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

Predicting Sudden Cardiac Death in Patients With Sarcoidosis Using a Multimodal Artificial Intelligence Model.

Changxin Lai1, Minglang Yin2, Eugene G Kholmovski1

  • 1Alliance for Cardiovascular Diagnostic and Treatment Innovation, Johns Hopkins University, Baltimore, Maryland, USA; Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA.

JACC. Clinical Electrophysiology
|December 5, 2025
PubMed
Summary

Related Concept Videos

Cardiomyopathy III: Hypertrophic Cardiomyopathy01:29

Cardiomyopathy III: Hypertrophic Cardiomyopathy

374
Hypertrophic cardiomyopathy, or HCM, is an autosomal dominant genetic disorder characterized by asymmetric left ventricular hypertrophy without ventricular dilation. It is more common in men and is typically diagnosed in young, athletic adults.EtiologyHCM is primarily genetic and is caused by mutations in genes encoding sarcomeric proteins. Researchers have identified over 1400 mutations across at least 11 different genes. Among these, the most frequently occurring mutations are found in the...
374

You might also read

Related Articles

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

Sort by
Same author

Direct Oral Anticoagulants in Primary and Secondary Prevention of Thrombotic Events: 2026 ACC Scientific Statement: A Report of the American College of Cardiology.

Journal of the American College of Cardiology·2026
Same author

A hidden predictor of sudden cardiac death uncovered by deep learning.

Nature·2026
Same author

Interpretable Multimodal AI to Predict the Presence of Late Gadolinium Enhancement on Cardiac Magnetic Resonance Imaging in Cardiac Sarcoidosis Patients.

Circulation. Arrhythmia and electrophysiology·2026
Same author

Predicting the <i>When</i> : Multimodal AI for Time-to-Recurrence Analysis After Atrial Fibrillation Ablation.

medRxiv : the preprint server for health sciences·2026
Same author

Genotype-specific digital twins for arrhythmia ablation targeting in arrhythmogenic right ventricular cardiomyopathy.

Communications medicine·2026
Same author

Bridging the Divide: Divergent Diagnostic Philosophies and Practice Pathways for Cardiac Sarcoidosis between Japan and North America.

Journal of cardiac failure·2026

A new AI model, MAARS-CS, accurately predicts sudden cardiac death (SCD) risk in cardiac sarcoidosis (CS) patients. This tool integrates imaging and clinical data, outperforming traditional LVEF measures for better patient care.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Cardiac sarcoidosis (CS) poses a high risk of sudden cardiac death (SCD).
  • Current risk stratification using left ventricular ejection fraction (LVEF) has limited accuracy.
  • Improved methods are needed for identifying high-risk CS patients.

Purpose of the Study:

  • To develop and evaluate a multimodal artificial intelligence for ventricular risk stratification in CS (MAARS-CS).
  • To integrate late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) images and clinical data for SCD risk prediction.
  • To assess MAARS-CS performance against LVEF in predicting SCD risk.

Main Methods:

  • A retrospective cohort of 317 sarcoidosis patients was analyzed.
  • MAARS-CS utilized a 3D convolutional neural network for LGE-CMR image analysis and a feedforward neural network for clinical covariates.
Keywords:
artificial intelligencecardiac magnetic resonance imagingcardiac sarcoidosisrisk stratificationsudden cardiac death

Related Experiment Videos

  • The model employed 5-fold cross-validation for training and testing.

    • Main Results:

    • MAARS-CS achieved an AUROC of 0.86, significantly outperforming LVEF criteria (AUROC: 0.59) and continuous LVEF (AUROC: 0.77).
    • The model demonstrated superior area under the precision-recall curve (0.54 vs 0.43) and balanced accuracy (0.83 vs 0.74) compared to continuous LVEF.
    • MAARS-CS showed robust performance across varying image qualities and identified key risk predictors.

    Conclusions:

    • MAARS-CS provides superior predictive accuracy and consistency for SCD risk in sarcoidosis patients compared to LVEF.
    • The model's interpretability and robustness support its use as a clinical decision support tool.
    • Further validation of MAARS-CS could enhance personalized patient care in sarcoidosis.