EHRs can accurately predict sepsis
Electronic health records can be an effective way to predict the onset of sepsis, a leading cause of death and hospitalization in the United States, according to a study published at the Journal of the American Medical Informatics Association.
Researchers at the University of California-Davis studied vital sign data from the EHRs of 741 patients with sepsis and found that data, along with serum white blood cell count, can accurately predict sepsis. In addition, the blood levels of lactate, blood pressure and respiratory rate could determine a patient's risk of death from sepsis.
"Rather than using a 'gut-level' approach in an uncertain situation, physicians can instead use a decision-making tool that 'learns' from patient histories to identify health status and probable outcomes," said Ilias Tagkopoulos, assistant professor of computer science at UC Davis and senior author of the study. "Another benefit of the sepsis predictor is that it is based on routine measures, so it can be used anywhere--on the battlefield or in a rural hospital in a third-world country."
The researchers are working on a specific sepsis-risk algorithm that can be automatically calculated in the EHR.
A project by defense contractor Lockheed Martin, which operates more than 50 medical clinics nationwide within the VA and Social Security Administration, applies missile defense data- crunching techniques to patient information. It says it has achieved 90 percent accuracy in identifying sepsis 16 hours before it manifests to most physicians, reports Health IT Analytics.
Meanwhile, a review of current practices for treating sepsis found they do not increase patients' chances of survival. The findings, to be published May 1 in the New England Journal of Medicine, could change the way sepsis is diagnosed and treated, according to the researchers at the University of Pittsburgh School of Medicine.
Mount Sinai Hospital in New York City is expanding a successful sepsis-reduction program hospital-wide after reporting a 40-percent reduction from a test program using alerts generated by electronic medical records. The EMR intervention program triggered a red alert based on subtle changes in vital signs, including higher temperatures and pulse or breathing rates, that rarely prompted intervention in the past.