Summary: Researchers are developing a machine learning model aimed at early detection of Alzheimer’s dementia. This model, which can be accessed via smartphones, can distinguish between Alzheimer’s patients and healthy individuals with 70-75% accuracy.
By focusing on speech patterns rather than content, the tool can offer invaluable early indicators, potentially initiating earlier treatment and slowing disease progression.
While not a substitute for healthcare professionals, it can enhance telehealth services and help overcome geographic or linguistic barriers.
Key Facts:
- A machine learning model can distinguish Alzheimer’s patients from healthy individuals with an accuracy of 70-75%.
- The tool examines acoustic and linguistic features of speech rather than specific words for identifying pain.
- The application of this model could be a simple, accessible screening tool on smartphones, providing early indicators of Alzheimer’s.
Source: University of Alberta
Researchers are working to make earlier diagnosis of Alzheimer’s dementia possible using a machine learning (ML) model that could one day be turned into a simple screening tool that anyone with a smartphone can use.
The model was able to distinguish Alzheimer’s patients from healthy controls with 70 to 75 percent accuracy, a promising figure for the more than 747,000 Canadians with Alzheimer’s or another form of dementia.
Alzheimer’s dementia can be difficult to detect in the early stages, as symptoms often begin relatively mild and can be confused with memory-related issues, typical of advanced age. But as the researchers note, the earlier potential issues are detected, the earlier patients can start taking action.
“Back then, you needed lab work, and medical imaging, to see changes in the brain; it takes time, it’s expensive, and nobody can test it in advance,” said Eleni Stroulia, a professor in the Department of Computing Science who was involved in the creation of the model.
“If you can use mobile phones to get an early indicator, that informs the patient’s relationship with their physician. It’s possible to start treatment earlier, and we can even start with simple interventions at home, as well on mobile devices, to slow down progress.”
A screening tool will not replace healthcare professionals. However, in addition to helping with earlier detection, it will create a convenient way to identify potential concerns via telehealth for patients who may face geographic or linguistic barriers to accessing services. in their place, explained Zehra Shah, a master’s student in the Department of Computing. Science and first author of the paper.
“We can think about testing patients with this kind of technology that is completely based on speech alone,” Shah said.
While the research team has previously looked at the language used by Alzheimer’s dementia patients, for this project they examined language-agnostic acoustic and linguistic speech features rather than specific words.
“Original work involves listening to what people say, understanding what they say, the meaning. That’s an easier computational problem to solve,” Stroulia said. “Now we say, listen to the voice. There are some properties in the way people speak that transcend language.”
“It’s more powerful than the version of the problem we were solving before,” Stroulia added.
The researchers started with speech characteristics that doctors noted were common in patients with Alzheimer’s dementia. These patients speak more slowly, with more pauses or interruptions in their speech.
They usually use shorter words, and their speech is often less intelligible. Researchers have found ways to translate these characteristics into speech features that the model can screen for.
Although the researchers focused on English and Greek speakers, “this technology has the potential to be used in many different languages,” Shah said.
And even though the model itself is complex, the end user experience for a tool that integrates it couldn’t be simpler.
“A person talks to the tool, it analyzes and makes a prediction: either yes, the person has Alzheimer’s, or no they don’t,” said Russ Greiner, a contributor to the paper and professor in the Department of Computing Science. . That information can be taken to a health care professional to determine the best course of action for the person.
Both Greiner and Stroulia lead the computational psychiatry research group at the U of A, whose members have developed similar AI models and tools to detect psychiatric disorders such as PTSD, schizophrenia, depression and bipolar disorder .
“Anything we can do to strengthen clinical processes, inform treatments and manage diseases earlier with lower costs is great,” Stroulia said.
About this machine learning and Alzheimer’s disease research news
Author: Adrianna MacPherson
Source: University of Alberta
Contact: Adrianna MacPherson – University of Alberta
Image: Image credited to Neuroscience News
Original Research: The findings will be presented at the ICASSP 2023—2023 IEEE International Conference on Acoustics, Speech and Signal Processing
Post a Comment