<p>Heart disease (HD) prediction has become an essential focus in healthcare, as it holds the potential to significantly reduce the global burden of cardiovascular diseases by enabling early detection and prevention. HD is a critical area of medical research aimed at reducing mortality rates by enabling early diagnosis and timely intervention. In this work, a novel multi-Cloud-based Unified Risk Evaluation for Heart Disease (CURE-HD) has been proposed which uses hybrid deep learning model for risk prediction in smart healthcare environments. Initially, data acquisition was performed using IoT devices and pre-processing at the Distributed Edge Server (DES). The pre-processed data is then fed into an Attention-based Long Short-Term Memory-Capsule Network (ALSTM-CapsNet) for classifying patient risk into three levels: low, moderate, and high based on Electronic Health Records (EHRs) and current sensor data. The risk classification results are managed by a Distributed Reinforced Scheduler (DRS) for Heart Disease Crisis Planning (HDCP), where patient data is scheduled according to their risk level using Multi-Agent Deep Reinforcement Learning (MA-DRL). Subsequently, the scheduled reports are sent to the Multi-Cloud Server (MCS) for heart disease detection, utilizing tailored AI models: Support Vector Machine (SVM) for low-risk, Convolutional Neural Network (CNN) for moderate risk, and Transformer based CNN (T-CNN) for high-risk patients. From the experimental results, the proposed CURE-HD demonstrated superior performance by achieving an accuracy of 99.01%. From the results, the proposed CURE-HD increases the overall accuracy by 11.38%, 10.92%, and 5.51% for FRIEND, DEEP-CARDIO, and Heart Sense respectively.</p>