FAST.AI, a new smartphone app, may offer prompt assistance to stroke patients and their families/caregivers in recognizing common symptoms and quickly calling 9-1-1, according to preliminary research.

Stroke is the fifth largest cause of death and a major contributor to disability in the United States, according to the American Heart Association. Approximately 85% of all strokes in the U.S. are ischemic strokes, which are triggered by a blood clot in a blood artery that prevents blood flow to the brain.

FAST.AI is a completely automated smartphone application that detects severe strokes by employing machine learning algorithms to distinguish facial asymmetry (muscle sagging in the face), arm weakness, and speech alterations – all of which are frequent stroke symptoms. This research is still under progress, and the mobile application is not yet accessible to the public.

The smartphone application examines 68 facial landmark points using a video of the patient’s face; sensors assess arm movement and orientation; and audio recordings identify speech changes. The results of each test were sent to a database server so that they could be looked at.

Nearly 270 patients with an acute stroke diagnosis (41 percent women; 71 years of age on average) were tested between July 2021 and July 2022 at four major urban stroke centers in Bulgaria: St. Anna University Hospital in Sofia, University Hospital Haskovo in Haskovo, University Hospital Pulmed in Plovdiv, and University Hospital “Prof. Dr. Stoyan Kirkovich” in Stara Zagora. The app was evaluated by neurologists who examined the patients, and they then compared the FAST.AI findings with their observations.

The research revealed:

• In almost all patients, the smartphone app correctly identified facial asymmetry brought on by a stroke.
• Over two-thirds of the time, the app correctly identified arm weakness.
• Preliminary investigations revealed that the slurred speech module may be able to accurately identify slurred speech, however, it has yet to be thoroughly verified and tested, according to the researchers.

Clot-busting drugs should be given within three hours after the onset of symptoms (or up to four and a half hours in certain qualified individuals). According to the American Stroke Association, a branch of the American Heart Association, 1.9 million brain cells die on average every minute that a stroke is left untreated, therefore the earlier treatment is given, the greater the chance for a better recovery. According to earlier studies, stroke patients who get therapy within 90 minutes of their initial symptoms had a nearly threefold higher chance of recovering with little to no impairment than those who receive care more than 90 minutes later.

“Many stroke patients don’t make it to the hospital in time for clot-busting treatment, which is one reason why it is vital to recognize stroke symptoms and call 9-1-1 right away,” remarks study author Radoslav I. Raychev. “These 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.”

The study’s limitation is that only neurologists, not patients, family members, or caregivers, performed the screenings and instructed patients on how to use the app.

Image Credit: Getty