Someone suffers a stroke every 40 seconds in the US, and every five minutes in the UK, and acting quickly is key to preventing permanent brain damage.
However, the symptoms, which include falling on one side, slurred speech or an inability to lift an arm, may not be easily recognized in an emergency.
Now, scientists have come up with an app that can help family and friends know when a stroke is happening – prompting them to call an ambulance.

Scientists at the University of California have developed an app that uses facial recognition and speech patterns to determine if a person is having a stroke with 100 percent accuracy (file photo).
The app, called FAST.AI, uses video of the patient’s face to analyze 69 facial points, measure hand movements and detect speech changes.
A team from the University of California tested nearly 270 patients who had an acute stroke within 72 hours of being hospitalized.
After testing the app, the neurologists who examined the patients compared the results with their own clinical examination.
In the analysis, the app correctly detected stroke-related facial droop in nearly 100 percent of patients.
The app also correctly detected arm weakness in more than two-thirds of cases, and preliminary analysis showed it could reliably identify hidden speech.
It is important to recognize the symptoms of a stroke as soon as possible because anticoagulants should be given within three hours of the onset of symptoms.
The sooner the treatment, the better the chance for a better recovery.
Researchers say their research is ongoing and the app is still a work in progress and not available to the public.
“Many stroke patients do not go to the hospital in time for treatment, which is one of the reasons why it is important to recognize and call for stroke symptoms,” said author Radolav Raychev. [for help] right away.
‘These early results show that the app reliably diagnoses acute stroke symptoms in the same way 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.