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: Jun 7, 2025

Myocardial Infarction and Functional Outcome Assessment in Pigs

Myocardial Infarction and Functional Outcome Assessment in Pigs

Published on: April 25, 2014

Anatomy-Informed Multimodal Learning for Myocardial Infarction Prediction.

Ivan-Daniel Sievering^1,2, Ortal Senouf^1,3, Thabo Mahendiran^4,5

¹Signal Processing Laboratory 4EPFL 1015 Lausanne Switzerland.

IEEE Open Journal of Engineering in Medicine and Biology

|November 19, 2024

Summary

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

Weight change and long-term cardiovascular outcomes in overweight and obese patients after acute coronary syndromes.

European heart journal open·2026

Same author

From angiography-derived physiology guided PCI to INOCA treatment and to coronary sinus reducer: navigating multiple pathophysiological targets in a single patient: a case report.

European heart journal. Case reports·2026

Same author

[Pacemakers and cardiac resynchronization therapy : recent advances].

Revue medicale suisse·2026

Same author

[Cardiac sarcoidosis in 2026 : current perspectives].

Revue medicale suisse·2026

Same author

Impact of Intravascular Imaging on Clinical Outcomes in Focal Versus Diffuse Coronary Artery Disease.

Circulation. Cardiovascular interventions·2026

Same author

Future cardiovascular events prediction from invasive coronary angiography: A graph representation learning perspective.

Medical image analysis·2026

This summary is machine-generated.

This study introduces an AI framework using clinical data and angiography images to predict myocardial infarction (MI). The multimodal approach shows promise but requires further development for clinical use.

Area of Science:

Cardiology
Artificial Intelligence
Medical Imaging

Background:

Predicting future cardiac events like myocardial infarction (MI) in coronary artery disease patients is challenging.
Current prediction methods often rely on single data sources, limiting accuracy.

Purpose of the Study:

To develop and evaluate a novel anatomy-informed multimodal deep learning framework for predicting future MI.
To assess the performance of this framework using clinical data and Invasive Coronary Angiography (ICA) images.

Main Methods:

Utilized Convolutional Neural Networks (CNNs) for ICA image analysis, guided by anatomical information.
Employed an Artificial Neural Network (ANN) for clinical data analysis.
Merged embeddings from both modalities for patient-level MI prediction.

Keywords:

Coronary artery disease deep learning invasive coronary angiography multimodal data myocardial infarction

More Related Videos

3D Whole-heart Myocardial Tissue Analysis

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

MRI and PET in Mouse Models of Myocardial Infarction

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

Related Experiment Videos

Last Updated: Jun 7, 2025

Myocardial Infarction and Functional Outcome Assessment in Pigs

Myocardial Infarction and Functional Outcome Assessment in Pigs

Published on: April 25, 2014

3D Whole-heart Myocardial Tissue Analysis

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

MRI and PET in Mouse Models of Myocardial Infarction

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

Main Results:

The multimodal deep learning framework demonstrated superior predictive power compared to single modalities and interventional cardiologists.
Achieved promising performance metrics (AUC: [Formula: see text], F1-Score: [Formula: see text]) in a study of 445 acute coronary syndrome patients.
Outperformed individual modality predictions (AUC: 0.54, F1-Score: 0.18).

Conclusions:

This represents the first deep learning framework combining multimodal data for future MI prediction.
The study highlights the advantage of multimodal approaches over single-modality methods.
While promising, the framework's current performance does not meet the criteria for practical clinical application.