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

Joseph Futoma, Sanjay Hariharan, Katherine Heller, Mark Sendak, Nathan Brajer, Meredith Clement, Armando Bedoya, Cara O’Brien
Proceedings of the 2nd Machine Learning for Healthcare Conference, PMLR 68:243-254, 2017.

Abstract

Sepsis is a poorly understood and potentially life-threatening complication that can occur as a result of infection. Early detection and treatmenz improves patient outcomes, and as such it poses an important challenge in medicine. In this work, we develop a flexible classifier that leverages streaming lab results, vitals, and medications to predict sepsis before it occurs. We model patient clinical time series with multi-output Gaussian processes, maintaining uncertainty about the physiological state of a patient while also imputing missing values. The mean function takes into account the effects of medications administered on the trajectories of the physiological variables. Latent function values from the Gaussian process are then fed into a deep recurrent neural network to classify patient encounters as septic or not, and the overall model is trained end-to-end using back-propagation. We train and validate our model on a large dataset of 18 months of heterogeneous inpatient stays from the Duke University Health System, and develop a new “real-time” validation scheme for simulat-ing the performance of our model as it will actually be used. Our proposed method substantially outperforms clinical baselines, and improves on a previous related model for detecting sepsis. Our model’s predictions will be displayed in a real-time analytics dashboard to be used by a sepsis rapid response team to help detect and improve treatment of sepsis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v68-futoma17a, title = {An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection}, author = {Futoma, Joseph and Hariharan, Sanjay and Heller, Katherine and Sendak, Mark and Brajer, Nathan and Clement, Meredith and Bedoya, Armando and O’Brien, Cara}, booktitle = {Proceedings of the 2nd Machine Learning for Healthcare Conference}, pages = {243--254}, year = {2017}, editor = {Doshi-Velez, Finale and Fackler, Jim and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {68}, series = {Proceedings of Machine Learning Research}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v68/futoma17a/futoma17a.pdf}, url = {https://proceedings.mlr.press/v68/futoma17a.html}, abstract = {Sepsis is a poorly understood and potentially life-threatening complication that can occur as a result of infection. Early detection and treatmenz improves patient outcomes, and as such it poses an important challenge in medicine. In this work, we develop a flexible classifier that leverages streaming lab results, vitals, and medications to predict sepsis before it occurs. We model patient clinical time series with multi-output Gaussian processes, maintaining uncertainty about the physiological state of a patient while also imputing missing values. The mean function takes into account the effects of medications administered on the trajectories of the physiological variables. Latent function values from the Gaussian process are then fed into a deep recurrent neural network to classify patient encounters as septic or not, and the overall model is trained end-to-end using back-propagation. We train and validate our model on a large dataset of 18 months of heterogeneous inpatient stays from the Duke University Health System, and develop a new “real-time” validation scheme for simulat-ing the performance of our model as it will actually be used. Our proposed method substantially outperforms clinical baselines, and improves on a previous related model for detecting sepsis. Our model’s predictions will be displayed in a real-time analytics dashboard to be used by a sepsis rapid response team to help detect and improve treatment of sepsis.} }
Endnote
%0 Conference Paper %T An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection %A Joseph Futoma %A Sanjay Hariharan %A Katherine Heller %A Mark Sendak %A Nathan Brajer %A Meredith Clement %A Armando Bedoya %A Cara O’Brien %B Proceedings of the 2nd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2017 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v68-futoma17a %I PMLR %P 243--254 %U https://proceedings.mlr.press/v68/futoma17a.html %V 68 %X Sepsis is a poorly understood and potentially life-threatening complication that can occur as a result of infection. Early detection and treatmenz improves patient outcomes, and as such it poses an important challenge in medicine. In this work, we develop a flexible classifier that leverages streaming lab results, vitals, and medications to predict sepsis before it occurs. We model patient clinical time series with multi-output Gaussian processes, maintaining uncertainty about the physiological state of a patient while also imputing missing values. The mean function takes into account the effects of medications administered on the trajectories of the physiological variables. Latent function values from the Gaussian process are then fed into a deep recurrent neural network to classify patient encounters as septic or not, and the overall model is trained end-to-end using back-propagation. We train and validate our model on a large dataset of 18 months of heterogeneous inpatient stays from the Duke University Health System, and develop a new “real-time” validation scheme for simulat-ing the performance of our model as it will actually be used. Our proposed method substantially outperforms clinical baselines, and improves on a previous related model for detecting sepsis. Our model’s predictions will be displayed in a real-time analytics dashboard to be used by a sepsis rapid response team to help detect and improve treatment of sepsis.
APA
Futoma, J., Hariharan, S., Heller, K., Sendak, M., Brajer, N., Clement, M., Bedoya, A. & O’Brien, C.. (2017). An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection. Proceedings of the 2nd Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 68:243-254 Available from https://proceedings.mlr.press/v68/futoma17a.html.

Related Material