Precision Medicine aims at providing the most accurate diagnosis and best treatments for each patient. Whereas this has primarily been genomic-centred so far, there is now a wide recognition of the need to consider a wide spectrum of lifestyle, environment, and biology conditions. Characterising such diversity of factors requires large quantity and quality of patients’ datasets, and at the same time, innovative approaches for their analysis, drawing on the increasing power of computers and algorithms. New concepts are being proposed, such as the Digital Twin, building on previous ones such as the Virtual Physiological Human, targeting the vision of ‘a comprehensive, virtual tool that integrates coherently and dynamically the clinical data acquired over time for an individual using statistical models and mechanistic modelling and simulation’. In this presentation, I will address this framework for cardiology, highlighting how combined computational approaches including modelling and simulation, and machine learning can boost the capacity for diagnosis and prognosis, as well as future treatments.