AI Case Study

Viz.ai's deep learning solution which automatically detects strokes from CTA scans reducing detection time from 66 to 6 minutes has earned FDA approval

Viz.ai has developed a deep learning algorithm to detect the possibility of arge vessel occlusion (LVO) strokes from CTA scans.
The solution which claims to reduce triage time to less than one tenth has earned FDA approval.

Industry

Healthcare

Healthcare Equipment And Supplies

Project Overview

"The software automatically analyzes CT scans of ER patients using machine-learning algorithms similar to detect blockages in major brain blood vessels. When the software thinks it has found a blockage—suggesting the most common form of stroke—it sends an alert to a brain specialist’s smartphone asking them to review the images. The software also flags the specific images it judges to be most important."

Reported Results

According to the company:

* Reduces notification time from 66 minutes to 6 minutes
* In a study involving 300 patients, the algorithm achieved an AUC of 0.91
* Recognized LVO strokes with 90% specificity and sensitivity

Technology

Function

Operations

General Operations

Background

"In the U.S., someone has a stroke every 40 seconds and someone dies from a stroke every 4 minutes.¹ Treatment with IV tPA and mechanical thrombectomy are time-dependent, making early stroke identification and notification of a specialist critical."

Benefits

Data