Predictive Modeling of Cardiovascular Disease Risk with IoT and ML

Novel prospects for improving online healthcare services have been made possible by recent developments in IoT and sensor technology. Cloud computing technologies are being used to properly manage the massive volumes of data generated by the medical IoT domain. A revolutionary healthcare application that integrates cloud and IoT technologies has been developed with the particular purpose of monitoring and diagnosing serious medical disorders. This is done in order to provide top-notch online healthcare services. This study used healthcare sensors and the UCI Repository dataset to create a simplified framework for predicting cardiac disease. To identify heart illness, patient data is analyzed using classification algorithms. Using information from a reliable benchmark dataset, the classifier is trained during this phase. Then, real patient data is evaluated in the testing phase to find out if cardiac disease is present. The benchmark dataset is extensively tested using a range of classifiers, such as J48, logistic regression (LR), multilayer perceptron (MLP), and support vector machine (SVM), in order to provide experimental validation. Simulation findings verify that the J48 classifier outperforms other models on several important measures, including recall, accuracy, precision, F-score, and kappa value.