EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records

• URL: http://arxiv.org/abs/2601.10020v1
• Date: Thu, 15 Jan 2026 03:02:15 GMT
• Title: EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records
• Authors: Lingfei Qian, Mauro Giuffre, Yan Wang, Huan He, Qianqian Xie, Xuguang Ai, Xeuqing Peng, Fan Ma, Ruey-Ling Weng, Donald Wright, Adan Wang, Qingyu Chen, Vipina K. Keloth, Hua Xu,
• Abstract summary: EHRNavigator is a multi-agent framework that harnesses AI agents to perform patient-level question answering across heterogeneous and multimodal EHR data.<n>It achieved 86% accuracy on real-world cases while maintaining clinically acceptable response times.
• Score: 31.559633376006442
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Clinical decision-making increasingly relies on timely and context-aware access to patient information within Electronic Health Records (EHRs), yet most existing natural language question-answering (QA) systems are evaluated solely on benchmark datasets, limiting their practical relevance. To overcome this limitation, we introduce EHRNavigator, a multi-agent framework that harnesses AI agents to perform patient-level question answering across heterogeneous and multimodal EHR data. We assessed its performance using both public benchmark and institutional datasets under realistic hospital conditions characterized by diverse schemas, temporal reasoning demands, and multimodal evidence integration. Through quantitative evaluation and clinician-validated chart review, EHRNavigator demonstrated strong generalization, achieving 86% accuracy on real-world cases while maintaining clinically acceptable response times. Overall, these findings confirm that EHRNavigator effectively bridges the gap between benchmark evaluation and clinical deployment, offering a robust, adaptive, and efficient solution for real-world EHR question answering.

Related papers

• Timely Clinical Diagnosis through Active Test Selection [49.091903570068155]
  We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design) to better emulate real-world diagnostic reasoning.<n>LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data.<n>We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use.
  arXiv  Detail & Related papers  (2025-10-21T18:10:45Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• Mitigating Clinician Information Overload: Generative AI for Integrated EHR and RPM Data Analysis [0.523377539745706]
  We present a comprehensive overview of the capabilities, requirements and applications of Generative Artificial Intelligence (GenAI)<n>We first provide some background on the forms and sources of patient data, namely real-time Remote Patient Monitoring ( RPM) streams and traditional Electronic Health Records ( EHRs)<n>These applications can enhance navigation of longitudinal patient data and provide actionable clinical decision support through natural language dialogue.
  arXiv  Detail & Related papers  (2025-08-26T17:10:21Z)
• A Dataset for Addressing Patient's Information Needs related to Clinical Course of Hospitalization [15.837772594006038]
  ArchEHR-QA is an expert-annotated dataset based on real-world patient cases from intensive care unit and emergency department settings.<n>Cases comprise questions posed by patients to public health forums, clinician-interpreted counterparts, relevant clinical note excerpts with sentence-level relevance annotations, and clinician-authored answers.<n>The answer-first prompting approach consistently performed best, with Llama 4 achieving the highest scores.
  arXiv  Detail & Related papers  (2025-06-04T16:55:08Z)
• Systematic Literature Review on Clinical Trial Eligibility Matching [0.24554686192257422]
  Review highlights how explainable AI and standardized ontology can bolster clinician trust and broaden adoption.<n>Further research into advanced semantic and temporal representations, expanded data integration, and rigorous prospective evaluations is necessary to fully realize the transformative potential of NLP in clinical trial recruitment.
  arXiv  Detail & Related papers  (2025-03-02T11:45:50Z)
• ACR: A Benchmark for Automatic Cohort Retrieval [1.3547712404175771]
  Current cohort retrieval methods rely on automated queries of structured data combined with manual curation. Recent advancements in large language models (LLMs) and information retrieval (IR) offer promising avenues to revolutionize these systems. This paper introduces a new task, Automatic Cohort Retrieval (ACR), and evaluates the performance of LLMs and commercial, domain-specific neuro-symbolic approaches.
  arXiv  Detail & Related papers  (2024-06-20T23:04:06Z)
• EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries [9.031182965159976]
  Large Language Models (LLMs) show promise in efficiently analyzing vast and complex data. We introduce EHRNoteQA, a novel benchmark built on the MIMIC-IV EHR, comprising 962 different QA pairs each linked to distinct patients' discharge summaries. EHRNoteQA includes questions that require information across multiple discharge summaries and covers eight diverse topics, mirroring the complexity and diversity of real clinical inquiries.
  arXiv  Detail & Related papers  (2024-02-25T09:41:50Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• 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)
• Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching [49.78442796596806]
  We propose an innovative privacy-aware data augmentation approach for patient-trial matching (LLM-PTM) Our experiments demonstrate a 7.32% average improvement in performance using the proposed LLM-PTM method, and the generalizability to new data is improved by 12.12%.
  arXiv  Detail & Related papers  (2023-03-24T03:14:00Z)
• COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching [70.08786840301435]
  We propose CrOss-Modal PseudO-SiamEse network (COMPOSE) to address these challenges for patient-trial matching. Experiment results show COMPOSE can reach 98.0% AUC on patient-criteria matching and 83.7% accuracy on patient-trial matching.
  arXiv  Detail & Related papers  (2020-06-15T21:01:33Z)

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.