Artificial intelligence tool could speed stroke detection
The Food and Drug Administration has approved for marketing new decision support software that could alert doctors of a potential stroke in one of their patients.
The software, which uses artificial intelligence, analyzes computed tomography results and notifies providers if findings of a stroke or potential stroke are detected.
“The software device could benefit patients by notifying a specialist earlier, thereby decreasing the time to treatment,” says Robert Ochs, acting deputy director for radiological health in FDA’s Center for Devices and Radiological Health.
The vendor is Viz.AI, born at Stanford University. Viz.AI is computer-aided triage software using an artificial intelligence algorithm to analyze images for indications associated with stroke. Additional algorithms also can assist providers in selecting the most appropriate treatment options.
After analyzing CT images of the brain, Viz.AI sends a text notification to the appropriate provider if a suspected large vessel blockage has been identified.
“The algorithm will automatically notify the specialist during the same time the first-line provider is conducting a standard review of the images, potentially involving the specialist sooner than the usual standard of care in which patients wait for a radiologist to review CT images and notify a neurovascular specialist,” according to the company. “The notification can be sent to a mobile device but the specialist still needs to review the images on a clinical workstation.”
Use of Viz.AI is intended for vascular neurologists, neuro-radiologists, neuro-interventional specialists and other professionals with similar training.
In seeking FDA approval, Viz.AI submitted a study of 300 images that assessed the performance and functionality of the decision support software against the performance of two neuro-radiologists to detect large vessel blockages in the brain and the study showed that Viz.AI can get data to clinicians faster.