AI could spot Alzheimer’s in MRI scans up to a decade before symptoms show

New research from Italy suggests an algorithm can be trained to spot changes in the brain linked to the disease

(BT.com) — Artificial intelligence can be trained to spot structural changes in the brain linked to Alzheimer’s disease nearly 10 years before doctors can diagnose it through symptoms, researchers claim.

According to New Scientist, a team at the University of Bari in Italy has developed a machine learning algorithm that is able to spot alterations in how different regions of the brain are connected – alterations that could be early signs of the disease.

Their algorithm was trained using MRI scans from 67 patients, 38 of which were from people affected by the disease and 29 from healthy patients. The scans came from the Alzheimer’s Disease Neuroimaging Initiative database at the University of Southern California in Los Angeles.

The AI was trained to correctly spot the difference between diseased and healthy brains, before being tested on its accuracy abilities on a second set of 148 scans – 52 of which were healthy, 48 had Alzheimer’s and the other 48 had a mild cognitive impairment that was known to develop into Alzheimer’s within 10 years. (…)

read full story

share/partager