Artificial Intelligence Advancements in Cardiomyopathies: Implications for Diagnosis and Management of Arrhythmogenic Cardiomyopathy

Abstract

Purpose of Review: This review aims to explore the emerging potential of artificial intelligence (AI) in refining risk prediction, clinical diagnosis, and treatment stratification for cardiomyopathies, with a specific emphasis on arrhythmogenic cardiomyopathy (ACM). Recent Findings: Recent developments highlight the capacity of AI to construct sophisticated models that accurately distinguish affected from non-affected cardiomyopathy patients. These AI-driven approaches not only offer precision in risk prediction and diagnostics but also enable early identification of individuals at high risk of developing cardiomyopathy, even before symptoms occur. These models have the potential to utilise diverse clinical input datasets such as electrocardiogram recordings, cardiac imaging, and other multi-modal genetic and omics datasets. Summary: Despite their current underrepresentation in literature, ACM diagnosis and risk prediction are expected to greatly benefit from AI computational capabilities, as has been the case for other cardiomyopathies. As AI-based models improve, larger and more complicated datasets can be combined. These more complex integrated datasets with larger sample sizes will contribute to further pathophysiological insights, better disease recognition, risk prediction, and improved patient outcomes.