Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA

• URL: http://arxiv.org/abs/2503.17933v1
• Date: Sun, 23 Mar 2025 04:26:06 GMT
• Title: Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA
• Authors: Justice Ou, Tinglin Huang, Yilun Zhao, Ziyang Yu, Peiqing Lu, Rex Ying,
• Abstract summary: RAG is extensively applied to provide factual medical knowledge.<n>Case-based knowledge is critical for effective medical reasoning.<n>We propose Experience Retrieval Augmentation - ExpRAG framework.
• Score: 14.331262700941268
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To improve the reliability of Large Language Models (LLMs) in clinical applications, retrieval-augmented generation (RAG) is extensively applied to provide factual medical knowledge. However, beyond general medical knowledge from open-ended datasets, clinical case-based knowledge is also critical for effective medical reasoning, as it provides context grounded in real-world patient experiences. Motivated by this, we propose Experience Retrieval Augmentation - ExpRAG framework based on Electronic Health Record (EHR), aiming to offer the relevant context from other patients' discharge reports. ExpRAG performs retrieval through a coarse-to-fine process, utilizing an EHR-based report ranker to efficiently identify similar patients, followed by an experience retriever to extract task-relevant content for enhanced medical reasoning. To evaluate ExpRAG, we introduce DischargeQA, a clinical QA dataset with 1,280 discharge-related questions across diagnosis, medication, and instruction tasks. Each problem is generated using EHR data to ensure realistic and challenging scenarios. Experimental results demonstrate that ExpRAG consistently outperforms a text-based ranker, achieving an average relative improvement of 5.2%, highlighting the importance of case-based knowledge for medical reasoning.

Related papers

• DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients [4.062920795080979]
  Existing medical RAG systems mainly leverage knowledge from medical knowledge bases.<n>We propose DoctorRAG, a RAG framework that emulates doctor-like reasoning by integrating both explicit clinical knowledge and implicit case-based experience.<n>Our approach generates more accurate, relevant, and comprehensive responses, taking a step towards more doctor-like medical reasoning systems.
  arXiv  Detail & Related papers  (2025-05-26T05:56:23Z)
• ICA-RAG: Information Completeness Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis [16.186500907377965]
  ICA-RAG is a novel framework for enhancing RAG reliability in disease diagnosis.<n>It uses an adaptive control module to assess the necessity of retrieval based on the input's information completeness.<n> Experiments on three Chinese electronic medical record datasets demonstrate that ICA-RAG significantly outperforms baseline methods.
  arXiv  Detail & Related papers  (2025-02-20T14:52:36Z)
• RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering [29.065294682044]
  The current paradigm, Retrieval-Augmented Generation (RAG), acquires expertise medical knowledge through large-scale corpus retrieval. This paper introduces RGAR, a recurrence generation-augmented retrieval framework that retrieves both relevant factual and conceptual knowledge from dual sources.
  arXiv  Detail & Related papers  (2025-02-19T01:50:10Z)
• Enhancing Health Information Retrieval with RAG by Prioritizing Topical Relevance and Factual Accuracy [0.7673339435080445]
  This paper introduces a solution driven by Retrieval-Augmented Generation (RAG) to enhance the retrieval of health-related documents grounded in scientific evidence. In particular, we propose a three-stage model: in the first stage, the user's query is employed to retrieve topically relevant passages with associated references from a knowledge base constituted by scientific literature. In the second stage, these passages, alongside the initial query, are processed by LLMs to generate a contextually relevant rich text (GenText) In the last stage, the documents to be retrieved are evaluated and ranked both from the point of
  arXiv  Detail & Related papers  (2025-02-07T05:19:13Z)
• Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering [70.44269982045415]
  Retrieval-augmented generation (RAG) has emerged as a promising approach to enhance the performance of large language models (LLMs) We introduce Medical Retrieval-Augmented Generation Benchmark (MedRGB) that provides various supplementary elements to four medical QA datasets. Our experimental results reveals current models' limited ability to handle noise and misinformation in the retrieved documents.
  arXiv  Detail & Related papers  (2024-11-14T06:19:18Z)
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
  KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning. Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
  arXiv  Detail & Related papers  (2024-10-06T18:46:28Z)
• STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering [58.79671189792399]
  STLLaVA-Med is designed to train a policy model capable of auto-generating medical visual instruction data. We validate the efficacy and data efficiency of STLLaVA-Med across three major medical Visual Question Answering (VQA) benchmarks.
  arXiv  Detail & Related papers  (2024-06-28T15:01:23Z)
• MedInsight: A Multi-Source Context Augmentation Framework for Generating Patient-Centric Medical Responses using Large Language Models [3.0874677990361246]
  Large Language Models (LLMs) have shown impressive capabilities in generating human-like responses. We propose MedInsight:a novel retrieval framework that augments LLM inputs with relevant background information. Experiments on the MTSamples dataset validate MedInsight's effectiveness in generating contextually appropriate medical responses.
  arXiv  Detail & Related papers  (2024-03-13T15:20:30Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)
• Toward Cohort Intelligence: A Universal Cohort Representation Learning Framework for Electronic Health Record Analysis [15.137213823470544]
  We propose a universal COhort Representation lEarning (CORE) framework to augment EHR utilization by leveraging the fine-grained cohort information among patients. CORE is readily applicable to diverse backbone models, serving as a universal plug-in framework to infuse cohort information into healthcare methods for boosted performance.
  arXiv  Detail & Related papers  (2023-04-10T09:12:37Z)
• 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)
• SPeC: A Soft Prompt-Based Calibration on Performance Variability of Large Language Model in Clinical Notes Summarization [50.01382938451978]
  We introduce a model-agnostic pipeline that employs soft prompts to diminish variance while preserving the advantages of prompt-based summarization. Experimental findings indicate that our method not only bolsters performance but also effectively curbs variance for various language models.
  arXiv  Detail & Related papers  (2023-03-23T04:47:46Z)
• Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine [68.7814360102644]
  We propose the Re$3$Writer method with retrieval-augmented generation and knowledge-grounded reasoning. We demonstrate the effectiveness of our method in generating patient discharge instructions.
  arXiv  Detail & Related papers  (2022-10-23T16:34:39Z)
• Robust and Efficient Medical Imaging with Self-Supervision [80.62711706785834]
  We present REMEDIS, a unified representation learning strategy to improve robustness and data-efficiency of medical imaging AI. We study a diverse range of medical imaging tasks and simulate three realistic application scenarios using retrospective data.
  arXiv  Detail & Related papers  (2022-05-19T17:34:18Z)
• Transformer-based unsupervised patient representation learning based on medical claims for risk stratification and analysis [3.5492837081144204]
  Transformer-based Multimodal AutoEncoder (TMAE) can learn efficient patient representation by encoding meaningful information from the claims data. We trained TMAE using a real-world pediatric claims dataset containing more than 600,000 patients.
  arXiv  Detail & Related papers  (2021-06-23T21:29:50Z)

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.