Related Experiment Video
Updated: Jun 22, 2025
Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
Published on: April 11, 2025
Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of
Maarten Z H Kolk1,2, Samuel Ruipérez-Campillo3,4, Cornelis P Allaart5
1Department of Clinical and Experimental Cardiology, Heart Center, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands.
Insights
A new deep learning model integrating cardiac MRI and ECG data accurately predicts ventricular arrhythmias in patients with non-ischaemic cardiomyopathy. This approach improves risk stratification for sudden cardiac death prevention in heart failure patients.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Imaging
Background:
- The role of implantable cardioverter-defibrillators (ICDs) for primary prevention of sudden cardiac death in non-ischaemic cardiomyopathy is debated.
- Accurate prediction of malignant ventricular arrhythmias is crucial for guiding ICD therapy.
Purpose of the Study:
- To develop and validate a multimodal deep learning model for predicting ventricular arrhythmias.
- To integrate cardiac magnetic resonance imaging (LGE-MRI), electrocardiography (ECG), and clinical data for enhanced risk prediction.
Main Methods:
- A cohort of 289 patients with non-ischaemic cardiomyopathy undergoing ICD implantation was retrospectively analyzed.
- A residual variational autoencoder extracted features from LGE-MRI and ECG.
- A machine learning model (DEEP RISK) integrated these features with clinical data to predict ventricular arrhythmias.
Main Results:
- The multimodal DEEP RISK model achieved an AUROC of 0.84 for predicting malignant ventricular arrhythmias.
- Sensitivity was 0.98 and specificity was 0.73 in the validation cohort.
- Models using individual data modalities showed lower predictive performance compared to the multimodal approach.
Conclusions:
- Multimodal deep learning integrating LGE-MRI, ECG, and clinical data offers high prognostic accuracy for ventricular arrhythmias.
- This approach can aid in risk stratification for sudden cardiac death in patients with non-ischaemic systolic heart failure.
- The DEEP RISK model provides a promising tool for guiding ICD implantation decisions.
Abstract:
The efficacy of an implantable cardioverter-defibrillator (ICD) in patients with a non-ischaemic cardiomyopathy for primary prevention of sudden cardiac death is increasingly debated. We developed a multimodal deep learning model for arrhythmic risk prediction that integrated late gadolinium enhanced (LGE) cardiac magnetic resonance imaging (MRI), electrocardiography (ECG) and clinical data. Short-axis LGE-MRI scans and 12-lead ECGs were retrospectively collected from a cohort of 289 patients prior to ICD implantation, across two tertiary hospitals. A residual variational autoencoder was developed to extract physiological features from LGE-MRI and ECG, and used as inputs for a machine learning model (DEEP RISK) to predict malignant ventricular arrhythmia onset. In the validation cohort, the multimodal DEEP RISK model predicted malignant ventricular arrhythmias with an area under the receiver operating characteristic curve (AUROC) of 0.84 (95% confidence interval (CI) 0.71-0.96), a sensitivity of 0.98 (95% CI 0.75-1.00) and a specificity of 0.73 (95% CI 0.58-0.97). The models trained on individual modalities exhibited lower AUROC values compared to DEEP RISK [MRI branch: 0.80 (95% CI 0.65-0.94), ECG branch: 0.54 (95% CI 0.26-0.82), Clinical branch: 0.64 (95% CI 0.39-0.87)]. These results suggest that a multimodal model achieves high prognostic accuracy in predicting ventricular arrhythmias in a cohort of patients with non-ischaemic systolic heart failure, using data collected prior to ICD implantation.
Related Concept Videos
01:28Mechanism of Cardiac Arrhythmias
01:28Disturbances in Heart Rhythm
Arrhythmias are categorized by their speed, rhythm, and origin. A slow...