Predicting Septic Shock and Its Progression

Friday, September 27, 2019 -
2:00pm to 3:00pm
The FUNG Auditorium
Raimond L. Winslow

The Raj and Neera Singh Professor, Biomedical Engineering

Director, Institute for Computational Medicine

Director, BME-MSE Program

Vice Chair of Academic Programs, BME

The Johns Hopkins University School of Medicine

Predicting Septic Shock and Its Progression

Septic shock is a life-threatening condition in which timely treatment substantially reduces mortality. Reliable identification of patients with sepsis who are at elevated risk of developing septic shock therefore has the potential to save lives by opening an early window of intervention. We hypothesized the existence of a novel clinical state of sepsis referred to as the “pre-shock” state, and that patients with sepsis who enter this state are highly likely to develop septic shock at some future time. We applied three different machine learning techniques to the electronic health record data of 15,930 patients in the MIMIC-III database to test this hypothesis. This novel paradigm yields improved performance in predicting those patients with sepsis who will progress to septic shock with the best method achieving a 0.93 area under the receiver operating curve, 88% sensitivity, 84% specificity, and median early warning time of 7 hours. Additionally, we introduce the notion of patient-specific positive predictive value, assigning confidence to individual predictions, and achieving values as high as 90%. Reliable early prediction of impending septic shock, and thus early intervention, is possible many hours in advance (Liu et al 2019, Nat. Sci. Rept. 9: 6145)

Dr. Winslow is the Raj and Neera Singh Professor of Biomedical Engineering, and Founding Director of the Institute for Computational Medicine at Johns Hopkins University. His research is focused on two areas. The first is use of computational modeling to understand the molecular mechanisms of cardiac arrhythmias and sudden death. The second is use of statistical and dynamical systems modeling methods to predict the temporal evolution of patient clinical state. He holds joints appointments in the departments of Electrical and Computer Engineering, Computer Science, and the Division of Health Care Information Sciences at Johns Hopkins University.