HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911616482672640 |
|---|---|
| author | Liu, Yuyu Patil, Sarang Rajendra Xu, Mengjia Ma, Tengfei |
| author_facet | Liu, Yuyu Patil, Sarang Rajendra Xu, Mengjia Ma, Tengfei |
| contents | Electronic health record (EHR) question answering is often handled by LLM-based pipelines that are costly to deploy and do not explicitly leverage the hierarchical structure of clinical data. Motivated by evidence that medical ontologies and patient trajectories exhibit hyperbolic geometry, we propose HypEHR, a compact Lorentzian model that embeds codes, visits, and questions in hyperbolic space and answers queries via geometry-consistent cross-attention with type-specific pointer heads. HypEHR is pretrained with next-visit diagnosis prediction and hierarchy-aware regularization to align representations with the ICD ontology. On two MIMIC-IV-based EHR-QA benchmarks, HypEHR approaches LLM-based methods while using far fewer parameters. Our code is publicly available at https://github.com/yuyuliu11037/HypEHR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21027 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering Liu, Yuyu Patil, Sarang Rajendra Xu, Mengjia Ma, Tengfei Artificial Intelligence Electronic health record (EHR) question answering is often handled by LLM-based pipelines that are costly to deploy and do not explicitly leverage the hierarchical structure of clinical data. Motivated by evidence that medical ontologies and patient trajectories exhibit hyperbolic geometry, we propose HypEHR, a compact Lorentzian model that embeds codes, visits, and questions in hyperbolic space and answers queries via geometry-consistent cross-attention with type-specific pointer heads. HypEHR is pretrained with next-visit diagnosis prediction and hierarchy-aware regularization to align representations with the ICD ontology. On two MIMIC-IV-based EHR-QA benchmarks, HypEHR approaches LLM-based methods while using far fewer parameters. Our code is publicly available at https://github.com/yuyuliu11037/HypEHR. |
| title | HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.21027 |