One of the first studies shows impressive accuracy results
Infrared retinal scans can detect multiple sclerosis (MS) with “surprising” accuracy, which could lead to early diagnosis and treatment, according to researchers.
“This approach fills an unmet need in the diagnosis of multiple sclerosis,” said researcher Rahele Kafieh from the Department of Engineering at Durham University in the UK.
The researchers used a computer program called a machine learning model that was trained to recognize certain types of patterns.
The model was designed to use two different types of eye scans to look for key signs of MS after being trained by researchers using eye scan data from 32 MS patients and 70 healthy subjects.
According to the researchers, the results were impressive as the program was nearly 100% accurate.
However, “although the results are promising, this approach is not yet ready for clinical use,” Kafieh said.
More research with larger and more diverse populations is needed to see if the findings can be replicated, he said.
In any case, “improved diagnostic performance with high sensitivity and specificity suggests that this method can better distinguish between multiple sclerosis and healthy individuals, filling the need for more accurate and reliable diagnostic tools for multiple sclerosis,” he said.