Prediction of Health Risk Based on Multi-Level IOT Data Using Decision Trees

This research paper presents a novel decision tree-based method for predicting health hazards based on multilevel Internet of Things (IoT). This study's primary objective is to employ machine learning and deep learning techniques to the field of medical science in an effort to make physicians' jobs easier and have a positive effect on humanity. This study's dataset consists of 132 parameters from which 42 distinct disease types can be predicted. The data is collected by Internet of Things (IoT) devices, which are also used for validation purposes. The dataset is used to train the decision tree classifier, which is then integrated into an IoT-based device for real-time health risk prediction. Using classification metrics, the accuracy of the model is evaluated, and the feature importances are analysed to determine the most significant parameters for predicting health risks. In addition, a process of feature selection is employed to eradicate less significant parameters, resulting in a refined model. Using multi-level IoT data, the proposed method demonstrates promising results with high accuracy in predicting health hazards. This research can contribute to the development of intelligent healthcare systems and facilitate early disease detection and prevention.