NEED TO KNOW
A tool accessible via smart home devices can help diagnose people with Parkinson’s disease.
The AI-powered tool was developed as part of a study by scientists at University of Rochester.
The tool prompts users to perform neurological tests in their own homes that involve speech, facial expression and finger movements
A tool accessible via smart home devices can help diagnose people with Parkinson’s disease.
The AI-powered tool, called PARK, was developed as part of a study by scientists at University of Rochester.
According to the website, the tool prompts users to perform a variety of web-based neurological tests in their own homes that involve speech, facial expression and finger movements.
The tasks are then analyzed to detect whether the user shows signs of Parkinson’s disease. After the results are given, the tool provides personalized resources for treatment or care.
getty
Stock image of an elderly person being comforted
Newsweek reports that the test asks users to recite two short sentences that use every letter of the alphabet at least once. Then, in mere seconds, the AI can analyze the recordings to look for patterns linked to the disease.
The toll has an 86% accuracy rate, per Newsweek.
PARK can be accessed by any major web browser, but the researchers also note that it can be a useful tool for smart home devices, such as Amazon Alexa or Google Assistant.
Never miss a story — sign up for PEOPLE’s free daily newsletter to stay up-to-date on the best of what PEOPLE has to offer, from celebrity news to compelling human-interest stories.
“While we haven’t established partnerships with these companies yet, our model is very lightweight and well-suited for such integration,” computer scientist Tariq Adnan told Newsweek.
“With appropriate privacy safeguards and user consent, it could operate passively or on-demand through such widely used home devices,” he added. “Once integrated, [in theory] a user could say something like ‘screen me for Parkinson’s symptoms,’ and the system would prompt a short sentence to be read aloud.”
The tool was trained with data from over 1,300 participants in home care settings, clinical settings and at the InMotion Parkinson’s disease care center in Ohio, according to Newsweek. Possible indicators for the disease include uttering sounds, pausing, breathing and adding “features of unintelligibility,” according to computer science graduate student Abdelrahman Abdelkader.
The researchers note that access to neurological care can be a barrier for people to receive clinical diagnoses, and believe the tool can be used to encourage people to seek medical evaluation if they suspect they have the disease.
Getty Stock Images
University of Rochester
“We envision a gentle, user-centered experience. The tool would never deliver a diagnosis, rather would only flag whether a follow-up with a clinician might be worthwhile,” Adnan said.
Parkinson’s disease is characterized by the loss of nerve cells in the brain, per Mayo Clinic. It is unknown what causes the disease, although genes and environmental factors may play a risk.
The average onset of Parkinson’s disease is around 70 years old.
Symptoms of the disease include memory loss, trouble with language, feeling irritable, having trouble chewing and swallowing, and difficulty sleeping.
Parkinson’s Foundation states that about 1.1 million people in the United States have the disease.
Read the original article on People
