Computational Methods and Data-Driven Approaches in Cardiovascular Modeling

Cardiovascular diseases remain a leading cause of mortality globally, driving the need for more precise diagnostic and predictive tools. Traditional computational fluid dynamics (CFD) and fluid-structure interaction (FSI) models have provided deep insights into hemodynamic patterns and arterial mechanics relevant to disease diagnosis and mechanisms. However, the translation of these models into clinical practice is challenging due to high computational costs, lack of clinical validation, as well as the inherent biological variability and limited accessibility of patient-specific data.

Recent advances in Artificial Intelligence (AI) are opening new opportunities to address these challenges. In particular, Machine Learning (ML) techniques are enabling data-driven strategies that accelerate simulations through surrogate or reduced-order models and enhance medical image analysis. By automating image segmentation and extracting high-dimensional features from clinical imaging data, ML helps connect raw medical images and advanced numerical simulations, paving the way toward personalized cardiovascular Digital Twins.

The goal of this Research Topic is to showcase the synergy between traditional computational modeling and emerging data-driven technologies. We aim to collect contributions that advance the current state-of-the-art in cardiovascular modeling, addressing key challenges such as improving model building, computational efficiency, refining patient-specific parameter identification, and enhancing model reliability.

By bringing together experts in biomechanics, data science, and clinical imaging, we intend to record advancements for the future development of integrated frameworks for clinical planning, risk stratification, and the design of cardiovascular devices. Ultimately, the objective is to highlight how the convergence of physics-based and data-driven methods can lead to more robust, interpretable, and clinically useful cardiovascular models.

We welcome research papers focusing on innovative computational models and methods for the cardiovascular system. We additionally encourage submissions that leverage advanced data-driven approaches, AI-based methods, or hybrid frameworks. This collection will accept the following article types: Original Research, Systematic Review, Methods and Review. The scope includes, but is not limited to:

• Advanced CFD and FSI simulations of blood flow in cardiovascular structures
• Machine Learning applied to cardiovascular image segmentation, reconstruction, and feature extraction
• Hybrid models combining physics and data-driven approaches
• Uncertainty quantification and sensitivity analysis
• Multiscale modeling and clinical applications of cardiovascular Digital Twins
• Translational studies and clinical decision support tools utilizing computational pipelines