Improving patient outcomes and operational efficiency requires optimizing the command centers of TeleICU (Tele-Intensive Care Unit). This research offers a novel strategy for enhancing the functionality of Tele-ICU command centers by utilizing cloud computing and machine learning (ML). The system ensures smooth data flow and accessibility by integrating real-time data collection from multiple IoT-enabled devices. The Random Forest algorithm evaluates patient data, forecasts possible complications, and supports healthcare professionals in making prompt decisions. Integrating cloud computing makes real-time analytics, quick processing, and scalable data storage possible. Utilizing cloud computing and storage resources, the system can manage the massive volumes of data produced in a Tele-ICU setting. The Random Forest algorithm is especially well-suited for this application because of its high predictive accuracy, capacity to handle missing values, and ability to handle large datasets. Our findings show notable gains in overall patient management, predictive accuracy, and response times. By reducing the time required to recognize and address patient concerns, the deployment of this integrated system improves patient outcomes in the long run. The Random Forest algorithm's predictive powers also allow for proactive patient care management, which boosts the efficacy and efficiency of TeleICU command centers even more. The management and operation of Tele-ICU facilities could be completely transformed by this strategy, increasing their responsiveness and efficiency. © 2025 Elsevier B.V., All rights reserved.