Abstract
The integration of Internet of Things (IoT) technologies with Healthcare system(HS) has revolutionized patient monitoring, diagnosis, and treatment. Effective information sharing in such systems is hindered by resource constraints, including limited computational capacity, energy consumption, and the need for real-time data processing. Existing systems often struggle to deploy large-scale language models (LLMs) in resource-constrained environments, limiting their ability to analyse and communicate critical healthcare information effectively. To resolve these issues, this study recommends a Smart IoT-based Health Care environment utilizing a lightweight BERT (Bidirectional Encoder Representations from Transformers) model for efficient and scalable information sharing. By optimizing BERT for resource-limited IoT devices, the proposed system ensures real-time processing of patient data while maintaining accuracy and efficiency. The system was examined by utilizing the MIMIC-III clinical dataset, focusing on real-time health monitoring and communication between connected devices. Results demonstrated improved computational efficiency, reduced latency, and enhanced accuracy in extracting and sharing critical healthcare information. This innovative approach bridges the gap between IoT and healthcare by providing a resource-efficient solution for intelligent information sharing.