An Intelligent Decision-Making Framework for Cloud Adoption in Healthcare: Combining DOI Theory, Machine Learning, and Multi Criteria Approaches

Abstract

Cloud adoption in healthcare presents many benefits, including the superior accessibility of 
data, scalability, and cost efficiency. However, it remains to be accompanied by many strenuous 
challenges, such as security risks, regulatory compliance, interoperability, and organizational 
resistance to change. To address these complexities, this study proposes an intelligent decision
making framework that integrates DOI theory, machine learning, and MCDM techniques for 
making optimal cloud adoption decisions. The framework sets off with DOI theory. This 
assesses the readiness for adoption, and identifies a number of influencing factors that include 
relative advantage, compatibility, complexity, trialability, and observability. Predictions of 
cloud adoption probability and hidden patterns in the adoption of cloud services can be 
uncovered from historical and real-time healthcare data by machine learning algorithms such 
as decision trees and neural networks. MCDM techniques such as Analytic Hierarchy Process 
(AHP) and TOPSIS evaluate cloud service providers against multiple factors including cost, 
security, scalability, compliance, and performance. Results show that the proposed model 
yields 97% prediction accuracy, 96% decision confidence, and 65% complexity reduction, 
outperforming the traditional decision-making approach by a large margin. In addition, it 
enhances cost efficiency (90%), scalability (88%), and security compliance (92%), making the 
approach robust, adaptable, and data-driven for cloud adoption in healthcare. This study will 
help in making informed decisions, increasing operational efficiency, and regulatory alignment, 
which supports the smooth integration of clouds into healthcare organizations.