Scientists are developing a smartphone app that detects stroke symptoms as they occur – looking at facial drooping and slurred speech
In the US, a person suffers a stroke every 40 seconds, and in the UK it’s every five minutes, and acting quickly is key to preventing lasting brain damage.
However, the symptoms, which include a face drooping to one side, slurred speech, or the inability to lift an arm, are not so easily recognizable in an emergency.
Now scientists have developed an app that could help family and friends recognize a stroke when it happens, prompting them to call an ambulance.
The University of California scientists have developed an app that uses facial recognition and speech patterns to detect if someone is having a stroke with nearly 100% accuracy (file photo)
The app, called FAST.AI, uses facial video of the patient to examine 69 facial points, measure arm movements and detect language changes.
A University of California team tested it on nearly 270 patients diagnosed with acute stroke within 72 hours of admission to the hospital.
The neurologists who examined the patients tested the app and then compared the results with their own clinical diagnosis.
The analysis found that the app accurately detected stroke-associated facial droop in almost 100% of patients.
The app also accurately detected arm weakness in more than two-thirds of cases, and preliminary analysis suggests it could also reliably detect slurred speech.
It is important to recognize the signs of a stroke immediately, as anti-clot medications should be given within three hours of the onset of symptoms.
The sooner the treatment is given, the more chance there is for better recovery.
The 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 arrive at the hospital in time for treatment, which is one of the reasons why it is vital to recognize the symptoms of a stroke. ‘stroke and call [for help] right away.
“These initial results confirm that the app has reliably identified symptoms of acute stroke as accurately as a neurologist, and they will help improve the app’s accuracy in detecting signs and symptoms of a stroke. ‘a stroke.”
The findings were presented at the American Stroke Association’s International Stroke Conference in Dallas, Texas.