No in-person appointment is needed.

Researchers at Boston University have developed a new machine-learning based tool that detects Alzheimer’s Disease from voice recordings of neuropsychological exams. This could help automate the time-consuming and cumbersome process of a manual evaluation of the person’s responses, as well as make it possible for the diagnosis to be made online because an in-person appointment is not required. (Eurekalert)

Alzheimer’s: Earlier screenings of a larger population

The tool could help diagnose the advent of Alzheimer’s Disease and cognitive decline much earlier and across a larger population. Ultimately, it could improve the chances of the development of clinical cures that could slow down neurological decline in people.

“This approach brings us one step closer to early intervention,” says Ioannis Paschalidis, a coauthor on the paper and a BU College of Engineering Distinguished Professor of Engineering. “It can form the basis of an online tool that could reach everyone and could increase the number of people who get screened early.”

How it works

The neuropsychological recordings of over 1,000 individuals were used to train a natural language processing (NLP) AI model together with automated online speech recognition tools. Detection was further enhanced by incorporating demographic data and actual diagnoses from neuropsychologists.

Paschalidis says the final model was not only able to accurately distinguish between healthy individuals and those with dementia, but also detect differences between those with mild cognitive impairment and dementia.

“Our models can help clinicians assess patients in terms of their chances of cognitive decline,” says Paschalidis, “and then best tailor resources to them by doing further testing on those that have a higher likelihood of dementia.”

Related Story: AI May Provide An Objective Second Opinion On Parkinson’s