Can Computers Diagnose Alzheimer's Disease and Dementia? - Neuroscience News

Summary: New machine learning algorithms are able to accurately detect cognitive impairment by analyzing voice recordings.

Source: Boston University

It takes a lot of time—and money—to diagnose Alzheimer’s disease. After running a lengthy face-to-face neuropsychological exam, the doctor must copy, review, and analyze each response in detail.

But researchers at Boston University have developed a new tool that could automate the process and eventually allow it to move online. Their machine learning-powered computational model can detect cognitive impairment from audio recordings of neuropsychological tests—no in-person appointment required.

Their findings were published in Alzheimer’s & Dementia: Journal of the Alzheimer’s Association.

“This approach brings us one step closer to early intervention,” said Ioannis Paschalidis, co-author of the paper and BU College of Engineering Distinguished Professor of Engineering.

He said faster early detection of Alzheimer’s could prompt larger clinical trials that focus on individuals in the early stages of the disease and potentially enable clinical interventions that slow cognitive decline: “This could form the basis of an online tool that can reach everyone and could increase the number of people in the world.” which was checked earlier.”

The research team trained their model using audio recordings of neuropsychological interviews from more than 1,000 individuals in the Framingham Heart Study, a long-standing BU-led project that looks at cardiovascular disease and other physiological conditions.

Using automated online voice recognition tools—think, “Hey, Google!”—and a machine learning technique called natural language processing that helps computers understand text, they asked their program to transcribe interviews, then encode them into numbers.

The latter model was trained to assess the likelihood and severity of individual cognitive impairment using demographic data, text coding, and real diagnoses from neurologists and neurologists.

Paschalidis said the model was not only able to accurately distinguish between healthy individuals and those with dementia, but also detected differences between those with mild cognitive impairment and dementia. And, it turns out, the quality of the recordings and the way people speak—whether their words are misspelled or constantly stuttering—is less important than the content of what they say.

“We were surprised that speech flow or other audio features were not so important; You can automatically copy interviews fairly well, and rely on text analysis via AI to assess cognitive impairment,” said Paschalidis, who is also the new director of the Rafik B. Hariri Institute for Computing and BU Computational Science & Engineering.

While the team still needs to validate their results against other data sources, the findings suggest their tool can support clinicians in diagnosing cognitive impairment using audio recordings, including those from virtual or telehealth appointments.

Screening before Symptom Onset

The model also provides insight into which parts of the neuropsychological examination may be more important than others in determining whether a person has cognitive impairment. The researchers’ model divides the exam transcript into sections based on the clinical trials conducted.

Paschalidis said the model was not only able to accurately distinguish between healthy individuals and those with dementia, but also detected differences between those with mild cognitive impairment and dementia. Image is in public domain

They found, for example, that the Boston Naming Test—in which doctors ask individuals to label pictures using a single word—is most informative for an accurate diagnosis of dementia.

“This might allow clinicians to allocate resources in a way that allows them to do more screening, even before the onset of symptoms,” Paschalidis said.

Early diagnosis of dementia is not only important for patients and their caregivers to be able to develop effective treatment and support plans, but it is also important for researchers working on therapies to slow and prevent the progression of Alzheimer’s disease.

“Our model can help clinicians assess patients in terms of their likelihood of cognitive decline,” Paschalidis said, “and then tailor the best resources for them by conducting further testing in those with a higher likelihood of dementia.”

See also

Want to Join the Research Effort?

The research team is looking for volunteers to take online surveys and submit anonymous cognitive tests—the results will be used to provide personalized cognitive assessments and will also help the team refine their AI model.

About this AI and Alzheimer’s disease research news

Author: Molly Gluck
Source: Boston University
Contact: Molly Gluck – Boston University
Picture: Image is in public domain

Original Research: Closed access.
“Automatic detection of mild cognitive impairment and dementia from voice recordings: A natural language processing approach” by Ioannis Paschalidis et al. Alzheimer’s & Dementia

---

Abstract

Automatic detection of mild cognitive impairment and dementia from voice recordings: A natural language processing approach

introduction

Automated computational assessment of neuropsychological tests will enable broad and cost-effective dementia screening.

Method

A newly developed and validated natural language processing approach to identify different stages of dementia based on the automated transcription of digital voice recordings from neuropsychological tests of subjects performed by the Framingham Heart Study (n = 1084). Sentences transcribed from the tests were coded into quantitative data and several models were trained and tested using these data and the demographic characteristics of the participants.

Results

The average area under the curve (AUC) in the withheld test data reached 92.6%, 88.0%, and 74.4%, respectively, to distinguish Normal Cognition from Dementia, Normal or Mild Cognitive Impairment (MCI) from Dementia, and Normal from MCI.

Discussion

The proposed approach offers fully automated identification of MCI and dementia based on recorded neuropsychological tests, providing the opportunity to develop a remote screening tool that can be easily adapted to any language.

#Computers #Diagnose #Alzheimers #Disease #Dementia #Neuroscience #News