A logistic regression model incorporating cardiac magnetic resonance parameters, including late gadolinium enhancement and left ventricular ejection fraction, predicted adverse cardiac events in pediatric myocarditis with an AUC of 0.893.
Cohort (n=77)
No
Machine learning models incorporating CMR parameters, particularly late gadolinium enhancement and left ventricular ejection fraction, can effectively predict poor prognosis in pediatric patients with acute myocarditis.
OBJECTIVE: To develop machine learning (ML) models incorporating explanatory cardiac magnetic resonance (CMR) parameters for predicting the prognosis of myocarditis in pediatric patients. MATERIALS AND METHODS: 77 patients with pediatric myocarditis diagnosed clinically between January 2020 and December 2023 were enrolled retrospectively. All patients were examined by ultrasound, electrocardiogram (ECG), serum biomarkers on admission, and CMR scan to obtain 16 explanatory CMR parameters. All patients underwent follow-up echocardiography and CMR. Patients were divided into two groups according to the occurrence of adverse cardiac events (ACE) during follow-up: the poor prognosis group (n = 23) and the good prognosis group (n = 54). Four models were established, including logistic regression (LR), random forest (RF), support vector machine classifier (SVC), and extreme gradient boosting (XGBoost) model. The performance of each model was evaluated by the area under the receiver operating characteristic curve (AUC). Model interpretation was generated by Shapley additive interpretation (Shap). RESULTS: Among the four models, the three most important features were late gadolinium enhancement (LGE), left ventricular ejection fraction (LVEF), and SAXPeak Global Circumferential Strain (SAXGCS). In addition, LGE, LVEF, SAXGCS, and LAXPeak Global Longitudinal Strain (LAXGLS) were selected as the key predictors for all four models. Four interpretable CMR parameters were extracted, among which the LR model had the best prediction performance. The AUC, sensitivity, and specificity were 0.893, 0.820, and 0.944, respectively. The findings indicate that the presence of LGE on CMR imaging, along with reductions in LVEF, SAXGCS, and LAXGLS, are predictive of poor prognosis in patients with acute myocarditis. CONCLUSION: ML models, particularly the LR model, demonstrate the potential to predict the prognosis of children with myocarditis. These findings provide valuable insights for cardiologists, supporting more informed clinical decision-making and potentially enhancing patient outcomes in pediatric myocarditis cases.
Hu et al. (Fri,) conducted a cohort in Pediatric myocarditis (n=77). Logistic Regression machine learning model based on CMR parameters vs. Other machine learning models (Random Forest, SVC, XGBoost) was evaluated on Area under the receiver operating characteristic curve (AUC) for predicting adverse cardiac events. A logistic regression model incorporating cardiac magnetic resonance parameters, including late gadolinium enhancement and left ventricular ejection fraction, predicted adverse cardiac events in pediatric myocarditis with an AUC of 0.893.