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

Multimodal Data Integration Improves Disease Risk Prediction in the UK Biobank.

Xiayuan Huang1, Hang Zhou1, Yitao Hong1

  • 1Yale University, New Haven, CT, USA.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|February 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

Excitation-polarization-dependent dynamics of polariton condensates in the ZnO microwire at room temperature.

Journal of physics. Condensed matter : an Institute of Physics journal·2022
Same author

Growth regulators promote soybean productivity: a review.

PeerJ·2022
Same author

Mitochondrial Glutathione Depletion Nanoshuttles for Oxygen-Irrelevant Free Radicals Generation: A Cascaded Hierarchical Targeting and Theranostic Strategy Against Hypoxic Tumor.

ACS applied materials & interfaces·2022
Same author

Erythrocytes Are an Independent Protective Factor for Vascular Cognitive Impairment in Patients With Severe White Matter Hyperintensities.

Frontiers in aging neuroscience·2022
Same author

Structural and Functional Asymmetry in Precentral and Postcentral Gyrus in Patients With Unilateral Chronic Shoulder Pain.

Frontiers in neurology·2022
Same author

Hyaluronic acid oligosaccharide-collagen mineralized product and aligned nanofibers with enhanced vascularization properties in bone tissue engineering.

International journal of biological macromolecules·2022
Same journal

Sensitivity Analyses of a Scoring System for a Contraception Decision Aid.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Improving electronic health record processing of large language models via retrieval-augmented generation: A case study on dietary supplements.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Developing a User-Centered Mobile Application Prototype: Bridging Lower-Limb Fracture Care from Skilled Nursing Facility and Back to the Community.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Automating Adjudication of Cardiovascular Events Using Large Language Models.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Predictive Factors and State-Level Barriers to Postpartum Birth Control Usage in the United States: Insights from PRAMS Phase 8.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
See all related articles

A new AI model, ALIGATEHR-Gen, integrates electronic health records and genetic data to significantly improve chronic disease risk prediction. This approach enhances patient risk assessment by combining clinical and genetic factors for better healthcare outcomes.

Area of Science:

  • Computational biology
  • Genomics
  • Medical informatics

Background:

  • Family health history is crucial for assessing chronic disease risk.
  • Integrating electronic health records (EHRs) with genetic data can enhance disease risk prediction by capturing diverse patient factors.
  • Current models often struggle to comprehensively integrate multimodal patient data.

Purpose of the Study:

  • To develop and evaluate ALIGATEHR-Gen, a novel graph attention network for improved disease risk prediction.
  • To integrate multimodal patient data, including genetic information, EHRs, and medical ontologies.
  • To enhance patient representation by incorporating genetically inferred relationships and disease ontology embeddings.

Main Methods:

  • ALIGATEHR-Gen utilizes a graph attention network architecture.

Related Experiment Videos

  • The model integrates multimodal patient data: genetic information, diagnosis codes, and demographics.
  • External medical ontology knowledge and genetically inferred first-degree relationships are incorporated.
  • Model performance is evaluated on 118 diseases using UK Biobank data.

    • Main Results:

    • ALIGATEHR-Gen outperforms state-of-the-art baseline models by an average of at least 6% in disease risk prediction.
    • The model demonstrates effective distinction of patient subgroups for fibrotic and related diseases based on clinical and genetic features.
    • Unified patient representations enhance predictive accuracy.

    Conclusions:

    • ALIGATEHR-Gen shows significant potential for advancing predictive and interpretable modeling in healthcare.
    • The integration of multimodal data, including genetic and EHR information, is key to improving disease risk prediction.
    • This approach offers a pathway to more personalized and accurate patient risk stratification.