New EHR models leverage ICD code hierarchy for improved predictions

Researchers have developed new methods for electronic health record (EHR) foundation models to better utilize the hierarchical structure of ICD diagnosis codes. Current models treat these codes as flat tokens, ignoring their inherent relationships. This work explores augmenting BERT-style transformers with hierarchical tokens and incorporating hierarchy into graph-based code representations. Experiments on MIMIC-IV and eICU datasets demonstrate that explicitly encoding ICD hierarchy improves downstream prediction accuracy and cross-dataset transferability, with the most effective hierarchy level varying by task and model. AI

RANK_REASON Research paper published on arXiv detailing novel methods for EHR foundation models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Bert
• electronic health records
• Hugging Face
• ICD-10 Clinical Modification
• International Statistical Classification of Diseases and Related Health Problems
• MIMIC-IV

• paper
• model release
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →