Neighborhood Contrastive Learning Applied to Online Patient Monitoring
Hugo Yèche, Gideon Dresdner, Francesco Locatello, Matthias Hüser, Gunnar Rätsch
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.
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.}
}