The development of big data analytics in healthcare has created a demand for privacy-conscious and scalable machine learning algorithms that can allow the use of patient information across different healthcare organizations. In this study, the difficulties that come with traditional federated learning frameworks in healthcare sectors, such as scalability, computational effectiveness, and preserving patient privacy for numerous healthcare systems, are discussed. In this work, a new conceptual model known as Hierarchical Federated Learning (HFL) for large, integrated healthcare organizations that include several institutions is proposed. The first level of aggregation forms regional centers where local updates are first collected and then sent to the second level of aggregation to form the global update, thus reducing the message-passing traffic and improving the scalability of the HFL architecture. Furthermore, the HFL framework leveraged more robust privacy characteristics such as Local Differential Privacy (LDP), Gaussian Differential Privacy (GDP), Secure Multi-Party Computation (SMPC) and Homomorphic Encryption (HE). In addition, a Novel Aggregated Gradient Perturbation Mechanism is presented to alleviate noise in model updates and maintain privacy and utility. The performance of the proposed HFL framework is evaluated on real-life healthcare datasets and an artificial dataset created using Generative Adversarial Networks (GANs), showing that the proposed HFL framework is better than other methods. Our approach provided an accuracy of around 97% and 30% less privacy leakage compared to the existing models of FLBM-IoT and PPFLB. The proposed HFL approach can help to find the optimal balance between privacy and model performance, which is crucial for healthcare applications and scalable and secure solutions.

Coronary artery disease (CAD) is a leading cause of mortality worldwide, demanding more precise diagnostic strategies. Traditional AI algorithms, like CNNs, RNNs, often fail to absorb these complex relational patterns within cardiovascular data. GNNs give an alternative because they can process such dynamic relationships. This work attempts to study GNNs for CAD progression modeling and diagnosis, including the integration of such models within cloud infrastructures for a scalable and real-time deployment. A systematic literature review was performed in accordance with PRISMA guidelines. The databases searched were PubMed, Web of Science, IEEE Xplore, and Google Scholar, yielding 259 articles. After applying inclusion criteria, 32 studies were selected. These were analyzed from the perspective of GNN architecture, CAD application area, strategies for cloud deployment, and diagnostic performance. GNN-based diagnostic models with accuracies of up to 96% and AUCs higher than 0.90 have been reported in the literature. Subsequent cloud deployment of these models allows real-time inference and easy integration into hospital systems, enabling federated learning of new models while preserving patient data privacy. Use cases include coronary imaging, ECG analysis, and behavioral risk profiling. GNNs, combined with cloud technologies, present a transformative approach for precision cardiology, enabling accurate and personalized CAD diagnostics. However, adoption in clinical settings requires further advancements in model explainability, privacy safeguards, and regulatory compliance. Future research should emphasize open CAD graph datasets, improve GNN interpretability, and validate these systems in real-world clinical environments