Changes in speech patterns may indicate that mild cognitive impairment is worsening to Alzheimer's disease, according to a new study.
Artificial intelligence was able to detect subtle changes in speech that the human ear (and mind) may not necessarily pick up -- and those changes correlated to worsening cognitive health, the Boston University study indicated. Their AI program was able to detect a likelihood of declining brain health over the course of six years with a 78.5% accuracy rate.
Related: The One New Year's Resolution Longevity Experts Are Begging People Over 50 to Stop Making
A team of neurobiologists, engineers, computer scientists and data scientists trained an algorithm to examine audio recordings of 166 participants with mild cognitive impairment ranging from ages 66 to 97. The participants themselves were studied over the course of six years, and the scientists in the study already knew which participants developed Alzheimer's over the course of that time.
"We combine the information we extract from the audio recordings with some very basic demographics -- age, gender, and so on -- and we get the final score," Dr. Ioannis Paschalidis, Ph.D., director of the Boston University Rafik B. Hariri Institute for Computing and Computational Science & Engineering, told Boston University's The Brink. "You can think of the score as the likelihood, the probability, that someone will remain stable or transition to dementia. It had significant predictive ability."
The algorithm specifically examined not how participants spoke in terms of their voices, accents or inflections, but the words that participants used in their recordings, as well as the overall content in their speech and how that content was structured. After analyzing that data, AI had a 78.5% accuracy rate in predicting which participants eventually were diagnosed with Alzheimer's disease.
Related: The Surprising Sign of Dementia You Might Miss, According to Neurologists
The use of AI in diagnostics is obviously controversial and still being studied, but when you consider that many Alzheimer's patients are never even formally diagnosed or treated, it may open your mind a bit to the idea of the practice, Dr. Rhoda Au, Ph.D., professor of anatomy and neurology at Boston University noted.
🩺 SIGN UP for tips to stay healthy & fit with the top moves, clean eats, health trends & more delivered right to your inbox twice a week 💊
"Technology can overcome the bias of work that can only be done by those with resources, or care that has relied on specialized expertise that is not available to everyone," Dr. Au said, adding, "A method for cognitive assessment that has the potential to be maximally inclusive -- possibly independent of age, sex/gender, education, language, culture, income, geography -- could serve as a potential screening tool for detecting and monitoring symptoms related to Alzheimer's disease."
"We hope, as everyone does, that there will be more and more Alzheimer's treatments made available," says Dr. Paschalidis concurred. "If you can predict what will happen, you have more of an opportunity and time window to intervene with drugs, and at least try to maintain the stability of the condition and prevent the transition to more severe forms of dementia."
Up Next: