Internet of things‐enabled intelligent systems for remote chronic disease monitoring

Abstract

The possibility of remotely monitoring and managing chronic diseases is made feasible by the Internet of Things (IoT), which enables the collection and analysis of vast amounts of data from various sources such as sensors, devices, and wearables. However, conventional machine learning approaches often encounter difficulties when dealing with IoT data due to its noise, heterogeneity, and high dimensions. In this study, we introduce a novel technique for developing human‐centric intelligent systems for remote monitoring of chronic diseases using deep learning in an IoT context. This technique is capable of handling complex and diverse IoT data, providing accurate and comprehensible predictions and recommendations. We outline a standardized architecture for these systems, comprising of three distinct phases: data acquisition, data processing, and data visualization. To demonstrate the effectiveness of our methodology, we apply it to a case study involving the development and evaluation of a human‐centered intelligent system for remote monitoring of hypertension and diabetic patients, involving real users. Our findings reveal a substantial enhancement in prediction accuracy when employing our proposed hybrid algorithm. When compared to traditional algorithms, our proposed hybrid algorithm exhibits superior performance, achieving an accuracy of 93.5%, surpassing the Restricted Boltzmann Machine (RBM) with an accuracy of 88.2%, Long Short‐Term Memory (LSTM) networks at 90.4%, and Convolutional Neural Networks (CNN) at 91.6%. This improvement in accuracy is critical for ensuring reliable disease monitoring and management, highlighting the effectiveness of our approach. In terms of precision, scalability, and user satisfaction, we demonstrate the effectiveness and efficiency of our method. Furthermore, we address the social and ethical implications inherent in our methodology and suggest avenues for future research in this domain.