Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189917,
        author = {DR. P.Pandia Vadivu and Dr. S.Logeshwaran and Dr. S.Jeeva Lakshmi},
        title = {Clinical Validation of an Artificial Intelligence–Driven Diabetic Retinopathy Screening System: Evidence from a Large Multicenter Study in India},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {6678-6683},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189917},
        abstract = {Diabetic retinopathy (DR) remains one of the foremost causes of preventable visual impairment and blindness globally, with a disproportionately high burden in low- and middle-income countries such as India. Despite strong evidence that early detection and timely intervention can substantially reduce vision loss, large-scale DR screening is hindered by shortages of trained ophthalmologists, infrastructural constraints, and limited access to specialist eye care, particularly in rural and underserved regions. To overcome these barriers, an AI-Driven Diabetic Retinopathy Screening System (AIDRSS) was developed using advanced deep-learning algorithms for automated detection and grading of DR from retinal fundus images. This article presents findings from a large multicenter validation study conducted across diverse Indian healthcare settings, evaluating the diagnostic accuracy, clinical utility, and scalability of AIDRSS. The system demonstrated high diagnostic performance, achieving 92% sensitivity and 88% specificity, with excellent detection of referable diabetic retinopathy. The results underscore the potential of AI-enabled screening tools to facilitate early diagnosis, optimize referral pathways, and support population-level eye care programs in resource-constrained environments. The study highlights the role of artificial intelligence as a transformative approach for strengthening diabetic eye care delivery and reducing preventable blindness in India.},
        keywords = {Artificial intelligence; Diabetic retinopathy; Automated screening; Deep learning; Retinal fundus imaging; Multicenter validation; Resource-limited settings; Public health ophthalmology; Digital health; India},
        month = {January},
        }