Researchers have developed an app called Fast AI to detect the most common stroke symptoms — facial asymmetry, hand weakness and changes in speech — using machine learning algorithms. Preliminary results will be presented at the American Heart Association’s International Stroke Conference next week.
“Our goal is very simple. We want to detect stroke early,” said study lead author Radoslav I. Rechev, a vascular neurologist at the University of California, Los Angeles.
The app isn’t ready for public use, and it’s unclear when it will be available or to whom it will be marketed.
Ultimately, Rechev said, the goal is to move beyond the app to other devices or platforms.
“When someone is in a video chat, or when they’re talking to a virtual assistant like “Alexa,” or when they’re driving their autonomous driving vehicle, we want to be able to do that passive monitoring to capture the symptoms of a patient. A stroke happens,” he explained.
Using the app as an educational tool
Neurologists from four major metropolitan stroke centers in Bulgaria tested the app with approximately 270 patients with confirmed acute stroke.
Using video recordings and device sensors, the app was able to identify facial asymmetry with more than 97 percent accuracy and hand weakness with more than 72 percent accuracy, according to the abstract, which has been peer-reviewed but not yet published. Medical Journal.
Since the initial research phase, the app has been tested on several hundred patients, Rechev said. It is also designed to detect abnormal speech, but that function has not yet been tested in patients, he said.
Experts say a smartphone app that can help detect stroke symptoms is a good idea. But, they said, the app should be used to educate people about symptoms and encourage them to call 911, not as a diagnostic tool.
Some experts worry that a false negative result could discourage some people from seeking emergency medical care, for example, which could have disastrous consequences.
“This is an exciting and interesting opportunity to see how we can use AI technology to learn more about stroke symptoms,” said Andrew Rossman, chief of the stroke program and medical director of the Cleveland Clinic’s Comprehensive Stroke Center.
“But in no way should it be considered a method for making decisions about whether to call 911 or decide whether someone is definitely having stroke symptoms. It’s just a piece of information that sounds interesting at the moment but has no real application.”
Early detection is important for stroke
Stroke, which occurs when blood flow to the brain is blocked or a blood vessel ruptures, is the fifth leading cause of death and the leading cause of long-term disability in the United States.
Time is critical to diagnosing the condition and starting treatment protocols, said Matthew Potts, surgical director of Northwestern Memorial Hospital’s Comprehensive Stroke Center. “When blood is cut off in your brain, every minute that passes, the neurons are dying,” he said.
“Clot-busting” drugs can break up clots in the first few hours of an ischemic stroke, which accounts for 87 percent of strokes, to prevent or reduce brain damage.
But these drugs like Alteplase IV r-tPA should be given within 4.5 hours of the onset of ischemic stroke. In some cases, the clot can be removed during a thrombectomy, a procedure that manually removes it from the artery.
Hemorrhagic strokes can be managed with medication or require surgical intervention.
Prognosis depends on the area of the brain and the amount of tissue affected, but time is key, and in some cases, quick action can prevent damage, experts said.
Although transient ischemic attacks, or TIAs, in which blood clots are temporary and do not cause permanent injury, they can be a warning sign that a patient is at risk of a future stroke. So stroke patients – and those around them – should be aware of the symptoms.
Common warning signs of stroke
The acronym FAST is used to teach people the most common warning signs of stroke.
- “F” is for face tilt: The face may droop to one side, especially when the person smiles.
- “A” is for arm weakness: when both arms are raised, one arm starts to go down.
- “S” is for difficulty speaking: the person may be slurring words.
- “T” is for time: If someone is experiencing these symptoms, call an ambulance immediately.
There are also other symptoms, which can be difficult for the app to detect, that could indicate a stroke, Rossman said. Stroke patients may have sudden and severe headaches, confusion, loss of vision in one or both eyes, numbness or tingling on one side of their body or dizziness, or trouble walking due to loss of balance or coordination.
Greg Albers, director of the Stanford Stroke Center at Stanford Medical Center, said stroke symptoms can be disabling.
“The type of vision you lose from a stroke, for example, is usually half of your visual field,” he said. “If you’re bumping into things because you can’t see, you’re waving your hand in front of your eyes and there’s a big chunk of lost vision, that’s very worrying.”
“Symptoms come on very suddenly,” he added.
Other times, however, the symptoms are mild, and patients may not take them seriously and seek medical attention, which can leave them with permanent losses, experts said.
Albers acknowledged that it can be difficult to determine whether someone is having a stroke, which is one reason why there should be a “low threshold” for people to call 911 when symptoms indicate a stroke.
Even in the emergency room, he said, doctors must perform brain scans and other tests before making a definitive diagnosis and starting treatment because of the “clot-busting” drug given to a patient with a bleeding stroke — including an artery in an artery. The brain leaks or bursts – the result can be “a catastrophe”.
“They will bleed more,” he said.
Experts say the goal of smartphone technology that can detect stroke symptoms should be to get stroke patients to the ER more quickly.
“We want people to err on the side of coming to the hospital, not on the side of staying at home,” said Matthew Fink, chief of neurology at Weill Cornell Medical Center and New York-Presbyterian Hospital.