Identifying early permanent teeth caries factors in children using random forest algorithm

IntroductionEarly permanent dental caries can pose a serious threat to oral health in the coming years. This study aimed to investigate the key factors influencing early dental caries in permanent teeth among first-grade Iranian children.MethodsA cross-sectional study involving 778 randomly selected first-grade children from public schools in Tehran, Iran, was conducted between November 2017 and January 2018. The oral health of the children, evaluated by two trained dentists, was recorded based on the DMFT index. Information on maternal education, gender, dmft index, brushing frequency, dental visits, flossing, and sweet consumption was also collected. The Random Forest method was employed to identify factors associated with early permanent dental caries, and its performance was compared with logistic regression using the Area Under the Curve (AUC) index.ResultsLogistic regression, represented by odds ratios (OR), revealed a significant association between early permanent dental caries and dmft index [OR = 1.13, 95% CI (1.07, 1.20), p-value