Artificial intelligence applications in hypertrophic cardiomyopathy: turns and loopholes

Abstract

Hypertrophic cardiomyopathy (HCM) is a heterogeneous disease where, despite recent advances, accurate diagnosis, risk stratification, and personalized treatment remain challenging. Artificial intelligence (AI) offers a transformative approach to HCM by enabling rapid, precise analysis of complex data. This article reviews the current and potential applications of AI in HCM. AI enhances diagnostic accuracy by analysing electrocardiograms, echocardiography, and cardiac magnetic resonance images, differentiating HCM from other forms of left ventricular hypertrophy, identifying subtle phenotypic variations, and standardizing myocardial fibrosis assessment. Multimodal AI-driven approaches improve risk stratification, therapeutic decision-making, and monitoring of both established and novel therapies, such as cardiac myosin inhibitors. Emerging AI-driven in silico trials and digital twin platforms highlight the potential of combining data-driven and knowledge-based AI with biophysical models to simulate patient-specific disease trajectories, supporting preclinical evaluation and personalized care. As a multidisciplinary case study, the SMASH-HCM consortium is presented to illustrate how digital twin technologies and hybrid modelling can bring AI into clinical practice. Integration of genetic data further enhances AI's ability to identify at-risk individuals and predict disease progression. However, widespread AI applications raise concerns regarding data privacy, ethical considerations, and the risk of biases. Guidelines for researchers and developers-e.g. on trustworthy AI, regulatory frameworks, and transparent policies-are essential to address these possible pitfalls. As AI rapidly evolves, it has the potential to revolutionize drug discovery, disease management, and the patient journey in HCM, making interventions more precise, timely, and patient-centred.

Keywords: Deep learning; Digital-twin; Hypertrophic cardiomyopathy; Left ventricular hypertrophy; Machine learning; artificial intelligence.

Graphical Abstract

Figure 1

Diagram illustrating AI taxonomy and the different applications in HCM. The figure illustrates the hierarchy of AI models, with ML encompassing DL, which includes CNNs, and NLP as a separate approach. AI applications in HCM, such as risk stratification, diagnosis, imaging analysis, genotype prediction, and patient management, are linked to their respective models using colour-coded arrows: blue for ML, yellow for DL, red for CNNs, and green for NLP. Overlapping connections indicate that multiple models can contribute to the same application, highlighting AI's versatility in HCM management. CNN, convolutional neural network; DL, deep learning; ECG, electrocardiogram; AI, artificial intelligence; CMI, cardiac myosin inhibitor; LVH, left ventricular hypertrophy; CMR, cardiac magnetic resonance; HCM, hypertrophic cardiomyopathy; ML, machine learning; NLP, natural language processing; oHCM, obstructive hypertrophic cardiomyopathy.

Figure 2

Timeline of key milestones in AI applications for HCM. This timeline illustrates selected landmark studies showcasing the evolution of artificial intelligence (AI) in the diagnosis, risk stratification, genetic profiling, and treatment evaluation of hypertrophic cardiomyopathy (HCM). Studies were included based on their innovation (e.g. first to introduce a novel AI application) or relevance (e.g. large-scale, multicentre, or externally validated work). The timeline is organized across thematic domains—early detection, differential diagnosis, genetic insights, risk stratification, treatment efficacy, and in silico trials/digital twin technologies—highlighting the progressive integration of AI into various aspects of HCM management. AI, artificial intelligence; CNN, convolutional neural network; ECG, electrocardiogram; LVH, left ventricular hypertrophy; HCM, hypertrophic cardiomyopathy.

Figure 3

SMASH-HCM project design. The SMASH-HCM project introduces a three-level digital twin platform designed to maximize risk stratification. At the first level, it integrates standard clinical data like ECGs and echocardiography with AI-driven insights from combined clinical, in vitro, and synthetic population data. The second level incorporates extended patient data, enabling the development of biophysical digital twin models. At the third level, the platform uses comprehensive phenotyping to refine the digital twin, providing advanced tools for personalized treatment and improved management. ECG, electrocardiogram; AI, artificial intelligence; LVH, left ventricular hypertrophy; CMR, cardiac magnetic resonance; HCM, hypertrophic cardiomyopathy; hiPSC-CM, human-induced pluripotent stem cell-derived cardiomyocytes; ICD, implantable cardioverter defibrillator; US, ultrasound.