[Skip to Content]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address 35.173.234.140. Please contact the publisher to request reinstatement.
[Skip to Content Landing]
Original Investigation
June 13, 2019

Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India

Author Affiliations
  • 1Google Research, Mountain View, California
  • 2Aravind Eye Hospital, Madurai, India
  • 3Verily Life Sciences, San Francisco, California
  • 4Shri Bhagwan Mahavir Vitreoretinal Services, Sankara Nethralaya, Chennai, Tamil Nadu, India
JAMA Ophthalmol. 2019;137(9):987-993. doi:10.1001/jamaophthalmol.2019.2004
Key Points

Question  What is the performance of a deep-learning model in a cohort of patients with diabetes in India?

Findings  In this observational study of moderate or worse diabetic retinopathy and referable diabetic macular edema, the automated diabetic retinopathy system's performance was equal to or exceeded manual grading.

Meaning  Deep-learning models performed well within a population of patients with diabetes from India.

Abstract

Importance  More than 60 million people in India have diabetes and are at risk for diabetic retinopathy (DR), a vision-threatening disease. Automated interpretation of retinal fundus photographs can help support and scale a robust screening program to detect DR.

Objective  To prospectively validate the performance of an automated DR system across 2 sites in India.

Design, Setting, and Participants  This prospective observational study was conducted at 2 eye care centers in India (Aravind Eye Hospital and Sankara Nethralaya) and included 3049 patients with diabetes. Data collection and patient enrollment took place between April 2016 and July 2016 at Aravind and May 2016 and April 2017 at Sankara Nethralaya. The model was trained and fixed in March 2016.

Interventions  Automated DR grading system compared with manual grading by 1 trained grader and 1 retina specialist from each site. Adjudication by a panel of 3 retinal specialists served as the reference standard in the cases of disagreement.

Main Outcomes and Measures  Sensitivity and specificity for moderate or worse DR or referable diabetic macula edema.

Results  Of 3049 patients, 1091 (35.8%) were women and the mean (SD) age for patients at Aravind and Sankara Nethralaya was 56.6 (9.0) years and 56.0 (10.0) years, respectively. For moderate or worse DR, the sensitivity and specificity for manual grading by individual nonadjudicator graders ranged from 73.4% to 89.8% and from 83.5% to 98.7%, respectively. The automated DR system’s performance was equal to or exceeded manual grading, with an 88.9% sensitivity (95% CI, 85.8-91.5), 92.2% specificity (95% CI, 90.3-93.8), and an area under the curve of 0.963 on the data set from Aravind Eye Hospital and 92.1% sensitivity (95% CI, 90.1-93.8), 95.2% specificity (95% CI, 94.2-96.1), and an area under the curve of 0.980 on the data set from Sankara Nethralaya.

Conclusions and Relevance  This study shows that the automated DR system generalizes to this population of Indian patients in a prospective setting and demonstrates the feasibility of using an automated DR grading system to expand screening programs.

×