Tooth Loss, Patient Characteristics, and Coronary Artery Calcification

Abstract

This study, for the first time, explores the integration of data science and machine learning for the classification and prediction of coronary artery calcium (CAC) scores, investigating both tooth loss and patient characteristics as key input features. By employing these advanced analytical techniques, we aim to enhance the accuracy of classifying CAC scores into tertiles and predicting their values. Our findings reveal that patient characteristics are particularly effective for tertile classification, while tooth loss provides more accurate predicted CAC scores. Moreover, the combination of patient characteristics and tooth loss demonstrates improved accuracy in identifying individuals at higher risk of cardiovascular issues related to CAC. This research contributes valuable insights into the relationship between oral health indicators, such as tooth loss, patient characteristics, and cardiovascular health, shedding light on their potential roles in predictive modeling and classification tasks for CAC scores.