Article Text

Download PDFPDF
Feasibility and acceptance of artificial intelligence-based diabetic retinopathy screening in Rwanda
  1. Noelle Whitestone1,
  2. John Nkurikiye2,3,
  3. Jennifer L Patnaik1,4,
  4. Nicolas Jaccard1,
  5. Gabriella Lanouette1,
  6. David H Cherwek1,
  7. Nathan Congdon1,5,
  8. Wanjiku Mathenge1,2
  1. 1Clinical Services, Orbis International, New York, New York, USA
  2. 2RIIO iHospital, Rwanda International Institute of Ophthalmology, Kigali, Rwanda
  3. 3Department of Ophthalmology, Rwanda Military Hospital, Kigali, Rwanda
  4. 4Department of Ophthalmology, University of Colorado Denver School of Medicine, Aurora, Colorado, USA
  5. 5Centre for Public Health, Queen's University Belfast, Belfast, UK
  1. Correspondence to Wanjiku Mathenge, Orbis International, New York, NY 10018, USA; ciku.mathenge{at}riio.org

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.

  • Retina
  • Imaging
  • Macula
  • Public health

Data availability statement

Data are available upon reasonable request.

Statistics from Altmetric.com

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Data availability statement

Data are available upon reasonable request.

View Full Text

Footnotes

  • Contributors Conception or design of the work: JN, NJ, GL, DHC, NC, WM. Data collection: JN, NJ, GL, WM. Data analysis and interpretation: NW, JP, NJ, GL, NC, WM. Drafting the article: NW, JP, NJ, GL, NC, WM. Critical revision of the article: all authors. Final approval of the version to be published: all authors. Guarantor: WM.

  • Funding This work was supported by Orbis International and the Association for Research in Vision and Ophthalmology Roche Award.

  • Competing interests None declared.

  • Provenance and peer review Not commissioned; externally peer reviewed.