Published Evidence

Autonomous Diabetic Retinopathy Screening: What the Research Actually Shows

Eye screening software, including systems cleared to give a result without a specialist reading the image. The deepest evidence base in autonomous AI.

If you want to know whether autonomous AI can work in real medicine, this is the literature to read, because this is where it was actually tried at scale.

The conditions were unusually favorable. Millions of people with diabetes need an annual eye check, the photograph is standardized, the disease is treatable when caught, and there have never been enough eye specialists to read every image. The alternative to software was not a specialist. It was nobody.

The research covers both halves of the question: whether the software reads the image correctly, and whether putting it in a clinic actually gets more people screened. The second half is the one that decides whether a program was worth running, and it is studied less often than the first.

What Kind of Evidence This Is

Not every study carries the same weight. This is the mix behind the list below.

What to Measure in Your Own Setting

A published result is somebody else's hospital. These are the numbers worth tracking in yours.

  • Screening completion rate, not screening accuracy. The disease-preventing effect comes from reaching people who were not being checked at all.
  • The share of images the software cannot grade, and where those patients end up.
  • Referral follow-through. Flagging someone who then never sees an eye doctor has not helped them.
  • Performance in the groups your clinic actually serves, since retinal images vary by ethnicity and by camera.

The Studies

Every entry links to the source record. Summaries are the study's own abstract, shortened but not reworded.

  1. Study JAMA, 2017 ... cited 1419 times

    Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes.

    Ting DSW and 28 others

    ImportanceA deep learning system (DLS) is a machine learning technology with potential for screening diabetic retinopathy and related eye diseases.ObjectiveTo evaluate the performance of a DLS in detecting referable diabetic retinopathy, vision-threatening diabetic retinopathy, possible glaucoma, and age-related macular degeneration (AMD) in community and clinic-based multiethnic populations with diabetes.Design, set...

    PMID 29234807 ... doi:10.1001/jama.2017.18152

  2. Study NPJ digital medicine, 2018 ... cited 961 times ... free to read

    Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices.

    Abràmoff MD and 4 others

    Artificial Intelligence (AI) has long promised to increase healthcare affordability, quality and accessibility but FDA, until recently, had never authorized an autonomous AI diagnostic system. This pivotal trial of an AI system to detect diabetic retinopathy (DR) in people with diabetes enrolled 900 subjects, with no history of DR at primary care clinics, by comparing to Wisconsin Fundus Photograph Reading Center (FP...

    PMID 31304320 ... doi:10.1038/s41746-018-0040-6

  3. Study Investigative ophthalmology & visual science, 2016 ... cited 566 times

    Improved Automated Detection of Diabetic Retinopathy on a Publicly Available Dataset Through Integration of Deep Learning.

    Abràmoff MD and 6 others

    PurposeTo compare performance of a deep-learning enhanced algorithm for automated detection of diabetic retinopathy (DR), to the previously published performance of that algorithm, the Iowa Detection Program (IDP)-without deep learning components-on the same publicly available set of fundus images and previously reported consensus reference standard set, by three US Board certified retinal specialists.MethodsWe used ...

    PMID 27701631 ... doi:10.1167/iovs.16-19964

  4. Study Ophthalmology, 2017 ... cited 555 times

    Automated Identification of Diabetic Retinopathy Using Deep Learning.

    Gargeya R and 1 others

    PurposeDiabetic retinopathy (DR) is one of the leading causes of preventable blindness globally. Performing retinal screening examinations on all diabetic patients is an unmet need, and there are many undiagnosed and untreated cases of DR. The objective of this study was to develop robust diagnostic technology to automate DR screening.

    PMID 28359545 ... doi:10.1016/j.ophtha.2017.02.008

  5. Review The lancet. Diabetes & endocrinology, 2020 ... cited 434 times

    Screening for diabetic retinopathy: new perspectives and challenges.

    Vujosevic S and 6 others

    Although the prevalence of all stages of diabetic retinopathy has been declining since 1980 in populations with improved diabetes control, the crude prevalence of visual impairment and blindness caused by diabetic retinopathy worldwide increased between 1990 and 2015, largely because of the increasing prevalence of type 2 diabetes, particularly in low-income and middle-income countries.

    PMID 32113513 ... doi:10.1016/s2213-8587(19)30411-5

  6. Review Frontiers in endocrinology, 2022 ... cited 338 times ... free to read

    Diabetic retinopathy: Looking forward to 2030.

    Tan TE and 1 others

    Diabetic retinopathy (DR) is the major ocular complication of diabetes mellitus, and is a problem with significant global health impact. Major advances in diagnostics, technology and treatment have already revolutionized how we manage DR in the early part of the 21st century.

    PMID 36699020 ... doi:10.3389/fendo.2022.1077669

  7. Review Journal of diabetes investigation, 2021 ... cited 326 times ... free to read

    Update in the epidemiology, risk factors, screening, and treatment of diabetic retinopathy.

    Lin KY and 4 others

    Despite progress in the treatment of diabetic macular edema and diabetic retinopathy, the rate of lower fundus examination due to limitations of medical resources delays the diagnosis and treatment of diabetic retinopathy.

    PMID 33316144 ... doi:10.1111/jdi.13480

  8. Study Ophthalmology, 2018 ... cited 263 times

    Grader Variability and the Importance of Reference Standards for Evaluating Machine Learning Models for Diabetic Retinopathy.

    Krause J and 7 others

    PurposeUse adjudication to quantify errors in diabetic retinopathy (DR) grading based on individual graders and majority decision, and to train an improved automated algorithm for DR grading.DesignRetrospective analysis.ParticipantsRetinal fundus images from DR screening programs.MethodsImages were each graded by the algorithm, U.S. board-certified ophthalmologists, and retinal specialists.

    PMID 29548646 ... doi:10.1016/j.ophtha.2018.01.034

  9. Study Eye (London, England), 2018 ... cited 240 times ... free to read

    Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence.

    Rajalakshmi R and 3 others

    ObjectivesTo assess the role of artificial intelligence (AI)-based automated software for detection of diabetic retinopathy (DR) and sight-threatening DR (STDR) by fundus photography taken using a smartphone-based device and validate it against ophthalmologist's grading.MethodsThree hundred and one patients with type 2 diabetes underwent retinal photography with Remidio 'Fundus on phone' (FOP), a smartphone-based dev...

    PMID 29520050 ... doi:10.1038/s41433-018-0064-9

  10. Study JAMA ophthalmology, 2013 ... cited 226 times

    Automated analysis of retinal images for detection of referable diabetic retinopathy.

    Abràmoff MD and 13 others

    ImportanceThe diagnostic accuracy of computer detection programs has been reported to be comparable to that of specialists and expert readers, but no computer detection programs have been validated in an independent cohort using an internationally recognized diabetic retinopathy (DR) standard.ObjectiveTo determine the sensitivity and specificity of the Iowa Detection Program (IDP) to detect referable diabetic retinop...

    PMID 23494039 ... doi:10.1001/jamaophthalmol.2013.1743

  11. Study The Lancet. Digital health, 2019 ... cited 219 times

    Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study.

    Bellemo V and 19 others

    BackgroundRadical measures are required to identify and reduce blindness due to diabetes to achieve the Sustainable Development Goals by 2030. Therefore, we evaluated the accuracy of an artificial intelligence (AI) model using deep learning in a population-based diabetic retinopathy screening programme in Zambia, a lower-middle-income country.MethodsWe adopted an ensemble AI model consisting of a combination of two c...

    PMID 33323239 ... doi:10.1016/s2589-7500(19)30004-4

  12. Review Eye (London, England), 2020 ... cited 213 times

    Artificial intelligence for diabetic retinopathy screening: a review.

    Grzybowski A and 6 others

    Diabetes is a global eye health issue. Given the rising in diabetes prevalence and ageing population, this poses significant challenge to perform diabetic retinopathy (DR) screening for these patients. Artificial intelligence (AI) using machine learning and deep learning have been adopted by various groups to develop automated DR detection algorithms.

    PMID 31488886 ... doi:10.1038/s41433-019-0566-0

  13. Study Nature communications, 2021 ... cited 199 times ... free to read

    A deep learning system for detecting diabetic retinopathy across the disease spectrum.

    Dai L and 19 others

    Retinal screening contributes to early detection of diabetic retinopathy and timely treatment. To facilitate the screening process, we develop a deep learning system, named DeepDR, that can detect early-to-late stages of diabetic retinopathy. DeepDR is trained for real-time image quality assessment, lesion detection and grading using 466,247 fundus images from 121,342 patients with diabetes.

    PMID 34050158 ... doi:10.1038/s41467-021-23458-5

  14. Study Acta ophthalmologica, 2018 ... cited 190 times ... free to read

    Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System.

    van der Heijden AA and 5 others

    PurposeTo increase the efficiency of retinal image grading, algorithms for automated grading have been developed, such as the IDx-DR 2.0 device. We aimed to determine the ability of this device, incorporated in clinical work flow, to detect retinopathy in persons with type 2 diabetes.MethodsRetinal images of persons treated by the Hoorn Diabetes Care System (DCS) were graded by the IDx-DR device and independently by ...

    PMID 29178249 ... doi:10.1111/aos.13613

  15. Study The Lancet. Digital health, 2020 ... cited 186 times

    Artificial intelligence for teleophthalmology-based diabetic retinopathy screening in a national programme: an economic analysis modelling study.

    Xie Y and 16 others

    BackgroundDeep learning is a novel machine learning technique that has been shown to be as effective as human graders in detecting diabetic retinopathy from fundus photographs. We used a cost-minimisation analysis to evaluate the potential savings of two deep learning approaches as compared with the current human assessment: a semi-automated deep learning model as a triage filter before secondary human assessment; an...

    PMID 33328056 ... doi:10.1016/s2589-7500(20)30060-1

  16. Study Ophthalmology, 2017 ... cited 182 times

    Automated Diabetic Retinopathy Image Assessment Software: Diagnostic Accuracy and Cost-Effectiveness Compared with Human Graders.

    Tufail A and 15 others

    ObjectiveWith the increasing prevalence of diabetes, annual screening for diabetic retinopathy (DR) by expert human grading of retinal images is challenging. Automated DR image assessment systems (ARIAS) may provide clinically effective and cost-effective detection of retinopathy.

    PMID 28024825 ... doi:10.1016/j.ophtha.2016.11.014

  17. Review Ophthalmologica. Journal international d'ophtalmologie. International journal of ophthalmology. Zeitschrift fur Augenheilkunde, 2020 ... cited 176 times

    Strategies to Tackle the Global Burden of Diabetic Retinopathy: From Epidemiology to Artificial Intelligence.

    Wong TY and 1 others

    Diabetes is a global public health disease projected to affect 642 million adults by 2040, with about 75% residing in low- and middle-income countries. Diabetic retinopathy (DR) affects 1 in 3 people with diabetes and remains the leading cause of blindness in working-aged adults. There are 3 broad strategic imperatives to prevent blindness caused by DR.

    PMID 31408872 ... doi:10.1159/000502387

  18. Study JAMA network open, 2021 ... cited 162 times ... free to read

    Pivotal Evaluation of an Artificial Intelligence System for Autonomous Detection of Referrable and Vision-Threatening Diabetic Retinopathy.

    Ipp E and 13 others

    ImportanceDiabetic retinopathy (DR) is a leading cause of blindness in adults worldwide. Early detection and intervention can prevent blindness; however, many patients do not receive their recommended annual diabetic eye examinations, primarily owing to limited access.ObjectiveTo evaluate the safety and accuracy of an artificial intelligence (AI) system (the EyeArt Automated DR Detection System, version 2.1.0) in det...

    PMID 34779843 ... doi:10.1001/jamanetworkopen.2021.34254

  19. Study Diabetes care, 2018 ... cited 161 times

    An Automated Grading System for Detection of Vision-Threatening Referable Diabetic Retinopathy on the Basis of Color Fundus Photographs.

    Li Z and 12 others

    ObjectiveThe goal of this study was to describe the development and validation of an artificial intelligence-based, deep learning algorithm (DLA) for the detection of referable diabetic retinopathy (DR).Research design and methodsA DLA using a convolutional neural network was developed for automated detection of vision-threatening referable DR (preproliferative DR or worse, diabetic macular edema, or both).

    PMID 30275284 ... doi:10.2337/dc18-0147

  20. Study JAMA, 2016 ... cited 158 times

    Artificial Intelligence With Deep Learning Technology Looks Into Diabetic Retinopathy Screening.

    Wong TY and 1 others

    PMID 27898977 ... doi:10.1001/jama.2016.17563

  21. Study JAMA ophthalmology, 2019 ... cited 156 times

    Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India.

    Gulshan V and 12 others

    ImportanceMore than 60 million people in India have diabetes and are at risk for diabetic retinopathy (DR), a vision-threatening disease. Automated interpretation of retinal fundus photographs can help support and scale a robust screening program to detect DR.ObjectiveTo prospectively validate the performance of an automated DR system across 2 sites in India.Design, setting, and participantsThis prospective observati...

    PMID 31194246 ... doi:10.1001/jamaophthalmol.2019.2004

  22. Study Medical image analysis, 2017 ... cited 156 times

    Deep image mining for diabetic retinopathy screening.

    Quellec G and 4 others

    Deep learning is quickly becoming the leading methodology for medical image analysis. Given a large medical archive, where each image is associated with a diagnosis, efficient pathology detectors or classifiers can be trained with virtually no expert knowledge about the target pathologies.

    PMID 28511066 ... doi:10.1016/j.media.2017.04.012

  23. Study JAMA ophthalmology, 2019 ... cited 148 times

    Diagnostic Accuracy of Community-Based Diabetic Retinopathy Screening With an Offline Artificial Intelligence System on a Smartphone.

    Natarajan S and 4 others

    ImportanceOffline automated analysis of retinal images on a smartphone may be a cost-effective and scalable method of screening for diabetic retinopathy; however, to our knowledge, assessment of such an artificial intelligence (AI) system is lacking.ObjectiveTo evaluate the performance of Medios AI (Remidio), a proprietary, offline, smartphone-based, automated system of analysis of retinal images, to detect referable...

    PMID 31393538 ... doi:10.1001/jamaophthalmol.2019.2923

  24. Study Diabetes technology & therapeutics, 2019 ... cited 148 times ... free to read

    The Value of Automated Diabetic Retinopathy Screening with the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes.

    Bhaskaranand M and 6 others

    Background: Current manual diabetic retinopathy (DR) screening using eye care experts cannot scale to screen the growing population of diabetes patients who are at risk for vision loss. EyeArt system is an automated, cloud-based artificial intelligence (AI) eye screening technology designed to easily detect referral-warranted DR immediately through automated analysis of patient's retinal images.

    PMID 31335200 ... doi:10.1089/dia.2019.0164

Study records come from Europe PMC, which indexes PubMed, MEDLINE, PMC and preprint servers. Titles, journals, years, identifiers, citation counts and abstracts are reproduced from the source record and are not rewritten here. Listing a study is not an endorsement of its conclusion, and citation count measures attention rather than quality. This page is a starting point for your own reading, not clinical guidance.