Using speech to diagnose Alzheimer’s

Diagnosis and dectect of Alzheimer’s disease has long been problematic. Now, a new technology may use an individual's speech patterns to detect and monitor cognitive disorders, including Alzheimer’s.

Using patient's descriptions of pictures, the program analyzes more than 400 different variables including pitch, tone, rhythm, rate of speech, pauses and choice of words. Diagnostic results can accurately identify Alzheimer’s, Parkinson’s and aphasia at an accuracy rate of at least 85 percent, according to Winterlight Labs, who produced the program.

"Speech is a rich source of information on people's cognitive health," Liam Kaufman, CEO and co-founder of Winterlight, told a panel of expert judges at the AGE-WELL Pitch Competition on July 23 in Toronto. "Because of word-finding difficulties, people with Alzheimer's disease will tend to pause more between words and the complexity of their vocabulary is reduced, so they will use a word such as 'car' instead of 'SUV' or 'sedan."

Further testing is set to begin soon in five senior care organizations, with a total of 100,000 seniors.

"The incidence of Alzheimer's disease and other dementias is growing worldwide, and new technologies like this novel speech-assessment tool present a real opportunity to help people with dementia and those who care for them," said Alex Mihailidis, PhD, AGE-WELL scientifice director.