New mobile app can detect Alzheimer’s disease with speech

Credit: Unsplash+

Alzheimer’s Disease: The Silent Epidemic

Alzheimer’s disease (AD) is a type of dementia that slowly and steadily impairs memory and thinking skills. It’s a common condition that affects millions of people worldwide.

One of the best ways to manage AD is to detect it early.

This allows for timely interventions that can delay the progression of the disease, especially during the mild cognitive impairment (MCI) stage, which is often a precursor to AD.

However, early detection of AD and MCI has always been a challenge. To address this, scientists are now turning to technology to develop screening tools that are easy to use and accessible in everyday life.

The Power of Speech in Detecting Alzheimer’s

One promising avenue for early detection lies in our speech. Language impairments often show up early in AD, and these changes can be used to detect the disease.

But there’s a snag: automatic speech recognition technology, which converts voice to text, doesn’t work as well with elderly voices as it does with younger ones.

This poses a challenge in developing an automatic screening tool.

New Mobile App to Detect Alzheimer’s

To overcome this challenge, a team of researchers from the University of Tsukuba in Japan developed a prototype mobile application.

This app can be used by individuals themselves and is designed to assist in the early detection of AD and MCI.

In the study, the researchers collected and analyzed speech data from 114 participants.

The participants included individuals with AD, those with MCI, and those with normal cognitive function.

They were asked to complete five cognitive tasks, such as describing a picture or performing a verbal fluency task.

A Breakthrough in Early Detection

The results were promising. The study showed that language impairments, especially those related to semantics (like informativeness and vocabulary richness), could be reliably identified even with poor speech recognition accuracy.

But the researchers didn’t stop there. They used machine learning models to analyze not just the linguistic features, but also the acoustic and prosodic features (like rhythm, stress, and intonation) of the participants’ voices.

The result? The models could reliably detect MCI and AD with an accuracy of 88% and 91%, respectively.

These findings, published in the journal Computer Speech & Language, represent a significant step forward.

They show that it’s possible to create a self-administered, automatic screening tool for AD and MCI that can reliably pick up on language impairments, even in less-than-ideal conditions.

The Future of Alzheimer’s Disease Detection

This pioneering study paves the way for more accessible and user-friendly screening tools for AD. It’s the first of its kind to demonstrate the potential of a mobile application in detecting AD and MCI.

By making screening tools more accessible, we can increase the early detection of AD, giving individuals the best chance of delaying disease progression.

If you care about brain health, please read studies about vitamin D deficiency linked to Alzheimer’s and vascular dementia, and higher magnesium intake could help benefit brain health.

For more information about brain health, please see recent studies about antioxidants that could help reduce dementia risk, and coconut oil could help improve cognitive function in Alzheimer’s.

The study was published in Computer Speech & Language.

Copyright © 2023 Knowridge Science Report. All rights reserved.