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.
@article{arxiv.2403.18316,
title = {Multi-Modal Contrastive Learning for Online Clinical Time-Series Applications},
author = {Fabian Baldenweg and Manuel Burger and Gunnar Rätsch and Rita Kuznetsova},
journal= {arXiv preprint arXiv:2403.18316},
year = {2024}
}