Neighborhood Contrastive Learning Applied to Online Patient Monitoring

Hugo Yèche, Gideon Dresdner, Francesco Locatello, Matthias Hüser, Gunnar Rätsch
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11964-11974, 2021.

Abstract

Intensive care units (ICU) are increasingly looking towards machine learning for methods to provide online monitoring of critically ill patients. In machine learning, online monitoring is often formulated as a supervised learning problem. Recently, contrastive learning approaches have demonstrated promising improvements over competitive supervised benchmarks. These methods rely on well-understood data augmentation techniques developed for image data which do not apply to online monitoring. In this work, we overcome this limitation by supplementing time-series data augmentation techniques with a novel contrastive learning objective which we call neighborhood contrastive learning (NCL). Our objective explicitly groups together contiguous time segments from each patient while maintaining state-specific information. Our experiments demonstrate a marked improvement over existing work applying contrastive methods to medical time-series.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-yeche21a, title = {Neighborhood Contrastive Learning Applied to Online Patient Monitoring}, author = {Y{\`e}che, Hugo and Dresdner, Gideon and Locatello, Francesco and H{\"u}ser, Matthias and R{\"a}tsch, Gunnar}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {11964--11974}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/yeche21a/yeche21a.pdf}, url = {https://proceedings.mlr.press/v139/yeche21a.html}, abstract = {Intensive care units (ICU) are increasingly looking towards machine learning for methods to provide online monitoring of critically ill patients. In machine learning, online monitoring is often formulated as a supervised learning problem. Recently, contrastive learning approaches have demonstrated promising improvements over competitive supervised benchmarks. These methods rely on well-understood data augmentation techniques developed for image data which do not apply to online monitoring. In this work, we overcome this limitation by supplementing time-series data augmentation techniques with a novel contrastive learning objective which we call neighborhood contrastive learning (NCL). Our objective explicitly groups together contiguous time segments from each patient while maintaining state-specific information. Our experiments demonstrate a marked improvement over existing work applying contrastive methods to medical time-series.} }
Endnote
%0 Conference Paper %T Neighborhood Contrastive Learning Applied to Online Patient Monitoring %A Hugo Yèche %A Gideon Dresdner %A Francesco Locatello %A Matthias Hüser %A Gunnar Rätsch %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-yeche21a %I PMLR %P 11964--11974 %U https://proceedings.mlr.press/v139/yeche21a.html %V 139 %X Intensive care units (ICU) are increasingly looking towards machine learning for methods to provide online monitoring of critically ill patients. In machine learning, online monitoring is often formulated as a supervised learning problem. Recently, contrastive learning approaches have demonstrated promising improvements over competitive supervised benchmarks. These methods rely on well-understood data augmentation techniques developed for image data which do not apply to online monitoring. In this work, we overcome this limitation by supplementing time-series data augmentation techniques with a novel contrastive learning objective which we call neighborhood contrastive learning (NCL). Our objective explicitly groups together contiguous time segments from each patient while maintaining state-specific information. Our experiments demonstrate a marked improvement over existing work applying contrastive methods to medical time-series.
APA
Yèche, H., Dresdner, G., Locatello, F., Hüser, M. & Rätsch, G.. (2021). Neighborhood Contrastive Learning Applied to Online Patient Monitoring. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:11964-11974 Available from https://proceedings.mlr.press/v139/yeche21a.html.

Related Material