Towards a Design Ecosystem for a Personal Digital Twin for Well-Being

This thesis focuses on Personal Digital Twins (PDTs) for well-being and their transformative impact on healthcare. It proposes an integration of technologies such as virtual reality, artificial intelligence (AI), machine learning (ML), and data analytics, which opens new avenues for research in eHealth and Personal Digital Twins for well-being. The thesis presents the design of an ecosystem for implementing PDTs for healthcare, which extends beyond the traditional boundaries of telemedicine. This ecosystem is scalable and interoperable, capable of handling real-time health data from various sources, including electronic health records, wearable sensors, and patient-generated data. The core of the thesis explores the challenges of designing a digital twin that not only replicates a patient's physical state but also interacts dynamically with health data to offer personalized care. The study emphasizes the role of machine learning (ML) in processing vast amounts of health data, enabling predictive health insights and enhancing the decision-making process in clinical settings. This integration also opens the door for practical applications that promise to revolutionize patient monitoring, diagnostics, and treatment planning, moving towards a more proactive and preventive healthcare model. The thesis presents the implementations of two PDTs proof of concepts, namely Cardio Twin and COVIDMe. However, deploying PDTs for health is not without challenges; this thesis discusses the potential challenges in adopting this technology. It sets a foundational blueprint for the future exploration of personal digital twins for health. It paves the way for innovative research lines, advocating for a collaborative approach that involves researchers, healthcare professionals, engineers, and policymakers.