We performed a systematic review to evaluate the success of machine learning algorithms in the diagnosis and prognostic prediction of dental caries. The review protocol was a priori registered in the PROSPERO, CRD42020183447. The search involved electronic bibliographic databases: PubMed/Medline, Scopus, EMBASE, and Web of Science, and grey literature until December 2020. We excluded review articles, case series, case reports, editorials, letters, comments, educational methodologies or assessments of robotic devices and articles with less than 10 participants or specimens. Two independent reviewers selected the studies and performed the assessment of the methodological quality based on standardized scales. We summarize data on the machine learning algorithms used, software, performance outcomes such as accuracy/precision sensitivity/recall, specificity, area under the receiver operating characteristic curve (AUC), and positive/negative predictive values related to dental caries. Meta-analyses were not performed due to methodological differences. Our review included 15 studies (10 diagnostic studies and 5 prognostic prediction studies). Cross-sectional design studies were predominant (12). The most frequently used statistical measure of performance reported in diagnostic studies was AUC value, which ranged from 0.745 to 0.987. For most diagnostic studies, data from contingency tables were not available. Reported sensitivities were higher in low risk of bias prognostic prediction studies (median [IQR] of 0.996 [0.971-1.000] versus unclear/high risk of bias studies 0.189 [0-0.340]; p-value 0.025). While there were no significant differences in the specificity between these subgroups. We concluded that the use of these technologies for the diagnosis and prognostic prediction of dental caries, although promising, is at an early stage. The general applicability of the evidence was limited given that most models were developed outside the real clinical setting with a prevalence of unclear/high risk of bias. Researchers must increase the overall quality of their research protocols by providing a comprehensive report on the methods implemented.

Background Dentists should assess pathways influencing the increment of dental caries among children to guide the prevention and treatment of the disease. Aim Evaluate the pathways that influence the increment of carious lesions in pre‐school children. Design This is a 2‐year cohort study was conducted with a random sample of 639 pre‐school children in southern Brazil. Caries experience, socioeconomic status (SES), social capital, and psychosocial characteristics were obtained at baseline. Increment of dental caries was assessed at 2 years follow‐up in 467 children (cohort retention rate of 73.1%). Previously calibrated examiners assess the caries through the International Caries Detection and Assessment System (ICDAS). Structural equation modeling (SEM) was performed to test the pathways influencing dental caries increment. Results Dental caries at baseline was heavily influenced by children's age (SC: 0.381, P < .01), tooth plaque (SC: 0.077, P = .02), parent's perception child oral health (SC: 0.295, P < .01), and household (SC: 0.148, P < .01). Increment of dental caries was directly affected by dental caries at baseline (Standardized Coefficients [SC]: 0.377, P < .01). Indirect paths were not significant. Conclusions Dental caries experience was the main factor of direct influence on the increment of caries, reinforcing the theory of risk accumulation over time.

No abstract

This study aimed to assess the impact of determinants of the individual and contextual level on the untreated dental caries during adolescence. A cohort study was started in 2012 with a random sample of 1,134 12 years-old adolescents in the city of Santa Maria, RS, Brazil. The adolescents were clinically evaluated by calibrated dentists and investigated variables: contextual, demographic, socioeconomic factors, dental service use, toothache, and subjective variables. After two years (T2) and six years (T3), the same adolescents were reevaluated (retention rate of 67.9% and 67.8%, respectively). Untreated dental caries (component "D" of the DMFT index) was the outcome and was collected at all three times. Multilevel Poisson regression analyses considered repeated measures (level 1 - times), nested to adolescents (level 2), were used to assess the association between predictors (baseline) and untreated dental caries. High neighborhood’ mean income was associated with the lowest risk of dental caries. Low household income [Incidence Rate Ratio (IRR) 1.57; Confidence Interval (CI) 95% 1.35-1.82], low mother education (IRR 1.19; CI95%1.03-1.38), toothache (IRR 1.73; CI95% 1.47-2.03), gingival bleeding (IRR 1.23; CI95% 1.05-1.45), and poor self-perception of oral health (IRR 1.19; CI95% 1.07-1.32) were risk factors for untreated dental caries. In conclusion, our results showed that socioeconomic disadvantages and oral conditions in early adolescence are risk factors for untreated caries among adolescents.

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.