Machine Learning and MANET-Driven 5G Technology for Smart Healthcare: Enhanced Patient Diagnosis and Treatment

This article presents the design, development, implementation, and evaluation of a system for patient health monitoring by synergistically combining machine learning models, mobile ad hoc networks (MANET), and Internet of Things (IoT). In this patient health monitoring system, data are gathered from numerous sensors installed on IoT devices in real-time to support dynamic and continuous health monitoring of patients within predefined constraints. The data are sent over MANET, which has nodes that send data to cloud storage for a centralized management. The data collected from the patients are used to train various Machine Learning (ML) models to learn when the patient is likely to experience a health problem. The analysis carried out in this study reveal that the Support Vector Machine (SVM) is found to be the most accurate model for predicting patient health problems, with an accuracy of 91.23%. The Artificial Neural Network (ANN), Random Forest (RF), and Naive Bayes (NB) rank next, respectively, with accuracy of 88.7%, 86.5%, and 84.4% respectively, following SVM. Recall, accuracy, and F1 score are given to provide comparative information on the relative merits of these models. This integrated healthcare monitoring system, with its timely alert system, real-time monitoring, and powerful predictive analytics, provide patients with personalized and proactive care. It enhances healthcare practices by showing that the data-driven strategic approach and its associated technologies are transforming patient outcomes in the emerging field of healthcare.