Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier

Joseph Futoma, Sanjay Hariharan, Katherine Heller
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:1174-1182, 2017.

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v70-futoma17a, title = {Learning to Detect Sepsis with a Multitask {G}aussian Process {RNN} Classifier}, author = {Joseph Futoma and Sanjay Hariharan and Katherine Heller}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {1174--1182}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/futoma17a/futoma17a.pdf}, url = {https://proceedings.mlr.press/v70/futoma17a.html}, 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.} }
Endnote
%0 Conference Paper %T Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier %A Joseph Futoma %A Sanjay Hariharan %A Katherine Heller %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-futoma17a %I PMLR %P 1174--1182 %U https://proceedings.mlr.press/v70/futoma17a.html %V 70 %X 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.
APA
Futoma, J., Hariharan, S. & Heller, K.. (2017). Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:1174-1182 Available from https://proceedings.mlr.press/v70/futoma17a.html.

Related Material