Integrated Model for Predicting Cancer Therapy-Related Cardiac Dysfunction in Non-Hodgkin Lymphoma

Background/Objectives: Cancer Therapy-Related Cardiac Dysfunction (CTRCD) is a major complication in patients with non-Hodgkin lymphoma (NHL), potentially leading to heart failure and other severe cardiovascular events. Early identification of patients at risk is crucial for timely interventions. Methods: A prospective analytical cohort study was conducted on 127 adult NHL patients to evaluate chemotherapy-related cardiac dysfunction over a 6-month period, with the aim of assessing early adverse cardiac effects. Assessments included echocardiography, cardiorespiratory exercise testing, 24-h Holter monitoring, and measurement of cardiac-specific biomarkers (troponin I and NT-proBNP) to identify early subclinical cardiac changes. Results: A predictive model for CTRCD was developed using clinical, serological, echocardiographic, cardiopulmonary, and treatment-related parameters in patients with non-Hodgkin lymphoma. The model demonstrated high overall accuracy (94.2%) and strong discriminative ability (AUC 0.95; precision-sensitivity AUC 0.824) for 6-month cardiotoxicity. SHAP analysis identified the most influential predictors as baseline SDNNi, mean daily heart rate, total doxorubicin dose, NT-proBNP, QT corrected interval, hemoglobin, age, left atrial volume, and diastolic function indices (E/e', E/A). Lower cardiopulmonary reserve was also associated with increased risk. Conclusions: The predictive model developed in this study serves as a practical and robust tool for assessing the risk of cancer therapy-related cardiac dysfunction.