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.

Background: Right ventricular (RV) morphology has been associated with adverse clinical outcomes in Fontan patients. The impact of RV versus left ventricular morphology on ventricular stress and strain in single ventricles is not well known. Methods and Results: Cardiac magnetic resonance examinations in 193 patients with the Fontan circulation were retrospectively analyzed. Ventricular mass, volume, global circumferential and longitudinal strain, and global average end-systolic fiber stress were calculated using previously published methods. Compared with left ventricular morphology, RV morphology (48%) was associated with higher ventricular end-diastolic volume (110 mL/BSA ^1.3 versus 84 mL/BSA ^1.3 , P <0.001), lower mass-to-volume ratio (0.46 versus 0.57, P <0.001), higher global average end-systolic fiber stress (23 kPa versus 20 kPa, P =0.002), worse global circumferential strain (−21% versus −24%, P <0.001), and higher prevalence of greater than or equal to moderate atrioventricular valve regurgitation (25% versus 6%, P <0.001). Ejection fraction and global longitudinal strain were similar between the groups. Death or listing for heart transplantation occurred in 24 (12%) with a median follow-up of 6.2 years. On univariate analysis, RV morphology, ventricular dilatation, and worse global circumferential strain were associated with this composite outcome. Conclusions: In comparison to Fontan patients with a dominant left ventricle, those with a dominant RV have higher fiber stress, a higher rate of ventricular dilatation, lower circumferential fiber shortening, and similar longitudinal shortening. RV morphology, ventricular dilation, and worse circumferential strain are associated with death or heart transplantation. The difference in myofiber architecture may contribute to suboptimal adaptation of the RV as a systemic ventricle.

Maldistribution of pulmonary artery blood flow (MPBF) is a potential complication in patients who have undergone single ventricle palliation culminating in the Fontan procedure. Cardiovascular magnetic resonance (CMR) is the best modality that can evaluate MPBF in this population. The purpose of this study is to identify the prevalence and associations of MPBF and to determine the impact of MPBF on exercise capacity after the Fontan operation. This retrospective single-center study included all patients after Fontan operation who had maximal cardiopulmonary exercise test (CPET) and CMR with flow measurements of the branch pulmonary arteries. MPBF was defined as > 20% difference in branch pulmonary artery flow. Exercise capacity was measured as percent of predicted oxygen consumption at peak exercise (% predicted VO2). Linear and logistic regression models were used to determine univariate and multivariable predictors of exercise capacity and correlates of MPBF, respectively. A total of 147 patients who had CMR between 1999 and 2017 were included (median age at CMR 21.8 years [interquartile range (IQR) 16.5–30.6]) and the median time between CMR and CPET was 2.8 months [IQR 0–13.8]. Fifty-three patients (36%) had MPBF (95% CI 29–45%). The mean % predicted VO2 was 63 ± 16%. Patients with MPBF had lower mean % predicted VO2 compared to patients without MPBF (60 ± 14% versus 65 ± 16%, p = 0.04). On multivariable analysis, a lower % predicted VO2 was independently associated with longer time since Fontan, higher ventricular mass-to-volume ratio, and MPBF. On multivariable analysis, only compression of the branch pulmonary arteries by the ascending aorta or aortic root was associated with MPBF (OR 6.5, 95% CI 5.6–7.4, p < 0.001). In patients after the Fontan operation, MPBF is common and is independently associated with lower exercise capacity. MPBF was most likely to be caused by pulmonary artery compression by the aortic root or the ascending aorta. This study identifies MPBF as an important risk factor and as a potential target for therapeutic interventions in this fragile patient population.

Background and Aims: Robust and convenient risk stratification of patients with paediatric and adult congenital heart disease (CHD) is lacking. This study aims to address this gap with an artificial intelligence-enhanced electrocardiogram (ECG) tool across the lifespan of a large, diverse cohort with CHD. Methods: A convolutional neural network was trained (50%) and tested (50%) on ECGs obtained in cardiology clinic at the Boston Children’s Hospital to detect 5-year mortality. Temporal validation on a contemporary cohort was performed. Model performance was evaluated using the area under the receiver operating characteristic and precision-recall curves. Results: The training and test cohorts composed of 112 804 ECGs (39 784 patients; ECG age range 0–85 years; 4.9% 5-year mortality) and 112 575 ECGs (39 784 patients; ECG age range 0–92 years; 4.6% 5-year mortality from ECG), respectively. Model performance (area under the receiver operating characteristic curve 0.79, 95% confidence interval 0.77–0.81; area under the precision-recall curve 0.17, 95% confidence interval 0.15–0.19) outperformed age at ECG, QRS duration, and left ventricular ejection fraction and was similar during temporal validation. In subgroup analysis, artificial intelligence-enhanced ECG outperformed left ventricular ejection fraction across a wide range of CHD lesions. Kaplan–Meier analysis demonstrates predictive value for longer-term mortality in the overall cohort and for lesion subgroups. In the overall cohort, precordial lead QRS complexes were most salient with high-risk features including wide and low-amplitude QRS complexes. Lesion-specific high-risk features such as QRS fragmentation in tetralogy of Fallot were identified. Conclusions: This temporally validated model shows promise to inexpensively risk-stratify individuals with CHD across the lifespan, which may inform the timing of imaging/interventions and facilitate improved access to care.