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 Experiment Video

Updated: May 24, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Combining Anti-Hallucination Strategies for Reliable LLM-Based Clinical Information Extraction.

Jean Yapo1,2, Chuanming Dong1, Marc Cuggia1

  • 1Univ Rennes, CHU Rennes, INSERM, LTSI-UMR 1099, Rennes, France.

Studies in Health Technology and Informatics
|May 23, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Development and Validation of a Multi-Modal Algorithm for Chronic Kidney Disease Detection in a Hospital Clinical Data Warehouse.

Studies in health technology and informatics·2026
Same author

OPTIMA-DAW: Improving Cerebral Vasospasm Detection After Aneurysmal Subarachnoid Haemorrhage Using Machine Learning.

Studies in health technology and informatics·2026
Same author

Qualifying Missingness in Real-World Clinical Data for Secondary Use.

Studies in health technology and informatics·2026
Same author

Implementing a Semi-Automated Method for Surgical Site Infections Monitoring in a Limited Setting: The SPICMI Method in Martinique University Hospital.

Studies in health technology and informatics·2026
Same author

MINE: An Interactive Platform for Expert-Guided Medical Information Extraction.

Studies in health technology and informatics·2026
Same author

A Hybrid Pipeline for Mapping French UCD Drug Codes to RxNorm with Dosage Preservation.

Studies in health technology and informatics·2026

We developed a new method using large language models (LLMs) for medical concept extraction, reducing errors. Our system uses multiple anti-hallucination techniques for reliable clinical text analysis, especially in secure hospital settings.

Area of Science:

  • Artificial Intelligence
  • Natural Language Processing
  • Biomedical Informatics

Background:

  • Accurate medical concept extraction is vital for clinical text analysis.
  • Hallucinations in LLMs pose a significant challenge in sensitive healthcare data processing.
  • Smaller models are often necessary for privacy in hospital environments.

Purpose of the Study:

  • To introduce a novel LLM-based approach for medical concept extraction.
  • To implement and evaluate multiple anti-hallucination strategies.
  • To provide a flexible framework for clinical text processing in privacy-constrained settings.

Main Methods:

  • Developed a modular framework using LLMs for medical concept extraction.
  • Integrated ensemble methods, Chain-of-Verification, contextual grounding, and LLM-as-a-Judge.
Keywords:
HallucinationLarge Language ModelMedical Data Extraction

Related Experiment Videos

Last Updated: May 24, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

  • Built a Streamlit web application for flexible pipeline configuration.

    • Main Results:

    • The approach effectively combines multiple anti-hallucination strategies.
    • Demonstrated a modular framework addressing hallucinations in clinical text.
    • Enabled flexible pipeline configuration for diverse clinical text analysis needs.

    Conclusions:

    • The proposed LLM-based method offers a robust solution for medical concept extraction.
    • The framework successfully mitigates hallucinations, enhancing reliability in clinical text processing.
    • The system is particularly suitable for smaller models in privacy-sensitive hospital environments.