Background: Increasing use of EHRs has generated widespread interest in the potential of computerized clinical decision support to improve treatment of sepsis. Electronic sepsis alerts have thus far had mixed results due to poor test characteristics, development from administrative data which cannot identify the onset of sepsis, and often use of outside software which limits generalizability. We describe validation of an accurate and timely severe sepsis alert embedded in a common commercial EHR platform (Epic Systems, Verona WI).
Methods: The sepsis alert was developed by identifying the most common severe sepsis criteria among a cohort of patients with ICD 9 codes indicating a diagnosis of sepsis. This alert requires criteria in three categories: indicators of a systemic inflammatory response, evidence of suspected infection from physician orders, and markers of end-organ dysfunction. Physician chart review was used to evaluate test performance and ability to detect clinical time zero, the point in time when a patient develops severe sepsis.
Results: Two physicians reviewed 100 positive cases and 75 negative cases. Based on this review, sensitivity was 74.5%, specificity was 86.0%, the positive predictive value was 50.3%, and the negative predictive value was 94.7%. The most common source of end-organ dysfunction was a MAP less than 70 mm/Hg (59%). The alert was triggered at clinical time zero in 41% of cases and within three hours of time zero in 59% of cases. 96% of alerts triggered before a manual nurse screen.
Conclusions: This is the first study to report the time between a sepsis alert and physician chart-review clinical time zero. Incorporating physician orders in the alert criteria improves specificity while maintaining reasonable sensitivity which is important to reduce alert fatigue. By leveraging out-of-the-box EHR functionality, this alert could be easily copied at many other healthcare systems.