Healthcare is one of humanity's fundamental rights, and the advent of embedded technology has made various healthcare devices accessible and efficient. In this study, we propose an Internet-Of-Disease (IoD) based cloud-integrated framework for real-time monitoring and classification of ECG signals to support smart healthcare applications. The proposed system employs an ECG sensor to continuously gather heart rate data, which is transmitted to cloud platforms via wireless communication protocols. We evaluated multiple machine learning and deep learning classifiers, including traditional ML models, CNN-based architectures, and YOLO variants. Among them, YOLOv11 achieved the highest performance with an accuracy of 99.50%, demonstrating its superiority in accurately classifying ECG signals and detecting abnormalities, while other models showed comparatively lower performance. Incorporating IoT capabilities with ML and DL approaches in the IoD platform enables automated, real-time collection, transmission, and analysis of diagnostic data, which is securely stored in cloud databases accessible only to authorized medical practitioners. Experimental results demonstrate that the proposed framework provides high accuracy and reliability, making it highly suitable for deployment in smart healthcare environments to enhance early disease detection and continuous patient monitoring.