NEW DELHI: Researchers have detected a new way to detect diabetes among Indians by taking a high-resolution photo of the retina or the back of the eye.
The research study, published in Diabetes Technology and Therapeutics journal, shows that AI can spot tiny warning signs in the eye’s blood vessels that are invisible to the human eye that can differentiate people with and without diabetes without a finger prick blood test.
“Think of the eye as a window that looks into the rest of your body," said the lead author, Dr. Soujanya Kaup, Associate Professor of Ophthalmology at Yenepoya (Deemed to be) University and Adjunct Associate Professor of Global Health at Emory University, Atlanta.
“By using AI to read the tiny clues in this window, we can tell if someone has diabetes after a quick retinal photo."
Added Dr. R Rajalakshmi, senior author, who is the Head of Medical Retina and Ocular Research at Dr. Mohan’ s Diabetes Specialities Centre and Madras Diabetes Research Foundation, “The study has utilised routine retinal images already captured during standard eye examinations. We noticed that there are subtle changes in the eye blood vessels that start, even before diabetes develops."
The researchers from Yenepoya (Deemed to be) University, Mangalore, Madras Diabetes Research Foundation, Chennai, and Emory University, Atlanta, the US, used AI techniques to look at the feature of the blood vessels and found that in the veins in the eyes showed considerable changes in people with diabetes.
The retina is the only place in the entire body where doctors can see live blood vessels without any surgery or invasive tools, by clicking a photograph.
The study found that the AI was precise in correctly identifying diabetes using retinal photographs in the test group with 95% sensitivity.
The system could even spot ‘prediabetes,’ which is the stage where lifestyle modification can help prevent diabetes.
It is also a non-invasive mode of detecting diabetes early.
According to Dr. Sudeshna Sil Kar, co-lead author from Emory University, said: "We trained the AI to look at specific shapes and patterns in the veins using retinal photos of people without and with diabetes."
"It is like a digital detective that is 95% accurate at identifying diabetes just by looking at one picture."
Dr. Anant Madabhushi, co-author on the study and Director of the Emory Empathetic AI for Health Institute, said the technology is built for everyone.
"This does not require expensive laboratory equipment. No blood draws, no fasting, just a quick photo of the back of the eye and the use of the AI."
Dr. V Mohan, Chairman of Dr. Mohan’ s Diabetes Specialities Centre and a senior diabetes expert in India, said, "India has over 100 million people with diabetes, and very often, many do not even know they have it. If the use of AI tools with simple retinal photos can help early diagnosis of diabetes, it can be used real-time in future, to screen for diabetes.”
“We have to validate these research findings in a larger population,” he added.
Dr. KM Venkat Narayan, Executive Director of the Emory Global Diabetes Research Center, said that this study adds to the foundation for leveraging AI and the eye as an early window to systemic disorders."
Globally, an estimated 828 million people live with diabetes, accounting for 1.5 million deaths annually. Alarmingly, more than half (59%, 445 million) remain untreated, and 84%-97% of the untreated are undiagnosed.
India bears a disproportionate share of this burden, with 101 million people with diabetes and 136 million with prediabetes.