Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping

Michael Moor, Max Horn, Bastian Rieck, Damian Roqueiro, Karsten Borgwardt
Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:2-26, 2019.

Abstract

Sepsis is a life-threatening host response to infection that is associated with high mortality, morbidity, and health costs. Its management is highly time-sensitive because each hour of delayed treatment increases mortality due to irreversible organ damage. Meanwhile, despite decades of clinical research, robust biomarkers for sepsis are missing. Therefore, detecting sepsis early by utilizing the affluence of high-resolution intensive care records has become a challenging machine learning problem. Recent advances in deep learning and data mining promise to deliver a powerful set of tools to efficiently address this task. This empirical study proposes two novel approaches for the early detection of sepsis: a deep learning model and a lazy learner that is based on time series distances. Our deep learning model employs a temporal convolutional network that is embedded in a multi-task Gaussian Process adapter framework, making it directly applicable to irregularly-spaced time series data. In contrast, our lazy learner is an ensemble approach that employs dynamic time warping. We frame the timely detection of sepsis as a supervised time series classification task. Consequently, we derive the most recent sepsis definition in an hourly resolution to provide the first fully accessible early sepsis detection environment. Seven hours before sepsis onset, our methods improve area under the precision–recall curve from 0.25 to 0.35 and 0.40, respectively, over the state of the art. This demonstrates that they are well-suited for detecting sepsis in the crucial earlier stages when management is most effective.

Cite this Paper


BibTeX
@InProceedings{pmlr-v106-moor19a, title = {Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping}, author = {Moor, Michael and Horn, Max and Rieck, Bastian and Roqueiro, Damian and Borgwardt, Karsten}, booktitle = {Proceedings of the 4th Machine Learning for Healthcare Conference}, pages = {2--26}, year = {2019}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {106}, series = {Proceedings of Machine Learning Research}, month = {09--10 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v106/moor19a/moor19a.pdf}, url = {https://proceedings.mlr.press/v106/moor19a.html}, abstract = {Sepsis is a life-threatening host response to infection that is associated with high mortality, morbidity, and health costs. Its management is highly time-sensitive because each hour of delayed treatment increases mortality due to irreversible organ damage. Meanwhile, despite decades of clinical research, robust biomarkers for sepsis are missing. Therefore, detecting sepsis early by utilizing the affluence of high-resolution intensive care records has become a challenging machine learning problem. Recent advances in deep learning and data mining promise to deliver a powerful set of tools to efficiently address this task. This empirical study proposes two novel approaches for the early detection of sepsis: a deep learning model and a lazy learner that is based on time series distances. Our deep learning model employs a temporal convolutional network that is embedded in a multi-task Gaussian Process adapter framework, making it directly applicable to irregularly-spaced time series data. In contrast, our lazy learner is an ensemble approach that employs dynamic time warping. We frame the timely detection of sepsis as a supervised time series classification task. Consequently, we derive the most recent sepsis definition in an hourly resolution to provide the first fully accessible early sepsis detection environment. Seven hours before sepsis onset, our methods improve area under the precision–recall curve from 0.25 to 0.35 and 0.40, respectively, over the state of the art. This demonstrates that they are well-suited for detecting sepsis in the crucial earlier stages when management is most effective.} }
Endnote
%0 Conference Paper %T Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping %A Michael Moor %A Max Horn %A Bastian Rieck %A Damian Roqueiro %A Karsten Borgwardt %B Proceedings of the 4th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2019 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v106-moor19a %I PMLR %P 2--26 %U https://proceedings.mlr.press/v106/moor19a.html %V 106 %X Sepsis is a life-threatening host response to infection that is associated with high mortality, morbidity, and health costs. Its management is highly time-sensitive because each hour of delayed treatment increases mortality due to irreversible organ damage. Meanwhile, despite decades of clinical research, robust biomarkers for sepsis are missing. Therefore, detecting sepsis early by utilizing the affluence of high-resolution intensive care records has become a challenging machine learning problem. Recent advances in deep learning and data mining promise to deliver a powerful set of tools to efficiently address this task. This empirical study proposes two novel approaches for the early detection of sepsis: a deep learning model and a lazy learner that is based on time series distances. Our deep learning model employs a temporal convolutional network that is embedded in a multi-task Gaussian Process adapter framework, making it directly applicable to irregularly-spaced time series data. In contrast, our lazy learner is an ensemble approach that employs dynamic time warping. We frame the timely detection of sepsis as a supervised time series classification task. Consequently, we derive the most recent sepsis definition in an hourly resolution to provide the first fully accessible early sepsis detection environment. Seven hours before sepsis onset, our methods improve area under the precision–recall curve from 0.25 to 0.35 and 0.40, respectively, over the state of the art. This demonstrates that they are well-suited for detecting sepsis in the crucial earlier stages when management is most effective.
APA
Moor, M., Horn, M., Rieck, B., Roqueiro, D. & Borgwardt, K.. (2019). Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping. Proceedings of the 4th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 106:2-26 Available from https://proceedings.mlr.press/v106/moor19a.html.

Related Material