HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 54 references that are in the map. First posted on arXiv 22 Apr 2026.
Builds on
21 of 54 references.
References · 21
- 2019Publicly Available Clinical BERT Embeddingscited by 1,002
- 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
- 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 349
- 2019BEHRT: Transformer for Electronic Health Recordscited by 263
- 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 162
- 2018emrQA: A Large Corpus for Question Answering on Electronic Medical Recordscited by 135
- 2018Hyperbolic Attention Networkscited by 122
- 2019Text-to-SQL Generation for Question Answering on Electronic Medical Recordscited by 77
- 2020Deep Representation Learning of Electronic Health Records to Unlock Patient Stratification at Scalecited by 39
- 2024EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summariescited by 35
- 2024Hyperbolic Fine-Tuning for Large Language Modelscited by 27
- 2025HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Expertscited by 26
9 more
- 2025Hyperbolic Deep Learning for Foundation Models: A Surveycited by 20
- 2022DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related Queriescited by 17
- 2021Self-Supervised Graph Learning with Hyperbolic Embedding for Temporal Health Event Predictioncited by 15
- 2025HMamba: Hyperbolic Mamba for Sequential Recommendationcited by 11
- 2023Question Answering for Electronic Health Records: A Scoping Review of datasets and modelscited by 7
- 2025Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddingscited by 6
- 2024Dynamic Q&A of Clinical Documents with Large Language Modelscited by 4
- 2025CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessmentcited by 3
- 2018Learning Contextual Hierarchical Structure of Medical Concepts with Poincair'e Embeddings to Clarify Phenotypescited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.