Effectiveness of Tele-ophthalmology for Diabetic Retinopathy Screening in Rural Settings : A Systematic Review
Keywords:
Diabetic retinopathy, tele-ophthalmology, artificial intelligence, rural screening, cost-effectiveness, diagnostic accuracy, referral adherenceAbstract
Introduction: Diabetic retinopathy (DR) is a leading cause of preventable blindness, yet screening rates remain critically low in rural and underserved settings due to limited access to ophthalmologists and logistical barriers. Tele-ophthalmology and artificial intelligence (AI)-based retinal imaging have emerged as potential solutions, but their effectiveness in rural contexts requires systematic evaluation.
Methods: This systematic review synthesized evidence from 38 studies, including randomized controlled trials, etc. Studies were included if they evaluated tele-ophthalmology or AI-based DR screening in rural, remote, or underserved populations and reported outcomes related to diagnostic accuracy, screening completion, referral adherence, cost-effectiveness, or implementation factors.
Results: Tele-ophthalmology significantly improved screening completion rates, with RCT demonstrating 94% completion in the telemedicine arm versus 56% in traditional surveillance (p<0.001). Referral adherence varied substantially from 13-52% depending on financial and logistical support. Pooled diagnostic sensitivity for referable DR ranged from 0.90-0.95 across tele-ophthalmology and AI modalities, with specificity of 0.81-0.91. Cost-effectiveness analyses consistently favored tele-ophthalmology, with ICERs ranging from cost-saving to $3,328 per QALY in rural settings.
Discussion: Tele-ophthalmology effectively addresses the access gap in rural DR screening. AI-based systems offer comparable diagnostic accuracy to human graders with added advantages in speed and immediate feedback, which can improve referral adherence when combined with patient support. However, long-term screening participation tends to decline without sustained engagement strategies. Implementation success depends on reliable infrastructure, task-shifting to non-ophthalmologist staff, and integration with functional referral pathways.
Conclusion: Tele-ophthalmology and AI-based screening are effective, accurate, and cost-effective for DR screening in rural settings. Successful programs require concurrent investment in referral infrastructure, patient navigation support, and quality assurance mechanisms. Future implementations should prioritize context-specific validation and sustainable engagement strategies.
References
Mansberger S, Gleitsmann K, Gardiner S, et al (2013) Comparing the Effectiveness of Telemedicine and Traditional Surveillance in Providing Diabetic Retinopathy Screening Examinations: A Randomized Controlled Trial. Telemedicine journal and e-health. https://doi.org/10.1089/tmj.2012.0313
Mansberger S, Sheppler CR, Barker G, et al (2015) Long-term Comparative Effectiveness of Telemedicine in Providing Diabetic Retinopathy Screening Examinations: A Randomized Clinical Trial. JAMA ophthalmology. https://doi.org/10.1001/jamaophthalmol.2015.1
Amin R, Rizky DA (2025) Tele-ophthalmology versus Traditional Fundus Photography for Diabetic Retinopathy Screening: A Comparative Meta-analysis of Diagnostic Accuracy, Cost-Effectiveness, and Health Policy Uptake. Community Medicine and Education Journal. https://doi.org/10.37275/cmej.v5i2.729
Sadjadi R (2021) Assessing the Performance of Artificial Intelligence Systems for the Screening of Diabetic Retinopathy. https://doi.org/10.20944/preprints202108.0030.v1
Wang T-W, Luo W-T, Tu Y-K, et al (2025) Systematic review and meta-analysis of regulator-approved deep learning systems for fundus diabetic retinopathy detections. npj Digital Medicine. https://doi.org/10.1038/s41746-025-02223-8
Mathenge W, Whitestone N, Nkurikiye J, et al (2022) Impact of Artificial Intelligence Assessment of Diabetic Retinopathy on Referral Service Uptake in a Low-Resource Setting. Ophthalmology Science. https://doi.org/10.1016/j.xops.2022.100168
Chauhan A, Vale L, Kankaria A, et al (2025) Assessing adoption of human and AI-enabled diabetic retinopathy screening in primary healthcare settings: findings from a pragmatic trial. Archives of Public Health. https://doi.org/10.1186/s13690-025-01757-3
Sharafeldin N, Kawaguchi A, Sundaram A, et al (2018) Review of economic evaluations of teleophthalmology as a screening strategy for chronic eye disease in adults. British Journal of Ophthalmology. https://doi.org/10.1136/bjophthalmol-2017-311452
Lee J, Lee SWH (2018) Telemedicine Cost–Effectiveness for Diabetes Management: A Systematic Review. Diabetes Technology & Therapeutics. https://doi.org/10.1089/dia.2018.0098
Pratiwi N (2026) A Comprehensive Systematic Review of The Role of Screening Programs in Preventing Blindness in Primary Setting. International journal of medical science and health research. https://doi.org/10.70070/ppw50b18
Avidor D, Loewenstein A, Waisbourd M, Nutman A (2020) Cost-effectiveness of diabetic retinopathy screening programs using telemedicine. Cost Effectiveness and Resource Allocation. https://doi.org/10.1186/s12962-020-00211-1
Zikhali T, Kalinda C, Xulu-Kasaba Z (2022) Screening of Diabetic Retinopathy Using Teleophthalmology to Complement Human Resources for Eye Health. Clinics and Practice. https://doi.org/10.3390/clinpract12040050
Piyasena MMPN, Murthy G, Yip J, et al (2018) Systematic review and meta-analysis of diagnostic accuracy of detection of any level of diabetic retinopathy using digital retinal imaging. Systematic Reviews. https://doi.org/10.1186/s13643-018-0846-y
Pasquel F, Hendrick A, Ryan M, et al (2016) Cost-effectiveness of Different Diabetic Retinopathy Screening Modalities. Journal of Diabetes Science and Technology. https://doi.org/10.1177/1932296815624109
Chidi R, Odimba U (2024) AI APPLICATIONS IN SCREENING AND DIAGNOSIS OF DIABETIC RETINOPATHY IN RURAL SETTINGS. International medical science research journal. https://doi.org/10.51594/imsrj.v4i3.918
Chid R, Akubue I (2024) Telemedicine in diabetic eye care: A meta-analysis of its effectiveness in underserved populations. World Journal of Biology Pharmacy and Health Sciences. https://doi.org/10.30574/wjbphs.2024.17.3.0104
Andayani A, Hendrawan K, Made N, et al (2025) Economic Evaluation of Diabetic Retinopathy Screening in Developing Countries. Korean Journal of Ophthalmology. https://doi.org/10.3341/kjo.2025.0047
Ha SK, Gilbert JB, Le E, et al (2025) Impact of teleretinal screening program on diabetic retinopathy screening compliance rates in community health centers: a quasi-experimental study. BMC Health Services Research. https://doi.org/10.1186/s12913-025-12472-8
Walsh LG, Hong SC, Chalakkal RJ, Ogbuehi K (2021) A Systematic Review of Current Teleophthalmology Services in New Zealand Compared to the Four Comparable Countries of the United Kingdom, Australia, United States of America (USA) and Canada. Clinical Ophthalmology. https://doi.org/10.2147/OPTH.S294428
Prayogo ME, Zaharo AF, Damayanti NNR, et al (2023) Accuracy of Low-Cost, Smartphone-Based Retinal Photography for Diabetic Retinopathy Screening. Clinical Ophthalmology. https://doi.org/10.2147/OPTH.S416422
Ramoutar RR (2024) An Economic Analysis for the Use of Artificial Intelligence in Screening for Diabetic Retinopathy in Trinidad and Tobago. Cureus. https://doi.org/10.7759/cureus.55745
Kumari R (2025) The Truth About Diabetic Eye Screening: A Deep Dive into Diagnostic Accuracy. Journal of Pharmaceutical Research. https://doi.org/10.18579/jopcr/v24.i3.82
Rizvi A, Rizvi F, Lalakia P, et al (2023) Is Artificial Intelligence the Cost-Saving Lens to Diabetic Retinopathy Screening in Low- and Middle-Income Countries? Cureus. https://doi.org/10.7759/cureus.45539
Wang T-W, Luo W-T, Tu Y-K, et al (2025) Diagnostic Accuracy of EyeArt for Fundus-Based Detection of Diabetic Retinopathy: A Systematic Review and Meta-analysis. American journal of ophthalmology-glaucoma. https://doi.org/10.37766/inplasy2025.5.0079
Samara SM, Laksono AK (2025) Evaluating the accuracy of Artificial Intelligence (AI)-integrated, Smartphone-based screening for Diabetic Retinopathy: Systematic Review. International Journal of Retina. https://doi.org/10.35479/ijretina.2025.vol008.iss001.294
Yudistira Y, Hendrawan K, Andayani A, et al (2025) Diabetic Retinopathy Screening Approaches in Developing Countries. Turkish journal of ophthalmology. https://doi.org/10.4274/tjo.galenos.2025.32916
Onyeze NS, Sartawi S, Nayyer Z (2025) Effectiveness of AI-Based Tools in Detecting Diabetic Retinopathy in Low- and Middle-Income Countries: A Systematic Review of Diagnostic Performance and Implementation Feasibility. Cureus. https://doi.org/10.7759/cureus.96554
Lestari YD, Jayanegara AP (2023) The Validity of Artificial Intelligence (AI) for Diabetic Retinopathy Screening in Asia. International Journal of Retina. https://doi.org/10.35479/ijretina.2023.vol006.iss002.241
Vilela M, Valença F, Barreto PKM, et al (2018) Agreement between retinal images obtained via smartphones and images obtained with retinal cameras or fundoscopic exams –. Clinical Ophthalmology. https://doi.org/10.2147/OPTH.S182022
Noriega A, Meizner D, Camacho D, et al (2020) Screening Diabetic Retinopathy Using an Automated Retinal Image Analysis System in Independent and Assistive Use Cases in Mexico: Randomized Controlled Trial. JMIR Formative Research. https://doi.org/10.2196/25290
Wang Z, Li Z, Li K, et al (2023) Performance of artificial intelligence in diabetic retinopathy screening. Frontiers in Endocrinology. https://doi.org/10.3389/fendo.2023.1197783
Rogers M, Kaggwa F, Arunga S, Wasswa W (2025) Feasibility and Equity of AI-Driven Models for Diabetic Retinopathy Screening in Sub-Saharan Africa: A Systematic Review and Meta-Analysis. Cureus Journal of Computer Science. https://doi.org/10.7759/s44389-025-07263-5
Cleland CR, Bascaran C, Makupa W, et al (2024) Artificial intelligence-supported diabetic retinopathy screening in Tanzania: rationale and design of a randomised controlled trial. BMJ Open. https://doi.org/10.1136/bmjopen-2023-075055
Hidayati N, Widyawati IY, Suarilah I, et al (2024) Diagnostic Accuracy of Artificial Intelligence-Based Systems for Detecting Diabetic Retinopathy: A Systematic Review. Indonesian Journal of Global Health Research. https://doi.org/10.37287/ijghr.v7i1.4011
Suebsaiphrom N, Takkametha T, Vanichakulthada N, Vongkancom U (2026) Diagnostic Performance of Artificial Intelligence and Deep Learning for Diabetic Retinopathy Screening: A Systematic Review and Meta-analysis. Journal of Optometry and Ophthalmology Research. https://doi.org/10.61440/joor.2026.v2.03
Rahmati M, Smith L, Piyasena MMPN, et al (2025) Artificial Intelligence improves follow-up appointment uptake for diabetic retinal assessment: a systematic review and meta-analysis. Eye. https://doi.org/10.1038/s41433-025-03849-4
Moannaei M, Jadidian F, Doustmohammadi T, et al (2025) Performance and limitation of machine learning algorithms for diabetic retinopathy screening and its application in health management: a meta-analysis. BioMedical Engineering OnLine. https://doi.org/10.1186/s12938-025-01336-1
Scott S, Grewal E, Varma M, Campbell DJT (2025) Evaluation of a pilot outreach program to support point-of-care screening for individuals with diabetes who are experiencing homelessness in Alberta, Canada: results of a mixed methods study. BMC Health Services Research. https://doi.org/10.1186/s12913-025-13316-1
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Arihta Johana Wulandari Ginting, Tria Pertiwi, Fasya Radilia, Theresia Fitri Hakna Sihombing, Indah Purnama (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors publishing here keep copyright but grant the journal first publication rights, under a Creative Commons Attribution-NonCommercial 4.0 License. They can distribute their work non-exclusively elsewhere with an acknowledgment of its first publication in this journal. Posting the work online before and during submission for earlier and greater citation is encouraged, reflecting Open Access benefits.
