Dive Brief:
- Johns Hopkins University researchers have developed a computer algorithm that correctly predicts septic shock early in 85 percent of cases. The method was also able to predict septic shock before organ dysfunction more than 66 percent of the time.
- The new method was published in the journal Science Translational Medicine. Study leader, Suchi Saria said the "critical advance our study makes is to detect these patients early enough that clinicians have time to intervene."
- Sepsis affects about a million Americans every year and kills an estimated 200,000, a good number of them based in hospitals and nursing facilities.
Dive Insight:
The researchers took data from 16,234 intensive care patients at Boston's Beth Israel Deaconess Medical Center from 2001 to 2007 and created an algorithm combining 27 factors into a score measuring septic shock risk. All the data is routinely collected, eliminating the need for new measurements. It's set apart from previous methods to predict the condition in that it is based on a larger data pool and includes more health indicators and factors in some elements that could have confounded results.
Implementation of the algorithm is the next step. David Hager, study co-author and director of the Medical Progressive Care Unit at Johns Hopkins Hospital, said the algorithm could be programmed into EHRs to alert clinicians about a patient at risk.
"The tricky issue is thinking about how the clinical team is provided with the information," Hager said. "But," he added, "we have to do this in a way that is well-integrated into the existing clinical workflow and does not cause alarm fatigue."