IoT based heart disease prediction and diagnosis model for healthcare using machine learning models

Latest advancements in field of IoT and sensing technologies can be employed for online healthcare services. The gigantic quantity of information is being formed through the IoT devices in the medical field and cloud computing techniques have been used to manage the massive amount of data. To avail good service to the user using the online healthcare services, a fresh Cloud as well as IoT based Healthcare application to monitor in addition to diagnose serious diseases is developed. In this study, an efficient framework is utilized for heart disease is created utilizing the UCI Repository dataset as well as the healthcare sensors to predict the public who suffer from heart disease. Moreover, classification algorithms are used to classify the patient data for the identification of heart disease. In the training phase, the classifier will be trained using the data from benchmark dataset. During the testing phase, the actual patient data to identify disease is used to identify the presence of disease. For experimentation, a benchmark dataset is tested using a set of classifiers namely J48, logistic regression (LR), multilayer perception (MLP) and support vector machine (SVM). The simulation results ensured that the J48 classifiers shows superior performance in terms of different measures such as accuracy, precision, recall, F-score and kappa value.