Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Healthcare Agencies II01:17

Healthcare Agencies II

There are various healthcare agencies in the United States—some of which are managed by religious institutions and others by different government branches.
Parish nursing is a growing specialty nursing profession that focuses on holistic healthcare, health promotion, and illness prevention. It blends professional nursing practice with a health ministry, focusing on health and healing within the context of a Christian community. Parish nurses serve as health educators, referral sources, and lay...
Longitudinal Studies01:26

Longitudinal Studies

Longitudinal studies are also widely used in other medical and social science fields. For instance, in cardiovascular research, they can monitor patients' health over decades to identify risk factors for heart disease, such as high cholesterol or smoking, and evaluate the long-term effectiveness of preventive measures. Similarly, in mental health studies, researchers might follow individuals from adolescence into adulthood to understand the development and progression of conditions like...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Perceived Usability, User Experience, and Technology Acceptance of Role-Specific Augmented Reality Decision Support Tools for Cardiac Arrest Resuscitation: Prospective Observational Pilot Study.

JMIR XR and spatial computing·2026
Same author

Driving factors in pediatric emergency department use: an ecological retrospective study.

PloS one·2026
Same author

Leveraging Large Language Models with Retrieval-Augmented Generation for Semantic Mapping of Clinical Data Lakes to SNOMED CT.

Studies in health technology and informatics·2026
Same author

Using Human-Centered Design to Build a Peer-Support Network for People Living with Chronic Diseases.

Studies in health technology and informatics·2026
Same author

Personalizing Mobile Applications for Health Behavioral Change According to Age and Gender.

Studies in health technology and informatics·2026
Same author

Augmented Reality-Guided Decision Support in Simulated Pediatric Cardiac Arrest: A Randomized Clinical Trial.

JAMA network open·2026

Related Experiment Video

Updated: May 24, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

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

Frederic Ehrler1, Florian Singer1, Deniz Geçer1

  • 1Direction of Digital Transformation and Augmented Intelligence, University Hospitals of Geneva.

Studies in Health Technology and Informatics
|May 23, 2026
PubMed
Summary

This study introduces a secure method for querying healthcare data lakes using large language models (LLMs) indirectly. This approach enhances data accessibility for research while protecting patient privacy.

Keywords:
Artificial IntelligenceData SharingDatabasesFactualInformation Storage and RetrievalMedical InformaticsNatural Language Processing

More Related Videos

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Related Experiment Videos

Last Updated: May 24, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Area of Science:

  • Health Informatics
  • Artificial Intelligence in Healthcare
  • Data Management

Background:

  • Healthcare data lakes integrate diverse information for research and clinical decisions.
  • Querying these data lakes, like MongoDB, is complex and requires specialized skills.
  • Direct use of large language models (LLMs) for querying poses significant privacy risks.

Purpose of the Study:

  • To present a method for indirect LLM-assisted querying of healthcare data lakes.
  • To ensure data confidentiality by preventing direct LLM access to sensitive information.
  • To explore the potential of LLMs in simplifying healthcare data access.

Main Methods:

  • A multistep workflow involving user intent clarification.
  • Schema and example-guided query generation.
  • Expert validation prior to query execution.
  • Indirect LLM assistance without direct data access.

Main Results:

  • The pipeline generated syntactically valid code aligned with user intent for test queries.
  • Qualitative assessment indicated potential for reducing technical barriers.
  • Limitations identified include hallucinated fields and missing lookups.

Conclusions:

  • Indirect LLM-assisted querying offers a promising, secure approach to accessing healthcare data lakes.
  • This method can improve usability for researchers and clinicians.
  • Further large-scale validation is necessary to confirm effectiveness and address limitations.