Nicola Amoroso and Marianna La Rocca and their colleagues at the University of Bari in Italy have unveiled a machine-learning algorithm, which is able to realise the structural changes in the brain that are caused by Alzheimer's disease.
La Rocca told the New Scientist: "Nowadays, cerebrospinal fluid analyses and brain imaging using radioactive tracers can tell us to what extent the brain is covered with plaques and tangles, and are able to predict relatively accurately who is at high risk of developing Alzheimer's 10 years later. However, these methods are very invasive, expensive and only available at highly specialised centres."
The algorithm was taught to identify between brains of those who are healthy and those who have Alzheimer's. From there, they then tested the algorithm on another set of scans from 148 subjects, of which, 52 were healthy, 48 had Alzheimer's disease and 48 had mild cognitive impairment but were known to have developed Alzheimer's disease years later.
The algorithm was able to detect between a healthy brain and one with Alzheimer's with an 86 per cent accuracy but it could also tell the difference between those with healthy brains and those with MCI at 84 per cent accuracy.