noting the presence of edema on an OCT scan is not the same as stating that its height and length are 411 and 3213 µm, accordingly.

    Imaging biomarkers can range from simple measurements of size or shape to complex computational models, providing valuable information to complement traditional diagnostic methods. They can also determine the presence and severity of a disorder, assess its progression, and evaluate treatment response.

    While biomarkers can be derived from various imaging modalities, OCT stands out in ophthalmology due to its high resolution and ability to visualize subtle retinal changes.

    How AI for OCT Revolutionizing clinical research and drug development trials

    Parametric images, which visually represent the spatial distribution of biomarker values, further enhance the analysis of OCT scans. This combination of quantitative data and visual representation empowers clinicians and researchers to make more informed decisions about diagnosis, treatment, and disease management.

    AI for OCT analyzing biomarkers

    Traditionally, medical image interpretation has relied heavily on visual assessment by experts, who recognize patterns and deviations from normal anatomy based on their accumulated knowledge. 

    While semi-quantitative scoring systems offer some level of objectivity, the field is rapidly evolving towards more quantitative and automated approaches. This shift is driven by advancements in standardization, sophisticated image analysis techniques, and the rise of machine and deep learning.

    In some clinical scenarios, automated image quantification can surpass manual assessment in objectivity and accuracy, interpreting subsequent changes with greater precision and clinical relevance by establishing thresholds for disease states. Unlike physical biomaterials, medical images are easily and rapidly shared for analysis, facilitating automated, reproducible, and blinded biomarker extraction.

    This transition to quantitative analysis is particularly evident in the study of AMD. For instance, non-neovascular (dry) AMD has been extensively evaluated using various imaging biomarkers, such as intraretinal hyper-reflective foci, complex drusenoid lesions, subretinal drusenoid deposits, and drusen burden. 

    While SD-OCT has traditionally described these features qualitatively, recent studies have demonstrated the predictive power of quantitative measures like ellipsoid zone integrity, sub-RPE compartment thickness, and automated drusen volume quantification.

    These quantitative biomarkers have shown stronger associations with disease progression than qualitative features, particularly in predicting the development of geographic atrophy. 

    This predictive power of AI extends to diabetic retinopathy as well. In DR, quantitative measures like central subfield retinal thickness and retinal nerve fiber layer thickness have been linked to disease severity. Disruption of retinal inner layers has been associated with worse visual acuity, and its presence is highly specific for macular nonperfusion. Both DRIL and outer retinal disruption are linked to visual acuity in DR and diabetic macular edema.

    Furthermore, morphological signs like hyperreflective foci, representing lipid extravasation and inflammatory cell aggregates, have emerged as potential biomarkers for monitoring inflammatory activity in diabetic eye disease. AI-powered segmentation and quantification of HRF can track changes in response to anti-VEGF and steroid injections.

    • Enrollment of the right patients

    Due to their complexity and scale, clinical trials, particularly Phase III trials, consume a significant portion of the budget required to bring a new drug to the market. However, the success rate for compounds entering clinical trials is dismal, with only about one in ten progressing to FDA approval. This high failure rate stems largely from ineffective patient recruitment, as each clinical trial has unique participant requirements, including eligibility criteria, disease stage, and specific sub-phenotypes. 

    Manual review of electronic medical records is time-consuming and prone to error, as staff must sift through vast amounts of data to identify eligible candidates.

    Infographic source

    AI can automate this process, rapidly analyzing medical imaging and extracting relevant information to determine patient eligibility. This reduces the burden on staff and allows for faster identification and enrollment of suitable participants, streamlining patient selection and ultimately leading to more efficient and successful clinical trials. 

    A targeted approach can dramatically improve recruitment efficiency by pinpointing ideal candidates and even revealing disease hotspots for geographically focused efforts.

    In later phases of clinical trials (Phase II and III), AI-powered image analysis can also play a pivotal role. In ophthalmology, AI can analyze OCT scans to precisely quantify disease biomarkers, ensuring that the trial participants are those most likely to benefit from the investigated drug. This improves the success rate of trials and minimizes potential harm to patients who might not be suitable candidates.

    AI-powered image analysis offers a crucial advantage: reducing variability in interpretation. 

    AI algorithms can standardize the imaging overview process by consistently identifying and quantifying key biomarkers, ensuring that different readers arrive at similar conclusions.

    • Real World Evidence

    Randomized controlled trials have long been the gold standard for evaluating the efficacy and safety of new therapies. However, controlled environments with strict inclusion and exclusion criteria may not fully reflect the diversity and complexity of real-world patient populations. 

    Real-world data (RWD) that is collected during routine clinical practice can provide critical insights into disease biomarkers and significantly impact the drug development process. This RWD can be transformed into real-world evidence (RWE) when appropriately analyzed.

    RWE is bridging the gap between clinical trials and real-world patient care, providing a more representative view of disease progression, treatment patterns, and long-term outcomes in everyday clinical settings.

    In ophthalmology, RWE already has played a crucial role in understanding the impact of anti-VEGF therapies for neovascular age-related macular degeneration. While RCTs demonstrated the initial efficacy of these treatments, RWE studies have shown variations in real-world outcomes and highlighted the need for continued and higher than previously provided treatment frequency and new treatment regimens such as treat-and-extend.

    Big data, encompassing a vast array of structured and unstructured information, is now an integral part of modern medicine, including ophthalmology.  By integrating RWE with traditional clinical trial data, researchers can better understand how a drug performs in the real world and conduct more pragmatic clinical trials designed to evaluate treatments in real-world settings with broader patient populations, ultimately accelerating the development of safer and more effective therapies.

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

     

    The future of ophthalmic drug trials

    The global AI-in-drug discovery market is poised for significant growth, driven by advancements in machine learning, natural language processing, and deep learning.

    Artificial intelligence has the potential to significantly impact drug discovery by enabling more creative and efficient experimentation. It can also reduce the cost and time associated with failures throughout the drug development process. By identifying promising leads earlier and eliminating less viable options, AI can streamline each stage, potentially halving the total cost of a single project. 

    Advanced simulation and modeling techniques powered by AI are also poised to revolutionize our understanding of disease mechanisms and accelerate the discovery of new drugs.

    The promising potential of AI in clinical trials extends to the proactive identification and mitigation of adverse events, enhancing patient safety and reducing trial risks. Data-driven AI tools are poised to revolutionize the entire clinical trial process, from design to execution. By streamlining patient recruitment, continuously monitoring participants, and facilitating comprehensive data analysis, AI can increase trial success rates, improve adherence, and yield more reliable endpoints.

    The future of ophthalmic drug trials is here, and it’s powered by AI. By embracing this technology, researchers and clinicians can unlock new possibilities for preventing blindness and preserving vision for future generations.

  • AI-assisted OCT in Eye Care: Attracting and Educating Patients

    AI-assisted OCT in eye-care
    Maria Znamenska
    26.04.2023
    9 min read

    Today patients are curious about AI, but they may also have some reservations. Researches suggest a cautious attitude towards autonomous AI in healthcare, but what happens when AI becomes a collaborative tool, assisting eye care professionals in educating and treating patients? This shift in focus can significantly affect patients’ comfort levels and acceptance of AI.

    Patients have some concerns about AI in healthcare. Let’s delve into the patient perspective and discover how addressing these apprehensions and implementing AI-assisted OCT in eye care can lead to a better understanding of the technology and, ultimately, healthier outcomes.

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

    How do patients react to AI?

    Interestingly, while surveys extensively document how eye care professionals feel about and interact with AI, the perspectives of the main beneficiary—the patient—remain less understood. The limited research available indicates mixed feelings towards this technology. Few studies examine patient attitudes toward AI in healthcare and eye care, suggesting a degree of caution. 

    Infographic on patient education: 94% of patients want patient education content

    However, these studies have focused on scenarios where AI fully replaces human healthcare providers. Patients demonstrated significant resistance to medical AI in these cases driven mostly by “uniqueness neglect” – concern that AI providers are less able than humans to account for a person’s unique characteristics and circumstances.

    For example,  in the “Resistance to Medical Artificial Intelligence” study, participants demonstrated less interest in using a stress assessment and were willing to pay less for it when administered by an automated system rather than a human, even with equivalent accuracy. Additionally, participants showed a weaker preference for a provider offering clearly superior performance if it was an AI system. 

    A survey of 926 patients reveals a mix of attitudes towards AI in healthcare but also gives us clues to understand the reasons behind it. While a majority believe AI could improve care, there’s also a significant undercurrent of caution:

    • Desire for Transparency: Over 95% of respondents felt it was either very or somewhat important to know if AI played a significant role in their diagnosis or treatment.
    • Unexplainable AI = Uncomfortable: Over 70% expressed discomfort with receiving an accurate diagnosis from an AI system that couldn’t explain its reasoning. This discomfort was more pronounced among those unsure about AI’s overall impact on healthcare.
    • Application Matters: Patients were more comfortable with AI for analyzing chest X-rays than for making cancer diagnoses.
    • Minority Concerns: Respondents from racial and ethnic minority groups expressed higher levels of concern about potential AI downsides, such as misdiagnosis, privacy breaches, reduced clinician interaction, and increased costs.

    These findings highlight the importance of being transparent with patients about how AI is used in their care. Explaining the role of AI and reassuring patients that it’s a tool for assisting your clinical judgment (not replacing it) will be essential. Additionally, being mindful of potential heightened concerns among minority patients is crucial for providing equitable care.

    A study solely focused on overcoming patients’ resistance to AI in healthcare found that demonstrating social proof (like highlighting satisfied customer reviews) increased trust in AI-involved help.

    The team has identified several additional strategies for reducing patient apprehension of AI recommendations. One effective approach is to emphasize AI’s collaborative nature, where a human doctor endorses recommendations. This highlights AI as a tool to assist, not replace, physicians. Demonstrating AI capabilities through real-world examples where AI exhibits nuanced reasoning can also encourage greater reliance on the technology.  

    How to attract patients with AI in eye care

    AI offers a powerful way to transform your practice and set yourself apart. It brings world-class diagnostic expertise directly to your community, potentially saving patients’ sight by catching eye diseases in their earliest stages. Here’s how to position AI for patients:

    • Emphasize Early Detection

    It brings world-class diagnostic expertise directly to your community, potentially saving patients’ sight by catching eye diseases in their earliest stages, including early signs of glaucoma, AMD, and many other pathologies that would often be invisible during a regular visit. Some retinal changes are so microscopic that they elude the human eye, making the program’s ability to detect tiny retinal changes invaluable. This makes AI a powerful tool during routine exams, potentially uncovering issues you may not even have been aware of as a patient.

    • More time for personalized care

    Patients expect personalized experiences, and AI empowers you to deliver exactly that. By analyzing each patient’s unique OCT image data, AI helps identify potential pathologies with greater accuracy. 

    Additionally, since AI acts as a meticulous assistant, double-checking your assessments and minimizing the risk of missed diagnoses, it frees up your time. This allows for more meaningful one-on-one conversations with patients, where you can explain their results and discuss the next steps, setting your practice apart regarding patient satisfaction.

    • Your old good eye care professional, but with superpower

    With AI-assisted OCT, you have the combined knowledge and experience of leading eye care specialists at your fingertips for every patient. This technology leverages massive datasets of medical images and clinical data meticulously analyzed by retinal experts during AI development.  It is a valuable second opinion tool, helping you confirm diagnoses and identify subtle patterns the human eye might miss.

    AI-assisted OCT in eye care: кetina specialists of Altris AI segmenting pathologies to teach AI detect them

    This offers your patients peace of mind – knowing their diagnosis has been informed by insights from a team of experts incorporated into the AI’s analysis.

    It’s crucial to emphasize that AI will never replace the human touch. It’s a powerful tool that frees up your time for what matters most: building trust through personalized care and addressing patient concerns with empathy.

    How to explain what AI is to patients 

    AI color coding in eye care, segmented by pixels pathologies on OCT

    Patient understanding is vital for building trust with you and any technology you use. It is especially important when talking about a sophisticated instrument like AI.

    For instance, we’ve found that patients sometimes struggle to understand how Altris AI, our AI-powered OCT analysis tool, works. We’ve crafted an explanation that helps them grasp the concept more quickly, covering how retinal specialists have taught the system to do its job, the AI’s role as a doctor’s help, and direct benefits for patients.

    OCT scans provide incredibly detailed images of the retina, the important layer at the back of your eye.  Eye doctors carefully analyze these scans to spot any potential problems.  To make this process even more thorough, AI systems are now being used to assist with OCT analysis.

    How does the system know how to do that? Real doctors have taught it. It works by first learning from thousands of OCT scans graphically labeled by experienced eye doctors. 

    The doctors analyzed images from real patients to detect and accurately measure over 70 pathologies and signs of pathology, including age-related macular degeneration and glaucoma, teaching the AI what to look for.

    The system leverages a massive dataset of thousands of OCT scans collected from 11 ophthalmic clinics over the years. Carefully segmented and labeled by retinal professionals, these scans were used to train the AI. By analyzing each pixel of an image and its position relative to others, the AI has learned to distinguish between different biomarkers and pathologies.

    The platform visualizes what is going on with the retina using color coding. This means that every problem on the OCT scan will be colored differently and signed so you will be able to understand what is going on with your retina.

    Biomarkers detected by Altris AI on OCT

    As with any innovative tool, Altris AI partially automates some routine tasks, so clinicians have more time for what is important: talking to patients, learning more about their eye health, and providing treatment advice.

    Why does this matter to you? Altris AI can help spot even the tiniest changes in your eyes, leading to earlier treatment and better protection of your eye health. Knowing a smart computer system is also double-checking your scans gives both you and your doctor extra confidence in the results.

    With the help of Altris AI, you will be able to see how the treatment affects you.  For example, if you have fluid in the retina (that is not supposed to be there), you will be able to see if its volume is decreasing or increasing with the help of color coding. 

    Detected by AI for OCT, Altris AI, biomarkers of Fibrovascular RPE Detachment on OCT scan: RPE disruption, Fibrovascular RPE Detachment , Subretinal fluid, Ellipsoid zone disruption

    Altris AI was designed by eye doctors for eye doctors. It’s a tool to help us take even better care of patients.

    AI color coding in eye care: how learning about diagnosis influences treatment adherence

    Patient-centered care, a key principle outlined by the Institute of Medicine, emphasizes patient education and involvement in decision-making. This is vital in ophthalmology, where insufficient patient engagement can lead to irreversible blindness.

    Research specifically targeting the ophthalmology patient population, which often includes older and potentially visually impaired individuals, reveals a clear preference for individualized education sessions and materials endorsed by their eye care provider. 

    According to Wolters Kluwer Health, patients crave educational materials from their providers, yet only two-thirds actually get them. This leaves patients searching for information, potentially exposing them to unreliable sources. 

    Providing clear, accessible patient education is crucial to ensure understanding and treatment adherence. 

    The human brain’s ability to process visual information far surpasses its speed with text, making visual aids a powerful tool for health education. In the field of eye care, this becomes even more critical. Patients often experience vision difficulties, potentially hindering their ability to absorb written materials. Providing clear visual representations of diagnoses can significantly improve patient understanding and compliance. 

    A study shows a strong preference for personalized educational materials, especially among older visually impaired patients. Seeing photos of their condition, like glaucoma progression, builds trust and reinforces the importance of treatment recommendations.

    Surveying eye care professionals specializing in dry eye disease revealed a strong emphasis on visual aids during patient education. Photodocumentation is a favored tool for demonstrating the condition to asymptomatic patients, tracking progress, and highlighting the positive outcomes of treatment.

    A visual approach is particularly motivating for patients. It provides tangible evidence of the benefits of their treatment investment, allowing for a deeper understanding of the “why” behind treatment recommendations and paving the way for ongoing collaboration with the patient.

    Understanding complex eye conditions can be challenging for patients. Altris AI aims to bridge this gap by using color coding for pathologies and their signs, severity grading, and pathology progression over time within its OCT analysis.

    With Altris AI, scans are color-coded for instant interpretation: all the detected pathologies are painted in different colors, highlighting the littlest bits that the unprepared eye of a patient would miss otherwise.

    AI in eye care: patient education through doctor explanation to patient color coded OCT scan, segmented by Altris AI, AI for OCT

    This easy-to-understand visual system empowers patients. They can clearly see what’s happening within their eyes and track the progress of any conditions during treatment.

    Eye care professionals are enthusiastic about its impact.

    Quote of Scott Sedlacek, OD, on color coding patient education through Altris AI

    The power of visuals goes beyond understanding a diagnosis. When patients see the interconnected structures that make up their vision, they gain a deeper appreciation for its complexity and the importance of preventative care. This understanding fosters a true partnership between doctor and patient, where the patient is an active, informed participant in their own eye health.

    Summing up

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

     

    Patients are increasingly curious and open to AI’s potential in general healthcare and eye care in particular, but naturally, some questions and hesitation remain. They stem from a desire to ensure AI considers their individual needs. By addressing these concerns proactively and clarifying when and how AI is used in their care, emphasize the collaborative doctor-AI model—highlight that YOU review and endorse all AI recommendations.

    You can successfully integrate this powerful technology into your practice by addressing patient concerns with empathy and highlighting AI’s benefits. This leads to a more informed and empowered patient experience, improving understanding, adherence to treatment, and, ultimately, better health outcomes.

     

     

  • Early Glaucoma Detection Challenges and Solutions

    early glaucoma detection
    Maria Martynova
    09.04.2023
    10 min read

    Glaucoma’s silent progression highlights a challenge we all face as clinicians. Millions of individuals remain at risk for irreversible vision loss due to undiagnosed disease – 50% or more of all cases. This emphasizes our responsibility to enhance early detection strategies for this sight-threatening condition.

    Existing clinical, structural, and functional tests depend on both baseline exams and the need to observe changes over time, delaying the assessment of treatment effectiveness and the identification of rapid progression.

    In this article, we will consolidate our knowledge as eye care professionals about Glaucoma, explore current clinical detection practices, and discuss potential areas to optimize early detection.

    FDA-cleared AI-powered OCT Glaucoma Risk Assessment

    Demo Account Get brochure

     

    What we know about Glaucoma

    Glaucoma is a complex neurodegeneration fundamentally linked to changes occurring in two locations: the anterior eye (elevated pressure) and the posterior eye (optic neuropathy). Factors influencing glaucoma development include:

    • age,
    • ethnicity,
    • family history,
    • corneal thickness,
    • blood pressure,
    • cerebrospinal fluid pressure,
    • intraocular pressure (IOP),
    • and vascular dysregulation.

    Early stages of Glaucoma are often asymptomatic, highlighting the importance of comprehensive eye exams, even without apparent vision issues. Current diagnostic criteria are insufficient and lack markers of early disease.

    Glaucoma is broadly divided into primary and secondary types, with primary open-angle Glaucoma (POAG) representing approximately three-quarters (74%) of all glaucoma cases. 

    Primary glaucomas develop independently of other eye conditions, while secondary glaucomas arise as a complication of various eye diseases, injuries, or medications.

    POAG is characterized by an open iridocorneal angle, IOP usually > 21 mmHg, and optic neuropathy. Risk factors include age (over 50), African ancestry, and elevated IOP. While IOP is a significant factor, it’s unpredictable – some patients with high IOP don’t develop Glaucoma, and some glaucoma progresses even at normal IOP.

    Normal-tension Glaucoma (NTG) shares POAG’s optic nerve degeneration but with consistently normal IOP levels (<21mmHg). Vascular dysregulation and low blood pressure are risk factors. While rarer than POAG, IOP lowering can still be beneficial.

    Primary Angle-Closure Glaucoma (PACG) is caused by narrowing the iridocorneal angle, blocking aqueous humor flow. More common in East Asian populations, it can be acute (severe symptoms, IOP often > 30mmHg) or chronic.

    Secondary glaucomas are caused by underlying conditions that elevate IOP. Examples include pseudoexfoliative, neovascular, pigmentary, and steroid-induced Glaucoma.

    Age is a central risk factor for glaucoma progression, linked to cellular senescence, oxidative stress, and reduced resilience in retinal ganglion cells and the trabecular meshwork. Intraocular pressure (IOP) remains the most significant modifiable risk factor. Understanding individual susceptibility to IOP-related damage is crucial. Existing IOP-lowering treatments have limitations in both efficacy and side effects.

     Intraocular pressure measuring device for early glaucoma detection

    Glaucoma has a strong genetic component, with complex interactions between genes, signaling pathways, and environmental stressors. For now, we know that mutations in each of three genes, myocilin (MYOC), optineurin (OPTN), and TANK binding kinase 1 (TBK1), may cause primary open-angle Glaucoma (POAG), which is inherited as a Mendelian trait and is responsible for ~5% of cases (Mendelian genes in primary open-angle Glaucoma).

    More extensive effect mutations are rare, and more minor variants are common. Genome-wide association studies (GWAS) reveal additional genes potentially involved in pressure sensitivity, mechanotransduction, and metabolic signaling. 

    Recent research also suggests a window of potential reversibility even at late stages of apoptosis (a programmed cell death pathway, which is likely the final step in RGC loss). Cells may recover if the harmful stimulus is removed. This offers hope that dysfunctional but not yet dead RGCs could be rescued.

    The Challenges of Early Glaucoma Detection

    One of the most insidious aspects of Glaucoma is its largely asymptomatic nature, especially in the early stages. This highlights the limitations of relying on symptoms alone and underscores the importance of proactive detection strategies.

    Relying on intraocular pressure (IOP) as a stand-alone glaucoma biomarker leads to missed diagnoses, especially in patients with normal-tension Glaucoma. Structural changes, such as optic disc cupping, also lack the desired sensitivity and specificity for early detection.  

    Optic nerve head evaluations remain subjective, with studies indicating that even experienced ophthalmologists can underestimate or overestimate glaucoma likelihood.  

    According to the research, even experienced clinicians can have difficulty evaluating the optic disc for Glaucoma. Both trainees and comprehensive ophthalmologists have been found to underestimate glaucoma likelihood in approximately 20% of disc photos. They may also misjudge risk due to factors like variations in cup-to-disc ratio, subtle RNFL atrophy, or disc hemorrhages.  

    Current Glaucoma Diagnosis in Clinical Practice

    Eye care professionals typically encounter new glaucoma diagnoses in one of two ways:

    • Firstly, during routine preventive examinations. A patient may come in for various reasons, including work requirements, and be found to have elevated intraocular pressure. This finding prompts further evaluation, potentially leading to a glaucoma diagnosis.
    • Secondly, it is a finding in older patients (often over 50-60). A patient may present with significant vision loss in one eye, and examination reveals Glaucoma. Unfortunately, vision loss at this stage is often irreversible.

    Alternatively, a patient may seek care for an unrelated eye problem. During the comprehensive examination, the eye care professional may discover changes suggestive of Glaucoma.

    As it is statistically prevalent, we most often work with primary Glaucoma, where no other underlying eye diseases are present. Functional changes, specifically as seen on visual field testing, help diagnose and stage glaucoma. During the test, a patient indicates which light signals are visible within their field of vision, building a map of each eye’s visual function. 

    Vision Field Test for Glaucoma Detection

    Vision text for glaucoma detection

    As the optic nerve transmits visual information from the retina to the brain and each part of the retina transmits data via a corresponding set of fibers within the optic nerve, damage to specific nerve fibers results in loss of the associated portion of the visual field.

    Challenges with this test include its complexity, especially for older patients, and its subjective nature.

    Changes in the visual field determine glaucoma severity. These changes indicate how much of the visual field is already damaged and which parts of the optic nerve are compromised. We call these ‘functional changes‘ as they directly impact visual function.

    Fundus photo for Glaucoma detection

    Alongside functional changes, Glaucoma causes visible structural changes in the optic nerve that can be observed during a fundus examination. The optic nerve begins at a point on the retina where all the nerve fibers gather, forming the optic disc (or optic nerve head). The nerve fibers are thickest near the optic disc, creating a depression or ‘hole’ within it. As Glaucoma progresses, this depression deepens due to increased pressure inside the eye. This pressure causes mechanical damage to the nerve fibers, leading to thinning and loss of function.

    Another crucial area on the retina is the macula, which contains a high density of receptors responsible for image perception. While the entire retina senses images, the macula provides the sharpest, clearest vision. We use this area for tasks like reading, writing, and looking at fine details. Therefore, the damage to the macular area significantly impacts a patient’s visual quality and clarity. Nerve fibers carrying visual information from this crucial region are essential when evaluating the visual field. We prioritize assessing the macula’s health because it directly determines the quality of a patient’s central vision.

    Unfortunately, even if the macula is healthy, damage to the nerve fibers transmitting its signals will still compromise vision.

    Glaucoma OCT detection

    The most effective way to get information about nerve states is OCT, which allows us to penetrate deep into the layers to see the nerve fiber layer separately, making it possible to assess the extent of damage and thinning to this layer in much more detail. 

    Retinal Layers shown on OCT, including Inner Plexiform Layer, Nerve Fiber Layer and Ganglion Cell Complex

    The Glaucoma OCT test provides valuable information about ganglion cells. These cells form the nerve fiber layer and consist of a nucleus and two processes. The short process collects information from other retinal layers, forming the inner plexiform layer. The ganglion cell layer comprises the cell nuclei, while the long processes extend out to create the nerve fiber layer.

    Damage to the ganglion cells or their processes leads to thinning across these layers, which we can measure as the thickness of the ganglion cell complex. OCT often detects these microscopic changes before we can see them directly. This enables the detection of structural changes alongside the functional changes observed with standard visual field tests.

    Ideally, OCT would be more widely accessible, as the human eye cannot detect early changes. However, how often a patient undergoes OCT depends on various factors. These include the doctor’s proficiency with the technology, the patient’s financial situation (as OCT can be expensive), and the overall clinical picture.  

    Ways to Enhance Early Glaucoma Detection 

    We surveyed eye care specialists, and there was a strong consensus that the most efficient ways to boost early glaucoma detection are regular eye check-ups (47%) and utilizing AI technology (40%). Educating patients was considered less significant (13%).

    Eye care professionals survey on ways to the most efficient ways to boost early glaucoma detection

    AI as a second opinion tool

    AI offers valuable insights into glaucoma detection, analyzing changes that may not be visible to the naked eye or even on standard OCT imaging.

    The Altris AI Early Glaucoma Risk Assessment Module specifically focuses on analyzing the ganglion cell complex, measuring its thickness, and identifying any thinning or asymmetry. These measurements help determine a patient’s glaucoma risk. If the ganglion cell complex has an average thickness and is symmetrical throughout the macula, the module will assign a low probability of Glaucoma.

    Asymmetries or variations in thickness increase the calculated risk, indicated by a yellow result color. Glaucoma GCC is often characterized by thinning or asymmetry, suggesting glaucomatous atrophy, indicating a high risk, and triggering a red result color.

    Changes are labeled as ‘risk’ rather than a diagnosis, as other clinical factors contribute to a confirmed glaucoma diagnosis. Indicators of atrophy could also signal different optic nerve problems, such as those caused by inflammation, trauma, or even conditions within the brain.

    Conor Reynold on the most efficient ways to boost early glaucoma detection

    It’s crucial to remember that AI glaucoma detection tools like this are assistive – they cannot independently make a diagnosis. Similarly, while helpful in assessing risk, they cannot completely rule out the possibility of developing a disease. This limitation stems from their reliance on a limited set of indicators. Like other technical devices, the module helps flag potential pathology but does not replace the clinician’s judgment.

    AI can be incredibly valuable as a supplemental tool, especially during preventive exams or alongside other tests, to catch possible early signs of concern. However, medicine remains a field with inherent variability. While we strive for precise measurements, individual patients, not just statistical averages, must be considered. 

     Therefore, it is unrealistic to expect devices to provide definitive diagnoses without the context of a complete clinical picture.

    Public Health Education 

    Elderly patient is investigating his OCT report with color coded by Altris AI biomarkers

    The asymptomatic nature of Glaucoma in its early stages, paired with limited public awareness, creates a fundamental barrier to early detection. 

    For example, 76% of Swiss survey respondents could not correctly describe Glaucoma or associate it with eye health. 

    A Canadian study similarly shows that less than a quarter of participants understand eye care professionals’ roles correctly and that most people are unaware eye diseases can be asymptomatic.  

    Crucially, these studies also found a strong desire across populations for more information about eye care, including Glaucoma (e.g., 97% of Swiss respondents agreed the public lacks knowledge, and 71% want more information). This indicates a receptive audience for targeted education initiatives.

    Health education programs, like the USA EQUALITY study, demonstrate the potential to address this challenge. This study combined accessible eye care settings with a culturally sensitive eye health education program, targeting communities with high percentages of individuals at risk for Glaucoma. 

    Maria Sampalis on the most efficient ways to boost early glaucoma detection

    Participants showed significant improvements in both glaucoma knowledge (a 62% increase in knowledge questions) and positive attitudes toward the importance of regular eye care (52% improvement). 

    These results show us that improving glaucoma detection involves more than medical tools. Successful education strategies should prioritize community outreach, partnering with community centers, primary care clinics, and local organizations to reach those lacking access or awareness of regular eye care. 

    Information about Glaucoma must be presented clearly and accessible, focusing on the basics—what Glaucoma is, its risk factors, and the importance of early detection. Addressing common misconceptions, such as the belief that Glaucoma can’t be present if vision is good, is crucial, as is targeting high-risk groups, including older adults, those with a family history of Glaucoma, and certain ethnicities.

    Screening Programs and Regular visits

    Community-based studies consistently demonstrate the benefits of targeted screening programs for early glaucoma detection in high-risk populations. 

    These programs are essential, as traditional glaucoma screening methods often miss individuals with undetected disease.

    Luke Baker on the most efficient ways to boost early glaucoma detection

    The USA Centers for Disease Control and Prevention (CDC) funded SIGHT studies focused on underserved communities, including those in urban areas with high poverty rates (MI-SIGHT, Michigan), residents of public housing and senior centers (NYC-SIGHT, New York), and the rural regions with limited access to specialist eye care (AL-SIGHT, Alabama). These programs successfully reached populations who often don’t have regular eye care. 

    Notably, the results across all three studies demonstrate the effectiveness of targeted programs – approximately 25% of participants screened positive for Glaucoma or suspected Glaucoma. 

    The SIGHT studies recognize that screening is just the first step, highlighting the importance of follow-up care, testing ways to improve follow-through, using strategies like personalized education, patient navigators, financial incentives, and providing free eyeglasses when needed.

    Summing up

    FDA-cleared AI-powered OCT Glaucoma Risk Assessment

    Demo Account Get brochure

     

    Glaucoma’s insidious nature demands better early detection strategies. While existing methods are essential, we must also invest in new technologies like AI, enhance public health education about Glaucoma, and focus on targeted screening within at-risk populations. Combining these approaches can protect sight and reduce the burden of glaucoma-related blindness.

     

  • Effective Eye Care Innovation: Altris AI for the Eye Place

    Altris AI
    1 min.

    The Client: the Eye Place is an optometry center in Ohio, the United States. It is a renowned center that provides comprehensive eye examinations, infant and pediatric eye care, emergency care, LASIK evaluations, and cataract assessment. They offer precise personalized care plans to better treat and prevent ocular disease and chronic illness. Scott Sedlacek, the optometry center owner, is an experienced OD, an American Optometric Association member, and a true innovator who implemented AI for OCT in the optometry practice among the first in the USA.

    The Problem:  The Eye Place owner has always been searching for innovations to transform the center making it truly digital.  The aim of the innovation was also to augment the analysis ability of the optometry specialists using it, while allowing for better visualization of the retinal layers affected for doctors and patients.

    The Solution: The Altris AI system was introduced in the Eye Place and it transformed the practice making it more efficient. Scott Sedlacek, the owner of the practice admits that:

    “We are one of the first Optometry offices with this AI technology. It is amazing at detecting and defining pathology in the 3D digital images I take with my Topcon Maestro2 OCT. We use Image Net6 software to export Dicom files to Altris AI. It’s fast and easy. If you want the right diagnosis, right away, this is the way to go.

    I’ve been using this technology on every patient every day since the beginning of January 2024. There is no other technology in my 25 years being an optometrist that was easier to implement and more impactful immediately.”

    FDA-cleared AI for OCT analysis

    Demo Account Get brochure

     

    effective eye care innovation

    ROI of the AI for OCT scan analysis

    Many eye care specialists worry about the ROI of Altris AI: will the system pay off? After all, it is an investment. That is the experience of Scott, the owner of the Eye Place:

    “Altris AI identified and described pathology that I could not. Early detection changes the treatment from doing nothing to something. Also, Altris AI described something that I thought was worse than it was. Saved me from over-referring. Patients love to see the color-coded images which help as an educational tool and get buy-in on the treatment plan which helps compliance. There is a wow factor for me and my patients that sets your practice apart from the others.”

    Effective Eye Care Innovation: What Else?

    Apart from AI for OCT analysis, the Eye Place utilizes advanced technology for diagnostics.

    • For instance, 3D OCT equipment is a highly advanced screening system that checks for serious conditions such as glaucoma, diabetes, macular degeneration, vitreous detachments, and more. Using this technology we can simultaneously take a digital photograph and a 3-D cross-section of the retina.
    • Additionally, AdaptDX Pro can detect macular degeneration earlier than by any other means.
    • Cognivue Thrive is a personalized, consistent, and reliable way to receive an overall screening of brain health.It is interactive, non-invasive, self-administered, secure, and confidential. It is a five-minute screening for patients of all ages, and you get immediate results in a simple 1-page report.

    These are just some examples of innovative tools that optometry centers can use to automate and improve the level of diagnostics. If you want to imagine how Optometry Centers might look like in 2040, here is the article for you. The future is here, and those centers that digitalize have more chances of winning the competition and the hearts of the clients, much like the Eye Place which is highly appreciated by patients.

    As you see, effective eye care innovations are an integral part of the work of the Eye Place which is why Artificial Intelligence for OCT analysis was seamlessly integrated into the workflow of the optometry center.

     

     

  • Will AI have a Positive Effect on Eye Care Specialists?

    Cover for an article about AI in eye care
    Maria Martynova
    18.03.2023
    13 min read

    Will AI improve your practice or it’s another hype topic that will vanish like NFT or VR glasses?

    This article examines present AI’s impact on eye care specialists, exploring its promises and challenges. To gain a realistic view, we surveyed eye care specialists on their experiences and expectations of this topic.

    Let’s start with what has already been implemented in eye care and the results we can see already.

    FDA-cleared AI for OCT Analysis

    Demo Account Get brochure

    AI in Eye Care Industry: Current Status

    Disease screening: DR, AMD, and rare pathologies & biomarkers

    A 2022 study by the University of Illinois showed that eye care specialists mostly see AI helping with disease screening, monitoring, and patient triage tasks. Notably, a significant increase in willingness to incorporate AI in practice has emerged after the COVID-19 pandemic, presumably due to a need for remote consultations.

    Optometrists Survey Infographic on AI implementation in eye care practice

    The growing interest in AI for disease screening and monitoring coincides with the development of sophisticated AI systems. Due to their significant causes of visual impairment, Diabetic Retinopathy and AMD are the primary targets for AI screenings.

    With over 422 million people worldwide affected by diabetic retinopathy and an estimated 80 million suffering from age-related macular degeneration, the workload on eye care specialists is immense. Unsurprisingly, most AI-powered screening solutions focus on helping clinicians with these diagnoses.

    AI algorithms are trained to recognize DR-related alterations on images: hemorrhages, exudates, and neovascularization. AI also offers significant advancements in Age-related Macular Degeneration screening. Algorithms accurately segment data in OCT scans, helping assess retinal structures and quantify fluids during treatment. Trained models predict disease progression risks and analyze treatment responses.

    Screenshot of Wet AMD detected by Altris AIAI in eye care can segment retinal structures to distinguish between normal retina scans and pathology on OCT, detect atrophic changes, and follow all alterations over time. It can even highlight rare inherited retinal dystrophies. For example, Altris AI is trained to recognize Vitelliform dystrophy and Macular telangiectasia type 2.

    More Efficient Patient Triage

    The number of eye scans clinicians are performing is growing at a pace much faster than human experts are able to interpret them. This delays the diagnosis and treatment of sight-threatening diseases, sometimes with devastating results for patients.

    Our recent survey showed that among more than 1000 participating eye care specialists, 40% have more than 10 OCT exams daily. Meanwhile, 35% of eye care specialists have 5-10 OCT daily examinations. Unfortunately, more patients per day mean an increased risk that specialists may miss some minor, rare, or early conditions.

    Infographic on survey for eye care professionals Why would you avoid offering OCT

    AI systems can quickly triage scans based on severity. Prioritized urgent cases can be flagged for immediate attention. Healthy patients can be monitored without urgency.

    This ensures patients with time-sensitive conditions get the care they need, while less urgent cases receive a timely but less immediate review.

    Optometrists can use AI systems to specify the need to refer patients based on eye image analysis.

    Louise Steenkamp eye care professional, quotation on AI usage in optometry and ophthalmology

    Another advantage of AI used as a “copilot” is its continuous improvement. Providers that create such systems usually integrate new data and research findings into algorithms, resulting in an ever-evolving resource for eye care specialists.

    In other words, the accuracy of the patients’ triage will get better and better with the data.

    Early Glaucoma Detection

    Glaucoma is a leading cause of vision-related morbidity worldwide. Although blindness is the most feared outcome, even mild visual field loss may harm the quality of life.

    In a way, glaucoma is one of the most challenging eye diseases that specialists must treat; with most eye problems, the patient comes when something is wrong. Glaucoma, however, has no symptoms until it is advanced, and the damage can not be reversed.
    One common reason glaucoma is not diagnosed early is the inability to recognize glaucomatous optic disc and RNFL damage. Ophthalmologists often rely primarily on intraocular pressure and visual fields and not on the appearance of the optic disc.

    Craig McArthur, eye care professional, quotation on AI usage in optometry and ophthalmology

    Combining optical coherence tomography imaging and artificial intelligence, Altris AI offers a solution to the problem. The platform performs Ganglion Cell Complex asymmetry analysis on OCT scan that categorizes the risk of developing glaucoma. Glaucoma Early Risk Assessment Module can help decrease the number of false-positive referrals and increase the standard of care by supporting early diagnosis to improve patients’ prognosis.

    Better Education for Patients

    Eye care specialists don’t always have time to explain to patients what is going on with their eye health.

    Artificial intelligence can easily perform this task. AI systems will also enhance eye care education, offering innovative and immersive learning experiences: with the help of color-coding, user-friendly reports, and chat bots.

    AI-generated OCT reports can propel patient education and engagement. By translating complex medical data into clear, visual formats, AI can help understand patients’ diagnoses, significantly improving treatment adherence and fostering greater patient loyalty.

    For example, Altris AI employs smart reports with color-coded segmentation of pathologies that are easy for clinicians and their patients to understand.

    Biomarkers detected by Altris AI on OCT

    When patients fully grasp the nature of their eye conditions and track therapy progress, they are far more likely to prioritize annual checkups and actively engage in their care.

    Teleoptometry and teleophthalmology

    The COVID-19 pandemic has accelerated the adoption of telemedicine, especially in the image-rich field of ophthalmology.

    In recent years, many digital home measurement tests have been introduced. These include home-based and smartphone/tablet-based devices, which are cost-effective in specific patient cohorts.

    One example is an artificial intelligence-enabled program for monitoring neovascular Age-related Macular Degeneration (nAMD) that uses a home-based OCT device. Patient self-measurements from home have proved to be a valuable adjunct to teleophthalmology. In addition to reducing the need for clinical visits, they serve as a collection of high-quality personal data that can guide targeted management.

    Currently, most commercial providers of telemedical services and devices use artificial intelligence. However, these services are not autonomous. AI works simultaneously with so-called “backup” ophthalmologists. If a finding is unknown or unclear to the artificial intelligence, an ophthalmologist reads the image.

    Non-medical AI: General Workflow Enhancements

    COVID-19 made it crystal clear that healthcare worldwide has a full spectrum of problems, such as staffing shortages, fragmented technologies, and administrative complexities. So, the AI boom three years after the pandemic has come timely and handy.

    Louise Steenkampю eye care professional, quotation on AI usage in optometry and ophthalmology

    Intelligent algorithms can solve the mentioned issues. For example, generative AI can enable easier document creation by digesting all types of reports and streamlining them. It can also ease the administrative workload for short-staffed clinicians (the average US nurse spends 25% of their work time on regulatory and administrative activities).

    Probabilistic matching of data across different databases, typical for Machine Learning, is another technology that can take a burden off staff about claims and payment administration.

    Patient engagement and adherence also can benefit from the technology. Providers and hospitals often use their expertise to develop a plan to improve a patient’s health, but that frequently doesn’t matter as the patient fails to make the behavioural adjustment. AI-based capabilities can personalize and contextualize care, using machine learning for nuanced interventions. It can be messaging alerts and targeted content that provokes actions at needed moments or better-designed ‘choice architecture’ in healthcare apps.

    Another side of the coin: AI for OCT limitations

    When discussing AI in eye care, it’s essential to recognize that AI is a tool. Like any tool, it is neutral. So, its effectiveness and potential for unintended consequences hinge not only on the quality of its design and the data used to train it but also on the expertise of the healthcare professionals interpreting its output. Here are some of the challenges to keep in mind when working with AI.

    AI is fundamentally limited by the datasets used for training. An outsized amount of images can slow training and lead to overfitting, while a lack of demographic diversity compromises accuracy.

    Thomas Mirabile, eye care professional, quotation on AI usage in optometry and ophthalmology

    One challenge facing AI implementation in medicine is the interdisciplinary gap between technological development and clinical expertise. These fields are developing separately and usually do not intersect. Therefore, cross-collaboration can suffer because tech experts may not understand medical needs, and clinicians may not have the technical knowledge to guide AI development effectively.

    So, a successful AI solution requires bridging this breach to ensure AI solutions are grounded in medical realities and address the specific needs of clinicians (Clinical & Experimental Ophthalmology, 2019).

    The commercialization of AI will also pose future issues. Trained models will likely be sold with and for implementation with certain medical technologies. Additionally, if AI does improve medical care, it will be essential to pass those improvements on to those who cannot afford them.

    Overreliance on the technology can also be a problem.

    Craig McArthur, eye care professional, quotation on AI usage in optometry and ophthalmology

    AI is a tool, like any other equipment in the clinical environment. Decision-making is always on the side of an eye care practitioner who has to take into account many additional data: clinical history, other lab results, and concomitant diseases in order to make a final diagnosis.

    And, of course, there are ethical dilemmas. Many practical problems can be solved relatively easily – secure storage, anonymization, and data encryption to protect patient privacy. However, some of them need a whole new field of law. The regulations surrounding who holds responsibility in case of a misdiagnosis by AI is still a significant question mark. Since most current AI algorithms diagnose not so many diseases, there is room for error by omission, and a correct AI diagnosis is not a comprehensive clinical workup.

    Summing up

    Dr. Katrin Hirsch, eye care professional, quotation on AI usage in optometry and ophthalmology

    While AI in eye care isn’t without limitations and ethical considerations, its revolutionizing potential is hardly deniable. It already has proven itself working with disease screening, monitoring, and triaging, saving specialists time and improving patient outcomes. AI offers a “second opinion” for complex cases and expands access through telemedicine.

    FDA-cleared AI for OCT Analysis

    Demo Account Get brochure

    Yet, despite all its promises, the implementation of AI in practice should be seen as a new tool and technique, like the invention of the ophthalmoscope, IOL, OCT, and fundus camera. Optometrists and ophthalmologists will need to combine the best of their clinical skills and AI tools for best practices. Being an innovative tool does not make AI a magic wand, fortunately or not.

     

  • Technologies in Optometry: Altris AI for Clare and Illingworth

    technologies in optometry
    Altris Team
    3 min.
    3 min.

    The Client: Clare and Illingworth, renowned leaders in the field of optometry located in the UK.

    The problem: The need to speed up the process of OCT interpretation and unburden the optometry team.

    The Solution: Clare and Illingworth have embraced cutting-edge technology to enhance their Optical Coherence Tomography (OCT) analysis workflow. The introduction of Altris AI at this optometry center marks a significant milestone in their commitment to providing high-quality services to patients.

    According to one of the owners of the optometry center, Richard, “We are adding a new OCT to one of our practices and will benefit from some extra support with AI to speed up the interpretation of results and assist the busy Optometry team.”

    Altris AI, a leading provider of artificial intelligence solutions for healthcare, specializes in developing algorithms and software applications that augment medical imaging analysis. The integration of Altris AI into the British Optometry Center’s OCT workflow brings forth a host of advantages, revolutionizing the way eye conditions are diagnosed and managed.

    FDA-cleared AI for OCT Analysis

    Try it yourself in our Demo Account or get a Brochure

    Demo Account Get brochure

     

    Technologies in Optometry and Ophthalmology: How AI Helps

    One of the key benefits of Altris AI is its ability to automate and expedite the analysis of OCT scans. Traditionally, optometrists spent considerable time manually reviewing and interpreting OCT images.

    FDA-cleared Altris AI is created to make the OCT workflow more effective

    How does it work? Altris AI serves as a copilot, analyzing OCT scans in parallel to the eye care specialist. For instance, on this OCT scan, Altris AI detects Diffuse Edema, Floaters, Intraretinal Hyperreflective Foci, Posterior Hyaloid Membrane Detachment, RPE disruption, Shadowing, Hard Exudates, Intraretinal Cystoid Fluid. 

    • The classification in this case would be Diabetic Retinopathy. 

    AI blindness prevention

    With Altris AI, the process becomes significantly faster and more efficient. The AI algorithms can quickly analyze intricate details within the scans, providing clinicians with accurate and timely insights into the patient’s eye health.

    Moreover, the use of Altris AI contributes to increased diagnostic accuracy. The algorithms are trained on vast datasets, learning to recognize subtle patterns and anomalies that may escape the human eye.

    Thus, Altris AI recognizes 70+ retina pathologies and biomarkers, including DME, DR, GA, AMD, etc. 

    FDA-cleared AI for OCT Analysis

    Try it yourself in our Demo Account or get a Brochure

    Demo Account Get brochure

    Technologies in Optometry are paving the way to a new future where eye care specialists and AI will work together for better patient outcomes.  AI will never be able to substitute eye care specialists because the final diagnosis must include clinical history, results of lab tests, and other diagnostic methods.

     

  • Retina Layers Segmentation on OCT

    Maria Martynova
    5 min.
    5 min.

    The knowledge about macular retinal layer thicknesses and volume is an important diagnostic tool for any eye care professional today.  The information about the macular retinal layers often correlates with the evaluation of severity in many pathologies. 

    Manual segmentation is extremely time-consuming and prone to numerous errors, which is why OCT equipment manufacturers use automatic macular retinal layer thickness segmentation.

    Test FDA-cleared AI for OCT analysis

    Demo Account Get brochure

    Yet, retina layer segmentation in different OCT equipment manufacturers as well as in different OCT models varies significantly. It is sometimes difficult even for an experienced ECP to find the correlations and track the pathology dynamics. The normative bases refer only to the thickness of the entire retina, they are not related to segmentation. However, if the segmentation is performed incorrectly by the machine, it will lead to an incorrect calculation of the thickness of the retina or its layers, and then the assessment will be incorrect.

    At Altris AI we aim to visualize retina layers for a more accurate understanding of pathological process localization.  Such retina layers segmentation allows for defining the localization of the pathological process and tracing in dynamics the spread of the pathological process or the aftermath in the retina structure after its completion.

     

    For instance, the EZ layer is important in terms of vision loss forecasting.

    OCT Manufacturers  & Retina Layers Analysis

    From 2010 most eye care specialists have used the same OCT International Nomenclature for Optical Coherence Tomography. OCT equipment manufacturers rely on this nomenclature for retina layer thickness calculation and most ophthalmologists use it as well.

    Taking into account retina structure, some layers can be united into complexes. For instance, the ganglion complex includes RNFL, ganglion cell layer & OPL. 

    Let’s take a look at various OCT equipment manufacturers and the way they perform retina layer segmentation analysis. 

    For instance, here is how Topcon Advanced Boundary Segmentation (TABSTM) automated segmentation differentiates between nine intraretinal boundaries:

    • ILM
    • NFL/GCL,
    • GCL/IPL, 
    • IPL/INL, 
    • INL/OPL, 
    • ELM
    • EZ
    • OS/RPE
    • BM

    Zeiss CIRRUS uses two approaches to retina layer segmentation.  

    The existing segmentation algorithm (ESA) in CIRRUS estimates the positions of the inner plexiform layer (IPL) and outer plexiform layer (OPL) based on the internal limiting membrane (ILM) and retinal pigment epithelium (RPE). To improve the accuracy of the segmentation of these layers, a multi-layer segmentation algorithm (MLS) was introduced, it truly segments layers instead of estimating their position. 

    Heidelberg Engineering offers to learn about the following inner and outer retina layers on their website. There are 10 retina layers according to Heidelberg, and they are the following:

    • ILM
    • RNFL
    • GCL
    • IPL
    • INL
    • OPL
    • ONL
    • ELM
    • PR
    • RPE
    • BM
    • CC
    • CS

     

    Why accurate retina layer segmentation is important?

    Retina layers segmentation helps eye care professionals to understand which pathology to consider in the first turn. For instance, changes in RPE and PR signify the development of Macular Degeneration. 

    Often such changes can also inform eye care specialists about the development of pathologies that lead to blindness, such as glaucoma, AMD, and Diabetic Retinopathy. 

     

    • Early Glaucoma Detection

    Historically, evaluation of early glaucomatous change has focused mostly on optic disk changes.  Modalities such as optical coherence tomography (OCT), confocal scanning laser ophthalmoscopy (HRT) or scanning laser polarimetry (GDx) with specially developed software algorithms have been used to quantitatively assess such changes. However, glaucomatous damage is primarily focused on retinal ganglion cells, which are particularly abundant in the peri-macular region (the only retinal area with a ganglion cell layer more than 1 layer thick), constituting, together with the nerve fiber layer, up to 35% of retinal macular thickness.

     Therefore, glaucomatous changes causing ganglion cell death could potentially result in a reduction of retinal macular thickness. Indeed, by employing specially developed algorithms to analyze OCT scans, previous studies have reported that glaucoma, even during the early stage, results in the thinning of inner retinal layers at the macular region.

    According to this study, the RNFL, GCL, and IPL levels out of all the retinal layers, the inner-most layers of the retina: the retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL) show the best discriminative power for glaucoma detection. Among these, the RNFL around the circumpapillary region has shown great potential for discrimination. The automatic detection and segmentation of these layers can be approached with different classical digital image processing techniques.

    Test FDA-cleared AI for OCT analysis

    Demo Account Get brochure

     

    • Detection of AMD

    This first population-based study on spectral-domain optical coherence tomography-derived retinal layer thicknesses in a total of ∼1,000 individuals provides insights into the reliability of auto-segmentation and layer-specific reference values for an older population. 

    The findings showed a difference in thicknesses between early AMD and no AMD for some retinal layers, suggesting these as potential imaging biomarkers. When comparing layer thicknesses between early AMD and no AMD (822 eyes, 449 participants), the retinal pigment epithelium/Bruch’s membrane complex demonstrated a statistically significant thickening, and photoreceptor layers showed a significant thinning.

    • Detection of DR

    The depth and spatially resolved retinal thickness and reflectance measurements are potential biomarkers for the assessment and monitoring of Diabetic Retinopathy, one of the key reasons for blindness around the globe.

    For instance, this study confirmed that decreased RNFL thickness and increased INL/OPL thickness in diabetics without DR or with initial DR suggest early alterations in the inner retina. On the contrary, the outer retina seems not to be affected at the early stages of DM. Automatic intraretinal layering by SD-OCT may be a useful tool to diagnose and monitor early intraretinal changes in DR.

    Conclusion:

    Retina layer segmentation is crucial for the accurate detection of pathologies in the eye, especially in the field of ophthalmology and medical imaging. Here are several reasons why it is important:

    Precise Diagnosis: Retina layer segmentation provides a detailed map of the different retinal layers, which helps in the precise diagnosis of various eye conditions. It allows clinicians to identify the exact location of abnormalities, such as cysts, hemorrhages, or lesions, within the retina.

    Quantitative Analysis: It enables quantitative analysis of retinal structures. By measuring the thickness, volume, and other characteristics of specific layers, clinicians can assess the severity and progression of diseases like diabetic retinopathy, macular degeneration, and glaucoma.

    Early Detection: Some retinal pathologies manifest in specific layers of the retina before becoming visible on a fundus photograph. Retina layer segmentation can help detect these changes at an early stage, potentially leading to earlier intervention and improved outcomes.

    Treatment Planning: Knowing the precise location of pathologies within the retina’s layers can aid in the planning of treatment strategies. For example, in cases of macular holes or retinal detachment, surgeons can use this information to guide their procedures.

    Monitoring Disease Progression: Retina layer segmentation is valuable for monitoring how retinal diseases progress over time. Changes in the thickness or integrity of specific layers can be tracked to assess the effectiveness of treatments or the worsening of conditions.

     

  • Altris AI for Buckingham and Hickson Optometry, the UK

    Altris Team
    1 min.

    The Client: Buckingham and Hickson is a family-run optometry practice that was established in 1960 in the United Kingdom. The optometry practice offers a number of services:

    • Wide range of spectacle frames and lenses.
    • Contact lenses.
    • Glaucoma referral refinement.
    • Cataract choice referral.
    • OCT examination.
    • NHS and private eye tests.
    See how it works

    FDA approved AI for OCT scan analysis

    Demo Account Get brochure

     

    The challenge: The optometry owners wanted to test how Artificial Intelligence can assist them in OCT examination or, to be more precise, in providing a second opinion regarding OCT scans.

    OCT examination is one of the best retina diagnostics methods, however in many cases OCT scan interpretation can be really challenging for several reasons:

    1. Variability in Anatomy: There is significant natural anatomical variation among individuals. What may be considered normal for one person may be abnormal for another. Eye care specialists need to account for these variations when interpreting OCT scans, but this often requires years of experience.
    2. Various Eye Conditions: Eye care specialists use OCT scans to diagnose and monitor a wide range of eye conditions, including macular degeneration, diabetic retinopathy, and retinal detachment, among others. Each of these conditions can manifest in different ways on OCT scans, making interpretation challenging.
    3. Progression Monitoring: Ophthalmologists often use OCT to monitor disease progression and the effectiveness of treatment. Tracking subtle changes over time can be difficult, as it requires precise comparisons of multiple scans.
    4. Artifacts: OCT scans are susceptible to artifacts, such as shadowing, motion artifacts, and signal dropout, which can obscure or distort the image. Recognizing and mitigating these artifacts is essential for accurate interpretation.
    5. Experience and Training: Accurate interpretation of OCT scans in optometry and ophthalmology requires specialized training and experience.
    6. Evolving Technology: OCT technology continues to advance, introducing new techniques and capabilities. Staying current with these advancements and understanding their clinical implications is an ongoing challenge for ophthalmologists.

    The solution: Artificial intelligence (AI) can play a significant role in OCT (Optical Coherence Tomography) scan interpretation for ophthalmologists and optometrists in various ways. Artificial Intelligence (AI) provides eye care specialists with more accurate results, severity level detection ( to work only with pathological scans), and assists in early pathologies detection.
    According Ian, one of the owners of Buckingham and Hickson optometry, “they are using Altris AI to get a second opinion on OCT scans.”
    According to Altris AI Medical Director, Maria Znamenska, who is MD, Ph.D., Associate Professor of Ophthalmology, “It is getting more common to double-check the interpretation of OCT scans ( and other medical images) with modern AI tools as they are getting safer and more efficient. Altris AI has received FDA clearance recently apart from having a CE certificate.”
  • 8 Reasons why Optometry Groups Invest in Artificial Intelligence for OCT Scan Analysis

    Mark Braddon
    5 min.

    Optometry chains offer a wide range of eye care services, making it convenient for patients to access eye care locally. 

    However, the widespread accessibility of optometry chains has a reverse side for them. The shortage of employees, new unfamiliar equipment for diagnostics, and a large number of patients create an extremely challenging workflow for many optometrists. This, in turn, creates a number of challenges that can be more familiar to Optometry chains: low optometrist recruitment and retention, inconsistent quality of examination throughout the practices, lack of communication with patients, etc. 

    Automation of routine processes and digitalization have always served as answers to challenges like these in any industry, and healthcare is no exception. Luckily, automation of one of the most complex tasks for optometrists – OCT examination is already available to optometry chains with Artificial Intelligence (AI).   

    OCT proves to be one of the most efficient diagnostic tools for many modern top-notch optometry practices, however, mastering it requires skills and time. Artificial intelligence tools, such as AI for OCT analysis platform, can automate many routine processes which will have enormous benefits for any optometry chain. The top 8 benefits are the following: 

    • #1 AI for OCT increases clinical efficiencies

    Automating OCT scan analysis through AI reduces the time optometrists spend on image interpretation. This allows optometrists to focus on more complex cases, patient interactions, and personalized treatment plans. For any large optometry chain, saving time means providing more patients with high-quality service. 

    How does it work in practice?

    For instance, Altris AI has a severity grading of b-scans. Severity grading means that it is easy to see if the eye is healthy ​(removing any need to spend time interpreting) or highlight ​where the pathology is and the degree of severity. ​

    • Green- no pathology detected
    • Yellow- mild to medium level of severity
    • Red – severe pathology detected

    • #2 AI for OCT provides consistently high standard of quality throughout the chain

    AI algorithms provide consistent and standardized analysis regardless of the individual interpreting OCT scans. This reduces variability in diagnoses and ensures that patients receive uniform care across different clinics and practitioners within the optometry chain.

    AI algorithms can analyze OCT scans with incredible precision and consistency. They can detect subtle changes in retinal structures that might be missed by human observers, leading to earlier and more accurate diagnoses of various eye conditions such as macular degeneration, glaucoma, diabetic retinopathy, and more.

    This will help younger less experienced optometrists and will serve as a second opinion tool for more experienced specialists. 

    Test how Altris AI analyzes OCT

    Demo Account Get brochure

    • #3  AI for OCT enables better retention of employees

    The shortage of optometrists in the world is staggering. 14 million optometry specialists are needed worldwide according to the WHO, while today there are only 331K ready to work.

     It is equally difficult to hire and retain a good optometrist for a company in 2023. However, more and more young optometrists choose innovative businesses that use technology to improve the workflow. Top-notch equipment, convenient scheduling tools, and of course, Artificial Intelligence for OCT & fundus photo analysis might be the perks that will help optometrists to choose your optometry business. 

    Fresh from college optometrists feel more confident when they know that they will have a backup when reviewing OCT scans

    • #4 Reduced Workload Burden

    Optometrists often have heavy workloads, and AI can help alleviate some of this burden by handling routine tasks like initial image analysis. This enables optometrists to spend more time on patient consultations and treatment planning.

    According to a survey by the General Optical Council, 57% of optometrists worked beyond their hours in 2022. Optometrists were more likely to be working beyond their hours (60%) or finding it difficult to provide patients with the sufficient level of care they needed (34%) when compared to other registration types.

    It is possible to outsource preliminary image analysis to Artificial Intelligence tools but communication and empathy are human tasks only. 

    • # 5 AI promotes enhanced patient education

    Let’s not forget about the patients. AI-generated OCT reports can help explain complex medical conditions to patients in a more understandable, visual way. After all 80% of all the information we receive is visual: imagine your optometrists not only telling but also showing what is going on with patients.  

    Comprehensive, color-coded OCT reports may improve patient education and engagement, leading to better treatment adherence and loyalty. 

    When patients don’t understand what they are paying for they are not likely to return for annual checkups. At Altris AI we created smart OCT reports that are comprehensible for patients as well as optometrists. We visualize all the pathologies and the patients can trace the dynamics of 

    #6 Reducing a clinical risk. No chances of getting a legal inquiry because of a pathology missed

    Optometry chains can perform around 40K OCT scans a week. Statistically speaking, the chance of missing a minor early pathology is huge simply because of the big number.

    With the double-check that AI for OCT scan analysis provides, It is not possible to wipe the risk out for 100%, but it is possible to diminish the risk to the absolute minimum. 

    For the optometry chain, it might mean no bad PR and weird stories in the papers and subsequently, a better brand image.

    • #7 AI makes early detection of pathologies possible on OCT

    AI algorithms can identify early signs of eye diseases that might not be easily recognizable in their early stage. This early detection can lead to timely interventions, preventing or minimizing patient vision loss.

    Glaucoma, Wet AMD, Diabetic Retinopathy, and genetic diseases are among the pathologies that lead to blindness if not detected in time. Detecting pathological signs and pathologies related to these disorders in time can literally save patients from future blindness.

    Early detection of pathologies means that it is possible to stop or reduce the risk of total blindness which is the best result in any sense. Early detection will allow optometrists to give valid recommendations, and advise on dieting and supplements right at the optical store. 

    • #8 Competitive Edge

    AI is a buzzword, and it’s not accidental. All major players understand its enormous value and invest in it. During the last presentation, the CEO of Google said “AI” 140 times, and let’s be honest, it is not to show off. It is because AI can actually make changes in business: automation of repetitive processes, workflow optimization, and human error reduction. 

    Adopting AI technology for OCT analysis showcases the optometry chain’s commitment to staying at the forefront of technological advancements in healthcare. Gaining a real competitive edge is another big goal. 

    This can attract patients who value cutting-edge approaches to diagnosis and treatment. A younger generation of patients are curious about new technologies, and this can be an additional lead magnet for them.

    Conclusion

    Incorporating AI for OCT analysis into optometry chains can enhance patient outcomes, make the workflow more efficient, and improve the performance of each optometry center. However, it’s important to ensure that the AI systems are properly validated, integrated into clinical workflows, and monitored to maintain their accuracy and effectiveness. More than that, it should complement, not replace, the expertise of optometrists. The technology should be used as a tool to aid optometrists and make OCT examination more effective.

     

Recently Posted

  • technologies in optometry

    Technologies in Optometry: Altris AI for Clare and Illingworth

    Altris Team
    3 min.
    3 min.

    The Client: Clare and Illingworth, renowned leaders in the field of optometry located in the UK.

    The problem: The need to speed up the process of OCT interpretation and unburden the optometry team.

    The Solution: Clare and Illingworth have embraced cutting-edge technology to enhance their Optical Coherence Tomography (OCT) analysis workflow. The introduction of Altris AI at this optometry center marks a significant milestone in their commitment to providing high-quality services to patients.

    According to one of the owners of the optometry center, Richard, “We are adding a new OCT to one of our practices and will benefit from some extra support with AI to speed up the interpretation of results and assist the busy Optometry team.”

    Altris AI, a leading provider of artificial intelligence solutions for healthcare, specializes in developing algorithms and software applications that augment medical imaging analysis. The integration of Altris AI into the British Optometry Center’s OCT workflow brings forth a host of advantages, revolutionizing the way eye conditions are diagnosed and managed.

    FDA-cleared AI for OCT Analysis

    Try it yourself in our Demo Account or get a Brochure

    Demo Account Get brochure

     

    Technologies in Optometry and Ophthalmology: How AI Helps

    One of the key benefits of Altris AI is its ability to automate and expedite the analysis of OCT scans. Traditionally, optometrists spent considerable time manually reviewing and interpreting OCT images.

    FDA-cleared Altris AI is created to make the OCT workflow more effective

    How does it work? Altris AI serves as a copilot, analyzing OCT scans in parallel to the eye care specialist. For instance, on this OCT scan, Altris AI detects Diffuse Edema, Floaters, Intraretinal Hyperreflective Foci, Posterior Hyaloid Membrane Detachment, RPE disruption, Shadowing, Hard Exudates, Intraretinal Cystoid Fluid. 

    • The classification in this case would be Diabetic Retinopathy. 

    AI blindness prevention

    With Altris AI, the process becomes significantly faster and more efficient. The AI algorithms can quickly analyze intricate details within the scans, providing clinicians with accurate and timely insights into the patient’s eye health.

    Moreover, the use of Altris AI contributes to increased diagnostic accuracy. The algorithms are trained on vast datasets, learning to recognize subtle patterns and anomalies that may escape the human eye.

    Thus, Altris AI recognizes 70+ retina pathologies and biomarkers, including DME, DR, GA, AMD, etc. 

    FDA-cleared AI for OCT Analysis

    Try it yourself in our Demo Account or get a Brochure

    Demo Account Get brochure

    Technologies in Optometry are paving the way to a new future where eye care specialists and AI will work together for better patient outcomes.  AI will never be able to substitute eye care specialists because the final diagnosis must include clinical history, results of lab tests, and other diagnostic methods.

     

  • Retina Layers Segmentation on OCT

    Maria Martynova
    5 min.
    5 min.

    The knowledge about macular retinal layer thicknesses and volume is an important diagnostic tool for any eye care professional today.  The information about the macular retinal layers often correlates with the evaluation of severity in many pathologies. 

    Manual segmentation is extremely time-consuming and prone to numerous errors, which is why OCT equipment manufacturers use automatic macular retinal layer thickness segmentation.

    Test FDA-cleared AI for OCT analysis

    Demo Account Get brochure

    Yet, retina layer segmentation in different OCT equipment manufacturers as well as in different OCT models varies significantly. It is sometimes difficult even for an experienced ECP to find the correlations and track the pathology dynamics. The normative bases refer only to the thickness of the entire retina, they are not related to segmentation. However, if the segmentation is performed incorrectly by the machine, it will lead to an incorrect calculation of the thickness of the retina or its layers, and then the assessment will be incorrect.

    At Altris AI we aim to visualize retina layers for a more accurate understanding of pathological process localization.  Such retina layers segmentation allows for defining the localization of the pathological process and tracing in dynamics the spread of the pathological process or the aftermath in the retina structure after its completion.

     

    For instance, the EZ layer is important in terms of vision loss forecasting.

    OCT Manufacturers  & Retina Layers Analysis

    From 2010 most eye care specialists have used the same OCT International Nomenclature for Optical Coherence Tomography. OCT equipment manufacturers rely on this nomenclature for retina layer thickness calculation and most ophthalmologists use it as well.

    Taking into account retina structure, some layers can be united into complexes. For instance, the ganglion complex includes RNFL, ganglion cell layer & OPL. 

    Let’s take a look at various OCT equipment manufacturers and the way they perform retina layer segmentation analysis. 

    For instance, here is how Topcon Advanced Boundary Segmentation (TABSTM) automated segmentation differentiates between nine intraretinal boundaries:

    • ILM
    • NFL/GCL,
    • GCL/IPL, 
    • IPL/INL, 
    • INL/OPL, 
    • ELM
    • EZ
    • OS/RPE
    • BM

    Zeiss CIRRUS uses two approaches to retina layer segmentation.  

    The existing segmentation algorithm (ESA) in CIRRUS estimates the positions of the inner plexiform layer (IPL) and outer plexiform layer (OPL) based on the internal limiting membrane (ILM) and retinal pigment epithelium (RPE). To improve the accuracy of the segmentation of these layers, a multi-layer segmentation algorithm (MLS) was introduced, it truly segments layers instead of estimating their position. 

    Heidelberg Engineering offers to learn about the following inner and outer retina layers on their website. There are 10 retina layers according to Heidelberg, and they are the following:

    • ILM
    • RNFL
    • GCL
    • IPL
    • INL
    • OPL
    • ONL
    • ELM
    • PR
    • RPE
    • BM
    • CC
    • CS

     

    Why accurate retina layer segmentation is important?

    Retina layers segmentation helps eye care professionals to understand which pathology to consider in the first turn. For instance, changes in RPE and PR signify the development of Macular Degeneration. 

    Often such changes can also inform eye care specialists about the development of pathologies that lead to blindness, such as glaucoma, AMD, and Diabetic Retinopathy. 

     

    • Early Glaucoma Detection

    Historically, evaluation of early glaucomatous change has focused mostly on optic disk changes.  Modalities such as optical coherence tomography (OCT), confocal scanning laser ophthalmoscopy (HRT) or scanning laser polarimetry (GDx) with specially developed software algorithms have been used to quantitatively assess such changes. However, glaucomatous damage is primarily focused on retinal ganglion cells, which are particularly abundant in the peri-macular region (the only retinal area with a ganglion cell layer more than 1 layer thick), constituting, together with the nerve fiber layer, up to 35% of retinal macular thickness.

     Therefore, glaucomatous changes causing ganglion cell death could potentially result in a reduction of retinal macular thickness. Indeed, by employing specially developed algorithms to analyze OCT scans, previous studies have reported that glaucoma, even during the early stage, results in the thinning of inner retinal layers at the macular region.

    According to this study, the RNFL, GCL, and IPL levels out of all the retinal layers, the inner-most layers of the retina: the retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL) show the best discriminative power for glaucoma detection. Among these, the RNFL around the circumpapillary region has shown great potential for discrimination. The automatic detection and segmentation of these layers can be approached with different classical digital image processing techniques.

    Test FDA-cleared AI for OCT analysis

    Demo Account Get brochure

     

    • Detection of AMD

    This first population-based study on spectral-domain optical coherence tomography-derived retinal layer thicknesses in a total of ∼1,000 individuals provides insights into the reliability of auto-segmentation and layer-specific reference values for an older population. 

    The findings showed a difference in thicknesses between early AMD and no AMD for some retinal layers, suggesting these as potential imaging biomarkers. When comparing layer thicknesses between early AMD and no AMD (822 eyes, 449 participants), the retinal pigment epithelium/Bruch’s membrane complex demonstrated a statistically significant thickening, and photoreceptor layers showed a significant thinning.

    • Detection of DR

    The depth and spatially resolved retinal thickness and reflectance measurements are potential biomarkers for the assessment and monitoring of Diabetic Retinopathy, one of the key reasons for blindness around the globe.

    For instance, this study confirmed that decreased RNFL thickness and increased INL/OPL thickness in diabetics without DR or with initial DR suggest early alterations in the inner retina. On the contrary, the outer retina seems not to be affected at the early stages of DM. Automatic intraretinal layering by SD-OCT may be a useful tool to diagnose and monitor early intraretinal changes in DR.

    Conclusion:

    Retina layer segmentation is crucial for the accurate detection of pathologies in the eye, especially in the field of ophthalmology and medical imaging. Here are several reasons why it is important:

    Precise Diagnosis: Retina layer segmentation provides a detailed map of the different retinal layers, which helps in the precise diagnosis of various eye conditions. It allows clinicians to identify the exact location of abnormalities, such as cysts, hemorrhages, or lesions, within the retina.

    Quantitative Analysis: It enables quantitative analysis of retinal structures. By measuring the thickness, volume, and other characteristics of specific layers, clinicians can assess the severity and progression of diseases like diabetic retinopathy, macular degeneration, and glaucoma.

    Early Detection: Some retinal pathologies manifest in specific layers of the retina before becoming visible on a fundus photograph. Retina layer segmentation can help detect these changes at an early stage, potentially leading to earlier intervention and improved outcomes.

    Treatment Planning: Knowing the precise location of pathologies within the retina’s layers can aid in the planning of treatment strategies. For example, in cases of macular holes or retinal detachment, surgeons can use this information to guide their procedures.

    Monitoring Disease Progression: Retina layer segmentation is valuable for monitoring how retinal diseases progress over time. Changes in the thickness or integrity of specific layers can be tracked to assess the effectiveness of treatments or the worsening of conditions.

     

  • Altris AI for Buckingham and Hickson Optometry, the UK

    Altris Team
    1 min.

    The Client: Buckingham and Hickson is a family-run optometry practice that was established in 1960 in the United Kingdom. The optometry practice offers a number of services:

    • Wide range of spectacle frames and lenses.
    • Contact lenses.
    • Glaucoma referral refinement.
    • Cataract choice referral.
    • OCT examination.
    • NHS and private eye tests.
    See how it works

    FDA approved AI for OCT scan analysis

    Demo Account Get brochure

     

    The challenge: The optometry owners wanted to test how Artificial Intelligence can assist them in OCT examination or, to be more precise, in providing a second opinion regarding OCT scans.

    OCT examination is one of the best retina diagnostics methods, however in many cases OCT scan interpretation can be really challenging for several reasons:

    1. Variability in Anatomy: There is significant natural anatomical variation among individuals. What may be considered normal for one person may be abnormal for another. Eye care specialists need to account for these variations when interpreting OCT scans, but this often requires years of experience.
    2. Various Eye Conditions: Eye care specialists use OCT scans to diagnose and monitor a wide range of eye conditions, including macular degeneration, diabetic retinopathy, and retinal detachment, among others. Each of these conditions can manifest in different ways on OCT scans, making interpretation challenging.
    3. Progression Monitoring: Ophthalmologists often use OCT to monitor disease progression and the effectiveness of treatment. Tracking subtle changes over time can be difficult, as it requires precise comparisons of multiple scans.
    4. Artifacts: OCT scans are susceptible to artifacts, such as shadowing, motion artifacts, and signal dropout, which can obscure or distort the image. Recognizing and mitigating these artifacts is essential for accurate interpretation.
    5. Experience and Training: Accurate interpretation of OCT scans in optometry and ophthalmology requires specialized training and experience.
    6. Evolving Technology: OCT technology continues to advance, introducing new techniques and capabilities. Staying current with these advancements and understanding their clinical implications is an ongoing challenge for ophthalmologists.

    The solution: Artificial intelligence (AI) can play a significant role in OCT (Optical Coherence Tomography) scan interpretation for ophthalmologists and optometrists in various ways. Artificial Intelligence (AI) provides eye care specialists with more accurate results, severity level detection ( to work only with pathological scans), and assists in early pathologies detection.
    According Ian, one of the owners of Buckingham and Hickson optometry, “they are using Altris AI to get a second opinion on OCT scans.”
    According to Altris AI Medical Director, Maria Znamenska, who is MD, Ph.D., Associate Professor of Ophthalmology, “It is getting more common to double-check the interpretation of OCT scans ( and other medical images) with modern AI tools as they are getting safer and more efficient. Altris AI has received FDA clearance recently apart from having a CE certificate.”
  • 8 Reasons why Optometry Groups Invest in Artificial Intelligence for OCT Scan Analysis

    Mark Braddon
    5 min.

    Optometry chains offer a wide range of eye care services, making it convenient for patients to access eye care locally. 

    However, the widespread accessibility of optometry chains has a reverse side for them. The shortage of employees, new unfamiliar equipment for diagnostics, and a large number of patients create an extremely challenging workflow for many optometrists. This, in turn, creates a number of challenges that can be more familiar to Optometry chains: low optometrist recruitment and retention, inconsistent quality of examination throughout the practices, lack of communication with patients, etc. 

    Automation of routine processes and digitalization have always served as answers to challenges like these in any industry, and healthcare is no exception. Luckily, automation of one of the most complex tasks for optometrists – OCT examination is already available to optometry chains with Artificial Intelligence (AI).   

    OCT proves to be one of the most efficient diagnostic tools for many modern top-notch optometry practices, however, mastering it requires skills and time. Artificial intelligence tools, such as AI for OCT analysis platform, can automate many routine processes which will have enormous benefits for any optometry chain. The top 8 benefits are the following: 

    • #1 AI for OCT increases clinical efficiencies

    Automating OCT scan analysis through AI reduces the time optometrists spend on image interpretation. This allows optometrists to focus on more complex cases, patient interactions, and personalized treatment plans. For any large optometry chain, saving time means providing more patients with high-quality service. 

    How does it work in practice?

    For instance, Altris AI has a severity grading of b-scans. Severity grading means that it is easy to see if the eye is healthy ​(removing any need to spend time interpreting) or highlight ​where the pathology is and the degree of severity. ​

    • Green- no pathology detected
    • Yellow- mild to medium level of severity
    • Red – severe pathology detected

    • #2 AI for OCT provides consistently high standard of quality throughout the chain

    AI algorithms provide consistent and standardized analysis regardless of the individual interpreting OCT scans. This reduces variability in diagnoses and ensures that patients receive uniform care across different clinics and practitioners within the optometry chain.

    AI algorithms can analyze OCT scans with incredible precision and consistency. They can detect subtle changes in retinal structures that might be missed by human observers, leading to earlier and more accurate diagnoses of various eye conditions such as macular degeneration, glaucoma, diabetic retinopathy, and more.

    This will help younger less experienced optometrists and will serve as a second opinion tool for more experienced specialists. 

    Test how Altris AI analyzes OCT

    Demo Account Get brochure

    • #3  AI for OCT enables better retention of employees

    The shortage of optometrists in the world is staggering. 14 million optometry specialists are needed worldwide according to the WHO, while today there are only 331K ready to work.

     It is equally difficult to hire and retain a good optometrist for a company in 2023. However, more and more young optometrists choose innovative businesses that use technology to improve the workflow. Top-notch equipment, convenient scheduling tools, and of course, Artificial Intelligence for OCT & fundus photo analysis might be the perks that will help optometrists to choose your optometry business. 

    Fresh from college optometrists feel more confident when they know that they will have a backup when reviewing OCT scans

    • #4 Reduced Workload Burden

    Optometrists often have heavy workloads, and AI can help alleviate some of this burden by handling routine tasks like initial image analysis. This enables optometrists to spend more time on patient consultations and treatment planning.

    According to a survey by the General Optical Council, 57% of optometrists worked beyond their hours in 2022. Optometrists were more likely to be working beyond their hours (60%) or finding it difficult to provide patients with the sufficient level of care they needed (34%) when compared to other registration types.

    It is possible to outsource preliminary image analysis to Artificial Intelligence tools but communication and empathy are human tasks only. 

    • # 5 AI promotes enhanced patient education

    Let’s not forget about the patients. AI-generated OCT reports can help explain complex medical conditions to patients in a more understandable, visual way. After all 80% of all the information we receive is visual: imagine your optometrists not only telling but also showing what is going on with patients.  

    Comprehensive, color-coded OCT reports may improve patient education and engagement, leading to better treatment adherence and loyalty. 

    When patients don’t understand what they are paying for they are not likely to return for annual checkups. At Altris AI we created smart OCT reports that are comprehensible for patients as well as optometrists. We visualize all the pathologies and the patients can trace the dynamics of 

    #6 Reducing a clinical risk. No chances of getting a legal inquiry because of a pathology missed

    Optometry chains can perform around 40K OCT scans a week. Statistically speaking, the chance of missing a minor early pathology is huge simply because of the big number.

    With the double-check that AI for OCT scan analysis provides, It is not possible to wipe the risk out for 100%, but it is possible to diminish the risk to the absolute minimum. 

    For the optometry chain, it might mean no bad PR and weird stories in the papers and subsequently, a better brand image.

    • #7 AI makes early detection of pathologies possible on OCT

    AI algorithms can identify early signs of eye diseases that might not be easily recognizable in their early stage. This early detection can lead to timely interventions, preventing or minimizing patient vision loss.

    Glaucoma, Wet AMD, Diabetic Retinopathy, and genetic diseases are among the pathologies that lead to blindness if not detected in time. Detecting pathological signs and pathologies related to these disorders in time can literally save patients from future blindness.

    Early detection of pathologies means that it is possible to stop or reduce the risk of total blindness which is the best result in any sense. Early detection will allow optometrists to give valid recommendations, and advise on dieting and supplements right at the optical store. 

    • #8 Competitive Edge

    AI is a buzzword, and it’s not accidental. All major players understand its enormous value and invest in it. During the last presentation, the CEO of Google said “AI” 140 times, and let’s be honest, it is not to show off. It is because AI can actually make changes in business: automation of repetitive processes, workflow optimization, and human error reduction. 

    Adopting AI technology for OCT analysis showcases the optometry chain’s commitment to staying at the forefront of technological advancements in healthcare. Gaining a real competitive edge is another big goal. 

    This can attract patients who value cutting-edge approaches to diagnosis and treatment. A younger generation of patients are curious about new technologies, and this can be an additional lead magnet for them.

    Conclusion

    Incorporating AI for OCT analysis into optometry chains can enhance patient outcomes, make the workflow more efficient, and improve the performance of each optometry center. However, it’s important to ensure that the AI systems are properly validated, integrated into clinical workflows, and monitored to maintain their accuracy and effectiveness. More than that, it should complement, not replace, the expertise of optometrists. The technology should be used as a tool to aid optometrists and make OCT examination more effective.

     

  • Normative database OCT

    Why Eye Care Specialists Consider Innovative Tools in Addition to Normative Database

    Maria Martynova
    06.09.2023
    6 min read

    The first normative database for OCT was created in the early 2000s and were based on small studies of mostly white patients. However, as OCT technology has evolved, so too have the normative databases. Recent databases are larger and more diverse, reflecting the increasing ethnic and racial diversity of the population.

    FDA-cleared AI for OCT

    Make your eye care business technological

    Demo Account Get brochure

    Nowadays, eye care specialists use normative database to compare the characteristics of a patient to a population-wide norm. This allows them to quickly and easily assess whether a patient’s retinal dimensions fall within normal limits. According to our survey, 79% of eye care specialists rely on the normative databases for OCT verdict with every patient.

    Normative database OCT

    However, despite the fact that normative databases are very widespread among specialists worldwide, they are not perfect. They can be affected by factors such as age, gender, axial length, and refractive error.

    They can be influenced by low image quality due to different eye pathologies. It is essential to be aware of these limitations when interpreting normative data OCT parameters. That is why, in this article, we will discuss the benefits of the collaboration between AI decision-making tools and normative databases to improve patient outcomes.

    What is a normative database, and is there a difference between normative databases for different devices? 

    Before diving into the subject of the benefits and limitations of normative databases, we would like to remind you what a normative database is. From the moment of its invention, the OCT exam has rapidly gained widespread adoption and has become indispensable in the eye care practice. Critical to this success has been the ability of software to automatically produce important measurements, such as the thickness of the peripapillary retinal nerve fiber layer (RNFL) in tracking glaucoma progression or the total retinal thickness in the assessment of macular diseases. 

    In order to accurately interpret OCT scans, normative databases were created. These databases are now built into almost all commercial OCT devices, allowing eye care specialists to view colored reports and progression maps that assist in the rapid recognition and tracking of pathology.

    Summing up, a normative database for OCT is a set of data that provides references for OCT thickness measurements in a healthy population. These databases are used to compare the OCT measurements of your patient to a population-wide norm. 

    Here are some of the OCT parameters that are commonly measured and compared to normative databases:

    • Retinal nerve fiber layer (RNFL) thickness: the RNFL is a retinal layer that is measured around the optic nerve. This measurement is important for diagnosing optic nerve atrophy.
    • Macular thickness: the macula is responsible for sharp central vision.
    • Ganglion cell complex thickness: the ganglion cell complex is a group of cells in the retina that are responsible for transmitting visual information to the brain.
    • Cup-to-disc ratio, neuroretinal rim, and other optic nerve parameters: are very important for diagnosing glaucoma and other optic nerve pathologies

    These are just a few of the OCT parameters that are commonly measured in normative databases. The specific parameters that are measured can vary depending on the type of OCT device and the clinical application. 

    In addition, different OCT devices can have different measurement capabilities and resolutions. For example, a device that uses time-domain OCT (TD-OCT) technology may have a lower resolution than a device that uses spectral-domain or swept-source OCT (SD or SS-OCT) technology. This means that the normative database for a TD-OCT device may not be as accurate as the normative database for an SD or SS-OCT device.

    What is more, the normative database for a particular device may be based on a specific population of patients. What are the benefits and limitations of normative databases?

    Now that we have highlighted different aspects of the normative database definition let us discuss the benefits and limitations of this tool. Normative databases can sometimes be very helpful for eye care specialists in diagnosis, decision-making, and creating a treatment strategy for eye diseases such as glaucoma and macular degeneration.

    • The measurement provided by the normative database can be used as a baseline for tracking a patient’s response to medication or other treatment. Eye care specialists can track changes between a few visits and determine the impact on the patient.
    • Normative databases show deviations from the norm, which may be a reason for a more comprehensive examination.
    • Eye care specialists can also use normative databases to compare the results of different OCT devices. This can help to ensure that they are using the most accurate device for their patients.

    There are still challenges that must be overcome to develop normative databases sufficient for use in clinical trials. That is why current normative databases also have a lot of limitations.

    Does not detect pathology

    The normative database works only with the thickness of the retina and does not detect what is inside the retina. Therefore, it cannot detect all pathologies where there is no change in retinal thickness. In the early stages, these are absolutely all diseases. We can see deviations from the normative base only when the disease progresses to a later and more severe stage when the retinal thickness decreases or increases.

    Limited diversity

    Normative databases can be limited by factors like age, gender, and ethnicity of the population used to create them. This can result in reduced accuracy for patients who are not well-represented in the database.

    Population variation

    Even healthy patients can have some anatomical variations that fall within the range of normal. These variations may be falsely flagged as abnormalities when compared to the database.

    How Altris AI platform can complement the information provided by the normative database

    Normative databases in OCT play a crucial role in aiding diagnosis and treatment planning, but they also have limitations related to representation, disease progression, and data quality. Eye care specialists need to interpret the results in the context of the patient’s individual characteristics and other clinical information, using additional tools for scan interpretations.

    Sometimes, low-quality OCT scans can be inaccurately interpreted by the eye care specialist, and the normative database can showcase inaccurate measurements. Altris AI platform detects low-quality scans automatically and warns about the possibility of inaccurate results. In addition, the platform automates the detection of 70+ pathologies and pathological signs. Once the user uploads the scan, they can see visualized and highlighted pathological areas and pathology classification that the algorithm has detected. The user can also calculate the area and volume of detected biomarkers.

    Normative database OCT

    Artificial intelligence-based tools for OCT interpretation used along with normative databases can play a crucial role in clinical eye care. Altris AI, for example, can provide eye care specialists with additional and more precise information about separate retinal layer thickness. The system analyzes the thickness of each retina layer or several layers combined.

    Normative database OCT

    While normative databases provide information only about the thickness, AI tools equipped with deep learning models can detect pathological signs in OCT scans that might be missed by the normative database or the human eye, enhancing diagnostic accuracy. Altris AI algorithm classifies the OCT scans based on the degree of pathology found. It can distinguish green concern, which indicates normal retina, yellow – moderate with slight deviations, and red concern, which means high severity level.

    Normative database OCT

    Summing up

    Despite their limitations, normative databases are an essential tool for the clinical use of OCT. They provide a valuable reference point for assessing patients and can help to identify some diseases. However, the normative database measures only the thickness, which is not enough to accurately diagnose the patient and create a treatment plan.

    FDA-cleared AI for OCT

    Make your eye care business technological

    Demo Account Get brochure

    That is why incorporating AI into OCT interpretation streamlines the decision-making process. By automating the initial analysis of OCT scans, specialists can focus their attention on more complex cases, making the best use of their skills and experience. Moreover, embracing AI technologies empowers eye care specialists to personalize patient care with greater precision.

  • AI blindness prevention

    AI Blindness Prevention: How We Can Use Artificial Intelligence to Help Prevent Blindness

    Maria Martynova
    07.08.2023
    9 min read

    The total number of people with near or distant vision impairment reaches 2.2 billion worldwide.

    Of these, 43 million people are blind, and 295 million are suffering from moderate to severe visual impairment. Although the numbers are constantly changing as new research is conducted, the global burden of blindness and visual impairment remains a significant problem of humanity in the fight against which specialists combine their forces with AI technologies.

    AI blindness prevention

    AI blindness prevention tools are being actively developed to transform the landscape of vision care in many ways. Eye care specialists use AI systems for screening and detecting diseases that lead to vision loss. AI-powered smart monitors assist specialists in finding proper contact lenses and glasses. In addition, many researches are held with the help of AI algorithms, as they are able to process vast amounts of data.

    In this article, we will discuss different applications of AI in blindness prevention, specifically how artificial intelligence tools can empower eye care specialists and extend beyond the clinical setting. 

    FDA-cleared AI for OCT scan analysis

    Make your eye care business technological

    Demo Account Get brochure

    Today’s conditions and risk factors of blindness you should pay attention to

    Before talking about the developments in the AI sector toward blindness prevention, we would like to discuss the most common causes and risk factors of this impairment. Many health and lifestyle factors can influence the risk of vision loss. Smoking, excessive alcohol consumption, sun exposure, and poor nutrition can contribute to diseases that lead to vision loss. 

    In addition, there are many conditions that can lead to blindness if left with no proper treatment, among which are the following. 

    Age-related eye diseases

    The global population is aging rapidly. The number of people aged 65 and over is projected to triple from 1 billion in 2020 to 2.1 billion in 2050. Considering this fact, age-related eye diseases have become a prominent cause of blindness. Such diseases as age-related macular degeneration (AMD), cataract, and glaucoma are more prevalent in older patients, and if left untreated, they can lead to fast and significant vision loss. Regular eye check-ups and timely interventions are crucial in managing these diseases and preventing severe visual impairment.

    AI blindness prevention

    Besides AMD, there are a lot of age-related conditions which can be a red flag when examining the patient. Among these are macular holes, mactel, and vascular diseases, for example,  central retinal vein occlusion (CRVO) and central retinal artery occlusion (CRAO). Detecting even one of these pathological conditions in the early stages of their development is crucial for preventing vision loss. 

    However, many eye care specialists sometimes don’t have enough resources to dedicate more time to analyzing patients’ images. Our recent survey detected that among more than 300 participating optometrists, 40% of them have more than 10 OCT exams per day. Meanwhile, 35% of eye care specialists have 5-10 OCT examinations per day. The greater the number of patients per day, the greater the likelihood that eye care specialists may miss some minor, rare, or early conditions.

    AI blindness prevention

    Fortunately, nowadays, there are a lot of ways to empower the clinical workflow, and AI blindness prevention tools are gaining popularity. Artificial intelligence systems like Altris AI can analyze retinal images and other diagnostic data to detect early signs of age-related eye diseases. Altris AI platform, for example, can detect 70+ pathologies and pathological signs, including the ones, that refer to age-related diseases.

    AI blindness prevention

    Altris AI platform allows eye care specialists to rely on its disease classification when diagnosing a patient. It detects all the most common age-related pathologies, such as AMD, mactel, and vascular diseases – CRVO, CRAO.

    AI blindness prevention

    Diabetes and diabetic retinopathy

    Diabetes and related conditions are also common causes of vision loss. In the United States, about 12% of all new cases of blindness are caused due to diabetes. Globally, diabetes is estimated to cause 4.8% of all blindness. In addition, the risk of blindness from diabetes increases with the duration of diabetes. People with untreated diabetes for years are 25 times more likely to be blind than people without diabetes.

    AI blindness prevention

    The complication of diabetes, called Diabetic retinopathy (DR), affects the blood vessels of the retina and can lead to impaired vision or blindness. With the rising prevalence of diabetes worldwide, DR has become a significant problem. Early detection, proper control of diabetes, and regular eye exams are essential to prevent vision loss. 

    The American diabetes association (ADA) recommends that people with diabetes have an OCT scan of their eyes every year. This is because OCT can help to detect early signs of DR with high precision. In some cases, eye care specialists may recommend more frequent OCT scans. This may be the case if the patient has advanced diabetic retinopathy or a family history of diabetic retinopathy.

    AI blindness prevention

    AI algorithms such as Altris AI can assist in detecting the pathological signs of diabetic retinopathy or diabetic macular edema. Our web platform differentiates certain pathological signs that indicate diabetes-related diseases. Among these are:

    • Intraretinal fluid
    • Subretinal fluid
    • Hard exudates
    • Hyperreflective foci
    • Epiretinal fibrosis

    Genetic and inherited conditions

    Some patients are at a greater risk of developing visual impairment due to genetic factors or the inheritance of certain conditions. For example, retinitis pigmentosa is an inherited disease that affects the photoreceptor cells in the retina and gradually leads to night blindness and loss of peripheral vision. Genetic testing and counseling can help identify people at risk and provide early intervention.

    AI blindness prevention

    Some genetic eye conditions, such as myopia, vitelliform dystrophy, or retinoschisis, can be detected in the early stages with the help of OCT examination and artificial intelligence systems. Altris AI platform can help eye care specialists in their daily practice and make eye care more accessible, allowing specialists to perform regular eye check-ups, and provide timely treatment of genetic conditions.

    AI blindness prevention

    Current ways to prevent blindness with AI 

    As you can see, blindness risk factors encompass a wide range of conditions, pathologies, and circumstances that can significantly impact a patient’s health and increase the likelihood of severe visual impairment. Poorly managed age-related eye diseases, genetic and hereditary factors, and chronic health conditions can lead to eye-related complications, further elevating the risk of blindness.

    AI blindness prevention

    In the following paragraphs, we will describe in detail the modern ways of using artificial intelligence to detect and prevent blindness: from AI-based retinal imaging for early detection of eye diseases to personalized treatment recommendations and remote patient monitoring.

    AI for image interpretation

    AI blindness prevention

    It is important to understand that the timely detection of eye diseases is key to the effective treatment of visual impairments. However, today we have an unfortunate tendency to diagnose severe forms of disease too late. A large-scale survey by Eyewire conducted in 2021 found that about 40% of people in the USA said they had not had an eye exam in more than a year, and 10% said they had not had one in more than five years. 

    In addition, recent research by the British Journal of Ophthalmology found that 25.3% of people in Europe over the age of 60 have early signs of AMD. In the UK, about 200 people a day are affected by a severe form of AMD (wet AMD), which can cause severe blindness. 

    These studies show us that while eye care specialists around the world are trying to treat as many patients as possible, unfortunately, many patients are going blind due to delays in diagnosis. However, using advanced AI-based image analysis systems can speed up the detection of warning signs, allowing you to reach more patients.

    One of the advantages of AI for image analysis is its assistance in decision-making. Altris AI is a great example of how an image analysis system can help prevent blindness with AI. The platform allows eye care specialists to detect 74 retina pathologies and pathological signs, including risk conditions for vision loss, like AMD, Diabetic retinopathy, Vascular diseases of the retina, and others. 

    Diagnosing eye disease in children

    AI blindness prevention

    Today, one of the most important AI blindness prevention research is focused on teaching artificial intelligence algorithms to detect retinopathy in premature infants. Retinopathy of prematurity is the main cause of childhood blindness in middle-income countries. Some researches show that around 50,000 children all over the world are blind due to the disease.

    Unfortunately, experts’ forecasts show that these figures are likely to grow. Retinopathy of prematurity is becoming more and more common, especially in African countries. About 30% of children born in sub-Saharan Africa have this disease and, due to late detection and insufficient attention due to the lack of eye care specialists, can also go blind.

    An artificial intelligence model developed by an international team of scientists from the UK, Brazil, Egypt, and the US, with support from leading healthcare institutions, is able to identify children who are at risk of blindness if left untreated. The team of scientists hopes that this AI system will make access to screening and monitoring of young patients more affordable in many regions with limited eye care services and few qualified eye care specialists.

    AI monitors for eye strain control

    Another interesting application of AI to prevent blindness is eye care monitors. They are planned to be used to avoid eye strain due to prolonged computer work. Such monitors will be programmed to monitor the user’s facial expressions, blinks, and eye movements. They will also be able to assess the level of light in the room, and artificial intelligence will automatically adjust the screen brightness and image contrast.

    Since a huge number of the world’s population has switched to remote work since the pandemic and spends almost all day at the computer, such AI monitors are considered a huge help for users in preventing eye diseases that can lead to visual impairment.

    AI to determine better glasses or contact lenses

    AI blindness prevention

    In the field of developing and calculating suitable lenses, there are also a number of companies that have joined the development of AI tools. AI monitors will collect important information about the patient’s eye condition, analyze it, and prescribe suitable contact lenses or glasses. 

    In addition, these monitors will be able to analyze the patient’s medical history, including medical images, and create the most suitable treatment strategy to maximize visual acuity.

    AI for studying the human eye

    AI blindness prevention

    Today, AI is a promising tool for studying human eye tissue and developing new tools for diagnosing and treating eye diseases, including those that lead to vision loss. Artificial intelligence tools are used to analyze OCT images of the eye to detect changes that may indicate diseases such as diabetic retinopathy, macular degeneration, and glaucoma. AI is also used to predict the development of eye diseases based on genetic or risk factors. This is expected to help doctors identify people at risk of developing eye diseases at an early stage and prevent the progression of the disease.

    Summing up

    Today AI blindness prevention tools are already developing by many leading companies and institutions, and some companies, like Altris AI, are already using the potential of artificial intelligence to provide early detection and diagnostic advice for eye care specialists. But it’s worth noting that AI tools are not capable of coming up with innovative solutions for blindness prevention.

    FDA-cleared AI for OCT scan analysis

    Make your eye care business technological

    Demo Account Get brochure

    Only in close cooperation with eye care specialists AI blindness prevention tools can help in many ways, like early detection, providing access to medical care in underserved regions, detecting minor or rare conditions, and allowing to focus on personalized care and treatment of patients.