AI Interprets Retinal Images To Identify Alzheimer’s Disease
A form of artificial intelligence (AI) designed to interpret a combination of retinal images was able to successfully identify a group of patients who were known to have Alzheimer's disease, say, researchers.
According to the study, published in the British Journal of Ophthalmology, the novel computer software looks at the retinal structure and blood vessels on images of the inside of the eye that have been correlated with cognitive changes.
The findings provide proof-of-concept that machine learning analysis of certain types of retinal images has the potential to offer a non-invasive way to detect Alzheimer's disease in symptomatic individuals.
Follow NewsGram on Twitter to stay updated about the World news.
"Diagnosing Alzheimer's disease often relies on symptoms and cognitive testing. Additional tests to confirm the diagnosis are invasive, expensive, and carry some risk," said study author Sharon Fekrat from Duke University in the US.
"Having a more accessible method to identify Alzheimer's could help patients in many ways, including improving diagnostic precision," Fekrat added.
The team built on earlier work in which they identified changes in retinal blood vessel density that correlated with changes in cognition.
Additional studies will also determine how well the AI approach compares to current methods of diagnosing Alzheimer's disease. Pixabay
They found a decreased density of the capillary network around the center of the macula in patients with Alzheimer's disease.
Want to read more in Hindi? Checkout : सरकार का प्रत्येक व्यक्ति को कोविड-19 वैक्सीन देने का कोई इरादा नहीं
Using that knowledge, they then trained a machine learning model, known as a convolutional neural network (CNN), using four types of retinal scans as inputs to teach a computer to discern relevant differences among images.
Scans from 159 study participants were used to build the CNN: 123 patients were cognitively healthy, and 36 patients were known to have Alzheimer's disease.
"We tested several different approaches, but our best-performing model combined retinal images with clinical patient data," said study lead author C Ellis Wisely.
"Our CNN differentiated patients with symptomatic Alzheimer's disease from cognitively healthy participants in an independent test group," Wisely added.
The researchers noted that additional studies will also determine how well the AI approach compares to current methods of diagnosing Alzheimer's disease, which often includes expensive and invasive neuroimaging and cerebral spinal fluid tests. (IANS)
