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 Videos

Dynamic Gating of Modality-Specific Experts for Interpretable CHD Diagnostic Prediction.

Yunan He, Jie Li, Daimin Li

    IEEE Journal of Biomedical and Health Informatics
    |June 18, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Heart Failure IV: Classification and Diagnostic Evaluation01:30

    Heart Failure IV: Classification and Diagnostic Evaluation

    Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...
    Acute Coronary Syndrome III: Diagnostic Studies01:30

    Acute Coronary Syndrome III: Diagnostic Studies

    Diagnosing acute coronary syndrome or ACS begins with a thorough patient history. Notable symptoms include central, crushing chest pain radiating to the left arm, neck, jaw, or back, along with shortness of breath, sweating (diaphoresis), nausea, vomiting, dizziness, and palpitations.It is crucial to note any history of cardiac illnesses and assess risk factors, including age, gender, smoking, hypertension, diabetes, hyperlipidemia, and a sedentary lifestyle.During physical examination, vital...

    You might also read

    Related Articles

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

    Sort by
    Same author

    The association of coronary non-calcified plaque loading based on coronary computed tomography angiogram and adverse cardiovascular events in patients with unstable coronary heart disease-a retrospective cohort study.

    Journal of thoracic disease·2022
    Same author

    Magnetic plasmons in a simple metallic nanogroove array for refractive index sensing.

    Optics express·2018
    Same author

    Synthesis and resolution of planar-chiral ruthenium-palladium complexes with ECE' pincer ligands.

    Chemistry (Weinheim an der Bergstrasse, Germany)·2009
    Same author

    Highly selective biotransformation of ginsenoside Rb1 to Rd by the phytopathogenic fungus Cladosporium fulvum (syn. Fulvia fulva).

    Journal of industrial microbiology & biotechnology·2009
    Same author

    Human DNA sequences: more variation and less race.

    American journal of physical anthropology·2009
    Same author

    Determination of organophosphorus pesticides in underground water by SPE-GC-MS.

    Journal of chromatographic science·2009
    Same journal

    An Ultra-Lightweight Cross-scale Attention Mamba Network for Accurate Skin Lesion Segmentation.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Explanation-Guided Reconstruction of Missing Clinical Features for Survival Prediction in Pancreatic Cancer.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    stDGCN: A dual-augmentation graph convolutional network for identifying spatial domains with attention mechanism.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Patient-specific Biomechanical Investigation of Percutaneous Pulmonary Valves: Towards the Integration of Routinely Acquired Clinical Data and Fluid-structure Interaction Simulations.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Cross-subject fMRI-to-Image with Visual-cortex 2D Representation and Pre-Training.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    PGCASurv: A Prior-Guided Cross-Attention Framework for Dynamic Survival Model with Longitudinal Data.

    IEEE journal of biomedical and health informatics·2026
    See all related articles

    A new Compositional Mixture-of-Experts (MoE) model dynamically fuses patient data for Coronary Heart Disease (CHD) prediction. This adaptive approach outperforms static methods, especially for younger patients, improving diagnostic accuracy.

    Area of Science:

    • Artificial Intelligence in Medicine
    • Biomedical Informatics
    • Machine Learning for Healthcare

    Background:

    • Traditional Coronary Heart Disease (CHD) prediction models use static multimodal fusion, failing to account for shifting evidence importance between data types (biomarkers, clinical notes).
    • This 'one-size-fits-all' approach limits diagnostic accuracy as critical information varies dynamically across patients.

    Purpose of the Study:

    • To introduce a novel Compositional Mixture-of-Experts (MoE) framework for adaptive, patient-specific multimodal fusion in CHD diagnostic prediction.
    • To address the limitations of static fusion strategies by enabling dynamic reweighting of information sources.

    Main Methods:

    • Developed a Compositional MoE architecture with heterogeneous, role-specific experts (Structured, Text, Fusion) and a Dynamic Gating Network for adaptive routing.

    Related Experiment Videos

  • Implemented an auxiliary loss to ensure expert specialization and prevent collapse.
  • Validated the model on a large-scale dataset (60,339 EMRs) comparing against static and attention-based fusion baselines.

    • Main Results:

    • The Compositional MoE achieved superior performance (AUPRC 0.9853), significantly outperforming baseline methods (p < 0.05).
    • The model demonstrated robustness to moderate modal corruption and class imbalance.
    • Significant performance gains were observed in diagnostically challenging subgroups, particularly younger patients (<50 years).

    Conclusions:

    • The proposed Compositional MoE framework offers a dynamic and adaptive approach to multimodal fusion for improved CHD diagnostic prediction.
    • The model provides modality-level transparency, adaptively prioritizing reliable data sources, aligning with clinical intuition.
    • This adaptive strategy holds promise for enhancing diagnostic accuracy, especially in complex or underrepresented patient populations.