Neighborhood Contrastive Learning Applied to Online Patient Monitoring
This work addresses the need for better online monitoring of critically ill patients in ICUs, representing an incremental improvement in applying contrastive learning to medical time-series data.
The paper tackled the problem of online patient monitoring in ICUs by introducing neighborhood contrastive learning (NCL), which groups contiguous time segments from patient data to improve performance over existing contrastive methods for medical time-series.
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.