Performance of a Deep Learning Diabetic Retinopathy Algorithm in India
In this cross-sectional study investigating the clinical performance of ARDA, sensitivity and specificity for severe NPDR and PDR exceeded 96% and caught 100% of patients with severe NPDR and PDR for ophthalmology referral. This preliminary large-scale postmarketing report of the performance of ARDA after screening 600 000 patients in India underscores the importance of monitoring and publication an algorithm's clinical performance, consistent with recommendations by regulatory bodies.
Authors
- Florence Thng
- Naresh Babu (ORCID: https://orcid.org/0000-0002-3993-9790)
- Sunny Virmani (ORCID: https://orcid.org/0009-0008-0647-8853)
- Dale R. Webster (ORCID: https://orcid.org/0000-0002-3023-8824)
- Jonathan Krause (ORCID: https://orcid.org/0000-0002-1952-3480)
- Arthur Brant (ORCID: https://orcid.org/0000-0002-1105-4747)
- Yossi Matias (ORCID: https://orcid.org/0000-0003-3960-6002)
- Kim Ramasamy (ORCID: https://orcid.org/0000-0003-0650-1220)
- Greg S. Corrado (ORCID: https://orcid.org/0000-0001-8817-0992)
- Yang Lu (ORCID: https://orcid.org/0000-0002-3027-3064)
- Kasumi Widner
- Jay Nayar
- Divleen Jeji
- Xiang Yin (ORCID: https://orcid.org/0009-0003-5364-2787)
- Preeti Singh (ORCID: https://orcid.org/0000-0003-1033-3725)
- Lily Peng (ORCID: https://orcid.org/0009-0007-5552-5428)
- Yun Liu (ORCID: https://orcid.org/0000-0002-8158-3783)
- Anchintha Meenu
Institutions
- Google (United States) (US)
- Aravind Eye Hospital (IN)
Publication Details
- Journal
- JAMA Network Open
- Published
- 2025-03-19
- DOI
- https://doi.org/10.1001/jamanetworkopen.2025.0984
- Citations
- 9
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 12.24