Sepsis Trajectory Prediction Using Privileged Information and Continuous Physiological Signals

TL;DR

This study explores using privileged information and physiological signals to predict sepsis progression, finding that electrocardiogram data is informative for prognosis.

Contribution

The novel contribution is applying the privileged information paradigm to sepsis prognosis using signal processing techniques.

Findings

Privileged information improved signal-informed models in a small, critically ill cohort.

Electrocardiogram data was informative for predicting sepsis progression across both cohorts.

Learning using privileged information did not significantly improve results overall but shows promise for future study.

Abstract

The aim of this research is to apply the learning using privileged information paradigm to sepsis prognosis. We used signal processing of electrocardiogram and electronic health record data to construct support vector machines with and without privileged information to predict an increase in a given patient’s quick-Sequential Organ Failure Assessment score, using a retrospective dataset. We applied this to both a small, critically ill cohort and a broader cohort of patients in the intensive care unit. Within the smaller cohort, privileged information proved helpful in a signal-informed model, and across both cohorts, electrocardiogram data proved to be informative to creating the prediction. Although learning using privileged information did not significantly improve results in this study, it is a paradigm worth studying further in the context of using signal processing for sepsis prognosis.

Figures