How researchers use language to identify dementia


According to the World Health Organization, over 10 million people worldwide are diagnosed with dementia each year. As Ivanhoe reports, new research using a simple recording of your voice and a special computer algorithm could help early detection of dementia.

Neurological tests to determine a person’s cognitive abilities can take a long time because doctors have to transcribe, review, and analyze every response in minute detail.

But now researchers at Boston University have developed a new tool that could automate the process. The machine-learning computer model can detect cognitive impairment from audio recordings of neuropsychological tests without you even having to see a doctor.

“Why have dementia when we can reduce the things that we know can be changed and are strongly associated with dementia risk?” says Dr. James E Galvin of the University of Miami Miller School of Medicine.

By using automated online voice recognition tools like “Hey, Google!” and a machine learning technique called “natural language processing” that helps computers understand your recorded text, allowing the model to access the likelihood and severity of a person’s cognitive impairment.

Faster and earlier detection of Alzheimer’s could spur larger clinical trials that focus on people in the early stages of the disease and potentially enable clinical interventions that slow cognitive decline.

“The idea is that instead of waiting for a disease to appear, we try to prevent it first,” Galvin said.

Not only was the model able to accurately discriminate between healthy people and people with dementia, but it also recognized differences between people with mild cognitive impairment and dementia. As it turned out, the quality of the recordings and the way people spoke were less important than the content of what they actually said.

The research team trained their model using audio recordings from more than a thousand neuropsychological interviews and has yet to validate their results with other data sources. However, the results suggest that their tool could assist clinicians in diagnosing cognitive impairment using audio recordings, including those from virtual or telemedicine visits.

Copyright 2022 by Ivanhoe Newswire – All rights reserved.


Comments are closed.