Reproduce “Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tong Ding, Caiwei Tian, Dongmin Bang, Ming Y. Lu, Sophia J. Wagner, Andrew Zhang, Rowland Pettit, Long Phi Le and 1 more
MEDIATOR maps clinical descriptions across code systems to a shared, fixed vector-quantized codebook, allowing new strings to use existing tokens. It groups synonym views and uses descriptions, co-occurrence, and medical relations to organize tokens. Across 20 MIMIC-III tasks, it improves mean AUPRC by 4.0 points over MedTok; across 14 zero-shot eICU tasks, by 8.6 points, partly reflecting greater event coverage.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.