English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Intensive care units (ICU) are increasingly looking towards machine learningfor methods to provide online monitoring of critically ill patients. In machinelearning, online monitoring is often formulated as a supervised learningproblem. Recently, contrastive learning approaches have demonstrated promisingimprovements over competitive supervised benchmarks. These methods rely onwell-understood data augmentation techniques developed for image data which donot apply to online monitoring. In this work, we overcome this limitation bysupplementing time-series data augmentation techniques with a novel contrastivelearning objective which we call neighborhood contrastive learning (NCL). Ourobjective explicitly groups together contiguous time segments from each patientwhile maintaining state-specific information. Our experiments demonstrate amarked improvement over existing work applying contrastive methods to medicaltime-series.

Neighborhood Contrastive Learning Applied to Online Patient Monitoring