A smartphone app that could help identify stroke symptoms as soon as they appear
Scientists have developed a smartphone app that detects stroke symptoms as soon as they appear — by looking at a droopy face and slurred speech
In the US, a person has a stroke every 40 seconds and in the UK every five minutes, and acting quickly is key to preventing permanent brain damage.
However, the symptoms, which include the face hanging to one side, slurred speech or the inability to raise the arm, are not as easily recognized 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 911.
Scientists at the University of California have developed an app that uses facial recognition and speech patterns to detect whether a person is having a stroke with nearly 100 percent accuracy (file image)
The app, called FAST.AI, uses a video recording of the patient’s face to examine 69 facial points, measure hand movements and detect changes in speech.
A team from the University of California tested it on nearly 270 patients who were diagnosed with an acute stroke within 72 hours of being admitted to the hospital.
Neurologists examining patients tested the application and compared the results with their own clinical diagnosis.
The analysis found that the application accurately detected facial drooping caused by a stroke in almost 100 percent of patients.
The app also correctly detected hand 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 right away because clot-busting drugs should be administered within three hours of the onset of symptoms.
The faster the treatment is carried out, the greater the likelihood of a better recovery.
The researchers said their study is ongoing and the app is still under development and not available to the public.
Author Radoslav Raychev said: ‘Many stroke patients do not make it to hospital in time for treatment, which is one of the reasons why it is important to recognize stroke symptoms and call [for help] immediately.
‘These early results confirm that the app reliably identified acute stroke symptoms as accurately as a neurologist, and will help improve the app’s accuracy in detecting stroke signs and symptoms.’
The findings were presented at the American Stroke Association’s International Stroke Conference in Dallas, Texas.