Advancing Smart Healthcare: A Comprehensive Review of Data Mining Techniques in IoT-Driven Medical Systems

Abstract

By making intelligent, data-driven decisions, the Internet of Things (IoT) and data mining technology are revolutionizing healthcare today. Wearable sensors, cloud computing platforms, and networked healthcare devices are all employed by IoT -based healthcare systems to collect gigantic amounts of real-time patient information. But the effective management of this massive amount of medical information remains a major challenge. To enhance disease prediction, patient care optimization, and insights extraction, data mining methods such as Decision Trees, Naïve Bayes, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Neural Networks have been vital. This review paper provides an in- depth study of data mining methods applied to Internet of Things-enabled smart healthcare systems. It explores the extent to which they are able to diagnose diseases such as diabetes, cardiovascular disease, Parkinson's, and hypertension. It also contrasts accuracy, sensitivity, and computation speed of various methods using literature today to examine their strengths and weaknesses.To enhance the reliability and efficiency of IoT-based healthcare systems, it emphasizes the need for open, innovative, private, and scalable data mining methods. With the identification of research gaps and proposing directions for subsequent advances in the field, this research contributes to ongoing discussion in the area of smart healthcare.