FDA grants 1st permission for AI stroke-detection imaging software

According to a Feb. 13 press release, the FDA announced clearance for the marketing of the Viz.AI Contact application, a clinical decision support software created to analyze CT results and notify providers of a potential stroke.

This is the first approval of AI imaging software designed for stroke detection, according to an FDA spokesperson.

The release also notes this ruling creates a "new regulatory classification" for future AI-related platforms to follow—paving the way for an influx of new technology into the field.

“Subsequent computer-aided triage software devices with the same medical imaging intended use may go through the FDA’s premarket notification (510 (k)) process, whereby devices can obtain marketing authorization by demonstrating substantial equivalence to a predicate device,” according to the release.

The software uses an artificial intelligence (AI) algorithm to quickly search CT images of the brain for stroke indicators. If a suspected large vessel blockage is detected, a text notification is sent to a neurovascular specialist.

A retrospective study using the algorithm platform was submitted to the FDA assessing 300 CT images against two trained-neurologists, demonstrating the AI software’s ability to earlier notify a neurovascular specialist when a blockage was suspected.

“Strokes can cause serious and irreversible damage to patients. 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,” said Robert Ochs, PhD, and acting deputy director for radiological health in the Office of In Vitro Diagnostics and Radiological Health in the FDA’s Center for Devices and Radiological Health.

The Viz.AI Contact application was reviewed through the De Novo premarket review pathway, a regulatory pathway for some new types of medical devices that are low to moderate risk and have no legally marketed device to compare to.