EHR data can predict sepsis

EHRs can be used effectively to predict the onset of sepsis, according to researchers from the University of California at Davis. 

Researchers used routine information of hospitalized patients, including blood pressure, respiratory rate, temperature and white blood cell count. Analysis of the data from the EHRs of 741 patients with sepsis revealed that vital signs combined with serum white blood cell count can accurately predict sepsis, which is associated with increased blood levels of lactate. They found that lactate level, blood pressure and respiratory rate could determine a patient’s risk of death from sepsis. 

Sepsis is a leading cause of death and hospitalization in the U.S., occurring in more than 750,000 patients annually and killing nearly one-third of all people who develop the immune system response to infection that can damage organs and cause permanent physical and mental disabilities. Sepsis-related deaths and serious consequences, however, are preventable for up to 30 percent of patients. 

“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, in a statement. "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 UC Davis researchers now are working on a sepsis-risk algorithm that can be automatically calculated in an EHR. The study was funded by the Center for Information Technology Research in the Interest of Society and the National Center for Advancing Translational Sciences of the National Institutes of Health, and is published in the current issue of the Journal of the American Medical Informatics Association.