Researchers at Boston University (BU) have developed an AI model that can predict – with a high degree of accuracy – whether someone with mild cognitive impairment will develop Alzheimer’s-associated dementia within the next six years. This breakthrough could lead to earlier treatment interventions.
Current methods for assessing whether someone has Alzheimer’s disease involve a wide range of tests, including one-on-one interviews, brain imaging, and blood and cerebrospinal fluid tests. These cost valuable time, as, if caught early enough, new treatments can slow the disease’s progression.
Using neuropsychological data gathered from BU’s Framingham Heart Study, the team designed an AI computer program that analyzes a patient’s speech. The program used a combination of speech recognition tools and machine learning to train a model to spot connections between speech, demographics, diagnosis, and disease progression in audio recordings. The test subjects included 166 interviews with people between ages 63 and 97 who were diagnosed with mild cognitive impairment in their initial interviews. Of these 166, 76 remained stable for the next six years and 90 had cognitive function that progressively declined. They found that their model can predict, with an accuracy rate of 78.5%, whether someone with mild cognitive impairment is likely to remain stable over the next six years, or experience the dementia associated with Alzheimer’s disease.
In future, the team has plans to use data from more natural, everyday conversations, not just from formal interviews. They also hope to develop a smartphone app that could aid in diagnosing dementia.
“We hope, as everyone does, that there will be more and more Alzheimer’s treatments made available,” says Ioannis (Yannis) Paschalidis, a BU College of Engineering Distinguished Professor of Engineering. “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.”