Internet of Things-driven Predictive Analytics for Heart Disease Detection

The prevalence of cardiovascular diseases (CVDs) continues to be major public health concern worldwide, necessitating innovative approaches for early detection and management. This study proposes an Internet of Things (IoT) architecture augmented with machine learning algorithms for the prediction of cardiovascular disease risk. A comprehensive dataset is created for analysis using wearable sensors and devices connected to the Internet of Things (IoT). These devices collect physiological data in real-time, such as heart rate, blood pressure, and activity levels. Several machine learning models, including logistic regression, decision trees, and support vector machines, are trained on this dataset to predict the likelihood of cardiac disease happening. Several metrics are utilized to evaluate the efficacy of these models, including specificity, accuracy, precision, and area under the receiver operating characteristic curve (AUC-ROC). The results demonstrate that the methodology based on the Internet of Things (IoT) for predictive modeling effectively identifies persons at risk of developing heart disease. This paves the way for early intervention and tailored healthcare management approaches.