Resource-Efficient Personalized Healthcare via Cloud-Enabled Decision Tree Models

To optimize healthcare delivery and improve patient outcomes, it is vital to allocate resources efficiently in personalized patient navigation systems (PPNS). To accomplish these goals, this study presents a new method that makes use of cloud-enabled Decision Trees (CEDT). Static resource allocation techniques might hinder the efficiency of PPNS, which are meant to customize healthcare. This paper proposes a flexible and extensible system that combines CEDT with cloud computing. By optimizing resource allocation across several phases of patient care, CEDT enables real-time decision-making by analyzing patient data and current healthcare needs. Increased scalability and flexibility are benefits of cloud-based deployment that also makes it easier to integrate with preexisting healthcare IT systems. Optimal resource utilization increased operational efficiency, and better response to patient demands are some of the main advantages of the proposed method. Validation experiments on services using MIMIC-IV database using simulated patient settings show that CEDT improves PPNS performance over the status. Metrics for healthcare service performance and patient satisfaction both showed considerable improvements. Developing efficient and adaptable PPNS via the use of cloud computing and DT algorithms helps move personalized healthcare forward. The methodology enhanced resource utilization by 32%, diminished patient waiting times by 27%, and augmented decision-making efficiency by 40% illustrating the efficacy of CEDT in PPNS.