Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwon, Yeonsu, Kim, Jiho, Choi, Junseong, Rabaey, Paloma, Kim, Minseo, Im, Sujeong, Yang, Jeewon, Lee, Jun-Min, Lee, Sangji, Kim, Jiwon, Yoon, Hangyul, Kwon, Hyunwook, Choi, Edward
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917533679878144
author Kwon, Yeonsu
Kim, Jiho
Choi, Junseong
Rabaey, Paloma
Kim, Minseo
Im, Sujeong
Yang, Jeewon
Lee, Jun-Min
Lee, Sangji
Kim, Jiwon
Yoon, Hangyul
Kwon, Hyunwook
Choi, Edward
author_facet Kwon, Yeonsu
Kim, Jiho
Choi, Junseong
Rabaey, Paloma
Kim, Minseo
Im, Sujeong
Yang, Jeewon
Lee, Jun-Min
Lee, Sangji
Kim, Jiwon
Yoon, Hangyul
Kwon, Hyunwook
Choi, Edward
contents Data consistency between unstructured clinical notes and structured tables in Electronic Health Records (EHRs) is essential for patient safety and clinical decision-making. However, existing work on note-table consistency verification mainly relies on surface-level matching of numeric values or simple events. Such approaches fail to capture the reasoning underlying real-world EHR documentation, including clinical interpretation, event relations, and temporal changes. To address this gap, we introduce EHR-ReasonCon, a reasoning-intensive benchmark for note-table consistency verification. Built on MIMIC-III with expert-guided annotations, it comprises 8,048 entities derived from clinical notes and provides high-quality ground-truth labels. The annotation protocol is supported by specialized table-exploration tools to ensure systematic evidence retrieval and reliable consistency assessment. We also propose EHR-Inspector, an LLM-based framework that segments notes, extracts anchor entities and temporal references, and uses table-exploration tools to verify consistency against structured tables. Evaluated using expert-validated LLM-as-a-judge metrics under harsh and lenient criteria, EHR-Inspector achieves state-of-the-art performance across multiple model backbones. Analyses further demonstrate the effectiveness of its components and highlight differences from human verification.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26463
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records
Kwon, Yeonsu
Kim, Jiho
Choi, Junseong
Rabaey, Paloma
Kim, Minseo
Im, Sujeong
Yang, Jeewon
Lee, Jun-Min
Lee, Sangji
Kim, Jiwon
Yoon, Hangyul
Kwon, Hyunwook
Choi, Edward
Computation and Language
Artificial Intelligence
Data consistency between unstructured clinical notes and structured tables in Electronic Health Records (EHRs) is essential for patient safety and clinical decision-making. However, existing work on note-table consistency verification mainly relies on surface-level matching of numeric values or simple events. Such approaches fail to capture the reasoning underlying real-world EHR documentation, including clinical interpretation, event relations, and temporal changes. To address this gap, we introduce EHR-ReasonCon, a reasoning-intensive benchmark for note-table consistency verification. Built on MIMIC-III with expert-guided annotations, it comprises 8,048 entities derived from clinical notes and provides high-quality ground-truth labels. The annotation protocol is supported by specialized table-exploration tools to ensure systematic evidence retrieval and reliable consistency assessment. We also propose EHR-Inspector, an LLM-based framework that segments notes, extracts anchor entities and temporal references, and uses table-exploration tools to verify consistency against structured tables. Evaluated using expert-validated LLM-as-a-judge metrics under harsh and lenient criteria, EHR-Inspector achieves state-of-the-art performance across multiple model backbones. Analyses further demonstrate the effectiveness of its components and highlight differences from human verification.
title Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.26463