Related Experiment Video
Updated: Mar 19, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Predicting Sepsis Risk Using the "Sniffer" Algorithm in the Electronic Medical Record
Evelyn M Olenick1, Kathie S Zimbro, Gabrielle M DʼLima
1Sentara CarePlex Hospital, Hampton, Virginia (Dr Olenick); Phoebe Putney Memorial Hospital, Albany, Georgia (Dr Olenick); Quality Research Institute, Clinical & Business Intelligence, Sentara Healthcare, Virginia Beach, Virginia (Dr Zimbro); and Sentara Healthcare, Virginia Beach, Virginia (Dr D'Lima and Mss Ver Schneider and Jones).
Abstract:
The Sepsis "Sniffer" Algorithm (SSA) has merit as a digital sepsis alert but should be considered an adjunct to versus an alternative for the Nurse Screening Tool (NST), given lower specificity and positive predictive value. The SSA reduced the risk of incorrectly categorizing patients at low risk for sepsis, detected sepsis high risk in half the time, and reduced redundant NST screens by 70% and manual screening hours by 64% to 72%. Preserving nurse hours expended on manual sepsis alerts may translate into time directed toward other patient priorities.
