A smartphone app could help identify stroke symptoms as they occur

A new smartphone application called FAST.AI could help stroke survivors, their families and caregivers recognize common stroke symptoms in real time so they can quickly call 9-1-1. may prompt you to do so. His 2023 Stroke International Conference at the Stroke Association. Held in person in Dallas February 8-10, 2023, the conference is the world’s premier conference for researchers and clinicians dedicated to the science of stroke and brain health.

According to the American Heart Association, stroke is the fifth leading cause of death and a leading cause of disability in the United States. Approximately 85% of all strokes in the United States are ischemic strokes and are caused by blood clots within blood vessels. Blocks blood flow to the brain.

FAST.AI is a fully automated smartphone application for severe stroke detection. It uses machine learning algorithms to recognize all common stroke symptoms, including facial asymmetry (drooping facial muscles), arm weakness, and speech changes. This research is ongoing and the mobile application is still under development and not available to the public.

A smartphone application uses videos of the patient’s face to examine 68 facial landmark points. A sensor that measures arm movement and orientation. Voice recording detects changes in speech. Information from each test was sent to a database server for analysis.

The researchers studied about 270 patients (41% female, mean age 71 years) diagnosed with acute stroke at stroke centers (St. Anna University Hospital, Sofia) in four metropolitan areas of Bulgaria, from admission to 72 We tested it in less than an hour and verified the performance of FAST.AI. Haskovo University Hospital, Haskovo; Palmed University Hospital, Plovdiv; from July 2021 to July 2022, University Hospital Stara Zagora “Professor Stoyan Kirkovich”). We compared the AI ​​results with their clinical impressions.

result of analysis:

• A smartphone app accurately detected stroke-related facial asymmetry in nearly 100% of patients.
• The app accurately detected arm weakness in over two-thirds of cases.
• The unintelligible speech module has not yet been fully validated and tested, but preliminary analysis confirms that it may be able to reliably detect illegible speech, according to the researchers.

Thrombolytics should be administered within 3 hours (up to 4.5 hours in certain eligible patients) of the onset of symptoms. An average of 1.9 million brain cells die every minute in an untreated stroke, according to the American Stroke Association, a division of the American Heart Association. A previous study found that stroke patients treated within 90 minutes of first symptoms had little or no disability compared with those treated more than 90 minutes after symptoms began. have been found to be almost three times more likely to recover at

“Many stroke patients do not arrive at the hospital in time for thrombectomy treatment. This is one reason why it is essential to recognize stroke symptoms and call 9-1-1 immediately.” said study author Radoslav I. Raychev. , MD, FAHA, Clinical Professor of Neurology and Vascular Neurologist at the University of California, Los Angeles. “These early results confirm that the app reliably identified acute symptoms of stroke as accurately as neurologists, and we believe there are ways to improve the app’s accuracy in detecting stroke signs and symptoms.” It helps.”

A limitation of this study is that a neurologist (not an individual, family member, or caregiver) performed the screening and instructed the patient how to use the application.

Daniel T. Lackland, Dr. PH, FAHA, Volunteer Professional with the American Stroke Association and Member of the EPI and Stroke Council, Professor of Translational Neuroscience and Population Studies, Department of Neurology, Charleston Medical College, South Carolina and Director Carolina, Ph.D., hailed the study as a promising tool to address major health challenges. That is, a way to encourage individuals with symptoms of stroke to seek treatment in the short term.

“This abstract describes an effective approach to easily assess signs of stroke and seek treatment. This app helps individuals assess signs of stroke without needing to be reminded of the warning signs.” It’s possible,” said Lackland. He is involved in research.