Integrating MCDM, Network Analysis, and Genetic Algorithms for Enhanced Cloud Service Selection in Healthcare Systems

Abstract

The selection of an optimal cloud service for health care requires the strategic balance between cost, security, scalability, and compliance by considering the complicated interdependencies that exist among such factors. This is where more traditional methods in cloud selection become ineffective, yielding suboptimal decisions that are likely to impact efficiency, cost- effectiveness, or regulatory compliance. This paper proposes an intelligent cloud service selection framework that bridges Multi-Criteria Decision-Making, Network Analysis, and enetic Algorithms to increase decision-making accuracy with elasticity. MCDM-based approaches systematically analyze and rank important decision criteria, so services chosen will align with healthcare operational requirements and regulations. Network Analysis shows interdependencies among criteria, such as how cost considerations determine the security and
performance that, in turn, offer a holistic view of trade-offs. Genetic Algorithms optimize cloud service configurations to find Pareto-optimal solutions that balance multiple competing priorities. This framework outperforms the traditional models by a considerable margin with 91% cost optimization, 96% optimization accuracy, and 95% decision confidence. It further increases scalability (90%) and security compliance (93%), making it robust and adaptive to the dynamic healthcare environment. This research helps healthcare organizations act on concrete knowledge for cloud adoption strategies, being data-driven, efficient, and regulatory compliant and aligned with long-term operational goals.