Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 5, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

A Unified Information Bottleneck Framework for Multimodal Biomedical Machine Learning.

¹Department of Electrical and Computer Engineering, Baylor University, Waco, TX 76798, USA.

Entropy (Basel, Switzerland)

|May 4, 2026

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 journal

Research on a Regional Availability Evaluation Model for Road-Area High-Entropy Energy Based on Synergy Factors.

Entropy (Basel, Switzerland)·2026

Same journal

Atmospheric Turbulence Channel Modeling and Performance Analysis of a CO-ZP-OFDM Coherent Optical Communication System for UAV Air-to-Ground Scenarios.

Entropy (Basel, Switzerland)·2026

Same journal

Information Geometry and Asymptotic Theory for SMML Estimators.

Entropy (Basel, Switzerland)·2026

Same journal

Correlation Entropy and Power-Law Kinetics.

Entropy (Basel, Switzerland)·2026

Same journal

Research on the Contagion of Systemic Financial Risk Under the Impact of Climate Risks-From the Perspective of Complex Networks and Machine Learning.

Entropy (Basel, Switzerland)·2026

Same journal

The Statistical-Mechanical Meaning of the Wave Function of Quantum Mechanics.

Entropy (Basel, Switzerland)·2026

This study introduces an information-theoretic framework for multimodal biomedical AI, enabling better understanding of data fusion and model trust. It enhances prediction accuracy and robustness by analyzing information flow across diverse health data sources.

Area of Science:

Biomedical Machine Learning
Information Theory
Artificial Intelligence in Healthcare

Background:

Multimodal AI integrates diverse data (imaging, omics, EHRs, sensors) for clinical prediction.
Existing systems lack theoretical grounding for data fusion, information distribution, and trustworthiness.
Understanding these aspects is crucial for reliable clinical decision support.

Purpose of the Study:

Develop a unified information-theoretic framework for multimodal biomedical learning.
Formalize multimodal representation learning via the information bottleneck principle.
Provide tools for analyzing modality contributions, redundancy, synergy, and model robustness.

Main Methods:

Formulated multimodal learning as an information optimization problem using the information bottleneck principle.

Keywords:

biomedical machine learning entropy foundation models information bottleneck missing modalities multi-omics multimodal learning mutual information representation learning transfer entropy uncertainty quantification

More Related Videos

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

Published on: August 22, 2025

Related Experiment Videos

Last Updated: May 5, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells

Published on: August 22, 2025

Derived a variational objective balancing predictive sufficiency and informational compression.

Introduced conditional mutual information for modality decomposition and transfer entropy for longitudinal modeling.

Main Results:

Demonstrated computable and interpretable framework quantities on biomedical datasets.
MI decomposition identified modality dominance and redundancy.
Entropy-based prediction improved accuracy from 0.787 to 0.939 at 50% coverage.
Transfer entropy revealed stage-dependent modality influence in disease progression.

Conclusions:

Entropy and mutual information serve as organizing principles for multimodal biomedical AI.
The framework enhances understanding, design, and evaluation of AI systems in healthcare.
Developed methods improve model robustness, interpretability, and prediction accuracy.