@inproceedings{lee-etal-2026-emr,
title = "{EMR}-{AGENT}: An {LLM} Agent Framework for Cohort and Feature Extraction from Heterogeneous {EHR} Databases",
author = "Lee, Kwanhyung and
Hong, Sungsoo and
Park, Joonhyung and
Lim, Jeonghyeop and
Choi, Juhwan and
Yoon, Donghwee and
Yang, Eunho",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2210/",
pages = "47341--47373",
ISBN = "979-8-89176-462-0",
abstract = "Electronic 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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-emr">
<titleInfo>
<title>EMR-AGENT: An LLM Agent Framework for Cohort and Feature Extraction from Heterogeneous EHR Databases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kwanhyung</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungsoo</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joonhyung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeonghyeop</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juhwan</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghwee</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunho</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Electronic 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.</abstract>
<identifier type="citekey">lee-etal-2026-emr</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2210/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>47341</start>
<end>47373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EMR-AGENT: An LLM Agent Framework for Cohort and Feature Extraction from Heterogeneous EHR Databases
%A Lee, Kwanhyung
%A Hong, Sungsoo
%A Park, Joonhyung
%A Lim, Jeonghyeop
%A Choi, Juhwan
%A Yoon, Donghwee
%A Yang, Eunho
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F lee-etal-2026-emr
%X Electronic 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.
%U https://aclanthology.org/2026.findings-emnlp.2210/
%P 47341-47373
Markdown (Informal)
[EMR-AGENT: An LLM Agent Framework for Cohort and Feature Extraction from Heterogeneous EHR Databases](https://aclanthology.org/2026.findings-emnlp.2210/) (Lee et al., Findings 2026)
ACL