arXiv Artificial Intelligence

HCOE: Hyperbolic Clinical Ontology Embeddings from Biomedical Language Models

1 hour ago 28.09.2026 07:00 👁 1 views
HCOE: Hyperbolic Clinical Ontology Embeddings from Biomedical Language Models

Quick summary

arXiv:2609.30763v1 Announce Type: new Abstract: Biomedical language models (LMs) encode textual semantics but do not explicitly preserve medical code hierarchies. We present Hyperbolic Clinical Ontology Embeddings (HCOE) for hierarchy-aware clinical concept representation. HCOE maps frozen BioBERT embeddings into a Poincare ball, combining parent-side and child-side ontology-guided contrastive learning with coarse-to-fine ontology-path aggregation. It uses International Classification of Diseases (ICD) codes organized by Clinical Classifications Software (CCS) and Anatomical Therapeutic Chemic

Key takeaways

  • arXiv:2609.30763v1 Announce Type: new Abstract: Biomedical language models (LMs) encode textual semantics but do not explicitly preserve medical code hierarchies.
  • We present Hyperbolic Clinical Ontology Embeddings (HCOE) for hierarchy-aware clinical concept representation.
  • HCOE maps frozen BioBERT embeddings into a Poincare ball, combining parent-side and child-side ontology-guided contrastive learning with coarse-to-fine ontology-path aggregation.

Why it matters

“HCOE: Hyperbolic Clinical Ontology Embeddings from Biomedical Language Models” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗