Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier

06/13/2017
by   Joseph Futoma, et al.
0

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 the Receiver Operating Characteristic and Precision Recall curves as compared to the NEWS score currently used by our hospital.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/19/2017

An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection

Sepsis is a poorly understood and potentially life-threatening complicat...
research
06/14/2016

A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification

We present a general framework for classification of sparse and irregula...
research
05/04/2022

GRU-TV: Time- and velocity-aware GRU for patient representation on multivariate clinical time-series data

Electronic health records (EHRs) provide a rich repository to track a pa...
research
06/01/2019

Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes

Multi-output Gaussian processes (GPs) are a flexible Bayesian nonparamet...
research
04/30/2021

Predicting Intraoperative Hypoxemia with Joint Sequence Autoencoder Networks

We present an end-to-end model using streaming physiological time series...
research
02/01/2021

Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network

We propose a robust in-time predictor for in-hospital COVID-19 patient's...
research
09/22/2022

Optimal Stopping with Gaussian Processes

We propose a novel group of Gaussian Process based algorithms for fast a...

Please sign up or login with your details

Forgot password? Click here to reset