Towards continuous monitoring in personalized healthcare through digital twins

Continuous and effective monitoring of chronic diseases and their associated treatments might have a decisive impact on reducing risks and improving life quality of patients. This, however, demands new and innovative methods for engineering systems that support the required capabilities. Research on the application of the novel concept of Digital Twin (DT) in healthcare might provide the means to revolutionize traditional medical practices. A DT comprises a set of virtual representations of both the structural elements and dynamics of any physical asset (e.g., a patient) throughout its lifecycle. In the healthcare domain, it might represent a significan step forward towards tightening and improving the interactions between systems, caregivers and patients. Moreover, integrating data-driven methods (e.g., Machine Learning) and DT could serve as a noteworthy mechanism to not only track patients' health continuously, but also to evaluate the application and evolution of medical treatments virtually. In this paper, we describe our vision for the application of DT in precision medicine. Our contributions are twofold. First, we describe our initial ideas for a reference model that leverages DT capabilities and research advances in self-adaptive systems and autonomic computing to engineer smart and fl xible software systems in healthcare. We expect these systems to alleviate complexity and assist in the planning and decision-making processes when applying medical treatments to patients by healthcare professionals. Then, we elaborate on the definitio of internal structures for DT to support precision medicine techniques in the context of continuous monitoring and personalized data-driven medical treatments.