AI platform designed to help diagnose stroke gains US regulatory approval

A platform which uses artificial intelligence to help clinicians identify certain types of stroke has received approval from the US Food and Drug Administration (FDA).

Viz.ai is the first product of its kind to be cleared by the US body, which means it can now be brought to market. It also means the FDA has established a new regulatory classification, relating to computer-aided triage software for certain medical imaging.

In January, the Viz.ai platform was also granted a European CE mark, which recognises its compliance with EU safety, health and environmental requirements.

The technology uses deep learning algorithms to automatically analyse images of the blood vessels and help identify suspected large vessel occlusion (LVO) strokes, in which a large blood vessel in the neck or brain becomes blocked.

If a patient is identified by the system as having a suspected LVO stroke, the clinician is alerted and can view the computerised tomography angiography images from their mobile device.

“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 Dr Chris Mansi, neurosurgeon and CEO at Viz.ai.

“We are thrilled to bring artificial intelligence to healthcare in a way that works alongside physicians and helps get the right patient, to the right doctor at the right time.”

Viz.ai has plans to launch trials in the NHS hospitals this year, though details about which trusts will be taking part and when have not yet been announced.

The use of AI in healthcare was the focus of a recent report by the Reform think tank which argued the technology could help with efficiencies within the NHS.