In recent years, machine learning methods have revolutionised data acquisition, analysis, imaging, and mathematical modelling in virtually every field of science, engineering and medicine. Cardiac research is no exception. Data-driven and model-based methods can reconstruct and combine various data from multimodal measurements far more extensively and in greater detail than before. This information can improve the understanding of physiology and disease mechanisms, and enhance the diagnosis and therapy of cardiac arrhythmias and other pathologies. Such research also has wider implications within the field of network physiology, where cardiac health plays an important role on the functionality of other organs and their physiological interactions.
The goal of this Research Topic is to comprehensively present the current state of research and application of modern machine learning methods in cardiac research, with relevance to network physiology. To achieve this goal, as many expert researchers as possible will be asked to present their current projects and results in this rapidly developing field. Since many of the methods developed and applied are universally applicable, we expect a high level of attention for this Research Topic and thus an accelerated dissemination of the diverse, novel methods.
We encourage submission of original research and short review articles that address the development, implementation, and application of artificial intelligence methods in cardiac research, including:
- prediction and reconstruction of relevant dynamical variables and parameters from observed data
- development and evaluation of novel machine learning methods applied to cardiac data
- AI assisted data assimilation based on (pre-) clinically available data
- advanced image and signal analysis methods employing machine learning
- novel tools for diagnostics and personalized medicine (e.g., digital twins}.
Keywords:
Machine learning in cardiology, electrocardiograms (EEG), data-driven cardiac modelling, cardiac MRI, echocardiography, cardiac digital twins, cardiac electrophysiology, cardiac biomechanics, physics-informed machine learning, network physiology
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
In recent years, machine learning methods have revolutionised data acquisition, analysis, imaging, and mathematical modelling in virtually every field of science, engineering and medicine. Cardiac research is no exception. Data-driven and model-based methods can reconstruct and combine various data from multimodal measurements far more extensively and in greater detail than before. This information can improve the understanding of physiology and disease mechanisms, and enhance the diagnosis and therapy of cardiac arrhythmias and other pathologies. Such research also has wider implications within the field of network physiology, where cardiac health plays an important role on the functionality of other organs and their physiological interactions.
The goal of this Research Topic is to comprehensively present the current state of research and application of modern machine learning methods in cardiac research, with relevance to network physiology. To achieve this goal, as many expert researchers as possible will be asked to present their current projects and results in this rapidly developing field. Since many of the methods developed and applied are universally applicable, we expect a high level of attention for this Research Topic and thus an accelerated dissemination of the diverse, novel methods.
We encourage submission of original research and short review articles that address the development, implementation, and application of artificial intelligence methods in cardiac research, including:
- prediction and reconstruction of relevant dynamical variables and parameters from observed data
- development and evaluation of novel machine learning methods applied to cardiac data
- AI assisted data assimilation based on (pre-) clinically available data
- advanced image and signal analysis methods employing machine learning
- novel tools for diagnostics and personalized medicine (e.g., digital twins}.
Keywords:
Machine learning in cardiology, electrocardiograms (EEG), data-driven cardiac modelling, cardiac MRI, echocardiography, cardiac digital twins, cardiac electrophysiology, cardiac biomechanics, physics-informed machine learning, network physiology
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.