Integrating IoMT and Federated Learning for Advanced Healthcare Monitoring in Healthcare 5.0

Introduction: The Internet of Medical Things (IoMT) has made it possible to create advanced health monitoring systems. It allows the system to detect problems early, thereby mitigating long-term effects. This development will likely enhance the quality of healthcare professionals by reducing their workload and healthcare costs. The IoT in medical technology offers a wide range of information technology capabilities, including intelligent and collaborative healthcare solutions. Aggregating health data in a single repository raises security, copyright, and compliance issues when building a complex machine-learning model. Method: Federated learning overcomes the above challenges by dispersing a global learning model through a central aggregate server. It retains mastery of patient data in a local participant who ensures data privacy and integrity. This research aims to develop an advanced healthcare monitoring system utilizing federated learning techniques. The system is designed to enable healthcare providers to effectively track patient health through medical sensors and respond promptly when necessary. Results: The federated learning-based XGBoost model achieved a predictive accuracy of 97.2% in diagnosing Parkinson’s disease. Additionally, the system demonstrated improved privacy preservation, significantly reducing sensitive data exposure with minimal computational overhead, confirming its practical effectiveness in clinical scenarios. Discussion: By leveraging federated learning, the proposed approach seeks to enhance the efficiency and effectiveness of health monitoring in clinical settings. To achieve accurate classification and early detection of Parkinson's disease, the study employs two key machine learning algorithms: Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost). These methods were selected for their statistical robustness and suitability for the task at hand. Conclusion: The combination of federated learning, SVM, and XGBoost enhances healthcare monitoring and ensures patient data privacy and integrity.