Harnessing Large Language Models for Precision Querying and Retrieval-Augmented Knowledge Extraction in Clinical Data Science
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910003606061056 |
|---|---|
| author | Jan, Juan Jose Rubio Wu, Jack Ive, Julia |
| author_facet | Jan, Juan Jose Rubio Wu, Jack Ive, Julia |
| contents | This study applies Large Language Models (LLMs) to two foundational Electronic Health Record (EHR) data science tasks: structured data querying (using programmatic languages, Python/Pandas) and information extraction from unstructured clinical text via a Retrieval Augmented Generation (RAG) pipeline. We test the ability of LLMs to interact accurately with large structured datasets for analytics and the reliability of LLMs in extracting semantically correct information from free text health records when supported by RAG. To this end, we presented a flexible evaluation framework that automatically generates synthetic question and answer pairs tailored to the characteristics of each dataset or task. Experiments were conducted on a curated subset of MIMIC III, (four structured tables and one clinical note type), using a mix of locally hosted and API-based LLMs. Evaluation combined exact-match metrics, semantic similarity, and human judgment. Our findings demonstrate the potential of LLMs to support precise querying and accurate information extraction in clinical workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20674 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Harnessing Large Language Models for Precision Querying and Retrieval-Augmented Knowledge Extraction in Clinical Data Science Jan, Juan Jose Rubio Wu, Jack Ive, Julia Computation and Language Artificial Intelligence This study applies Large Language Models (LLMs) to two foundational Electronic Health Record (EHR) data science tasks: structured data querying (using programmatic languages, Python/Pandas) and information extraction from unstructured clinical text via a Retrieval Augmented Generation (RAG) pipeline. We test the ability of LLMs to interact accurately with large structured datasets for analytics and the reliability of LLMs in extracting semantically correct information from free text health records when supported by RAG. To this end, we presented a flexible evaluation framework that automatically generates synthetic question and answer pairs tailored to the characteristics of each dataset or task. Experiments were conducted on a curated subset of MIMIC III, (four structured tables and one clinical note type), using a mix of locally hosted and API-based LLMs. Evaluation combined exact-match metrics, semantic similarity, and human judgment. Our findings demonstrate the potential of LLMs to support precise querying and accurate information extraction in clinical workflows. |
| title | Harnessing Large Language Models for Precision Querying and Retrieval-Augmented Knowledge Extraction in Clinical Data Science |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.20674 |