Multi-Modal Contrastive Learning for Online Clinical Time-Series Applications
This work addresses the challenge of integrating clinical notes and time-series data for ICU applications, representing an incremental improvement over existing supervised methods.
The paper tackled the problem of leveraging diverse data modalities in ICU EHR datasets for online clinical prediction tasks by applying self-supervised multi-modal contrastive learning, resulting in excellent linear probe and zero-shot performance.
Electronic Health Record (EHR) datasets from Intensive Care Units (ICU) contain a diverse set of data modalities. While prior works have successfully leveraged multiple modalities in supervised settings, we apply advanced self-supervised multi-modal contrastive learning techniques to ICU data, specifically focusing on clinical notes and time-series for clinically relevant online prediction tasks. We introduce a loss function Multi-Modal Neighborhood Contrastive Loss (MM-NCL), a soft neighborhood function, and showcase the excellent linear probe and zero-shot performance of our approach.