Google has announced the licensing of its AI model for detecting diabetic retinopathy in Thailand, where the shortage of eye specialists limits access to essential screening services. Nearly a decade ago, Google Research collaborated with Rajavithi Hospital in Thailand to explore AI’s potential in reducing preventable blindness due to diabetic retinopathy. Now, in partnership with Thai healthcare providers and health-tech company Perceptra, Google aims to distribute its AI-enabled diabetic retinopathy detection model widely.
This initiative also involves Thailand’s Ministry of Public Health’s Department of Medical Services (DMS), which oversees the country’s diabetic retinopathy screening. Through collaboration with DMS, Google’s model will join Thailand’s National Innovation program, facilitating integration within public hospitals and aiming for broader, cost-effective screening solutions.
The demand for diabetic retinopathy detection is increasing globally, with the number of cases expected to grow significantly by 2030. A 2022 Thai study published in The Lancet highlighted the high performance of deep-learning algorithms for detecting diabetic retinopathy, achieving 94.7% accuracy, 91.4% sensitivity, and 95.4% specificity—comparable to expert retina specialists. This AI-driven approach has shown potential to support large-scale screening efforts, helping to address the rising need for early detection and treatment.
(Source: MobiHealthNews)
