Scientists develop speech recognition tool to predict the onset of Alzheimer’s

New Delhi:

A new AI-based model could predict the onset of Alzheimer’s disease by analyzing an individual’s speech, developers said.

Trained on audio recordings of patients with mild cognitive impairment – ​​early stages of memory loss, the model achieved 78.5% accuracy in predicting whether patients would remain stable or progress to dementia within six years, according to the researchers.

Alzheimer’s disease is the most common form of dementia and affects daily activities, impairing memory and thinking.

Researchers at Boston University in the US used recordings of initial interviews from 166 patients aged between 63 and 97 and trained the model using machine learning to discern patterns between speech, demographics, diagnosis and how their condition was worsening.

The model analyzes interview content, such as spoken words and sentence structure, rather than speech characteristics such as enunciation or speed, the study published in the journal Alzheimer’s and Dementia showed.

“We combine the information we extract from the audio recordings with some basic demographic data – age, gender and so on – and we get the final score,” said Ioannis C. Paschalidis, professor of engineering and corresponding author of the study.

“You can think of the score as how likely someone is to remain stable or transition to dementia. It had significant predictive ability,” Paschalidis said.

The researchers said the model performed well despite challenges such as low-quality recordings and background noise.

The researchers emphasized that early prediction is crucial, since current diagnostic tests often identify Alzheimer’s disease only after significant cognitive decline has occurred, such as memories that begin to fade and personality traits that begin to fade. to change.

The team aims to make their model accessible via an app to make it accessible to patients in remote areas, potentially increasing the number of people being screened.

(Except the headline, this story has not been edited by NDTV staff and is published from a syndicated feed.)