Smartphone App Uses Artificial Intelligence to Detect Stroke Signs

Researchers discussed a newly created smartphone app that reliably identifies patients’ physical signs of stroke with the power of artificial intelligence at the Society of Neurointerventional Surgery’s (SNIS) 20th Annual Meeting. This discussion was based on a new study conducted by researchers from the UCLA David Geffen School of Medicine and multiple medical institutions in Bulgaria. They used data from 240 patients with stroke at four metropolitan stroke centers.

A stroke occurs when a blood vessel in the brain ruptures and bleeds, or when there’s a blockage in the blood supply to the brain. This prevents blood and oxygen from reaching the brain’s tissues. Without oxygen, brain cells begin to die within minutes (1^✔ ✔Trusted Source
Stroke: causes and clinical features

Go to source). This eventually leads to death.

According to the Centers for Disease Control and Prevention (CDC), stroke is a leading cause of death in the United States. Every year, more than 795,000 U.S. people have a stroke. Symptoms of a stroke show up in the body parts controlled by the damaged areas of the brain. Symptoms can come on without warning. Hence, it is important to recognize stroke symptoms and seek treatment quickly for a better outcome.

Developing Smartphone App for Early Diagnosis of Stroke

In this study researchers used smartphones to record videos of patients and test their arm strength to detect patients’ facial asymmetry, arm weakness, and speech changes—all classic stroke signs within 72 hours of the start of the patient’s symptoms.

To evaluate facial asymmetry, the study authors used machine learning to analyze 68 facial landmark points. To test arm weakness, the team used data from a smartphone’s standard internal 3D accelerometer, gyroscope, and magnetometer (2^✔ ✔Trusted Source
Smartphone App in Stroke Management: A Narrative Updated Review

Go to source).

To determine speech changes, researchers used mel-frequency cepstral coefficients, a typical sound recognition method that translates sound waves into images, to compare normal and slurred speech patterns. They then tested the app using neurologists’ reports and brain scan data, finding that the app was sensitive and specific enough to diagnose stroke accurately in nearly all cases.

Quick and accurate assessment of stroke symptoms is imperative to ensure that people with stroke survive and regain independence. Researchers hope the deployment of this app changes lives and the field of stroke care.

Advertisement

References:

1. Stroke: causes and clinical features - (https://www.medicinejournal.co.uk/article/S1357-3039(20)30138-9/fulltext)
2. Smartphone App in Stroke Management: A Narrative Updated Review - (https://www.j-stroke.org/journal/view.php?doi=10.5853/jos.2022.01410)

Source-Eurekalert