Sign In

Communications of the ACM

ACM TechNews

Scientists Discover New Computerized Linguistic Approach to Detect Alzheimer's Disease

View as: Print Mobile App Share:
Diagram of the brain of a person with Alzheimer's Disease.

Researchers have discovered how to diagnose Alzheimer's disease with more than 82% accuracy by evaluating the interplay between four linguistic factors and developing automated technology to detect these impairments.

Credit: Wikipedia

University Health Network researchers have discovered how to diagnose Alzheimer's disease with more than 82% accuracy by evaluating the relationship between four linguistic factors: semantic impairment, acoustic impairment, syntactic impairment, and information impairment.

"This study characterizes the diversity of language impairments experienced by people with Alzheimer's disease, and our automated detection algorithm takes this into account," says University of Toronto professor Frank Rudzicz.

The analysis achieved such high levels of accuracy with a large number of measurements that are precisely and automatically detected from speech using new software. The researchers say the technology is useful because it is repeatable, which means it is not susceptible to the sort of perceptual differences or biases that can occur between humans.

The researchers examined speech samples from a database of patients diagnosed with possible or probable Alzheimer's disease and additional samples from 97 control subjects. "These methods offer a way to assess speech quantitatively and objectively, so we can use them to test interventions such as novel drugs and brain stimulation," says Rotman Research Institute researcher Jed Meltzer.

The researchers soon will begin testing the automated screening technology with current patients and control subjects to validate the approach.

From University Health Network
View Full Article


Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account