Fog-driven IoT and trust-aware machine learning framework for early disability detection and rehabilitation in healthcare systems

The Internet of Things (IoT) and machine learning offer promising healthcare solutions for enhancing the functionalities of early detection and rehabilitation of disabilities. These systems minimize communication gaps between patients and healthcare providers by efficiently managing medical resources and providing timely responses to specific events. However, most approaches still face research challenges in managing the trust among interconnected medical devices, resulting in inconsistent data, leading to suboptimal care and delayed interventions for individuals with disabilities. To address these limitations, our research explores machine learning classification to introduce a fog-driven trusted disability detection healthcare (FTDD-HC) framework in an IoT environment, which enables timely responses by leveraging wearable sensors to monitor patient health and movement, thereby supporting clinicians in making informed, timely decisions for the early detection of disabilities. In addition, by incorporating trust, our proposed framework enables healthcare providers to develop more accurate, reliable, and personalized rehabilitation strategies for detecting disabilities accurately using real-time patient data. By leveraging machine learning, the proposed framework explores motion-related health metrics. It enhances the disability detection system by classifying normal and abnormal movement patterns, thus providing critical insights into patient conditions. The proposed framework is implemented in Python, and its performance results reveal a significant enhancement over existing healthcare applications, advancing the quality of care for patients with more effective rehabilitation support and early detection of disabilities.