arXiv AI
SMI: Ontology-Grounded Semantic IDs for Hierarchy-Aware Medical Concept Representation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 28
HCOE: Hyperbolic Clinical Ontology Embeddings from Biomedical Language Models
The paper introduces Hyperbolic Clinical Ontology Embeddings (HCOE), a method that transforms frozen BioBERT embeddings into a Poincaré ball to capture medical code hierarchies. HCOE employs ontology-guided contrastive learning and coarse‑to‑fine ontology‑path aggregation, leveraging ICD, CCS, and ATC hierarchies. Experiments on MIMIC‑IV demonstrate superior performance in clinical relation prediction, hierarchy transfer, and various predictive tasks such as mortality, readmission, medication recommendation, and rare drug prediction.
arXiv Machine Learning
Sep 15
Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV
arXiv:2609.15713v1 Announce Type: new Abstract: Recent approaches to 30-day hospital readmission prediction rely on pre-trained language models applied to discharge summaries. Although these methods...
arXiv AI
1d ago
Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling
The paper introduces MEDIATOR, a discrete, ontology‑agnostic tokenizer that maps any clinical concept—whether encoded, synonymous, or free‑text—into a shared vector‑quantized codebook. By collapsing equivalent expressions and organizing distinct concepts in a medically meaningful space, MEDIATOR serves as the token interface for an EHR Transformer, boosting mean AUPRC by 4.0 points on 20 MIMIC‑III tasks and 8.6 points in zero‑shot transfer to 14 eICU tasks, while enabling full event coverage and transferable attribution across hospitals.
arXiv AI
Sep 15
Discovering Hierarchy-Grounded Domains with Adaptive Granularity for Clinical Domain Generalization
The paper introduces UdonCare, a hierarchy‑pruning method that iteratively partitions patients into latent domains using medical ontologies, aiming to improve domain generalization in clinical prediction tasks. It addresses challenges of missing domain labels and lack of clinical insight by discovering hierarchy‑grounded patient domains. Experiments on MIMIC‑III, MIMIC‑IV, and eICU datasets show UdonCare outperforms eight baseline methods across four prediction tasks with significant domain gaps.
arXiv AI
Jun 16
Hierarchical Modeling of ICD Codes in EHR Foundation Models
arXiv:2606. 15447v1 Announce Type: new Abstract: Electronic health record foundation models typically treat ICD diagnosis codes as flat tokens, overlooking the clinically meaningful hierarchical structure that captures disease families, subcategories, and fine-grained diagnostic detail.
arXiv AI
Jun 15
STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction
arXiv:2604. 09737v2 Announce Type: replace-cross Abstract: Structured prediction with large language models requires outputs that are label-accurate, ontology-constrained, structurally valid, and evidence-grounded under label imbalance and heterogeneous group difficulty.