AI Tool Predicts Alzheimer's Through Speech Analysis
Researchers from Boston University developed an AI model capable of predicting Alzheimer's onset by analyzing speech. Training on audio recordings of patients with mild cognitive impairment, it achieved 78.5 percent accuracy. The study highlights the importance of early detection and the plan to make the model available via an app for remote areas.
Researchers from Boston University have created an AI-based model capable of predicting the onset of Alzheimer's disease by analyzing an individual's speech.
Training on audio recordings of 166 patients aged 63-97 with mild cognitive impairment, the model achieved a 78.5 per cent accuracy rate in determining whether patients would remain stable or progress to dementia within six years.
This study, published in the journal Alzheimer's and Dementia, demonstrates the model's ability to analyze interview content instead of speech features like enunciation.
The researchers stress the importance of early detection and plan to make the model accessible via an app to help patients in remote areas.