Treatment of Ventricular Tachycardia in Patients with Acute Myocardial Infarction: A Review of Current Approaches and the Potential of Hybrid Modeling

Abstract

This article discusses various approaches to understanding and predicting the risk of ventricular tachycardia (VT) in patients with acute myocardial infarction. These approaches include evidence-based medicine, which involves using the best available scientific evidence to inform clinical decision-making in the context of arrhythmogenic mechanisms such as VT; data-driven models, including artificial intelligence techniques such as machine learning and deep learning, which identify relationships in data and make predictions; and patientcentered modeling, which involves creating a patient-specific heart model based on multiple sources The texts also discuss the use of ablation to reduce VT and the potential of digital twins, which are virtual patient models that combine clinical data with mechanistic and data-driven models to improve personalized diagnosis, disease prediction, treatment planning, and prevention recommendations.