Related Experiment Video
Updated: Jul 4, 2025
Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
Published on: January 8, 2013
Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling
Joshua Mayourian1,2, William G La Cava3,2, Akhil Vaid4
1Department of Cardiology (J.M., S.J.G., T.G., A.D., M.E.A., J.K.T.), Boston Children's Hospital, MA.
Insights
An AI algorithm can detect left ventricular (LV) dysfunction and remodeling in children using ECGs, offering a promising, inexpensive screening tool. This technology democratizes pediatric cardiology expertise, improving access to care.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Diagnostics
Background:
- Artificial intelligence (AI) shows potential for ECG analysis in adults but is under-explored in pediatric populations.
- Detecting left ventricular (LV) dysfunction and remodeling in children using AI-enhanced ECGs is a critical unmet need.
Purpose of the Study:
- To develop and validate an AI algorithm for detecting LV dysfunction, hypertrophy, and dilation in pediatric patients.
- To assess the algorithm's performance against human experts and in external validation cohorts.
Main Methods:
- A convolutional neural network was trained on paired ECG-echocardiograms from pediatric patients (≤18 years).
- The model identified LV dysfunction, hypertrophy, and dilation, evaluated using AUROC and AUPRC metrics.
- Performance was tested on internal, emergency department, and external validation datasets.
Main Results:
- The AI model demonstrated strong performance in detecting LV abnormalities, comparable to or exceeding pediatric cardiologist benchmarks.
- External validation showed high negative predictive values for composite outcomes (99.0%-99.2%).
- Saliency mapping identified key ECG features predictive of LV dysfunction and remodeling.
Conclusions:
- An externally validated AI algorithm can effectively screen for LV dysfunction and remodeling in children via ECG.
- This technology offers an inexpensive method to broaden access to specialized pediatric cardiac care.
- The AI tool democratizes pediatric cardiology expertise, potentially improving early detection and management.
Background:
Artificial intelligence-enhanced ECG analysis shows promise to detect ventricular dysfunction and remodeling in adult populations. However, its application to pediatric populations remains underexplored.
Methods:
A convolutional neural network was trained on paired ECG-echocardiograms (≤2 days apart) from patients ≤18 years of age without major congenital heart disease to detect human expert-classified greater than mild left ventricular (LV) dysfunction, hypertrophy, and dilation (individually and as a composite outcome). Model performance was evaluated on single ECG-echocardiogram pairs per patient at Boston Children's Hospital and externally at Mount Sinai Hospital using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC).
Results:
The training cohort comprised 92 377 ECG-echocardiogram pairs (46 261 patients; median age, 8.2 years). Test groups included internal testing (12 631 patients; median age, 8.8 years; 4.6% composite outcomes), emergency department (2830 patients; median age, 7.7 years; 10.0% composite outcomes), and external validation (5088 patients; median age, 4.3 years; 6.1% composite outcomes) cohorts. Model performance was similar on internal test and emergency department cohorts, with model predictions of LV hypertrophy outperforming the pediatric cardiologist expert benchmark. Adding age and sex to the model added no benefit to model performance. When using quantitative outcome cutoffs, model performance was similar between internal testing (composite outcome: AUROC, 0.88, AUPRC, 0.43; LV dysfunction: AUROC, 0.92, AUPRC, 0.23; LV hypertrophy: AUROC, 0.88, AUPRC, 0.28; LV dilation: AUROC, 0.91, AUPRC, 0.47) and external validation (composite outcome: AUROC, 0.86, AUPRC, 0.39; LV dysfunction: AUROC, 0.94, AUPRC, 0.32; LV hypertrophy: AUROC, 0.84, AUPRC, 0.25; LV dilation: AUROC, 0.87, AUPRC, 0.33), with composite outcome negative predictive values of 99.0% and 99.2%, respectively. Saliency mapping highlighted ECG components that influenced model predictions (precordial QRS complexes for all outcomes; T waves for LV dysfunction). High-risk ECG features include lateral T-wave inversion (LV dysfunction), deep S waves in V1 and V2 and tall R waves in V6 (LV hypertrophy), and tall R waves in V4 through V6 (LV dilation).
Conclusions:
This externally validated algorithm shows promise to inexpensively screen for LV dysfunction and remodeling in children, which may facilitate improved access to care by democratizing the expertise of pediatric cardiologists.
