PT - JOURNAL ARTICLE AU - Thomas Desautels AU - Jana Hoffman AU - Christopher Barton AU - Qingqing Mao AU - Melissa Jay AU - Jacob Calvert AU - Ritankar Das TI - Pediatric Severe Sepsis Prediction Using Machine Learning AID - 10.1101/223289 DP - 2017 Jan 01 TA - bioRxiv PG - 223289 4099 - http://biorxiv.org/content/early/2017/11/22/223289.short 4100 - http://biorxiv.org/content/early/2017/11/22/223289.full AB - Early detection of pediatric severe sepsis is necessary in order to administer effective treatment. In this study, we assessed the efficacy of a machine-learning-based prediction algorithm applied to electronic healthcare record (EHR) data for the prediction of severe sepsis onset. The resulting prediction performance was compared with the Pediatric Logistic Organ Dysfunction score (PELOD-2) and pediatric Systemic Inflammatory Response Syndrome score (SIRS) using cross-validation and pairwise t-tests. EHR data were collected from a retrospective set of de-identified pediatric inpatient and emergency encounters drawn from the University of California San Francisco (UCSF) Medical Center, with encounter dates between June 2011 and March 2016. Patients (n = 11,127) were 2-17 years of age and 103 [0.93%] were labeled severely septic. In four-fold cross-validation evaluations, the machine learning algorithm achieved an AUROC of 0.912 for discrimination between severely septic and control pediatric patients at onset and AUROC of 0.727 four hours before onset. Under the same measure, the prediction algorithm also significantly outperformed PELOD-2 (p < 0.05) and SIRS (p < 0.05) in the prediction of severe sepsis four hours before onset. This machine learning algorithm has the potential to deliver high-performance severe sepsis detection and prediction for pediatric inpatients.AUROCarea under the receiver operating characteristic curveCVcross-validationDORdiagnostic odds ratioEHRelectronic health recordICD-9international classification of diseases, 9th revisionIQRinterquartile rangeMLmachine learningMLAmachine learning algorithmPELODPediatric Logistic Organ Dysfunction scoreROCreceiver operating characteristicSEstandard errorSIRSSystemic Inflammatory Response SyndromeUCSFUniversity of California San Francisco