Hemodynamic Modeling, Medical Imaging, and Machine Learning and Their Applications to Cardiovascular Interventions

Cardiovascular disease is a deadly global health crisis that carries a substantial financial burden. Innovative treatment and management of cardiovascular disease straddles medicine, personalized hemodynamic modeling, machine learning, and modern imaging to help improve patient outcomes and reduce the economic impact. Hemodynamic modeling offers a non-invasive method to provide clinicians with new pre- and post- procedural metrics and aid in the selection of treatment options. Medical imaging is an integral part in clinical workflows for understanding and managing cardiac disease and interventions. Coupling machine learning with modeling, and cardiovascular imaging, provides faster modeling, improved data fidelity, and an enhanced understanding and earlier detection of cardiovascular anomalies, leading to the development of patient-specific diagnostic and predictive tools for characterizing and assessing cardiovascular outcomes. Herein, we provide a scoping review of translational hemodynamic modeling, medical imaging, and machine learning and their applications to cardiovascular interventions. We particularly focus on providing an intuitive understanding of each of these approaches and their ability to support decision making during important clinical milestones.

Automated summary

Cardiovascular disease presents a global health crisis with significant financial consequences. Innovative approaches such as personalized hemodynamic modeling, machine learning, and modern imaging have been employed to enhance patient outcomes and decrease the economic burden. Hemodynamic modeling offers a non-invasive method to provide valuable metrics for clinicians, while medical imaging plays a crucial role in understanding and managing cardiac disease. By combining machine learning with modeling and cardiovascular imaging, it is possible to improve modeling speed, data accuracy, and early detection of cardiovascular anomalies, leading to the development of patient-specific diagnostic and predictive tools. This review provides an overview of translational hemodynamic modeling, medical imaging, and machine learning, highlighting their potential in supporting decision making during critical clinical milestones.