Cardiovascular Risk Assessment With Current Machine Learning Methods and Future Integration of Quantum Networks

Abstract

Heart strokes represent a significant global health concern, affecting individuals across diverse age groups, including children and teenagers. By applying the power of machine learning and analyzing crucial indicators such as age, gender, body mass index, average glucose level, smoking habits, employment status, and living conditions, the authors aim to predict the occurrence of heart strokes even before they happen. Various machine learning techniques, including support vector machines (SVM), logistic regression, gaussian naive bayes, k-nearest neighbor's (KNN), decision trees, random forest, and XGBoost, are employed to classify an individual's stroke risk level. The assessment offers a comprehensive comparison of these algorithms, ultimately identifying the most effective approach. Additionally, the authors explore the integration of quantum networks to enhance the predictive capabilities of these machine learning models, potentially revolutionizing the accuracy and efficiency of heart stroke prediction.