Sustainable IoHT-Based Machine Learning Modeled System for Prediction of Cardiovascular Disease Risk

This paper presents development of a sustainable cardiovascular disease risk detection system by integrating Internet of Health Things (IoHT) and various machine learning models or algorithms. Logistic regression, decision tree and random forest models are employed and evaluated using accuracy, confusion matrix and classification report with receiver operating characteristic curves to assess the performance of the models. The results indicate that the random forest model achieves the highest accuracy of 88.36%, outperforming the other models. In addition, data visualization has been conducted to gain insights into the relationships between different variables and their impact on heart disease risk. Further, the education level of individuals seems to have a little correlation with their heart disease risk. The developed model can aid in early intervention and prevention strategies, i.e., assisting healthcare professionals in identifying individuals at higher risk of heart disease and implementing targeted interventions.