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

You might also read

Related Articles

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

Sort by
Same author

Biomedical Knowledge Graph Alignment with GPT-Augmented Similarity Feature Construction via Tree-based Particle Swarm Optimization and Adaptive Fitness Optimization.

IEEE journal of biomedical and health informatics·2026
Same author

Multifunctional graphene oxide and PEDOTPSS nanocomposite enabling highly efficient blue multishelled ZnSeTe quantum dot light emitting diodes.

Scientific reports·2026
Same author

SHIELD: Blockchain-Enabled Lightweight Authentication Framework for Secure Wearable Health Monitoring in IoMT Environments.

IEEE journal of biomedical and health informatics·2026
Same author

Integrating artificial intelligence and sustainable materials for smart eco innovation in production.

Scientific reports·2025
Same author

Large Model Driven Multi-Granularity Medical Image Analysis: A Fuzzy Logic-Guided Framework.

IEEE journal of biomedical and health informatics·2025
Same author

An efficient deep learning network for brain stroke detection using salp shuffled shepherded optimization.

Scientific reports·2025

Related Experiment Video

Updated: Jun 7, 2025

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

504

Biomedical Information Integration via Adaptive Large Language Model Construction.

Xingsi Xue, Mu-En Wu, Fazlullah Khan

    IEEE Journal of Biomedical and Health Informatics
    |November 11, 2024
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a Two-Stage LLM construction (TSLLM) framework for biomedical information integration. TSLLM adaptively selects and combines Large Language Models (LLMs) to improve biomedical entity alignment and data integration accuracy.

    More Related Videos

    A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
    07:35

    A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

    Published on: October 13, 2023

    1.6K
    Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
    09:20

    Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

    Published on: February 23, 2019

    8.7K

    Related Experiment Videos

    Last Updated: Jun 7, 2025

    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

    504
    A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
    07:35

    A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

    Published on: October 13, 2023

    1.6K
    Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
    09:20

    Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

    Published on: February 23, 2019

    8.7K

    Area of Science:

    • Biomedical Informatics
    • Artificial Intelligence
    • Data Science

    Background:

    • Biomedical Information Integration (BII) is crucial for medical advancements but faces challenges due to data heterogeneity.
    • Accurate biomedical entity alignment is essential for effective BII.
    • Existing Large Language Models (LLMs) have limitations in capturing the full complexity of biomedical data for entity matching.

    Purpose of the Study:

    • To propose a novel Two-Stage LLM construction (TSLLM) framework for adaptive selection and combination of LLMs in BII.
    • To enhance the accuracy and efficiency of biomedical entity alignment.
    • To improve the discriminative power in distinguishing heterogeneous biomedical entities.

    Main Methods:

    • Developed a Multi-Objective Genetic Programming (MOGP) algorithm for generating versatile high-level LLMs.
    • Implemented a Single-Objective Genetic Algorithm (SOGA) with a confidence-based strategy to combine LLMs.
    • Evaluated TSLLM on OAEI datasets (Benchmark, Conference) and specialized datasets (LargeBio, Disease, Phenotype).

    Main Results:

    • TSLLM demonstrated significant efficiency in adaptively differentiating heterogeneous biomedical entities.
    • The proposed framework achieved superior performance compared to leading entity matching techniques.
    • Experimental findings validated the effectiveness of the adaptive LLM selection and combination strategy.

    Conclusions:

    • The TSLLM framework offers a robust solution for overcoming challenges in biomedical information integration.
    • Adaptive LLM combination enhances the accuracy of biomedical entity alignment.
    • TSLLM represents a significant advancement in leveraging AI for improved patient outcomes through better data integration.