Scientists develop smartphone app that detects stroke symptoms as they happen – looking at droopy faces and slurred speech
In the US, one person has a stroke every 40 seconds, and in the UK every five minutes, and acting quickly is key to avoiding permanent brain damage.
However, the symptoms, including a drooping face on one side, slurred speech or inability to lift an arm, are not so easy to spot in an emergency situation.
Now scientists have come up with an app that can help family and friends recognize a stroke when it’s happening, allowing them to call an ambulance.
University of California scientists have developed an app that uses facial recognition and speech patterns to detect if a person is having a stroke with near 100 percent accuracy (file photo)
The app, called FAST.AI, uses a patient’s facial video to examine 69 points of view, measure arm movements and detect speech changes.
A team from the University of California tested it on nearly 270 patients diagnosed with an acute stroke within 72 hours of hospitalization.
Neurologists who examined the patients tested the app and then compared the results with their own clinical diagnosis.
Analysis found that the app accurately detected stroke-associated facial droop in nearly 100 percent of patients.
The app also accurately detected arm weakness in more than two-thirds of cases, and preliminary analysis suggests it may also be able to reliably detect slurred speech.
It is important to recognize the signs of a stroke right away, as clotting medication must be administered within three hours of the onset of symptoms.
The sooner treatment is administered, the greater the chance of a better recovery.
Researchers said their study is ongoing and the app is still in development and not available to the public.
Author Radoslav Raychev said: ‘Many stroke patients do not reach the hospital in time for treatment, which is one of the reasons why it is vital to recognize and call for stroke symptoms. [for help] right away.
“These early results confirm that the app identifies acute stroke symptoms as accurately as a neurologist, and they will help improve the app’s accuracy in detecting signs and symptoms of stroke.”
The findings were presented at the American Stroke Association’s International Stroke Conference in Dallas, Texas.