Can a Computerized Sepsis Screening and Alert System Accurately Diagnose Sepsis in Hospitalized Floor Patients and Potentially Provide Opportunities for Early Intervention? A Pilot Study

Abstract

Title: Can a Computerized Sepsis Screening and Alert System Accurately Diagnose Sepsis in Hospitalized Floor Patients and Potentially Provide Opportunities for Early Intervention? A Pilot Study. Background: Sepsis Syndromes are major causes of morbidity and mortality for hospitalized patients. Several evidence-based interventions have been shown to improve outcomes but they must be instituted early to achieve better outcomes. However, early recognition of sepsis syndromes in hospitalized patients is challenging. Regrettably, SIRS is overly sensitive and not specific in the patient populations at greatest risk for developing sepsis. In addition, many hospitalized patients have baseline end-organ dysfunction, wherein subtle trends in laboratory abnormalities may escape detection. Electronic detection and alert systems offer a more focused and efficient methodology. This strategy has been deployed successfully in other aspects of critical care, e.g. in the early recognition of acute respiratory distress syndrome. We developed an electronic recognition and alert system to identify floor patients with sepsis syndromes. The objective of this study was to test the feasibility, accuracy, and potential value of a computerized sepsis screening and alert system in a large university hospital. Methods and findings: The sepsis alert used an abnormal white blood cell count coupled with a blood culture order to define sepsis. Cases were categorized as severe sepsis by meeting specified changes in laboratory tests for organ dysfunction in accordance with consensus conference criteria. Using a retrospective cohort study design, we evaluated 97 consecutive, non-intensive care unit patients who triggered a sepsis alert at a large, urban, academic medical center. The charts of the patients were reviewed and abstracted manually to determine whether sepsis was present. For confirmed sepsis cases, we determined adherence with sepsis care bundle measures, including the recognition of sepsis (using physician documentation as a proxy measure), measurement of serum lactate, administration of antibiotics, and intravenous fluid resuscitation for severe sepsis cases. Within the 97 patient cohort, 72 were confirmed to have sepsis or severe sepsis (positive predictive value of 74%). Sepsis or severe sepsis was not documented in 79%, serum lactate was not measured in 57%, antibiotics were not administered in 14% of patients with severe sepsis, and fluid boluses were not administered in 17% of patients with severe sepsis who had lactic acidosis, hypotension, and/or acute kidney injury. In patients with sepsis or severe sepsis, adherence to the complete sepsis bundle did not occur in 65%. Opportunities to improve sepsis care were more common when sepsis was not documented. Conclusion: A computerized sepsis screening and alert system designed to identify sepsis in hospitalized medical ward patients without the use of vital signs was feasible to implement and predictive for sepsis. This suggests that implementation of this system may improve the quality of sepsis care in hospitalized ward patients.