U.K. Researchers Develop CognoSpeak to Diagnose Dementia

Researchers at the University of Sheffield in England have developed an artificial intelligence-backed speech tool that could help doctors detect the early signs of dementia and Alzheimer's more quickly and efficiently.

Called CognoSpeak, the system uses a virtual agent to engage patients in conversation. It asks memory-probing questions like those used in outpatient consultations and conducts cognitive tests, such as picture descriptions and verbal fluency tests. The tool then uses artificial intelligence and speech technology to analyze language and speech patterns for signs of dementia, Alzheimer's disease, and other cognitive disorders.

CognoSpeak can be accessed through a web browser.

Early trials have shown the technology is as accurate at predicting Alzheimer's as current pen-and-paper tests, with accuracy rates of 90 percent.

The system is being developed by Dr. Dan Blackburn and Professor Heidi Christensen from the University of Sheffield's Departments of Neuroscience and Computer Science, working with Therapy Box, a speech and language technology company, and the U.K. National Institute for Health and Care Research. It is still in the research phase, with clinical trials due to start soon.

"The way a person speaks can tell us a great deal about their cognitive health and emotional well-being and give us a very early indication of any signs of cognitive decline that may not otherwise have been detected," Christensen said in a statement. "The system we've developed here at Sheffield uses speech technology to automatically extract these signs, and the automation means we can provide a consistent, accurate, and fast assessment for everyone."