Computerized approach detects Alzheimer's with 82% accuracy
Frank Rudzicz, Ph.D.
Researchers have discovered how speech impairments can be used to diagnose Alzheimer's disease with more than 82% accuracy and have developed automated technology to detect the impairments.
The work, led by Frank Rudzicz, Ph.D., a scientist at the Toronto Rehabilitation Institute of the University Health Network, was published in the December issue of the Journal of Alzheimer's Disease.
The analysis found that four collective dimensions of speech indicate dementia:
- semantic impairment, such as using overly simple words;
- acoustic impairment, such as speaking more slowly;
- syntactic impairment, such as using less complex grammar; and
- information impairment, such as not clearly identifying the main aspects of a picture.
The researchers reached their conclusions after examining speech samples, including audio files, from a database of people who had received a diagnosis of possible or probable Alzheimer's disease and additional samples from 97 control subjects.
“An advantage of this technology is that it is repeatable,” Rudzicz said. “It's not susceptible to the sort of perceptual differences or biases that can occur between humans.” An automated approach also would make screening easier and more accurate and cost-effective, he added.
The researchers will test the technology to validate their approach. Rudzicz also is partnering with the University of Toronto and industry to commercialize the technology through a start-up company called WinterLight Labs.