Real-time stroke detection available from new smartphone app

Feb. 3, 2023

Preliminary research shows that an app called FAST.AI, owned by Neuronics Medical, was able to detect stroke-related facial symptoms and arm weakness in people diagnosed with acute stroke.

Smartphone apps are fast becoming more than just entertainment or productivity tools — some can even monitor health and wellbeing. Now, a new app called FAST.AI may be able to determine if someone is having a stroke as it’s happening. Moreover, researchers suggest that the app may be as accurate as a neurologist at diagnosing stroke. 

Preliminary research on FAST.AI’s effectiveness in identifying stroke symptoms is scheduled for presentation at the American Stroke Association’s International Stroke Conference 2023. The conference will be held February 8-10 in Dallas, Texas. 

The app, owned by Neuronics Medical, detects severe strokes with algorithms that recognize arm weakness, speech changes, and facial asymmetry — a stroke symptom characterized by drooping of the face muscles. It works by using a facial video that looks at 68 facial landmark points. It also uses sensors to measure arm movement and orientation, and voice recordings to detect changes in speech. 

In a study, researchers investigated the effectiveness of FAST.AI on nearly 270 people within 72 hours of hospital admission for acute stroke. 

The scientists found that the app accurately detected facial asymmetry associated with stroke in almost 100% of the participants. FAST.AI also accurately identified arm weakness in two-thirds of those diagnosed with acute stroke. However, the voice detection system that looks for changes in speech still needs to be fully validated. Still, the preliminary analysis showed that it might be able to accurately detect stroke-associated slurred speech. 

"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," said study author Radoslav I. Raychev, M.D., FAHA, a clinical professor of neurology and a vascular neurologist at the University of California, Los Angeles in a press release. 

"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," Raychev added. 

Accurately detecting stroke early may help people get medical attention faster, thus reducing the chance of a lengthy recovery. Currently, FAST.AI is still in the research and development phase and is not available to the public. 

Healthnews release

ID 154742479 © Pop Nukoonrat | Dreamstime.com
Photo 284411646 | Ai Healthcare © Yuri Arcurs | Dreamstime.com
557322636 © 2ragon | stock.adobe.coom
Photo 197965296 © Ratz Attila | Dreamstime.com
Photo 99172901 © Mohamed Ahmed Soliman | Dreamstime.com