A new smartphone application may help people who are having a stroke or their family and caregivers recognize common stroke symptoms in real time, prompting them to quickly call healthcare providers.
Called FAST.AI, the app might be as accurate at diagnosing stroke as a neurologist, which may minimize the long-term effects of a stroke and improve chances for a full recovery, preliminary research suggests.
FAST.AI is a fully automated smartphone application for the detection of severe stroke using machine learning algorithms to recognize facial asymmetry (drooping of the muscles in the face), arm weakness, and speech changes — all common stroke symptoms.
The smartphone application uses a facial video of the patient to examine 68 facial landmark points; sensors that measure arm movement and orientation; and voice recordings to detect speech changes. Information from each test was sent to a database server for analysis.
“Early results confirm the app reliably identified acute stroke symptoms as accurately as a neurologist, and they will help to improve the app’s accuracy in detecting signs and symptoms of stroke,” said study author Radoslav I. Raychev, a clinical professor of neurology and a vascular neurologist at the University of California at Los Angeles.
Researchers validated FAST.AI’s performance by testing nearly 270 patients with a diagnosis of acute stroke within 72 hours of hospital admission at four major metropolitan stroke centers from July 2021 to July 2022.
Neurologists who examined the patients tested the app and then compared the FAST.AI results with their clinical impressions.
The analysis found that the smartphone app accurately detected stroke-associated facial asymmetry in nearly 100 percent of patients.
The app accurately detected arm weakness in more than two-thirds of the cases.
While the slurred speech module remains to be fully validated and tested, preliminary analyses confirmed that it may be able to reliably detect slurred speech, according to the researchers.
A limitation of the study is that neurologists (not the individuals, family members, or caregivers) conducted the screenings and taught patients how to use the application.
The findings of the study are set to be presented at the American Stroke Association International Stroke Conference 2023 in Dallas, the US, from February 8-10.
