Digital Twins for Healthcare and Telecommunications Applications: A Survey

Being a virtual model, designed to accurately reflect a physical object, Digital Twins (DTs) are gaining a lot of attention, nowadays. Indeed, by providing a virtual copy of a living or a non-living entity, DTs have revolutionized various domains by allowing seamless simulations, facilitating decision-making, and predicting the need for maintenance to name a few use-cases. The advancements of Artificial Intelligence (AI), Machine Learning (ML), and the Internet of Things (IoT) have resulted in significant improvements in DTs. However, despite a noticeable adoption in the fields of education, and Industry 4.0, DT is still at its early stages in the health and telecommunications domains. Therefore, in this paper, we comprehensively review the state-of-the-art of DTs in terms of technologies, applications, challenges and future directions with a focus on these two domains. Particularly, we investigate the advantages of integrating ML in the DT ecosystem. Moreover, we synthesize current approaches by providing a workflow comparison of trending DT-related research questions. Accordingly, when analyzing enablers for DTs, we concluded that some challenges need to be addressed such as data privacy, reliability, and scalability to enable further adoption of the DT in the real-world. We thoroughly discuss these before elaborating our views on future directions.