Presented By
Getty Images

Every hour treatment for sepsis is delayed, the risk of the patient dying increases by as much as 8%, making the systemic infection a leading cause of death in hospitals. But sepsis is hard to diagnose because its symptoms (such as fever) are so common in hospital patients. The Targeted Real-Time Early Warning System–developed by researchers at Johns Hopkins University and Bayesian Health–uses AI to analyze a patient’s medical records, symptoms, and lab results, alerting a clinician to probable sepsis cases. “The typical early-alert systems run at about 20% to 30% sensitivity,” says Suchi Saria, founder and CEO of Bayesian Health. “Our system was able to catch 82%.”

More Must-Reads From TIME

Contact us at letters@time.com.

Hydration Made Fun
A Modern Flip Phone
A Saliva Pregnancy Test
More Than a Fast Car
A Breakthrough Bassinet
EDIT POST