We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us

Download Mobile App





Deep Learning Algorithm That Detects ARDS with Expert-Level Accuracy Could Be Game-Changer in COVID-19 Treatment

By HospiMedica International staff writers
Posted on 26 Apr 2021
Print article
Illustration
Illustration
Researchers have found a solution that could help provide the right care to COVID-19 patients with Acute Respiratory Distress Syndrome (ARDS) which is a life-threatening lung injury that progresses rapidly and can often lead to long-term health problems or death, but can be difficult for physicians to recognize.

A research team at the Michigan Center for Integrative Research in Critical Care (MCIRCC; Ann Arbor, MI, USA) has developed a new artificial intelligence (AI) algorithm that analyzes chest X-rays for ARDS. Many patients who die from COVID-19 die from complications associated with the ARDS which occurs when fluid builds up in the lungs’ air sacs and deprives the organs of the oxygen they need to function.

Accurately interpreting a patient’s chest X-ray is a critical component of diagnosing ARDS. However, studies demonstrate that up to 65% of patients with ARDS are diagnosed late or missed and do not receive evidence-based therapies that improve outcomes. Every day of delay in evidence-based treatment is associated with increased mortality. Thus, there is an urgent need for computational tools that can analyze chest radiology studies to support clinicians with real-time ARDS surveillance and ensure fidelity with evidence-based treatments.

The MCIRCC research team showed that their AI algorithm that analyzes chest X-rays for ARDS could, in fact, identify ARDS findings with higher accuracy than many physicians. It also performed well when it was externally validated in patients from another hospital system. The algorithm they used, a type of machine-learning model called deep convolutional neural networks (CNNs), had 121 layers and seven million parameters.

Using an innovative approach, the team then trained the algorithm to identify common radiologic findings, but not ARDS, on 450,000 chest x-rays from publicly available sources. Then they trained the algorithm to detect ARDS using a unique dataset of 8,000 chest x-ray studies carefully reviewed and annotated for ARDS by Michigan Medicine physicians. This approach is called transfer learning, which has many parallels to how humans learn. Further research is needed to evaluate the impact of the algorithm in a clinical setting, but the team at MCIRCC is confident that it will be game-changer. They envision it will help physicians identify ARDS patients more quickly and accurately, and ensure patients receive evidence-based care.

“In our previous work, we found that physicians have difficulty identifying findings of ARDS on chest X-rays,” said Dr. Michael Sjoding, a pulmonary critical physician at Michigan Medicine and lead author of the study. “Early recognition and treatment are key factors in treating ARDS. Delays can be catastrophic. We now have a highly reliable way to identify ARDS patients, which will also allow us to study them more effectively.”


Related Links:
MCIRCC


Print article

Channels

Copyright © 2000-2021 Globetech Media. All rights reserved.