Development of toolkits for detecting dental caries and caries experience among children using self-report and parent report

How well do parents identify their child's baby teeth? Engagement and accuracy of parent-reported information on a tooth checklist survey

OBJECTIVES

Naturally exfoliated primary teeth are being increasingly collected in child development studies. Most of these odontological collections and tooth biobanks use parent-reported information from questionnaires or tooth checklists to collect data on offspring teeth. To the best of the authors' knowledge, no studies have assessed parental engagement in tooth checklists, nor parental accuracy in identifying their child's baby tooth. This study aimed to evaluate these dimensions by analysing data from the about this tooth checklist returned with donated primary teeth in a natural experimental study called STRONG (the Stories Teeth Record of Newborn Growth).

METHODS

Parental self-reported information were analysed on checklists returned with 825 primary teeth belonging to 199 children. The percentage of blank answers was calculated for each question. The accuracy of parents-reported tooth identification was evaluated by comparing parental ratings to researchers' ratings. Reliability of researchers' tooth identification was first evaluated by calculating intra-observer and inter-observer agreements, as well as Cohen's Kappa values. The percentage of accuracy of parents' tooth identification (relative to researcher's) was then calculated, and logistic regressions were used to evaluate if time elapsed between when exfoliation occurred and the checklist was completed associated with parental accuracy in tooth identification.

RESULTS

Parents returned 98.4% of the checklists and completed 74.9% to 97.7% of the questions. Excellent reliability was demonstrated for researchers' intra- and inter-rater tooth identification (agreement percentages >90%; Cohen's Kappa values >.83). Moderate accuracy of parents-reported tooth identifications was found, with parents correctly identifying 49.5% of the donated tooth. Better parental accuracies were highlighted for partial identifications (87.1% of correct jaw, 75.6% of correct tooth type, and 65.8% of correct lateralization). Logistic regressions showed the odds of correct parental identifications decreased on average by 1.8% every 30 days of distance between tooth exfoliation and checklist completion.

CONCLUSIONS

While parental engagement is high, parents-reported tooth identifications have moderate accuracy, which decreases over time. High accuracy is however found for partial identifications. Parent-reported information on the accompanying questionnaire of naturally exfoliated primary teeth collection or tooth biobanks, even when filled in a long time after exfoliation took place, should be encouraged. However, expert identifications of teeth should remain best practice.

Development of short forms for screening children's dental caries and urgent treatment needs using item response theory and machine learning methods

OBJECTIVES

Surveys can assist in screening oral diseases in populations to enhance the early detection of disease and intervention strategies for children in need. This paper aims to develop short forms of child-report and proxy-report survey screening instruments for active dental caries and urgent treatment needs in school-age children.

METHODS

This cross-sectional study recruited 497 distinct dyads of children aged 8-17 and their parents between 2015 to 2019 from 14 dental clinics and private practices in Los Angeles County. We evaluated responses to 88 child-reported and 64 proxy-reported oral health questions to select and calibrate short forms using Item Response Theory. Seven classical Machine Learning algorithms were employed to predict children's active caries and urgent treatment needs using the short forms together with family demographic variables. The candidate algorithms include CatBoost, Logistic Regression, K-Nearest Neighbors (KNN), Naïve Bayes, Neural Network, Random Forest, and Support Vector Machine. Predictive performance was assessed using repeated 5-fold nested cross-validations.

RESULTS

We developed and calibrated four ten-item short forms. Naïve Bayes outperformed other algorithms with the highest median of cross-validated area under the ROC curve. The means of best testing sensitivities and specificities using both child-reported and proxy-reported responses were 0.84 and 0.30 for active caries, and 0.81 and 0.31 for urgent treatment needs respectively. Models incorporating both response types showed a slightly higher predictive accuracy than those relying on either child-reported or proxy-reported responses.

CONCLUSIONS

The combination of Item Response Theory and Machine Learning algorithms yielded potentially useful screening instruments for both active caries and urgent treatment needs of children. The survey screening approach is relatively cost-effective and convenient when dealing with oral health assessment in large populations. Future studies are needed to further leverage the customize and refine the instruments based on the estimated item characteristics for specific subgroups of the populations to enhance predictive accuracy.

Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7

BACKGROUND

Dental caries is the most common chronic childhood infectious disease and is a serious public health problem affecting both developing and industrialized countries, yet it is preventable in most cases. This study evaluated the potential of screening for dental caries among children using a machine learning algorithm applied to parent perceptions of their child's oral health assessed by survey.

METHODS

The sample consisted of 182 parents/caregivers and their children 2-7 years of age living in Los Angeles County. Random forest (a machine learning algorithm) was used to identify survey items that were predictors of active caries and caries experience. We applied a three-fold cross-validation method. A threshold was determined by maximizing the sum of sensitivity and specificity conditional on the sensitivity of at least 70%. The importance of survey items to classifying active caries and caries experience was measured using mean decreased Gini (MDG) and mean decreased accuracy (MDA) coefficients.

RESULTS

Survey items that were strong predictors of active caries included parent's age (MDG = 0.84; MDA = 1.97), unmet needs (MDG = 0.71; MDA = 2.06) and the child being African American (MDG = 0.38; MDA = 1.92). Survey items that were strong predictors of caries experience included parent's age (MDG = 2.97; MDA = 4.74), child had an oral health problem in the past 12 months (MDG = 2.20; MDA = 4.04) and child had a tooth that hurt (MDG = 1.65; MDA = 3.84).

CONCLUSION

Our findings demonstrate the potential of screening for active caries and caries experience among children using surveys answered by their parents.

Socio-economic inequalities in dental pain in children: A birth cohort study

OBJECTIVE

To describe socio-economic inequalities in dental pain and dental caries in 5 and 12-year-old children enrolled in a birth cohort.

METHODS

This prospective study was carried out with children enrolled in a birth cohort in Pelotas, Brazil. The main outcome was history of dental pain in the last six months, collected at 5 and 12 years of age. Dental caries was evaluated as a secondary outcome. Inequalities dimensions were investigated using maternal education and family income. The inequalities indicators used were the slope index of inequality (SII) and the concentration index (CIX).

RESULTS

Some 1,114 and 990 children were included in the analyses at the 5- and 12-year follow-ups, respectively. The prevalence of dental pain was 16.5% (95% CI 14.4-18.8) at 5 years and 31.6% (95% CI 28.7-34.6) at 12 years. Regarding SII, the difference in the prevalence of dental pain was 14 and 11 percentage points at 5 and 12 years, respectively, when comparing the less to the more maternal schooled strata. Relative inequalities (CIX) were found for dental pain only at age 12, considering family income (-5.8 CI95% -11.0; -0.6). Absolute socio-economic inequalities were also observed for dental caries in both ages.

CONCLUSION

Dental pain in the last six months and dental caries was unequally distributed. Economically disadvantaged groups had the highest prevalence of dental pain and dental caries in both dentitions. Actions to tackle socio-economic inequalities must be designed throughout life.