LLM4EHR: Processed research article corpus and evaluation data for RAG-based extraction of MIMIC-IV studies
Abstract
This dataset contains the processed corpus of 12 research articles used in the LLM4EHR master's thesis project on retrieval-augmented generation (RAG) for structured information extraction from studies involving the MIMIC-IV database. The articles were obtained from publisher-hosted pages on Nature and Springer websites through an automated workflow initiated by the POST /api/v1/fetch/from-openalex endpoint. OpenAlex supports article discovery, while the publisher pages provide the source content. The workflow extracts scientific sections and tabular content and automatically saves one JSON record per article in the backend container. Each record contains the article identifier, source URL, title, and extracted text organized into five standardized sections: abstract, methods, results, discussion, and conclusion. Available linked full-size tables are retrieved and incorporated into their corresponding sections. Missing or unrecognized sections are represented by empty strings. The deposited JSON files preserve the processed article content used for indexing and the RAG experiments. This snapshot supports reproducibility because re-running acquisition may yield different content following changes to publisher pages or extraction dependencies. The accompanying README documents the record structure, extraction procedure, saving behavior, and known limitations. The dataset contains published research article content, not patient-level MIMIC-IV records. Original authorship and…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.