The advent of Internet of Things (IoT) technology has brought about an increase in automation with the seamless integration of sensors and end devices to present technologies which provide a solution for a robust and end-to-end automation system. The healthcare industry has seen an emergence in the integration of these technologies, which are reshaping the industry in terms of health monitoring and patient care. The incorporation of artificial intelligence and machine learning algorithms enables diagnostic and personalized treatment for each patient and predictive health analysis. The appearance of digital twin technology is an important development as it allows for users to interact with a digital representation of real-world objects. This paper gives an innovative IoT-based solution to efficient and non-invasive heart monitoring problems, addressing the challenges in data management, and accurate health insights. A distinctive characteristic of this system is the integration of digital twins for modeling the heart conditions of the patient, improving monitoring accuracy and enabling predictive analysis of acute heart conditions using a Convolution Neural Network (CNN)-based Image classification model trained on ECG images, to predict acute heart conditions, providing an effective and end-to-end system using the mentioned technologies. The CNN model gives a classification accuracy of 98.37%. The inclusion of these emergent technologies collectively contributes to more efficient, accessible and patient centric healthcare systems.