Design and analysis of TwinCardio framework to detect and monitor cardiovascular diseases using digital twin and deep neural network.

World Health Organization (WHO) estimates 17.9 million deaths globally every year due to Cardiovascular Disease or CVD, which includes an array of disorders of the heart and blood vessels, that includes coronary heart disease, cerebrovascular disease, rheumatic heart disease, and various other conditions. Notably, there has been nearly 30% increase in heart attack cases among individuals aged 25-44 between 2020 and 2023. These alarming trends make it pertinent for a deeper comprehensive integration of precision healthcare with digital twin. With the development of technologies, such as machine learning, cyber-physical systems, and the Internet of Things (IoT), digital twin is being applied in various industries as a precision simulation technology from concept to practice. Combining healthcare with digital twin paves the path to a more efficient means of delivering accurate and timely services to patients suffering from heart diseases. However, achieving personalized and precise healthcare management requires humans to be in loop with the digital twin, which will facilitate the integration of the patient's physical world with the medical virtual world to realize smart healthcare. This work proposes "TwinCardio"-a novel reference framework of digital twin enabled smart health monitoring and "TwinNet"-a customized neural network designed for cardiovascular disease classification and prediction. TwinCardio framework is designed for patient monitoring, diagnosing and predicting the aspects of the health of individuals using on-body sensors. It depicts different layer that describes continuous data acquisition, data simulation, evaluation inline with security protocols thus serving as a base to manufacture smart healthcare models.