EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Querying Healthcare Data Lake Using LLMs Without Direct Data Exposure: A Feasibility Study

Frederic Ehrler, Florian Singer, Deniz Geçer, Julien Houeix, Emmanuel Durand

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260287 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Frederic Ehrler und 4 weiteren Autor:innen. Beteiligte Einrichtung: Direction of Digital Transformation and Augmented Intelligence, University Hospitals of Geneva. Hauptthemen laut MEDLINE: Large Language Models, Information Storage and Retrieval, Natural Language Processing, Electronic Health Records. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of diverse healthcare data into unified data lake infrastructures is a promising way to support research and clinical decision-making. Yet, querying these data lakes, such as those based on MongoDB, remains complex, often requiring specialized expertise and custom scripts. Large language models (LLMs) offer new opportunities by translating natural language queries into executable commands, but direct access raises major privacy concerns. We present a method for indirect LLM-assisted querying of a healthcare data lake that preserves data confidentiality by avoiding any direct model access to real data. The multistep workflow includes user intent clarification, schema and example guided query generation, and expert validation before execution. In a preliminary evaluation using five representative test queries, the pipeline consistently produced syntactically valid code aligned with user intent. Qualitative assessment showed its potential for reducing technical barriers while also highlighting current limitations, including hallucinated fields and missing lookups. These findings suggest that indirect LLM-assisted querying represents a promising step toward more secure and usable access to healthcare data lakes, though further large-scale validation is required.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsInformation Storage and RetrievalNatural Language ProcessingElectronic Health RecordsFeasibility StudiesHumansConfidentialityComputer Security

Stichwörter der Autor:innen

Artificial IntelligenceData SharingDatabasesFactualInformation Storage and RetrievalMedical InformaticsNatural Language Processing

Autor:innen und Institutionen

  • Direction of Digital Transformation and Augmented Intelligence, University Hospitals of Geneva.

Zitieren

APA

Ehrler, F., Singer, F., Geçer, D., Houeix, J., & Durand, E. (2026). Querying Healthcare Data Lake Using LLMs Without Direct Data Exposure: A Feasibility Study. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260287

Vancouver

Ehrler F, Singer F, Geçer D, Houeix J, Durand E. Querying Healthcare Data Lake Using LLMs Without Direct Data Exposure: A Feasibility Study. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260287

BibTeX
@article{Ehrler2026,
  author = {Ehrler, Frederic and Singer, Florian and Geçer, Deniz and Houeix, Julien and Durand, Emmanuel},
  title = {Querying Healthcare Data Lake Using LLMs Without Direct Data Exposure: A Feasibility Study},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260287}
}
Kostenlos starten →