Abstract <p>Hypertrophic cardiomyopathy (HCM) is an inherited myocardial disorder associated with sudden cardiac death, atrial fibrillation (AF), and stroke, with prognosis varying widely among patients. Accurate long-term risk prediction requires comprehensive assessment of cardiac function, including left atrial performance, but conventional clinical and echocardiographic markers may not fully reflect the complexity of disease progression. This study aimed to develop a machine learning-based model that integrates clinical, echocardiographic, and CMR-derived parameter to improve prognostic risk stratification in patients with HCM.&#xa0;Between June 2008 and January 2016, 223 patients with complete demographic, clinical, echocardiographic, and CMR data were enrolled in the analysis. The composite of clinical outcome included of all-cause mortality, implantable cardioverter defibrillator shock, heart failure-related hospitalization, new-onset AF, and new-onset ischemic stroke. Five machine learning methodologies were evaluated.&#xa0;Models incorporating CMR-derived parameters outperformed those based solely on clinical and echocardiographic data. Among all models, penalized logistic regression integrating clinical, echocardiographic, and left atrial (LA) strain parameters demonstrated the highest predictive performance (AUC = 0.840, C-index = 0.795), and effectively stratified the long-term risk of outcome (low-risk group: 0%, intermediate-risk group: 27.3%, high-risk group: 77.8%, <i>p</i> = 0.002). Additionally, the LA strain model showed robust predictive performance across individual outcome components. Shapley additive explanations (SHAP) value analysis identified LA strains related to conduit function as the most significant predictor.&#xa0;CMR-derived parameters provide supplementary predictive impact in patients with HCM, with LA strain consistently outperforming other variables. Machine learning-based methodologies can effectively incorporate multiple variables and offer an effective approach for long-term risk stratification.</p> Graphical abstract <p>Development of risk stratification tools using machine learning-based methodologies in patients with hypertrophic cardiomyopathy. The graphical abstract illustrates the summarised study design of this study. To avoid overfitting caused by multicollinearity and to capture non-linear relationship between diverse parameters, we apply machine-learning based methodologies to integrate clinical, echocardiographic, and CMR derived parameters in HCM patients. Among various models, models which incorporates clinical, echocardiographic data and LA strain derived by CMR showed highest performance. Also, LA strain exhibited robust predictive performance across all clinical outcomes. Finally, machine learning-based models incorporating regularization effectively stratify the risk of clinical outcomes in the validation set of HCM patients. Note. Heart illustration from NIAID NIH BIOART source (bioart.Niaid.Nih.Gov/bioart/228). Abbreviations: CMR, cardiac magnetic resonance; E/e’, ratio of early mitral inflow velocity to early diastolic mitral annular velocity; ivsd, inter-ventricular septum thickness in diastole; LA, left atrium; LAEF, left atrial emptying fraction; LGE, late gadolinium enhancement; LV, left ventricle; LVEF, left ventricular ejection fraction measured by echocardiography; lvidd, left ventricular internal dimension at diastole; lvids, left ventricular internal dimension at systole; lvpwd, left ventricular posterobasal free wall thickness; SCD, sudden cardiac death; SHAP, shapley additive explanations; SR, strain rate</p> <p></p>