FDA gives its nod to AI-assisted software to help clinicians identify stroke victims

The FDA approved the use of Viz.AI’s artificial intelligence software that is designed to help quickly identify whether a patient has suffered a stroke.

The software was approved for marketing in a de novo premarket review channel that allows for the use of devices with low to moderate risk to patients.

The Silver Spring, Maryland-based company’s software uses a form of AI to analyze computed tomography images of the brain to find indicators associated with a stroke. Viz.AI’s Contact app can then send a text alert to a neurovascular specialist if it detects a suspected large vessel blockage, the regulatory agency said. Although the message is sent via a mobile device, a specialist will still need to review the images at a clinical work station.

"Strokes can cause serious and irreversible damage to patients,” Robert Ochs, Ph.D, of the FDA’s Center for Devices and Radiological Health said in a statement. “The software device could benefit patients by notifying a specialist earlier thereby decreasing the time to treatment. Faster treatment may lessen the extent or progression of a stroke.”

As part of the application, the company submitted a study of 300 CT images that assessed the independent performance of the image analysis algorithm and notification functionality of the Contact Viz.AI application against the performance of two trained neuroradiologists for the detection of large vessel blockages in the brain, the agency said.

Strokes are the No. 5 cause of death and a leading cause of disability in the U.S., according to the American Stroke Association.