A machine learning based decision tree analysis of influential factor for the number of remaining teeth in Korean adults / 대한구강보건학회지

ABSTRACT

Objectives@#This study aims to investigate the effect of determinants on the number of remaining teeth in Korean adults using a machine learning-based decision tree analysis. @*Methods@#The study used data from the Korea National Health and Nutrition Examination Survey (KNHANES) VII (2016-2018) and a decision-tree analysis to explain the causes for the number of remaining teeth in adults. The determinants for the study are sex, age, house income, education level, diabetes, BMI, smoking, alcohol drinking, tooth brushing per day, and periodontitis. @*Results@#Age had the most significant effect on the number of remaining teeth, followed by house income. @*Conclusions@#This research is meaningful as it provides a systematic index in the number of remaining teeth in Korean adults based on a combination of numerous variables. These variables have already been validated against the results of previous studies that have attempted to elucidate new variables affecting the number of remaining teeth.