Intelligent decision-making in healthcare telemonitoring via forward-backward chaining and IoT

Abstract

Healthcare telemonitoring has emerged as a promising approach to remotely monitor patients remotely, enabling timely intervention and personalized care. Internet of things (IoT) device-generated patient data necessitates innovative solutions for intelligent healthcare decision-making, as current methods struggle to provide timely, context-aware, and data-driven recommendations, resulting in suboptimal patient care. This study aims to develop an intelligent decision-making framework for healthcare telemonitoring by leveraging forward-backward chaining and IoT technology. The research focuses on a system using forward-backward chaining algorithms to analyze real-time patient data from IoT devices. It utilizes machine learning models to adapt to changing conditions and refine decision-making, demonstrating its ability to provide real-time context-aware recommendations. Temperature, blood pressure, oxygen level, and heart rate measurement errors are 2.01%, 1.74 to 2.13%, 0.61%, and 1.45%, respectively. The success rate of early disease diagnosis using an expert system is 81%, with an average application interface responsiveness time of 4.978 s. The integration of IoT data with intelligent decision-making algorithms in healthcare telemonitoring has the potential to revolutionize patient care. However, future work should focus on scalability and interoperability for diverse healthcare settings.