The health digital twin model to tackle cardiovascular disease: mapping an emerging interdisciplinary field

Abstract

Precision or personalised medicine seeks to manage the differences between patients with the same condition, using tailored diagnostics and treatment. Potential benefits in cardiovascular disease (CVD) include optimising risk stratification and treatment selection using multiple clinical, imaging, molecular, and other variables. An approach to realising this potential is the concept of the digital twin, whereby a virtual patient receives real-time updates of a range of data variables in order to predict disease and improve treatment selection in the real-life patient. Here we explore the concepts and challenges within this emerging field, and identify digital twin applications in CVD. A modified mapping review was undertaken, using a systematic search strategy from multiple data sources. The review found that digital twin research for CVD and other conditions is established globally. CVD applications were generally more-traditional simulation models, although some precursor models exist for the real-time cyber-physical system characteristic of a true digital twin. Key challenges in digital twin science concern computational power needs, cybersecurity, data sharing issues, ethical constraints, and potential clinician barriers to adoption of decision tools derived from artificial intelligence systems.