UC San Diego Health Implements AI Imaging Algorithm to Detect COVID-19 in 10 Days Using AWS

The healthcare industry has faced challenges in developing a cost-effective system to accurately detect indications of COVID-19 in patients with less-pronounced symptoms, but UC San Diego Health built on Amazon Web Services (AWS) to facilitate an experimental procedure with the goal of doing just that.

Although CT scans can be used to detect signs of COVID-19, it would be impractical and costly to perform a CT scan on every patient presenting with symptoms such as fever and fatigue. UC San Diego Health—deploying a machine learning–based algorithm that two of its radiologists had already been working on in the context of pneumonia detection using publicly available chest X-rays—was able to quickly create an experimental procedure for detecting COVID-19 signs through chest X-rays. “Their algorithm generates a probability map, which is a heat map that gets overlaid on top of the chest X-ray image,” says Mike Hogarth, clinical research information officer at UC San Diego Health.

When the COVID-19 pandemic began, UC San Diego Health already had an AWS environment. It began discussing the prospect of developing the algorithm project and had a scalable infrastructure in place just 10 days later. With this infrastructure, a gateway puts X-ray images into Amazon Elastic Compute Cloud (Amazon EC2) instances, the machine learning algorithm analyzes them and applies the heat map overlays, and then the images travel to be viewed by clinical personnel. “I want to underscore the benefit of having a HIPAA-secure environment in a highly scalable cloud infrastructure and the benefit of having this gateway—in just 5 days, we were able to implement a real clinical workflow connected to the real clinical picture archiving and communication system,” says Hogarth.