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

• URL: http://arxiv.org/abs/2605.26463v1
• Date: Tue, 26 May 2026 02:19:42 GMT
• Title: Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records
• Abstract summary: We introduce EHR-ReasonCon, a reasoning-intensive benchmark for note-table consistency verification.<n>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.
• Score: 19.696931844348814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records [0.056212519098516295]
  BERT-LER is a BERT-style model for coded EHR timelines pretrained and fine-tuned from a de-identified EHR dataset of 75 million patients.<n>We benchmark our approach on the public EHRShot benchmark suite and on an asthma severity progression study based on real-world data.<n>Our architecture and explainability approach can be applied to many therapeutic areas and prediction tasks using language models trained on structured EHRs.
  arXiv  Detail & Related papers  (2026-08-20T17:54:17Z)
• WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records [1.585843510099207]
  WISTERIA is a weakly supervised representation learning framework.<n>It learns representations by enforcing consistency across their induced label distributions.<n>It improves predictive performance across standard EHR benchmarks.
  arXiv  Detail & Related papers  (2026-05-10T21:25:41Z)
• Systematic Evaluation of Large Language Models for Post-Discharge Clinical Action Extraction [0.0]
  This paper evaluates zero-shot and few-shot large language models (LLMs) for safety-critical clinical action extraction using the CLIP discharge-note dataset.<n>We introduce a two-stage extraction framework that decomposes discharge notes, that are written in narrative form, into fine-grained, explicitly actionable clinical tasks.
  arXiv  Detail & Related papers  (2026-05-07T13:05:07Z)
• CT-FineBench: A Diagnostic Fidelity Benchmark for Fine-Grained Evaluation of CT Report Generation [51.11942945171396]
  Conventional evaluation metrics offer only coarse measures of lexical overlap or entity matching.<n>We propose CT-FineBench, a benchmark built from CT-RATE and Merlin to evaluate the fine-grained factual consistency of CT reports.<n>Our benchmark is constructed through a meticulous, Question-Answering (QA) based process.
  arXiv  Detail & Related papers  (2026-04-27T03:32:46Z)
• Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity [66.94391219005291]
  This paper proposes Agentic Cognitive Profiling (ACP), an agentic framework that realigns automated screening with clinical protocol logic.<n>Central to our design is decoupling semantic understanding from measurement by delegating all quantification to deterministic function calling.<n>ACP achieves 90.5% score match rate in task examination and 85.3% accuracy in AD prediction, surpassing popular baselines.
  arXiv  Detail & Related papers  (2026-03-18T06:15:35Z)
• AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization [6.99563009617414]
  We present AgenticSum, an inference-time framework that separates context selection, generation, verification, and targeted correction to reduce hallucinated content.<n>We evaluate AgenticSum on two public datasets, using reference-based metrics, LLM-as-a-judge assessment, and human evaluation.<n>Our results indicate that structured, agentic design with targeted correction offers an effective inference time solution to improve clinical note summarization.
  arXiv  Detail & Related papers  (2026-02-23T16:49:37Z)
• AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning [73.50200033931148]
  We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists.<n>By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback.<n> Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations.
  arXiv  Detail & Related papers  (2026-01-23T11:59:13Z)
• RaTEScore: A Metric for Radiology Report Generation [59.37561810438641]
  This paper introduces a novel, entity-aware metric, as Radiological Report (Text) Evaluation (RaTEScore) RaTEScore emphasizes crucial medical entities such as diagnostic outcomes and anatomical details, and is robust against complex medical synonyms and sensitive to negation expressions. Our evaluations demonstrate that RaTEScore aligns more closely with human preference than existing metrics, validated both on established public benchmarks and our newly proposed RaTE-Eval benchmark.
  arXiv  Detail & Related papers  (2024-06-24T17:49:28Z)
• EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records [14.69982800306006]
  EHRs are integral for storing comprehensive patient medical records, combining structured data (e.g., medications) with detailed clinical notes (e.g., physician notes)<n>These elements are essential for straightforward data retrieval and provide deep, contextual insights into patient care.<n>However, they often suffer from discrepancies due to unintuitive EHR system designs and human errors.<n>We developed EHRCon, a new dataset and task designed to ensure data consistency between structured tables and unstructured notes in EHRs.
  arXiv  Detail & Related papers  (2024-06-24T06:26:50Z)
• Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries [56.31117605097345]
  Large language models (LLMs) have shown the potential to generate accurate clinical text summaries, but still struggle with issues regarding grounding and evaluation.<n>Here, we explore a general mitigation framework using Attribute Structuring (AS), which structures the summary evaluation process.<n>AS consistently improves the correspondence between human annotations and automated metrics in clinical text summarization.
  arXiv  Detail & Related papers  (2024-03-01T21:59:03Z)
• TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network [54.332862955411656]
  Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials. We introduce a dynamic tree-based memory network model named TREEMENT to provide accurate and interpretable patient trial matching.
  arXiv  Detail & Related papers  (2023-07-19T12:35:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.