Global Search

Search articles, concepts, and chapters

Br J OphthalmolMay 202413 citations

Feasibility and acceptance of artificial intelligence-based diabetic retinopathy screening in Rwanda.

Whitestone Noelle, Nkurikiye John, Patnaik Jennifer L, Jaccard Nicolas, Lanouette Gabriella, Cherwek David H, Congdon Nathan, Mathenge Wanjiku


AI Summary

AI-based DR screening in Rwanda was accurate for referable DR (92% sensitivity) and highly accepted, demonstrating its practical utility for identifying patients needing follow-up, including for other eye anomalies.

Abstract

Background

Evidence on the practical application of artificial intelligence (AI)-based diabetic retinopathy (DR) screening is needed.

Methods

Consented participants were screened for DR using retinal imaging with AI interpretation from March 2021 to June 2021 at four diabetes clinics in Rwanda. Additionally, images were graded by a UK National Health System-certified retinal image grader. DR grades based on the International Classification of Diabetic Retinopathy with a grade of 2.0 or higher were considered referable. The AI system was designed to detect optic nerve and macular anomalies outside of DR. A vertical cup to disc ratio of 0.7 and higher and/or macular anomalies recognised at a cut-off of 60% and higher were also considered referable by AI.

Results

Among 827 participants (59.6% women (n=493)) screened by AI, 33.2% (n=275) were referred for follow-up. Satisfaction with AI screening was high (99.5%, n=823), and 63.7% of participants (n=527) preferred AI over human grading. Compared with human grading, the sensitivity of the AI for referable DR was 92% (95% CI 0.863%, 0.968%), with a specificity of 85% (95% CI 0.751%, 0.882%). Of the participants referred by AI: 88 (32.0%) were for DR only, 109 (39.6%) for DR and an anomaly, 65 (23.6%) for an anomaly only and 13 (4.73%) for other reasons. Adherence to referrals was highest for those referred for DR at 53.4%.

Conclusion

DR screening using AI led to accurate referrals from diabetes clinics in Rwanda and high rates of participant satisfaction, suggesting AI screening for DR is practical and acceptable.


MeSH Terms

HumansDiabetic RetinopathyRwandaFemaleArtificial IntelligenceMiddle AgedFeasibility StudiesMaleMass ScreeningAdultAged

Key Concepts6

Diabetic retinopathy (DR) screening using artificial intelligence (AI) in diabetes clinics in Rwanda led to accurate referrals and high rates of participant satisfaction, suggesting AI screening for DR is practical and acceptable.

DiagnosisCohortCross-sectional studyn=827 participantsCh10

Among 827 participants screened for diabetic retinopathy (DR) by artificial intelligence (AI) in diabetes clinics in Rwanda, 33.2% (n=275) were referred for follow-up.

DiagnosisCohortCross-sectional studyn=827 participantsCh10

Satisfaction with artificial intelligence (AI) screening for diabetic retinopathy (DR) was high (99.5%, n=823) among participants in diabetes clinics in Rwanda, and 63.7% of participants (n=527) preferred AI over human grading.

DiagnosisCohortCross-sectional studyn=827 participantsCh10

Compared with human grading, the sensitivity of the artificial intelligence (AI) system for referable diabetic retinopathy (DR) was 92% (95% CI 0.863%, 0.968%), with a specificity of 85% (95% CI 0.751%, 0.882%) in a screening program in Rwanda.

DiagnosisCohortCross-sectional studyn=827 participantsCh10

Of the participants referred by artificial intelligence (AI) for diabetic retinopathy (DR) screening in Rwanda, 88 (32.0%) were for DR only, 109 (39.6%) for DR and an anomaly, 65 (23.6%) for an anomaly only, and 13 (4.73%) for other reasons.

DiagnosisCohortCross-sectional studyn=275 referred participants from 827 totalCh10

Adherence to referrals for diabetic retinopathy (DR) screening using artificial intelligence (AI) in Rwanda was highest for those referred for DR at 53.4%.

DiagnosisCohortCross-sectional studyn=275 referred participants from 827 totalCh10

Is this article assigned to the wrong chapter(s)? Let us know.