Johns Hopkins AI sepsis tool speeds up detection, prevents deaths

Baltimore-based Johns Hopkins University researchers have developed an artificial intelligence tool designed to detect sepsis earlier.

The AI tool, the Targeted Real-Time Early Warning System, looks through medical records and clinician notes to determine which patients are at risk of developing sepsis. During testing, in 82 percent of sepsis cases, the AI was accurate nearly 40 percent of the time. This is a significant improvement over previous sepsis detection AI systems, according to July 21 reporting in Johns Hopkins' The Hub.

The tool reduced patients risk of death by 20 percent. 

"The approach used here is foundationally different," said Suchi Saria, PhD, founding research director of the Malone Center for Engineering in Healthcare at John Hopkins. "It's adaptive and takes into consideration the diversity of the patient population, the unique ways in which doctors and nurses deliver care across different sites, and the unique characteristics of each health system, allowing it to be significantly more accurate and to gain provider trust and adoption."

Copyright © 2024 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.

 

Featured Whitepapers

Featured Webinars