EHR Data Can Be Leveraged To Accurately Predict Sepsis, Study Finds
March 19, 2014 in News
Electronic health records can be used to predict the development of sepsis in an individual and his or her likely outcome if infected, according to a study published in the Journal of the American Medical Informatics Association, Health Data Management reports.
Background on Sepsis
Sepsis is a leading cause of death and hospitalization in the U.S., affecting more than 750,000 individuals annually. Thirty-three percent of sepsis cases result in death.
However, 30% of deaths or serious health problems stemming from sepsis are preventable, according to Health Data Management (Slabodkin, Health Data Management, 3/17).
The study was conducted by researchers from the University of California-Davis with funding from the Center for Information Technology Research in the Interest of Society and NIH’s National Center for Advancing Translational Sciences.
For the study, researchers analyzed EHR data of 741 patients diagnosed with sepsis, including patients’:
- Blood pressure;
- Respiratory rate;
- Temperature; and
- White blood cell count (Walsh, Clinical Innovation Technology, 3/17).
The study found that patients’ vital signs and white blood cell counts can be used to accurately predict sepsis.
It also found that researchers could determine an individual’s risk of death from contracting the disease by analyzing patients’:
- Blood pressure;
- Lactate level; and
- Respiratory rate (Health Data Management, 3/17).
The researchers are using the findings to develop an algorithm that can be used to create EHR alerts and provide instant information for health care providers (Bresnick, EHR Intelligence, 3/17).
Ilias Tagkopoulos — assistant professor of computer science at UC-Davis and senior author of the study — in a statement said, “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” (Health Data Management, 3/17).