FDA clears AI tool to alert providers of patients' stroke risk

The FDA cleared Viz.AI, a San Francisco-based health IT company, to market its clinical decision support software for stroke care Feb. 13.

The CDS application, called Contact, uses artificial intelligence to triage patients at risk of experiencing a stroke. The AI algorithm analyzes CT images to identify blockages in the brain and recommends treatment plans for at-risk patients.

After flagging a patient as a potential stroke victim, the application delivers a text notification to a neurovascular specialist. The specialist will then be able to review the relevant CT images on a clinical workstation.

Standard of care calls for patients to "wait for a radiologist to review CT images and notify a neurovascular specialist," according to a Feb. 13 FDA statement. However, Viz.AI's application reviews CT images at the same time as a first-line provider, potentially eliminating the need for a radiologist to review a patient's scans before sending to a specialist.

"Faster treatment may lessen the extent or progression of a stroke," said Robert Ochs, PhD, acting deputy director for radiological health at the Office of In Vitro Diagnostics and Radiological Health in the FDA's Center for Devices and Radiological Health. "The software device could benefit patients by notifying a specialist earlier, thereby decreasing the time to treatment."

The FDA reviewed Viz.AI's application under the agency's De Novo premarket review pathway, a regulatory pathway specific to new types of medical devices with low to moderate risk.

The FDA released draft guidance on CDS software in December, which aims to clarify how the technology is regulated. "The FDA is currently creating a regulatory framework for [CDS] products that encourages developers to create, adapt and expand the functionalities of their software to aid providers in diagnosing and treating diseases and conditions," the agency wrote in its Feb. 13 statement.

Copyright © 2024 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.

 

Featured Whitepapers

Featured Webinars