The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Artificial intelligence for diabetic retinopathy screening: a review
Open accessAbstract
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. This article aims to describe the state-of-art AI DR screening technologies that have been described in the literature, some of which are already commercially available. All these technologies were designed using different training datasets and technical methodologies. Although many groups have published robust diagnostic performance of the AI algorithms for DR screening, future research is required to address several challenges, for examples medicolegal implications, ethics, and clinical deployment model in order to expedite the translation of these novel technologies into the healthcare setting.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Artificial intelligence (AI) for medical diagnosis holds potential, demonstrating high performance in detecting various diseases.57”
From Using artificial intelligence to improve human performance: efficient retinal disease detection training with synthetic images (2024) · cites this paper as [7]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
Global prevalence and major risk factors of diabetic retinopathy
Yau, J. W. Y., Rogers, S. L., Kawasaki, R., Lamoureux, E. L., Kowalski, J. W., Bek, T., Chen, S.-J., Dekker, J. M., Fletcher, A., Grauslund, J., et al. (2012) · Diabetes Care · doi:10.2337/dc11-1909 · Cited by 4,985
Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C. S., Liang, H., Baxter, S. L., McKeown, A., Yang, G., Wu, X., Yan, F., et al. (2018) · Cell · doi:10.1016/j.cell.2018.02.010 · Cited by 4,842
Clinically applicable deep learning for diagnosis and referral in retinal disease
De Fauw, J., Ledsam, J. R., Romera-Paredes, B., Nikolov, S., Tomasev, N., Blackwell, S., Askham, H., Glorot, X., O’Donoghue, B., Visentin, D., et al. (2018) · Nature Medicine · doi:10.1038/s41591-018-0107-6 · Cited by 2,639
Ting, D. S. W., Cheung, C. Y.-L., Lim, G., Tan, G. S. W., Quang, N. D., Gan, A., Hamzah, H., Garcia-Franco, R., San Yeo, I. Y., Lee, S. Y., et al. (2017) · JAMA · doi:10.1001/jama.2017.18152 · Cited by 2,402
Lakhani, P., & Sundaram, B. (2017) · Radiology · doi:10.1148/radiol.2017162326 · Cited by 1,775
Abràmoff, M. D., Lavin, P. T., Birch, M., Shah, N., & Folk, J. C. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0040-6 · Cited by 1,638
Automated Identification of Diabetic Retinopathy Using Deep Learning
Gargeya, R., & Leng, T. (2017) · Ophthalmology · doi:10.1016/j.ophtha.2017.02.008 · Cited by 1,410
Cited by
Sorted by citations
Items 101–200 of 375
Advancements in AI for cardiac arrhythmia detection: A comprehensive overview
Rahul, J., & Sharma, L. D. (2025) · Computer Science Review · doi:10.1016/j.cosrev.2024.100719 · Cited by 25
Diabetic retinopathy screening using machine learning: a systematic review
Dejene, F. M., Debelee, T. G., Schwenker, F., Ayano, Y. M., & Feyisa, D. W. (2025) · BMC Biomedical Engineering · doi:10.1186/s42490-025-00098-0 · Cited by 32
“Grzybowski et al. [25] provides an overview of various AI technologies for DR, including several systems used, but it lacks a comparison and in-depth analysis of the methodologies employed in each research article.”
Artificial intelligence for detection of optic disc abnormalities
Miléa, D., Singhal, S., & Najjar, R. P. (2019) · Current Opinion in Neurology · doi:10.1097/wco.0000000000000773 · Cited by 20
Avci, S. N., Isiktas, G., Ergun, O., & Berber, E. (2022) · Journal of Surgical Oncology · doi:10.1002/jso.26884 · Cited by 21
“17 – 19 For instance, Korot et al. used a visual AI platform to predict sex from retinal fundus photographs with an 88.8% sensitivity and 83.6% specificity.”
InfluentialArtificial Intelligence based Techniques in Respiratory Healthcare Services: A Review
Chawla, J. S., & Walia, N. K. (2022) · International Conference on Computing, Analytics and Networks (ICAN) · doi:10.1109/ican56228.2022.10007236 · Cited by 23
“Today many pestilent diseases like Diabetic Retinopathy [8], brain tumors [9], Cardiac problems [10], Cancer [11] has technological solutions, but the research in Respiratory healthcare remains limited [4].”
BackgroundFundus Imaging-Based Healthcare: Present and Future
Kumar, V., & Paul, K. (2023) · ACM Transactions on Computing for Healthcare · doi:10.1145/3586580 · Cited by 21
Diagnostic Accuracy of Automated Diabetic Retinopathy Image Assessment Software: IDx-DR and RetCAD
Grzybowski, A. E., Brona, P., Krzywicki, T., & Ruamviboonsuk, P. (2024) · Ophthalmology and Therapy · doi:10.1007/s40123-024-01049-z · Cited by 20
Rajalakshmi, R., Pramodkumar, T. A., Naziyagulnaaz, A. S., Anjana, R. M., Raman, R., Suchetha, M., & Mohan, V. (2024) · Seminars in Ophthalmology · doi:10.1080/08820538.2024.2432902 · Cited by 22
“15 While AI has the potential to enhance screening of DR, addressing the challenges related to data quality, data privacy, the cost of real-time implementation in clinics and the regulatory aspects is crucial to ensure the safe and effective use of AI for DR screening in the real-world setting.”
Artificial Intelligence and Infectious Keratitis: Where Are We Now?
Soleimani, M., Cheraqpour, K., Sadeghi, R., Pezeshgi, S., Koganti, R., & Djalilian, A. R. (2023) · Life · doi:10.3390/life13112117 · Cited by 19
Cleland, C. R., Bascarán, C., Makupa, W., Shilio, B. R., Sandi, F. A., Philippin, H., Marques, A. P., Egan, C. A., Tufail, A., Keane, P. A., et al. (2024) · BMJ Open · doi:10.1136/bmjopen-2023-075055 · Cited by 19
“12 A review process informed the choice of AI system in this trial.”
BackgroundMethodThe evolution of diabetic retinopathy screening
Irodi, A., Zhu, Z., Grzybowski, A. E., Wu, Y.-L., Cheung, C. Y.-L., Li, H., Tan, G. S. W., & Wong, T. Y. (2025) · Eye · doi:10.1038/s41433-025-03633-4 · Cited by 24
“Training from a single dataset is prone to bias and exaggerates health inequity but acquiring diverse datasets can be difficult and costly [99].”
Gupta, M., Rao, I. R., Nagaraju, S. P., Bhandary, S. V., Gupta, J., & Babu, G. T. C. (2022) · International Journal of Nephrology · doi:10.1155/2022/3922398 · Cited by 18
Use of machine learning to achieve keratoconus detection skills of a corneal expert
Cohen, E., Bank, D., Sorkin, N., Giryes, R., & Varssano, D. (2022) · International Ophthalmology · doi:10.1007/s10792-022-02404-4 · Cited by 18
Zou, W., Zhang, Z., Luo, S., Cheng, L., Huang, X., Ding, N., Yu, J., Pan, Y., & Wu, Z. (2020) · Bioscience Reports · doi:10.1042/bsr20193256 · Cited by 18
Krzywicki, T., Brona, P., Zbrzezny, A. M., & Grzybowski, A. E. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12103587 · Cited by 17
“Automated screening for diabetic retinopathy (DR) is one facet of this transformation, with deep-learning algorithms already supplementing clinical practice in different parts of the world [4,5].”
BackgroundArtificial intelligence in retinal imaging: current status and future prospects
Heger, K. A., & Waldstein, S. M. (2023) · Expert Review of Medical Devices · doi:10.1080/17434440.2023.2294364 · Cited by 20
“The AUC for referable DR ranged from 89% to 99% in the individual studies [52–55].”
BackgroundArtificial intelligence in paediatric endocrinology: conflict or cooperation
Dimitri, P., & Savage, M. O. (2024) · Journal of Pediatric Endocrinology and Metabolism · doi:10.1515/jpem-2023-0554 · Cited by 18
Arjun, K. P., Kumar, K. S., Dhanaraj, R. K., Ravi, V., & Kumar, T. (2024) · Microscopy Research and Technique · doi:10.1002/jemt.24559 · Cited by 18
“…disease (Vijayalakshmi, 2019), lung cancer (Mohammed, 2019), diabetic retinopathy (Beli (cid:1) c et al., 2019), dengue (Wang et al., 2019), hepatitis (Grzybowski et al., 2020), heart diseases (Raja et al., 2019), liver disease (Kim et al., 2022), and rheumatoid arthritis (Singh & Kumar, 2020).”
BackgroundAsif, M., Rehman, F. U., Rashid, Z., Hussain, A., Mirza, A., & Qureshi, W. S. (2025) · IEEE Access · doi:10.1109/access.2025.3583647 · Cited by 21
Limwattanayingyong, J., Nganthavee, V., Seresirikachorn, K., Singalavanija, T., Soonthornworasiri, N., Ruamviboonsuk, V., Rao, C., Raman, R., Grzybowski, A. E., Schaekermann, M., et al. (2020) · Journal of Diabetes Research · doi:10.1155/2020/8839376 · Cited by 17
Sharafi, S. M., Ebrahimiadib, N., Roohipourmoallai, R., Farahani, A. D., Fooladi, M. I., & Pour, E. K. (2024) · Scientific Reports · doi:10.1038/s41598-024-57072-4 · Cited by 16
Updates on medical and surgical managements of diabetic retinopathy and maculopathy
Chen, Y., Radke, N. V., Amarasekera, S., Park, D. H., Chen, N., Chhablani, J. K., Wang, N., Wu, W., Ng, D. S., Bhende, P., et al. (2025) · Asia-Pacific Journal of Ophthalmology · doi:10.1016/j.apjo.2025.100180 · Cited by 17
Comparative Study of Transfer Learning Models for Retinal Disease Diagnosis from Fundus Images
Pin, K., Chang, J. H., & Nam, Y. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.021943 · Cited by 17
Application and prospect of artificial intellingence in diabetes care
Jia, W., & Fisher, E. B. (2023) · Medical Review · doi:10.1515/mr-2022-0039 · Cited by 14
Dan, A. O., Ştefănescu-Dima, A., Bălășoiu, A. T., Puiu, I., Mocanu, C. L., Ionescu, M., Tănasie, C. A., Târtea, E. A., & Sfredel, V. (2023) · Diagnostics · doi:10.3390/diagnostics13091648 · Cited by 15
“At the moment, AI in ophthalmology is mostly used to improve disease diagnoses such as DR, glaucoma, age-related macular degeneration (AMD) and other anterior segment diseases [16].”
BackgroundArtificial intelligence assisted pterygium diagnosis: current status and perspectives
Chen, B., Wu, M., Zhu, S., Zheng, B. R., Liu, B.-Q., Wu, T., Hong, X., Wang, J., & Yang, W. (2023) · International Journal of Ophthalmology · doi:10.18240/ijo.2023.09.04 · Cited by 15
Naz, H. U., Nijhawan, R., & Ahuja, N. J. (2024) · International Ophthalmology · doi:10.1007/s10792-024-02975-4 · Cited by 15
“These handheld devices are easy to use, allowing non-specialists such as general practitioners or community health workers to perform DR screening with their "point and shoot" functionality [17, 18].”
Pietris, J., Lam, A., Bacchi, S., Gupta, A. K., Kovoor, J. G., & Chan, W. O. (2022) · Asia-Pacific Journal of Ophthalmology · doi:10.1097/apo.0000000000000565 · Cited by 15
Adoption of machine learning for medical diagnosisPreprint
Shaheen, M. Y. (2021) · doi:10.31219/osf.io/t69w5 · Cited by 15
Djoumessi, K., Huang, Z., Kuehlewein, L., Rickmann, A., Simon, N., Koch, L. M., & Berens, P. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000831 · Cited by 16
“By now, multiple AI systems have received regulatory clearance [2,3] and have been found useful to triage patients not requiring specialist attention and those with vision-threatening DR, potentially contributing to increased screening adherence [4].”
Teoh, C. S., Wong, K. H., Xiao, D., Wong, H. C., Zhao, P., Chan, H. W., Yuen, Y. S., Naing, T., Kanagasingam, Y., & Koh, V. (2023) · Healthcare · doi:10.3390/healthcare11121697 · Cited by 14
“A direct comparison of available algorithms has been challenging due to variations in reference standards (either International Clinical Diabetic Retinopathy Disease Severity Scale or Early Treatment Diabetic Retinopathy Study Grading), grader experience and capabilities, the algorithm output of the system (diabetic r…”
BackgroundMethodInfluentialChuter, B., Huynh, J., Hallaj, S., Walker, E., Liebmann, J. M., Fazio, M. A., Girkin, C. A., Weinreb, R. N., Christopher, M. A., & Zangwill, L. M. (2024) · Ophthalmology Science · doi:10.1016/j.xops.2024.100623 · Cited by 15
Baharoon, M., Almatar, H., Alduhayan, R., Aldebasi, T. M., Alahmadi, B., Bokhari, Y., Alawad, M., Almazroa, A. A., & Aljouie, A. (2024) · Bioengineering · doi:10.3390/bioengineering11111080 · Cited by 21
Autonomous Screening for Diabetic Macular Edema Using Deep Learning Processing of Retinal Images
Bressler, I., Aviv, R., Margalit, D., Cohen, G. Y., Ianchulev, T., Savant, S. V., Ramsey, D. J., & Dvey-Aharon, Z. (2025) · Ophthalmology Science · doi:10.1016/j.xops.2025.100722 · Cited by 14
Enterprise imaging and big data: A review from a medical physics perspective
McCarthy, N., Dahlan, A., Cook, T. S., Hare, N. O., Ryan, M.-L., John, B. S., Lawlor, A., & Curran, K. M. (2021) · Physica Medica · doi:10.1016/j.ejmp.2021.04.004 · Cited by 14
“Detection of diabetic retinopathy or precursor findings [85,86].”
BackgroundChen, D. J., Ho, Y., Sasa, Y., Lee, J., Yen, C. C., & Tan, C. W. T. (2021) · Biosensors · doi:10.3390/bios11060182 · Cited by 14
“Artificial intelligence (AI) has seen tremendous breakthroughs in ophthalmic imaging in recent years [11], especially with respect to fundal imaging for the diagnosis of diabetic retinopathy [12,13], age-related macular degeneration [14,15], and glaucoma [16].”
BackgroundVariability of Grading DR Screening Images among Non-Trained Retina Specialists
Grzybowski, A., Brona, P., Krzywicki, T., gaca-Wysocka, M., Berlińska, A., & Święch, A. (2022) · Journal of Clinical Medicine · doi:10.3390/jcm11113125 · Cited by 13
“There are examples of all three grading levels employed within different automatic DR grading systems [11].”
BackgroundInfluentialWilliams, A. M., Weed, J. M., Commiskey, P. W., Kalra, G., & Waxman, E. L. (2022) · BMC Ophthalmology · doi:10.1186/s12886-022-02459-y · Cited by 14
“In the future, real-time analysis and artificial intelligence to detect DR from digital photographs may allow for immediate image interpretation, which could risk-stratify urgent referrals for vision-threatening disease [21, 22].”
BackgroundReview of Visualization Approaches in Deep Learning Models of Glaucoma
Gu, B., Sidhu, S., Weinreb, R. N., Christopher, M. A., Zangwill, L. M., & Baxter, S. L. (2023) · Asia-Pacific Journal of Ophthalmology · doi:10.1097/apo.0000000000000619 · Cited by 14
“AI-enabled diabetic retinopathy screening is one area where ophthalmology has advanced into clinical practice 75,76 and is demonstrating impact (stage 3) from the perspective of enhancing screening rates.”
BackgroundLi, Q., Drinkwater, J. J., Woods, K., Douglas, E., Ramirez, A., & Turner, A. W. (2025) · Australian Journal of Rural Health · doi:10.1111/ajr.70031 · Cited by 13
Zhang, P., Lin, F., Ma, F., Chen, Y., Liu, Y., Feng, X., Fang, S., Zhang, H., Xiao, S., Yang, X., et al. (2025) · Med · doi:10.1016/j.medj.2025.100668 · Cited by 13
Shao, A., Jin, K., Li, Y., Lou, L., Zhou, W., & Ye, J. (2022) · Frontiers in Endocrinology · doi:10.3389/fendo.2022.1032144 · Cited by 13
“…application of ML techniques in DR, including the clinical validation of DL systems based on the Singapore National Diabetic Retinopathy Screening Program or other multiethnic DR screening data and reviews that discussed the current status of AI techniques in the real-word DR screening (48, 49).”
MethodLoewenstein, A., Berger, A. R., Daly, A., Creuzot-Garcher, C. P., Gale, R. P., Ricci, F., Zarranz‐Ventura, J., & Guymer, R. H. (2023) · Eye · doi:10.1038/s41433-023-02540-w · Cited by 14
“AI-enabled algorithms — which are used in the United States and have been shown to effectively interpret retinal photographs — could serve as a useful screening aide for non-ophthalmic clinicians and other eye specialists to support detection and diagnosis [15 – 18].”
MethodAdoption of machine learning for medical diagnosisPreprint
Shaheen, M. Y. (2021) · doi:10.14293/s2199-1006.1.sor-.pphmka6.v1 · Cited by 13
“with the overwhelming issue of diabetes patients becoming blind, as well as reducing the cost of dealing with this problem (Grzybowski et al., 2020).”
BackgroundMethodInfluentialPinto, I., Olazarán, Á., Jurío, D., de la Osa, B., Sainz, M., Oscoz, A., Ballaz, J., Gorricho, J., Galar, M., & Andonegui, J. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1547045 · Cited by 14
Artificial intelligence in ophthalmology
Wiedemann, P. (2023) · International Journal of Ophthalmology · doi:10.18240/ijo.2023.09.01 · Cited by 12
Sanchez, M., Alford, K., Krishna, V., Huynh, T. M., Nguyen, C. D. T., Lungren, M. P., Truong, S. Q. H., & Rajpurkar, P. (2023) · Cell Reports Medicine · doi:10.1016/j.xcrm.2023.101207 · Cited by 13
An early-stage diagnosis of diabetic retinopathy based on ensemble framework
Rafid, A.-U.-I., Sanjana, S., Munir, M. B., & Sharmin, N. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02796-5 · Cited by 12
Monson, H., Demaine, J., Perryman, A., & Felfeli, T. (2024) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2023-100780 · Cited by 12
Grzybowski, A. E., Peeters, F., Barão, R., Brona, P., Rommes, S., Krzywicki, T., Stalmans, I., & Jacob, J. (2024) · Acta ophthalmologica · doi:10.1111/aos.17428 · Cited by 11
“…sensitivity rates (comparable or superior to human graders), diagnostic performance has varied substantially and specificity is often lower than human graders, which increases referrals for human contact (Grzybowski et al., 2020; Gunasekeran et al., 2020; Lee et al., 2021; Rajesh et al., 2023).”
InfluentialAI-Driven Management of Type 2 Diabetes in China: Opportunities and Challenges
He, Z., & Li, W. (2025) · Diabetes Metabolic Syndrome and Obesity · doi:10.2147/dmso.s495364 · Cited by 12
Karam-Palos, S., Andrés‐Blasco, I., Campos-Borges, C., Zanón‐Moreno, V., Gallego‐Martínez, A., Alegre, V. A., García‐Medina, J. J., Pastor‐Idoate, S., Sellés-Navarro, I., Vila-Arteaga, J., et al. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm13010074 · Cited by 11
“…are emerging, including (1) innovative medical laser–surgical treatments, (2) chorio-retinal multimodal imaging, (3) electrophysiological probes of the retina and optic pathway, and (4) novel digital technology domains, including arti fi cial intelligence (AI) and machine learning [3,6–11].”
BackgroundCurrent roles of artificial intelligence in ophthalmology
Keskinbora, K. H. (2023) · Exploration of Medicine · doi:10.37349/emed.2023.00194 · Cited by 11
Multiclass Classification and Identification of the External Eye Diseases using Deep CNN
Rashid, F., Abate, J., & Abdi, A. (2024) · Indian Journal of Science and Technology · doi:10.17485/ijst/v17i12.21 · Cited by 11
Diagnostic System Based on Deep Learning to Detect Diabetic Retinopathy
Singh, D., Dobhal, D. C., & Pant, J. (2024) · Pakistan Journal of Ophthalmology · doi:10.36351/pjo.v40i3.1771 · Cited by 11
Crew, A., Reidy, C., van der Westhuizen, H., & Graham, M. (2024) · Journal of Evaluation in Clinical Practice · doi:10.1111/jep.14237 · Cited by 10
“Another limitation is the prominence of authors on the included papers with company ‐ and patent ‐ related interests as three of the nine papers fit this description [10, 12, 20].”
Bhambhwani, V., Whitestone, N., Patnaik, J. L., Ojeda, A., Scali, J., & Cherwek, D. H. (2025) · Ophthalmic Epidemiology · doi:10.1080/09286586.2024.2434738 · Cited by 11
Barakat, A., Mobarak, O., Javaid, H. A., Awad, M. R., Hamweyah, K., Ouban, A., & Al-Hazzaa, S. A. F. (2023) · Frontiers in Medicine · doi:10.3389/fmed.2023.1303300 · Cited by 16
Chen, K.-Y., Chan, H.-C., & Chan, C.-M. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02627-0 · Cited by 12
Lopez-Bernal, D., Balderas, D., Ponce, P., Rojas, M., & Molina, A. (2023) · Life · doi:10.3390/life13041031 · Cited by 13
“Some of these applications include Healthcare Recommendation System(s) (HRS) for diabetes risk and complication predictions [15–17], automated retinal screening for diabetic retinopathy diagnosis [18], and short–long-term glycated hemoglobin response monitoring after insulin initiation [19].”
Kao, Y.-H., & Lin, C. (2024) · Electronics · doi:10.3390/electronics13112070 · Cited by 12
Application of deep learning algorithms for diabetic retinopathy screening
Poschkamp, B., & Stahl, A. (2022) · Annals of Translational Medicine · doi:10.21037/atm-2022-73 · Cited by 10
“One paper from Arcadu et al. describes the application of multiple deep learning models, on the output of which a random forest was built to subsequently predict disease progression at 6, 12, and 24 month time intervals (14).”
Malerbi, F. K., Nakayama, L. F., Prado, P., Yamanaka, F., Melo, G. B., Regatieri, C. V., & Stuchi, J. A. (2024) · Annals of Translational Medicine · doi:10.21037/atm-24-73 · Cited by 9
“DL algorithms have emerged as a promising solution, offering diagnostic performance for the detection of DR comparable to experts and the potential to scale up screening programs efficiently (7,9).”
Li, J., Liu, J., Das, V., Le, H., Aguilera, N., Bower, A. J., Giannini, J., Lu, R., Abouassali, S., Chew, E. Y., et al. (2025) · Communications Medicine · doi:10.1038/s43856-025-00803-z · Cited by 9
“Increasingly,arti fi cial intelligence (AI) is being applied to ophthalmology 1 – 3 .”
Lee, J., Jung, K., Newman, E., Chow, E., & Chen, Y. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713244 · Cited by 15
“…experiences, either as individuals directly interacting with AI-driven personal health technologies (e.g., tracking [43, 61, 172], chatbots [27, 126, 181]) or as patients benefiting from healthcare providers who use an AI system (e.g., screening [66, 77, 135], treat-ment selection [88, 98, 183]).”
Yadav, Y., Chand, S., Sahoo, R. C., Sahoo, B. M., & Kumar, S. (2022) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-212771 · Cited by 10
Nakayama, L., Ribeiro, L. Z., Malerbi, F., & Regatieri, C. (2022) · Frontiers in Ophthalmology · doi:10.3389/fopht.2022.898181 · Cited by 8
“…quality; it estimates DR progression and provides classi fi cation regarding retinopathy referral, with a sensitivity of 91.7% for DR screening and speci fi city of 94.7% (5, 18, 19). iGradingM provides disease/no disease grading in DR with a sensitivity of 97.4-99.1% and speci fi city of 98.3-99.3%.”
BackgroundMethodInfluentialLi, W., Bian, L., Ma, B., Sun, T., Liu, Y., Sun, Z., Zhao, L., Feng, K., Yang, F., Wang, X., et al. (2024) · Diagnostics · doi:10.3390/diagnostics14020121 · Cited by 9
Artificial Intelligence in Surgery
Filicori, F., & Meireles, O. R. (2021) · Springer eBooks · doi:10.1007/978-3-030-58080-3_171-1 · Cited by 9
Future of artificial intelligence for the diagnosis and treatment of retinal diseases
Katalevskaya, E. A., Solutions", D. V., M., Katalevskiy, D. Y., Tiurikov, M. I., Velieva, I. A., & Bol’shunov, A. V. (2022) · Russian Journal of Clinical Ophthalmology · doi:10.32364/2311-7729-2022-22-1-36-43 · Cited by 9
An initiative to improve follow‐up of patients with diabetic retinopathy
Sabharwal, S., Kuo, K., Roh, S., & Ramsey, D. J. (2022) · Ophthalmic and Physiological Optics · doi:10.1111/opo.12998 · Cited by 9
“Such QI efforts not only promote optimal care of patients by potentially reducing vision loss from DR progression, but also serve to maintain clinical productivity and reduce potential medicolegal liability arising from gaps in diabetic eye care.(24) This study identified several readilyobtainable EMR data elements th…”
Machines with vision for intraoperative guidance during gastrointestinal cancer surgery
Khalid, M. U., Laplante, S. J., & Madani, A. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.1025382 · Cited by 9
Prospective studies on artificial intelligence (AI)-based diabetic retinopathy screening
Nanegrungsunk, O., Ruamviboonsuk, P., & Grzybowski, A. E. (2022) · Annals of Translational Medicine · doi:10.21037/atm-2022-71 · Cited by 9
“With adoption of artificial intelligence (AI) using machine learning (ML) or deep learning (DL) into automated DR detection algorithms, these disruptive technologies have been demonstrated high diagnostic performance, lower cost and shorter acquisition time in a number of studies (7,8).”
ResultNissen, T. P. H., Nørgaard, T. L., Schielke, K., Vestergaard, P., Nikontovic, A., Dawidowicz, M., Grauslund, J., Vorum, H., & Aasbjerg, K. (2023) · Journal of Personalized Medicine · doi:10.3390/jpm13071128 · Cited by 9
“No performance studies of the software have been performed since the reintroduction of the software to the market in 2013 other than a pilot study [24,25].”
MethodRealistic fundus photograph generation for improving automated disease classification
Pandey, P. U., Micieli, J. A., Tone, S. O., Eng, K. T., Kertes, P. J., & Wong, J. C. Y. (2025) · British Journal of Ophthalmology · doi:10.1136/bjo-2024-326122 · Cited by 9
“9 10 Given the recent United States Food and Drug Administration approval of autonomous single-disease screening algorithms for diabetic retinopathy (DR), 11 12 the next step will be to develop accurate classifiers for multidisease screening.”
DS-Net: A model driven network framework for lesion segmentation on fundus image
Tan, F., Wang, Y., Xie, Q., Fu, J., Wang, R., & Meng, D. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113242 · Cited by 8
Guo, Y., Du, H., Zhang, Y., Ma, F., & Meng, J. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107813 · Cited by 9
Tools and methods for cataract recognition in low-resource settings: A narrative review
Truong, P. N., Merlinsky, E. A., Maamari, N. C., Weng, C. Y., & Lee, A. G. (2025) · PLOS Global Public Health · doi:10.1371/journal.pgph.0004619 · Cited by 8
“Most current AI models are trained to detect specific pathologies – such as diabetic retinopathy or early glaucomatous changes – and may overlook conditions for which they were neither trained nor intended to detect [53].”
To pretrain or not? A systematic analysis of the benefits of pretraining in diabetic retinopathy
Srinivasan, V., Strodthoff, N., Ma, J., Binder, A., Müller, K., & Samek, W. (2022) · PLoS ONE · doi:10.1371/journal.pone.0274291 · Cited by 16
Braun, M., Piasecka, D., Bobrowski, M., Kordek, R., Sądej, R., & Romańska, H. (2020) · Diagnostics · doi:10.3390/diagnostics10121060 · Cited by 8
Artificial Intelligence in Retina
Trinh, M., Ghassibi, M. P., & Lieberman, R. M. (2021) · Advances in Ophthalmology and Optometry · doi:10.1016/j.yaoo.2021.04.012 · Cited by 8
Vinayaki, V. D., & Kalaiselvi, R. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7391 · Cited by 8
“→ J LSTM x = → LSTM (Cx) , x ∈ [1, ρ], (5)”
Retinal multi-lesion segmentation by reinforcing single-lesion guidance with multi-view learning
Zhang, L., Fang, Z., Li, T., Xiao, Y., Zhou, J. T., & Yang, F. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105349 · Cited by 8
A clinician's guide to large language models
Briganti, G. (2023) · Future Medicine AI · doi:10.2217/fmai-2023-0003 · Cited by 15
Chawla, R., Karkhanis, P., Shah, M., Das, A., Sharma, R., Almaula, D. K., Venkatesh, P., Singh, H. V., Kumar, M., Samanta, R., et al. (2025) · Global Epidemiology · doi:10.1016/j.gloepi.2025.100209 · Cited by 9
“Past studies have also shown that AI-driven models such as those developed by EyePACS and Google have achieved over 90 % sensitivity and specificity in detecting referable DR across diverse datasets, including the Messidor-2 and EyePACS-1 datasets [15,16].”
Messica, S., Cohen, S., Hadad, A., Gordon, M., Katz, O., Presil, D., Dagan, N., Tsumi, E., & Rokach, L. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3578197 · Cited by 7
“However, contemporary models face difficulty due to a quality discrepancy between training datasets, which usually contain high-quality images, versus reduced-quality images that are taken at the clinic [20], [21], [22].”
Piatti, A., Romeo, F., Manti, R., Doglio, M., Tartaglino, B., Nada, E., & Giorda, C. B. (2023) · Acta Diabetologica · doi:10.1007/s00592-023-02172-2 · Cited by 7
“[13], of EYEART app (91.7% and 91.5”
InfluentialAUTOMATED DETECTION OF VITRITIS USING ULTRAWIDE-FIELD FUNDUS PHOTOGRAPHS AND DEEP LEARNING
Mhibik, B., Kouadio, D., Jung, C., Bchir, C., Toutée, A., Maestri, F., Gulic, K., Mière, A., Falcione, A., Touati, M., et al. (2024) · Retina · doi:10.1097/iae.0000000000004049 · Cited by 7
“21 This suggests that our AI model may similarly be of value to the health care systems.”
ResultChawla, J. S., & Walia, N. K. (2024) · International Conference for Innovation in Technology (INOCON) · doi:10.1109/inocon60754.2024.10512051 · Cited by 7
Piatti, A., Rui, C., Gazzina, S., Tartaglino, B., Romeo, F., Manti, R., Doglio, M., Nada, E., & Giorda, C. B. (2024) · European Journal of Ophthalmology · doi:10.1177/11206721241272229 · Cited by 10
“18,24 Additionally, IDX-DR (Idx LLC, Iowa, USA) recorded 91% sensitivity and 84% speci fi city, 25 EYEART app reported 91.7% sensitivity and 91.5% speci fi city, 25,26 and RETMARKER app showed 85% sensitivity.”
InfluentialTeleophthalmology Using Remote Retinal Imaging During the COVID-19 Pandemic
Lee, S. C., Alber, S. A., Lieng, M. K., Emami-Naeini, P., & Yiu, G. C. (2022) · Telemedicine Journal and e-Health · doi:10.1089/tmj.2022.0048 · Cited by 7
“21–23 However, adoption of these technologies has been modest due to financial, technical, and logistical barriers.”
Google Lens: A potential cost-effective screening tool for diabetic retinopathy
Venkatesh, P. (2022) · Medical Hypothesis Discovery & Innovation in Optometry · doi:10.51329/mehdioptometry147 · Cited by 7
Artificial intelligence in diabetic retinopathy
Williamson, T. H. (2020) · Eye · doi:10.1038/s41433-020-0855-7 · Cited by 7
Ocular imaging at the cutting-edge
Lai, T. Y. Y. (2020) · Eye · doi:10.1038/s41433-020-01268-1 · Cited by 7
Gould, D. S. W., Yang, J., & Clifton, D. A. (2024) · medRxiv · doi:10.1101/2024.02.12.24302676 · Cited by 6
“The exploration of integrating artificial intelligence tools into this procedure has shown encouraging outcomes [8], with many existing works focusing on binary or small-number multi-label disease classification [9–12].”
MethodPredictive Analytics in Medical Diagnosis
Upadhyaya, V. (2024) · doi:10.1002/9781394270910.ch2 · Cited by 7
Chauhan, A., Sarkar, D., Verma, G. S., Rastogi, H., Adapa, K., & Duggal, M. (2025) · BMC Medical Ethics · doi:10.1186/s12910-025-01265-7 · Cited by 10
“AI algorithms are increasingly deployed for DR screening (DRS) to meet the rising demand driven by the growing diabetic population worldwide [13, 14].”
Detection and diagnosis of diabetic retinopathy in retinal fundus images using agentic AI approaches
Sathya, R., & Valaramathi, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-34016-0 · Cited by 6
Duong, R. T., Abou-Samra, A., Bogaard, J. D., & Shildkrot, Y. (2023) · Clinical ophthalmology · doi:10.2147/opth.s389111 · Cited by 6
“However, as with many studies evaluating AI-based fundus interpretation software, photos with ABs were either never included in the training/testing datasets or were screened out due to poor image quality.(71,73) Compared with clinician review, a computer-based algorithm may be more at risk for falsely misinterpreting…”
MethodConstruction of Predictive Model for Type 2 Diabetic Retinopathy Based on Extreme Learning Machine
Liu, L., Wang, M., Li, G., & Wang, Q. (2022) · Diabetes Metabolic Syndrome and Obesity · doi:10.2147/dmso.s374767 · Cited by 6
Metadata
- Authors
- Grzybowski, A., Brona, P., Lim, G., Ruamviboonsuk, P., Tan, G. S. W., Abramoff, M., & Ting, D. S. W.
- Affiliations
- Foundation for the Development of Ophthalmology (PL)
- University of Warmia and Mazury in Olsztyn (PL)
- National University of Singapore (SG)
- Rajavithi Hospital (TH)
- Corresponding author
- Ting, Daniel S. W.
- ORCID
- Venue
- Eye
- Published
- 2019-09-05
- Volume
- 34
- Issue
- 3
- Pages
- 451-460
- ISSN
- 0078-5334 (ISSN-L)
- 0950-222X
- 1476-5454
- PMC
- PMC7055592
- OpenAlex
- W2972246881
- Cited by
- 376
- References
- 36
- Citations by year
- 2026: 34 · 2025: 69 · 2024: 70 · 2023: 76 · 2022: 63 · 2021: 40 · 2020: 21 · 2019: 2
- FWCI
- 4.72
- Type
- journal article
- Language
- en
- Update notices
- correction (2019-12-10)
- Open access
- bronze
- doi.org
- Locations
- Eye (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Health Sciences › Medicine › Ophthalmology › Retinal Diseases and Treatments
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- diabetic retinopathy, retinopathy screening, artificial intelligence, automated detection algorithm, deep learning, machine learning, medicolegal issues, ethics, clinical deployment
- MeSH terms
- Machine Learning, Algorithms, Artificial Intelligence, Diabetes Mellitus, Diabetic Retinopathy, Humans, Mass Screening
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
