fbpx
Connect with us
  • Elysium

Dementia news

How speech analysis via AI could detect dementia

Published

on

AI could be used to predict whether a person will develop Alzheimer’s-associated dementia by simply analysing their speech, scientists believe.

Researchers at Boston University are exploring how analysis of speech patterns via a machine learning model could detect with a high degree of accuracy whether someone with mild cognitive impairment will develop Alzheimer’s-associated dementia within six years

They say their model can predict, with an accuracy rate of 78.5 percent, whether someone with mild cognitive impairment is likely to remain stable over the next six years—or fall into the dementia associated with Alzheimer’s disease.

While allowing clinicians to make earlier diagnoses, the researchers say their work could also help make cognitive impairment screening more accessible by automating parts of the process;  with no expensive lab tests, imaging exams, or office visits required.

Ioannis (Yannis) Paschalidis, director of the Boston University Rafik B. Hariri Institute for Computing and Computational Science & Engineering, says: “We wanted to predict what would happen in the next six years—and we found we can reasonably make that prediction with relatively good confidence and accuracy.

“We hope, as everyone does, that there will be more and more Alzheimer’s treatments made available.

“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.”

The project involves a multidisciplinary team of engineers, neurobiologists, and computer and data scientists.

“We hope, as everyone does, that there will be more and more Alzheimer’s treatments made available,” says Paschalidis.

“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.”

To train and build their new model, the researchers turned to data from one of the oldest and longest-running studies in the US —the BU-led Framingham Heart Study.

Although the Framingham study is focused on cardiovascular health, participants showing signs of cognitive decline undergo regular neuropsychological tests and interviews, producing a wealth of longitudinal information on their cognitive well-being.

Paschalidis and his colleagues were given audio recordings of 166 initial interviews with people, between ages 63 and 97, diagnosed with mild cognitive impairment—76 who would remain stable for the next six years and 90 whose cognitive function would progressively decline.

They then used a combination of speech recognition tools—similar to the programs powering your smart speaker—and machine learning to train a model to spot connections between speech, demographics, diagnosis, and disease progression.

After training it on a subset of the study population, they tested its predictive prowess on the rest of the participants.

“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,” says Paschalidis. “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.”

Rather than using acoustic features of speech, like enunciation or speed, the model is just pulling from the content of the interview—the words spoken, how they’re structured.

And Paschalidis says the information they put into the machine learning program is rough around the edges: the recordings, for example, are messy—low-quality and filled with background noise.

“It’s a very casual recording,” he says. “And still, with this dirty data, the model is able to make something out of it.”

That’s important, because the project was partly about testing AI’s ability to make the process of dementia diagnosis more efficient and automated, with little human involvement.

In the future, the researchers say, models like theirs could be used to bring care to patients who aren’t near medical centers or to provide routine monitoring through interaction with an at-home app, drastically increasing the number of people who get screened.

According to Alzheimer’s Disease International, the majority of people with dementia worldwide never receive a formal diagnosis, leaving them shut off from treatment and care.

Rhoda Au, a coauthor on the paper, says AI has the power to create “equal opportunity science and healthcare.”

The study builds on the same team’s previous work, where they found AI could accurately detect cognitive impairment using voice recordings.

In future research, Paschalidis would like to explore using data not just from formal clinician-patient interviews—with their scripted questions and predictable back-and-forth—but also from more natural, everyday conversations.

He’s already looking ahead to a project on if AI can help diagnose dementia via a smartphone app, as well as expanding the current study beyond speech analysis—the Framingham tests also include patient drawings and data on daily life patterns—to boost the model’s predictive accuracy.

“Digital is the new blood,” says Au. “You can collect it, analyse it for what is known today, store it, and reanalyse it for whatever new emerges tomorrow.”

HIWIN

Trending