Background: Artificial intelligence (AI) algorithms offer an effective solution to alleviate the burden of diabetic retinopathy (DR) screening in public health settings. However, there are challenges in translating diagnostic performance and its application when deployed in real-world conditions. Objective: This study aimed to assess the technical feasibility of integration and diagnostic performance of validated DR screening (DRS) AI algorithms in real-world outpatient public health settings. Methods: Prior to integrating an AI algorithm for DR screening, the study involved several steps: (1) Five AI companies, including four from India and one international company, were invited to evaluate their diagnostic performance using low-cost nonmydriatic fundus cameras in public health settings; (2) The AI algorithms were prospectively validated on fundus images from 250 people with diabetes mellitus, captured by a trained optometrist in public health settings in Chandigarh Tricity in North India. The performance evaluation used diagnostic metrics, including sensitivity, specificity, and accuracy, compared to human grader assessments; (3) The AI algorithm with better diagnostic performance was integrated into a low-cost screening camera deployed at a community health center (CHC) in the Moga district of Punjab, India. For AI algorithm analysis, a trained health system optometrist captured nonmydriatic images of 343 patients. Results: Three web-based AI screening companies agreed to participate, while one declined and one chose to withdraw due to low specificity identified during the interim analysis. The three AI algorithms demonstrated variable diagnostic performance, with sensitivity (60%-80%) and specificity (14%-96%). Upon integration, the better-performing algorithm AI-3 (sensitivity: 68%, specificity: 96, and accuracy: 88·43%) demonstrated high sensitivity of image gradability (99.5%), DR detection (99.6%), and referral DR (79%) at the CHC. Conclusions: This study highlights the importance of systematic AI validation for responsible clinical integration, demonstrating the potential of DRS to improve health care access in resource-limited public health settings.

Diabetic retinopathy (DR), a prevalent microvascular complication of diabetes mellitus (DM), can be prevented with early detection and timely intervention. DR is asymptomatic in its early stages, highlighting the importance of screening for accurate referral and effective management. Multiple barriers impede access to diabetic retinopathy screening (DRS), creating significant public health challenges in regions with high DM prevalence. This study explores the perspectives of people with DM (PwDM) and healthcare providers (HCP) on these barriers. A qualitative study using in-depth interviews (IDI) was conducted between October 2022 and January 2023 in Punjab and Chandigarh. Through purposive sampling, IDIs were conducted with 7 PwDM and 19 HCPs, including retina specialists, ophthalmologists, optometrists, medical officers (MO), Community Health Officers (CHO), and ASHA workers from various public health facilities. A semi-structured topic guide facilitated the interviews, and thematic analysis was applied, utilizing the healthcare access barrier (HCAB) model as a framework. The study identified financial barriers due to insurance unawareness and employment constraints. Structural challenges included insufficient DRS infrastructure, untrained staff, the need for accompaniment, and limited access to screening sites. Limited awareness and misconceptions about DR characterized cognitive barriers, while psychological barriers involved mistrust of the health system, anxiety, and frustration from low vision. Addressing these issues is essential to improve DRS uptake and eye health outcomes. Managing diabetes and VTDR is challenging, highlighting the need for community-level DRS. Enhancing DR awareness and promoting public health insurance benefits are crucial for overcoming barriers and improving screening rates.

Background: Diabetic retinopathy (DR) is a leading cause of blindness globally. DR has increasingly affected both individuals and health care systems as the population ages. Objective: This study aims to explore factors and identify barriers associated with nonadherence to referral recommendations among older adult participants after DR screening (DRS) during the COVID-19 pandemic. Method: This paper presents findings from a pilot study on artificial intelligence–enabled DRS conducted in two districts in Punjab, India (Moga and Mohali) during the COVID-19 pandemic. The screenings were conducted from March to June 2022 at community health center Badhani Kalan in Moga and from March to June 2021 in community settings (homes) in Block Boothgarh, Mohali. Participants were referred to the district hospital for an ophthalmological review based on artificial intelligence–enabled screening. After 1 month, the participants were contacted by telephone to assess adherence to the referral recommendations. Participants who did not adhere to the referral were then interviewed alongside health care providers to understand the barriers explaining their nonadherence. Results: We aimed to recruit 346 and 600 older adult participants from 2 sites but enrolled 390. Key challenges included health facility closures due to COVID-19, low motivation among health personnel for recruitment, incomplete nonparticipation data, and high participant workloads. Approximately 45% of the participants were male and 55% female. Most participants (62.6%) were between 60 and 69 years old, while 37.4% were 70 or older, with a mean age of 67.2 (SD 6.2) years. In total, 159 participants (40.8%) were referred, while 231 participants (59.2%) were not. Only 23 (14.5%) of those referred followed through and visited a health facility for ophthalmological review, while 136 (85.5%) did not pursue further evaluation. Our analysis revealed no significant differences in the characteristics between adherent and nonadherent participants, suggesting that demographic and health factors alone do not predict adherence behavior in patients with DR. Interviews identified limited knowledge about DR, logistical challenges, financial constraints, and attitudinal barriers as the primary challenges. Conclusions: This study, conducted during the COVID-19 pandemic, showed suboptimal adherence to referral recommendations among older adult patients due to knowledge gaps, logistical challenges, and health system issues. Quantifying and understanding adherence factors are crucial for targeted interventions addressing barriers to referral recommendations after DRS. Integrating teleophthalmology into and strengthening infrastructure for artificial intelligence–enabled diabetic retinopathy screening to enhance access and outcomes.

Objectives To assess and compare the diagnostic accuracy of non-ophthalmologist-led diabetic retinopathy screening (DRS) at health and wellness centres (HWCs) and offline artificial intelligence (AI)-assisted community-based screening, using specialist grading as the reference standard in India. Design, settings and participants Pragmatic diagnostic accuracy study in primary healthcare settings. The settings included HWCs and community-based screening sites in rural Block Boothgarh, Mohali District, Punjab, India. A total of 600 people with diabetes aged ≥30 years were enrolled across three screening models: (1) non-ophthalmologist-led DRS at the HWC, (2) AI-assisted smartphone-based DRS in the community and (3) standard referral-based care. Retinal images were captured using non-mydriatic fundus cameras and independently graded by two masked human graders; a senior retina specialist resolved any disagreements. The AI was assessed for its ability to detect diabetic retinopathy (DR) and referable diabetic retinopathy (RDR). Diagnostic performance metrics were reported. Results The non-ophthalmologist-led model demonstrated 86.4% sensitivity (95% CI 65.1% to 97.1%) and 94.3% specificity (95% CI 88.5% to 97.7%) for DR detection, with an ungradability rate of 8%. For RDR, sensitivity reached 95.8% (95% CI 78.9% to 99.9%) and specificity was 93.1% (95% CI 88.0% to 96.5%). The offline AI-assisted model achieved 93.3% sensitivity (95% CI 68.1% to 99.8%) and 85.1% specificity (95% CI 76.9% to 91.2%) for RDR, but with a higher ungradability rate (38%), mainly due to cataracts and poor image quality. Both approaches effectively identified referable cases; however, the non-ophthalmologist-led model demonstrated greater accuracy and operational feasibility. Conclusions This study demonstrates that non-ophthalmologist-led DRS at HWCs can enhance access to primary care. Offline AI-enabled screening demonstrates potential for community use but is currently limited by image quality and binary classification outputs. Integrating both approaches may strengthen DRS coverage in resource-limited settings. Clinical trials registry of India CTRI/2022/10/046283.