Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier

TL;DR

This paper introduces a scalable end-to-end classifier combining multitask Gaussian processes and RNNs to predict sepsis from streaming clinical data, outperforming existing methods.

Contribution

It presents a novel framework that models multivariate physiological time series with Gaussian processes integrated with a neural classifier, handling missing data and irregular sampling.

Findings

Outperforms baseline models in sepsis prediction

Achieves 19.4% higher ROC AUC than NEWS score

Achieves 55.5% higher Precision-Recall AUC than NEWS score

Abstract

We present a scalable end-to-end classifier that uses streaming physiological and medication data to accurately predict the onset of sepsis, a life-threatening complication from infections that has high mortality and morbidity. Our proposed framework models the multivariate trajectories of continuous-valued physiological time series using multitask Gaussian processes, seamlessly accounting for the high uncertainty, frequent missingness, and irregular sampling rates typically associated with real clinical data. The Gaussian process is directly connected to a black-box classifier that predicts whether a patient will become septic, chosen in our case to be a recurrent neural network to account for the extreme variability in the length of patient encounters. We show how to scale the computations associated with the Gaussian process in a manner so that the entire system can be discriminatively trained end-to-end using backpropagation. In a large cohort of heterogeneous inpatient encounters at our university health system we find that it outperforms several baselines at predicting sepsis, and yields 19.4% and 55.5% improved areas under the Receiver Operating Characteristic and Precision Recall curves as compared to the NEWS score currently used by our hospital.