Skip to content
conftrace_
2026 EMNLP EMNLP 2026

EMR-AGENT: An LLM Agent Framework for Cohort and Feature Extraction from Heterogeneous EHR Databases

AbstractElectronic medical record (EMR) databases are widely used for clinical machine learning, but their preprocessing remains difficult to reproduce because cohort definitions, patient-level features, and clinical item-code mappings must be adapted to each database schema. We formulate EMR preprocessing as the task of translating study requests into database-specific cohort/feature extraction SQL and local clinical item-code mappings. Existing preprocessing and harmonization frameworks remain difficult to adapt because they rely on dataset-specific rules or predefined input formats. We introduce EMR-AGENT, an LLM-agent framework that reduces reliance on manual rule writing by automating database-specific cohort selection, feature extraction, and clinical code mapping from study requests. EMR-AGENT retrieves schema and documentation context, interacts with live databases through SQL, observes execution results, and refines extraction decisions from error feedback. To enable rigorous evaluation, we develop a benchmarking codebase for three intensive care unit (ICU) databases (MIMIC-III, eICU, and SICdb), covering reference databases and a newer SICdb version released after the backbone’s knowledge cutoff. Across these benchmarks, EMR-AGENT reduces schema-debugging and item-code search effort, enabling reproducible evaluation of preprocessing quality under expert review, while reducing reliance on hand-written database-specific pipelines.

More from EMNLP 2026

All EMNLP 2026 papers →