Early Childhood Predictors for Dental Caries: A Machine Learning Approach.

We aimed to develop and validate caries prognosis models in primary and permanent teeth after 2 and 10 y of follow-up through a machine learning (ML) approach, using predictors collected in early childhood. Data from a 10-y prospective cohort study conducted in southern Brazil were analyzed. Children aged 1 to 5 y were first examined in 2010 and reassessed in 2012 and 2020 regarding caries development. Dental caries was assessed using the Caries Detection and Assessment System (ICDAS) criteria. Demographic, socioeconomic, psychosocial, behavioral, and clinical factors were collected. ML algorithms decision tree, random forest, and extreme gradient boosting (XGBoost) were employed, along with logistic regression. The discrimination and calibration of models were verified in independent sets. From 639 children included at the baseline, we reassessed 467 (73.3%) and 428 (66.9%) children in 2012 and 2020, respectively. For all models, the area under receiver operating characteristic curve (AUC) at training and testing was above 0.70 for predicting caries in primary teeth after 2-y follow-up, with caries severity at the baseline being the strongest predictor. After 10 y, the SHAP algorithm based on XGBoost achieved an AUC higher than 0.70 in the testing set and indicated caries experience, nonuse of fluoridated toothpaste, parent education, higher frequency of sugar consumption, low frequency of visits to the relatives, and poor parents' perception of their children's oral health as top predictors for caries in permanent teeth. In conclusion, the implementation of ML shows potential for determining caries development in both primary and permanent teeth using easy-to-collect predictors in early childhood.

Pathways between Social Capital and Oral Health from Childhood to Adolescence.

This study aimed to evaluate the theoretical pathways by which social capital can influence dental caries and oral health-related quality of life (OHRQoL) of children over time. This 10-y prospective cohort started in 2010 with a sample of 639 preschoolers aged 1 to 5 y from the southern Brazil. Community and individual social capital were assessed at baseline through the presence of formal institutions in the neighborhood and social networks, respectively. In the 10-y follow-up, the individual social capital was evaluated by social trust and social networks. Dental caries was measured by the International Caries Detection and Assessment System (ICDAS), and the short version of the Child Perception Questionnaire (CPQ11-14) was used to assess OHRQoL. Demographic, socioeconomic, behavioral (frequency of toothbrushing and use of dental services), and psychosocial (sense of coherence) characteristics were also assessed. Structural equation modeling was used to evaluate the associations between variables over time. About 429 children were reassessed at 10-y follow-up (67.1% cohort retention rate). High community social capital at baseline directly predicted lower occurrence of dental caries and better OHRQoL after 10 y. Social capital at community level also indirectly predicted lower occurrence of dental caries through sense of coherence, frequency of toothbrushing, and use of dental services. Individual social capital at follow-up was indirectly linked to OHRQoL via the psychosocial pathway (sense of coherence). Community-level social capital was associated with dental caries and OHRQoL over time. The relationship between individual social capital and oral health was mediated through the psychosocial pathway.