The US Food and Drug Administration (FDA) has cleared a deep-learning algorithm that analyzes images to detect potential strokes. The computer-aided image software system from San Francisco-based AI-health firm Viz.ai, identifies suspected large vessel occlusion (LVO) strokes, and sends a notification by text message to specialists, who can view the results on their phone and decide whether to initiate emergency treatment. The approval is the first for a newly introduced regulatory classification for computer-aided triage software, within the FDA's 510(k) pathway. “The Viz.ai LVO Stroke Platform is the first example of applied artificial intelligence software that seeks to augment the diagnostic and treatment pathway of critically unwell stroke patients,” said Chris Mansi, neurosurgeon and chief executive officer of Viz.ai, in a press release. In addition to the FDA's go-ahead in February, the Viz.ai LVO Stroke System received a CE Mark by the EU in January, confirming its compliance with health, safety and environmental regulations. The system analyses computed tomography (CT) scans and sends an alert in approximately 6 minutes if it identifies a suspected LVO. According to Viz.ai, a study involving 300 CT scans comparing the performance of the software with that of neuroimaging specialists resulted in faster detection by the software in more than 95% of cases and saved an average of 52 minutes, an improvement that could slash the time to intervention that is critical for stroke recovery. According to the American Stroke Association, almost 800,000 people in the US have a stroke each year. There has been growing interest in the use of AI to assist clinicians' diagnoses. (Nat. Biotechnol. 35, 604–605, 2017).
About this article
Cite this article
FDA approves stroke-detecting AI software. Nat Biotechnol 36, 290 (2018). https://doi.org/10.1038/nbt0418-290
This article is cited by
Pilot Report for Intracranial Hemorrhage Detection with Deep Learning Implanted Head Computed Tomography Images at Emergency Department
Journal of Medical Systems (2022)
Genome Medicine (2019)