AI automates diagnosis of Alzheimer’s disease

The team’s machine learning–powered computational model is claimed to detect cognitive impairment from audio recordings of neuropsychological tests. Their findings have been published in Alzheimer’s & Dementia: The Journal of the Alzheimer’s Association.

“This approach brings us one step closer to early intervention,” said Ioannis Paschalidis, a co-author on the paper and a BU College of Engineering Distinguished Professor of Engineering. He said faster and earlier detection of Alzheimer’s could drive larger clinical trials that focus on individuals in early stages of the disease and potentially enable clinical interventions that slow cognitive decline.

 “It can form the basis of an online tool that could reach everyone and could increase the number of people who get screened early,” Paschalidis said in a statement.

The research team trained their model using audio recordings of neuropsychological interviews from over 1,000 individuals. Using automated online speech recognition tools and a machine learning technique called natural language processing, they had their program transcribe the interviews, then encode them into numbers. A final model was trained to assess the likelihood and severity of an individual’s cognitive impairment using demographic data, the text encodings, and real diagnoses from neurologists and neuropsychologists.