Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling.

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.

Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics.

BACKGROUND: Individuals with a Fontan circulation encompass a heterogeneous group with adverse outcomes linked to ventricular dilation, dysfunction, and dyssynchrony. The purpose of this study was to assess if unsupervised machine learning cluster analysis of cardiovascular magnetic resonance (CMR)-derived dyssynchrony metrics can separate ventricles in the Fontan circulation from normal control left ventricles and identify prognostically distinct subgroups within the Fontan cohort. METHODS: This single-center, retrospective study used 503 CMR studies from Fontan patients (median age 15 y) and 42 from age-matched controls from January 2005 to May 2011. Feature tracking on short-axis cine stacks assessed radial and circumferential strain, strain rate, and displacement. Unsupervised K-means clustering was applied to 24 mechanical dyssynchrony metrics derived from these deformation measurements. Clusters were compared for demographic, anatomical, and composite outcomes of death, or heart transplantation. RESULTS: Four distinct phenotypic clusters were identified. Over a median follow-up of 4.2 y (interquartile ranges 1.7-8.8 y), 58 (11.5%) patients met the composite outcome. The highest-risk cluster (largely comprised of right or mixed ventricular morphology and dilated, dyssynchronous ventricles) exhibited a higher hazard for the composite outcome compared to the lowest-risk cluster while controlling for ventricular morphology (hazard ratio [HR] 6.4; 95% confidence interval [CI] 2.1-19.3; P value 0.001) and higher indexed end-diastolic volume (HR 3.2; 95% CI 1.04-10.0; P value 0.043) per 10 mL/m2. CONCLUSION: Unsupervised machine learning using CMR-derived dyssynchrony metrics identified four distinct clusters of patients with Fontan circulation and healthy controls with varying clinical characteristics and risk profiles. This technique can be used to guide future studies and identify more homogeneous subsets of patients from an overall heterogeneous population.

Cardiac Biomarkers Aid in Differentiation of Kawasaki Disease from Multisystem Inflammatory Syndrome in Children Associated with COVID-19.

Kawasaki disease (KD) and Multisystem Inflammatory Syndrome in Children (MIS-C) associated with COVID-19 show clinical overlap and both lack definitive diagnostic testing, making differentiation challenging. We sought to determine how cardiac biomarkers might differentiate KD from MIS-C. The International Kawasaki Disease Registry enrolled contemporaneous KD and MIS-C pediatric patients from 42 sites from January 2020 through June 2022. The study population included 118 KD patients who met American Heart Association KD criteria and compared them to 946 MIS-C patients who met 2020 Centers for Disease Control and Prevention case definition. All included patients had at least one measurement of amino-terminal prohormone brain natriuretic peptide (NTproBNP) or cardiac troponin I (TnI), and echocardiography. Regression analyses were used to determine associations between cardiac biomarker levels, diagnosis, and cardiac involvement. Higher NTproBNP (≥ 1500 ng/L) and TnI (≥ 20 ng/L) at presentation were associated with MIS-C versus KD with specificity of 77 and 89%, respectively. Higher biomarker levels were associated with shock and intensive care unit admission; higher NTproBNP was associated with longer hospital length of stay. Lower left ventricular ejection fraction, more pronounced for MIS-C, was also associated with higher biomarker levels. Coronary artery involvement was not associated with either biomarker. Higher NTproBNP and TnI levels are suggestive of MIS-C versus KD and may be clinically useful in their differentiation. Consideration might be given to their inclusion in the routine evaluation of both conditions.

Updated Case Definition of MIS-C and Implications for Clinical Care.

OBJECTIVES: A broad, surveillance case definition was implemented when multisystem inflammatory syndrome in children (MIS-C) emerged in 2020. In 2023, a revised MIS-C case definition was constructed to improve specificity and reduce misclassification with other pediatric inflammatory conditions. This study aims to describe the impact of the updated definition on the classification of patients with MIS-C and Kawasaki Disease (KD). METHODS: Patients hospitalized from March 2020 to November 2022 with clinician-diagnosed KD and MIS-C at a single center were studied retrospectively. Specificity and positive predictive value were assessed; McNemar test was used to compare specificity. RESULTS: Among 119 patients with MIS-C per the 2020 definition, 20 (17%) did not fulfill the 2023 definition. Six of these 20 (30%) had shock or cardiac involvement. Of 59 KD patients, 10 (17%) met the 2020 MIS-C definition. Five patients (8%) met the 2023 MIS-C definition. Specificity for the 2020 and 2023 MIS-C definitions among KD patients were 83.1% and 91.5% respectively (McNemar, P = .0736). Positive predictive value was higher for the 2023 MIS-C case definition compared with the 2020 MIS-C case definition (95.2% vs 92.2%). CONCLUSIONS: Approximately 1 in 5 patients diagnosed with MIS-C using the 2020 case definition did not meet the 2023 definition, including patients with cardiovascular dysfunction. Overlap persisted between patients meeting KD and 2023 MIS-C case definitions, with a false positive rate of 8%. Implications for treatment should be considered, particularly in settings where presumed MIS-C may be treated with corticosteroid monotherapy.

Comparative utility of omnipolar and bipolar electroanatomic mapping methods to detect and localize dual nodal substrate in patients with atrioventricular nodal reentrant tachycardia.

BACKGROUND: Catheter-based slow pathway modification (SPM) for atrioventricular nodal reentrant tachycardia (AVNRT) is traditionally performed at empiric sites using anatomical landmarks and test ablation feedback within the triangle of Koch (TK). While studies have described more tailored techniques such as bipolar low voltage bridge (LVB) and wavefront collision identification, few have systematically compared the diagnostic yields of each and none have investigated whether omnipolar mapping technology provides incremental benefit. The objective of this study was to compare the utility of omnipolar and bipolar-derived qualitative and quantitative measurements in identifying and localizing dual AVN substrate in patients with versus without AVNRT. METHODS: A retrospective case-control study of consecutive patients with paroxysmal supraventricular tachycardia undergoing electrophysiology study with both omnipolar and bipolar mapping from 2022-2023. RESULTS: Thirteen AVNRT cases (median age 16.1 years, 512 TK points) were compared to nine non-AVNRT controls (median age 15.7 years, 332 TK points). Among qualitative variables, an omnipolar activation vector pivot, defined as a ≥45 degree change in activation direction within the TK, had the highest positive (81%) and negative predictive values (100%) for identifying AVNRT cases and had a median distance of 1 mm from SPM sites. Among quantitative variables, the optimal discriminatory performance for successful SPM sites was observed using bipolar voltage restricted to a peak frequency >340 Hz (c statistic 0.75). CONCLUSIONS: Omnipolar vector pivot analysis represents an automated, annotation-independent qualitative technique that is sensitive and specific for AVNRT substrate and co-localizes with successful SPM sites. Bipolar voltage quantitatively describes SP anisotropy better than omnipolar voltage, and the addition of peak frequency signal analysis further optimizes the selection of SPM sites.

Epicardial pacing outcomes in infants with heart block: Lead and device complications from a multicenter experience.

BACKGROUND: Infants with complete heart block (CHB) require epicardial pacemaker (PM) insertion. Prior studies described epicardial pacing outcomes in infants and children, although they were limited by small or heterogeneous populations. OBJECTIVE: This study aimed to explore patient- and procedure-level associations with device complications in infants with CHB who received a permanent PM. METHODS: This was a multicenter, retrospective cohort study including infants receiving an epicardial PM between 2000 and 2021 for CHB. The primary outcome was time to device-related adverse event: lead failure requiring revision; pocket infection; exit block requiring increased pacing output; or lead-related coronary artery compression. Time-to-event analysis was performed by the Kaplan-Meier method with a multivariable Cox proportional hazards model. RESULTS: There were 174 infants who received an epicardial PM (282 bipolar, 39 unipolar leads) for CHB. Median age and weight at PM were 93.5 days and 4.5 kg, respectively. Pacing indication was postoperative CHB in 63% and congenital CHB in 37%. The median follow-up was 2.1 years. The primary outcome occurred in 26 infants at a median time to event of 0.6 year. Age ≤90 days at PM implantation was the most significant risk factor for a device-related adverse event (hazard ratio, 7.02; P < .001), primarily driven by pocket infections. Lead failure occurred in 3% of leads with a 5- and 10-year freedom from failure of 93% and 83%, respectively. CONCLUSION: Device complications affect 15% of infants receiving a permanent PM for heart block. Age ≤90 days at PM implantation is especially associated with infectious complications. Epicardial lead durability appears similar to previously reported pediatric experiences.

Epidemiology of Postoperative Junctional Ectopic Tachycardia in Infants Undergoing Cardiac Surgery.

BACKGROUND: Junctional ectopic tachycardia (JET) complicates congenital heart surgery in 2% to 8.3% of cases. JET is associated with postoperative morbidity in single-center studies. We used the Pediatric Cardiac Critical Care Consortium data registry to provide a multicenter epidemiologic description of treated JET. METHODS: This is a retrospective study (February 2019-August 2022) of patients with treated JET. Inclusion criteria were (1) <12 months old at the index operation, and (2) treated for JET <72 hours after surgery. Diagnosis was defined by receiving treatment (pacing, cooling, and medications). A multilevel logistic regression analysis with hospital random effect identified JET risk factors. Impact of JET on outcomes was estimated by margins/attributable risk analysis using previous risk-adjustment models. RESULTS: Among 24,073 patients from 63 centers, 1436 (6.0%) were treated for JET with significant center variability (0% to 17.9%). Median time to onset was 3.4 hours, with 34% present on admission. Median duration was 2 days (interquartile range, 1-4 days). Tetralogy of Fallot, atrioventricular canal, and ventricular septal defect repair represented >50% of JET. Patient characteristics independently associated with JET included neonatal age, Asian race, cardiopulmonary bypass time, open sternum, and early postoperative inotropic agents. JET was associated with increased risk-adjusted durations of mechanical ventilation (incidence rate ratio, 1.6; 95% CI, 1.5-1.7) and intensive care unit length of stay (incidence rate ratio, 1.3; 95% CI, 1.2-1.3), but not mortality. CONCLUSIONS: JET is treated in 6% of patients with substantial center variability. JET contributes to increased use of postoperative resources. High center variability warrants further study to identify potential modifiable factors that could serve as targets for improvement efforts to ameliorate deleterious outcomes.