<p>The remote monitoring of patient’s vitals has become essentially useful for those patients who have been either discharged from hospitals or elderly and require constant monitoring at home. In this paper we propose a framework for remote monitoring of vital signs by integrating digital twins technology to enable real-time monitoring with minimal cost overhead. Framework employs image processing techniques to extract patient’s vital sign from video to create a digital copy of device on cloud, making it possible to virtually monitor patient’s state, interact with physical device indirectly and make decisions on patient’s state and history. However, sensitive and private information can not be directly stored on third party cloud. To address this issue, data is first encrypted and privacy preserving machine learning algorithm performs computations on encrypted data. Privacy preserving machine learning algorithm allows users to submit encrypted queries to machine learning service, receive encrypted predictions, and locally decrypt them. In this way data is protected from third party and only authorized users can access it. Performance evaluation highlights the system efficiency, accuracy and high security.</p>