Haixin Huang

Background: Pediatric heart failure (PHF) is a heterogeneous syndrome with high morbidity, but existing classification systems inadequately capture its developmental and pathophysiological complexity due to reliance on adult-centric parameters. Using machine learning, we aimed to identify clinically distinct PHF phenotypes with unique outcomes and therapeutic implications. Methods: In this multicenter retrospective study, we analyzed 2903 consecutive PHF patients (≤18 years) from 30 Chinese tertiary centers from 20 provinces (2013–2022). Unsupervised machine learning (k-means clustering with PCA) evaluated 99 clinical, biomarker, and echocardiographic variables to derive phenotypes, which were compared for mortality, hospitalization, and treatment responses. Results: Three phenotypically distinct clusters emerged. Cluster 1 (Chronic Hypertensive and Cardiorenal Profile, 30.1%) predominantly affected older children (78%) with hypertension (54.4%), renal dysfunction (creatinine 45.8 μmol/L), and ventricular tachycardia (53.8%). This cluster showed the lowest in-hospital mortality (2.5%) but frequent 7–14 day hospitalizations (35.8%) and the highest beta-blocker use (54.5%). Cluster 2 (Preterm and CHD-Associated HF, 43.4%) comprised preterm infants (71.4%) with congenital heart disease (72.2%) and preserved LVEF (67%), demonstrating the highest mortality (5.1%) and prolonged stays (>30 days: 10.6%) with predominant diuretic (40.6%) and antibiotic use (54.3%). Cluster 3 (Fulminant Myocarditis Profile, 26.5%) exhibited cardiogenic shock with severely reduced LVEF (33%) and elevated BNP (3234 pg/mL), showing bimodal outcomes (4.8% LOS < 3 days vs. 32.2% LOS 15–30 days) and the highest IVIG utilization (46.5%) with intermediate mortality (3.8%). The majority of between-group differences were statistically significant (p < 0.001). Conclusions: Machine learning identified three PHF phenotypes with distinct in-hospital risk profiles and therapeutic implications, challenging current classification systems. These findings highlight the potential for phenotype-specific management strategies and provide a rationale for future research into arrhythmia prevention in hypertensive profiles and early immunomodulation in fulminant myocarditis, while highlighting the need for specialized care pathways for preterm/CHD patients. Prospective validation is warranted to translate this framework into clinical practice.

Background: Pediatric heart failure (PHF) remains a major contributor to morbidity and mortality, yet standardized diagnostic and prognostic frameworks–particularly those leveraging left ventricular ejection fraction (LVEF)–are not well-established. This study evaluates clinical profiles, therapeutic interventions, and mortality outcomes across LVEF thresholds while identifying an optimal cutoff to refine risk stratification in PHF. Methods: This multicenter retrospective cohort study analyzed 1449 PHF patients (aged 1–18 years) across 30 tertiary centers (2013–2022). LVEF stratification employed conventional thresholds (50%, 55%) and an ROC-optimized cutoff (53%, derived via Youden index maximization). The primary outcome was in-hospital all-cause mortality. Multivariable logistic regression models, adjusted for clinical covariates, evaluated mortality predictors. The discriminative performance of LVEF thresholds was compared using area under the curve (AUC) analysis. Results: Distinct clinical profiles, etiologies, and treatments were observed across LVEF strata (50% vs. 55%; p < 0.05). A data-driven optimized LVEF threshold of 53% was identified for mortality prediction, demonstrating superior diagnostic accuracy with enhanced sensitivity and specificity across age groups. Multivariate analysis revealed LVEF ≥ 55% as protective (OR = 0.81, 95% CI: 0.68–0.96, p = 0.003), while ≥50% was non-significant (OR = 0.91, 95% CI: 0.74–1.12, p = 0.06). Elevated BNP (OR = 2.78, p < 0.001) and NT-proBNP (OR = 2.34, p < 0.001) strongly correlated with mortality risk. Age and sex showed no significant association with outcomes. Conclusion: In conclusion, an LVEF of 53% emerged as the optimal pediatric threshold for mortality prediction, outperforming conventional cutoffs of 50% and 55%. The integration of LVEF with biomarkers (BNP/NT-proBNP) provides a robust prognostic framework, underscoring the necessity for pediatric-specific LVEF criteria and multidimensional risk assessment in PHF management.