Empagliflozin Protects Against Doxorubicin Cardiotoxicity: Integrative Assessment of Cardiac Kinetics and Electrophysiology Using Machine Learning in a Rat Model

Background/Objectives: Anthracycline-induced cardiotoxicity remains a major challenge in cancer treatment, and researchers are showing interest in artificial intelligence (AI) to improve the prediction and detection of cancer therapy-related cardiac dysfunction (CTRCD). Current surveillance strategies rely mainly on left ventricular ejection fraction and, more recently, global longitudinal strain. Methods: The present study was designed to evaluate cardiac performance in a rat model of doxorubicin-induced cardiotoxicity and empagliflozin-mediated cardioprotection using a machine learning-based analytical framework. Eighteen adult male Sprague–Dawley rats were assigned to five experimental groups. We aimed to quantify ventricular wall dynamics and contractility using an advanced image-processing and object-detection model that has not been previously used to distinguish normal from impaired cardiac kinetics. During real-time recording, simultaneous electrocardiogram monitoring was performed, enabling direct correlation between deep learning-based ventricular wall motion metrics and cardiac electrical activity. The cardioprotective effects of empagliflozin were further validated by immunofluorescence staining (cTnI, vimentin, α-SMA, and Cx43) of rat cardiomyocytes and paraffin-embedded cardiac tissue, demonstrating attenuation of cellular injury and structural remodeling. Results: The integrated analysis of cardiac kinetic patterns derived via machine learning distinguishes not only extreme cardiotoxicity, but also tracks a graded pattern consistent with ECG-derived severity and treatment-related functional preservation. These findings indicate that the algorithm captures the gradient of empagliflozin’s cardioprotective effect within this internally validated preclinical setting. Additionally, immunofluorescence results validated the benefits of SGLT2 inhibition on myocardial integrity. Conclusions: The novelty of the present work lies at the intersection of advanced cardiac kinetic analysis using AI, preclinical modeling, and SGLT2-mediated cardioprotection in cardio-oncology.