Artificial Intelligence, Computational Biomechanics, and Multimodal Imaging for Valve Disease Phenotyping and Risk Prediction

This is a Research Topic initiated by ISACB, the International Society for Applied Cardiovascular Biology.Artificial intelligence (AI) and computational biomechanics are creating a new paradigm in the diagnosis and treatment of valvular heart disease. By integrating echocardiography, CT, and cardiac MRI, machine learning allows automated, quantitative assessment of valve morphology, function, and flow dynamics. In parallel, fluid–structure interaction simulations and patient-specific digital twins are enabling mechanistic understanding and predictive modeling of individual procedures. However, clinical adoption remains limited by variability in data quality, lack of prospective validation, and incomplete integration into clinical workflows. Ensuring that these tools are validated across diverse patient populations, imaging platforms, and clinical environments remains essential to equitable and generalizable implementation.This Research Topic aims to accelerate the implementation of AI-based and simulation-based methods for diagnosis, risk stratification, treatment planning, and outcome prediction in valve disease, with emphasis on clinically actionable tools that support guideline-based management and real-world decision-making. Through collaboration among clinicians, imaging experts, engineers, and data scientists, it seeks to establish validated, interpretable, equitable, and generalizable frameworks for precision cardiology.We welcome contributions addressing, but not limited to, the following areas:o Deep learning for automated echocardiographic quantification of morphology, disease progression, and severity gradingo CT-based AI pipelines for aortic valve calcium scoring, leaflet assessment, TAVR and SAVR procedural planning o Cardiac MRI and 4D flow imaging for hemodynamic characterization and remodeling quantificationo Fluid–structure interaction and finite element modeling for native and prosthetic valve dynamicso Patient-specific digital twins for anatomical reconstruction, simulation, and device sizingo AI-guided discovery of imaging biomarkers for early disease and structural degenerationo Integration of multimodal imaging with molecular, genetic, and clinical data for precision risk predictiono Prospective validation studies, clinical endpoints, and regulatory frameworks for AI deploymento Algorithm explainability and clinical adoption in decision support for valvular interventionso Multicenter validation, fairness, and generalizability of AI models across diverse patient populations, imaging vendors, and health systems. Topic editors: Antonino S Rubino, Mabruka Alfaidi Source: https://www.frontiersin.org/research-topics/84512/artificial-intelligence-computational-biomechanics-and-multimodal-imaging-for-valve-disease-phenotyping-and-risk-prediction