A preliminary prediction model of untreated dental caries by using machine learning method: a population-based cross-sectional survey

A preliminary prediction model of untreated dental caries by using machine learning method: a population-based cross-sectional survey | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article A preliminary prediction model of untreated dental caries by using machine learning method: a population-based cross-sectional survey Siqi Yan, Linxin Jiang, Zhuohang Chen, Yu He, Dingfang Luo, Jianbo Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7975886/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Objectives This study aimed to establish a preliminary prediction model for untreated dental caries among adolescents by using machine learning method. Materials and Methods Data were obtained from a cross-sectional epidemiological survey involving 1,641 adolescents aged 12 years in Guangdong, Southern China. Demographic information, socioeconomic status, and caries-related behaviors were collected via a structured questionnaire. A preliminary prediction model was developed using six machine learning (ML) algorithms. The performance of each algorithm was evaluated through stratified 5-fold cross-validation, with the following metrics: area under the receiver operating characteristic (ROC) curve (AUC), accuracy, precision, specificity, sensitivity, and F1 score. Variable importance rankings were generated, and calibration and decision curves were plotted. Results Among six machine learning algorithms, random forest performed the best, which demonstrated an AUC, accuracy, precision, specificity, sensitivity, and F1 score of 0.785 (0.759–0.811), 0.707 (0.685–0.728), 0.698 (0.673–0.724), 0.714 (0.695–0.737), 0.699 (0.675–0.730), and 0.698 (0.666–0.730) in stratified 5-fold cross-validation. The top three important variables: self-evaluation of oral condition, have a toothache in the past year, and oral health knowledge. Conclusions The prediction model based on random forest algorithm could help discriminate adolescents with untreated dental caries, which will assist healthcare providers in the individual management of caries in adolescents. Untreated dental caries Adolescents Machine learning Caries prevention Cross-sectional epidemiological survey Figures Figure 1 Figure 2 Figure 3 Figure 4 Introduction The common caries evaluation index is DMF (decayed-missing-filled) index, which reflects the past and present caries experience. Most epidemiological studies only focus on DMF index [ 1 ] . While treated caries do not contribute to the current medical burden, untreated caries can spread into the pulp, causing pain and infection [ 2 ] , and affecting children's growth, general health and academic achievement [ 3 ] . Therefore, untreated dental caries has imposed a serious health and economic burden on individuals and health care systems [ 4 ] , and predicting untreated caries is arguably more important for the assessment of the medical burden of caries and for the planning of oral public health services. Untreated caries is disproportionately distributed among people with lower socioeconomic status, which has a significant negative impact on schoolchildren's quality of life [ 5 , 6 ] . Low income is a significant risk factors of untreated caries [ 7 – 13 ] . Children from low-income families have the highest number of oral diseases and visit the dentist the most frequently for pain relief. However, these children visit the dentist the least often overall. Fewer preventive dental visits increase the disease burden of low-income children. Terrible oral health condition and lack of oral health services for low-income preschoolers, who are twice as likely to develop caries as high-income children in future [ 12 ] . Untreated carious cavities is associated with lower tooth brushing frequency [ 6 ] . Low life quality is a risk indicator for the new lesions of untreated dental caries after 2 years [ 7 ] . Recent dental visit contributes to increases in treated caries [ 8 , 11 ] . Toothache is s risk factor for untreated dental caries [ 9 ] . Low maternal educational attainment also affects untreated caries [ 6 , 9 ] . The literature on untreated caries related behaviors investigated parental eating behaviors and tooth brushing frequency. Positive parental diet behaviors can reduce the effect of negative parental behaviors on the prevalence of untreated caries in young children [ 14 ] . Oral health cognition and attitude towards caries influence untreated caries [ 9 , 15 ] . The most influential factors on untreated caries are the use of dental floss, unhealthy food consumption, self-declared race and exposure to fluoridated water [ 16 ] . Exploring new disease diagnosis models based on big data and machine learning algorithms has achieved remarkable results in disease risk prediction and diagnosis [ 17 ] . Artificial intelligence based on machine learning has been proven by numerous studies to have promising performance in disease prediction [ 18 – 20 ] . Machine learning methods will help predict those teenagers at higher risk of dental caries [ 16 ] . In this study, data from a cross-sectional study of untreated caries in 12 year old adolescents in Guangdong Province will be analyzed. The age of 12 is the recommended age for the investigation of permanent tooth caries by the World Health Organization. The aim of this study is to apply machine learning methods to predict adolescents with untreated caries, the related factors are further explored to provide a scientific basis for accurately identifying high-risk group and optimizing prevention policies for oral health of adolescents. Materials and Methods Study population The data of this study were derived from the 2021 Oral Health Monitoring Project for Key Populations in Guangdong Province, China, which was a representative cross-sectional study. The inclusion criteria entailed participants who were 12-year-old residents of Guangdong Province (who had lived there for at least six months prior to the survey month) and willing to cooperate with the investigators and maintain good compliance. In addition, their legal guardians had the ability to understand the study and the willingness to sign the relevant informed consent letter. The exclusion criteria were as follows: legal guardian could not understand and refused to participate in the study; participants with oral disease or major systematic disease which would affect the data integrity and/or the safety of participants. Ethical consideration The study passed ethical review by the Ethics Committee of the Stomatological Hospital, Southern Medical University on March 24, 2020 (Approval No.: 2020–08). This study was conducted in accordance with the Declaration of Helsinki. Informed consent was obtained from legal guardians of all adolescents as well as the adolescents themselves included in the study. Study design The formula for calculating the sample size was: N = deff \(\:\frac{{{\text{μ}}_{\text{α}\text{/2}}}^{\text{2}}\text{p(1−p)}}{{\text{δ}}^{\text{2}}}\) . The design effect (deff) was set at 2.5. The significance level α was set at 0.05, corresponding to a \(\:\text{μ}\) -value of 1.96 at the cumulative probability of α/2 for the standard normal distribution. The allowable relative error(δ) of the expected prevalence (p) was controlled at 10%, prevalence of untreated caries in 12-year-olds adolescents in the 4th Oral Health Survey of Guangdong province was 37.81% [ 21 ] . According to this calculation, the minimum sample size required for the investigation was 1580 participants. The research samples were sampled by stratified random sampling, and 13 monitoring districts were selected. Each monitoring district had approximately 120 to 140 adolescents sampled. There were 7 rural monitoring districts and 6 urban monitoring districts. The number of male and female was nearly equal. A total of 1,641 participants were ultimately included, exceeding the minimum sample size requirement. Clinical examination The examiners were guided by a standard examiner until the kappa values of inter-examiner were > 0.8 before examination. The participants were examined on portable dental chairs with lights. Caries examination was performed on each participant with a community periodontal index (CPI) probe and a plane mirror. The diagnostic criteria of dental caries were based on the oral health survey methods of World Health Organization (WHO) (5th edition) [ 22 ] . The kappa values of inter-examiner were calculated by repeated examination of 5% of participants. Questionnaire survey Before questionnaire survey, the training of questionnaire investigators included clarifying the purpose of the questionnaire, unifying the questionnaire filling method and standardizing the questioning procedure. Trained investigators conducted one-on-one questionnaires on the participants, each participant completed a questionnaire. The questionnaire, previously deployed in national surveys, shows robust reliability and validity [ 23 , 24 ] . The variables included in this study mainly fell into five categories: (1) basic demographic information, including gender and whether you are only children or not; (2) socioeconomic status, including household registration type and parental education level; (3) lifestyle related to caries, including oral hygiene habits, sweets consumption frequency, and tobacco consumption; (4) oral health-related experiences, including toothache, tooth trauma, self-evaluation of oral condition, and dental visit; (5) oral health knowledge and attitudes. Statistical analysis In terms of algorithms, six common machine learning algorithms were used to build models separately by using Python 3.11: Decision Tree (DTM), Random Forest (RF), Xtreme Gradient Boosting (XGBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), and Logistic Regression. The training process of the model consisted of four stages: dataset construction, data processing, training and validation, and prediction. It was divided into the training set and the test set in a ratio of 7:3. To obtain a more stable model and reduce overfitting, a 5-fold cross-validation was conducted on the data. The data was divided into five subsets of similar size, among which four subsets were used as the training sets for establishing and optimizing the model, and one subset was used as the test set for verifying the model's efficiency. A total of five repeated tests were conducted, and the optimal hyperparameters were finally obtained. The final model was trained using the combination of the optimal hyperparameters. The metrics used to evaluate the performance of each machine learning algorithm in stratified 5-fold cross-validation included the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, precision, specificity, sensitivity, and F1 score. The average AUC value was calculated from five repetitions of the model training process, and the other evaluation metrics were also obtained in the same way. AUC is a performance metric used to evaluate the quality of the learner. An AUC value between 0.7 and 0.9 indicates a certain level of accuracy in real diagnosis, and an AUC greater than 0.9 indicates high accuracy [ 25 ] . The higher the AUC value, the better the classification performance of the model [ 26 ] . The most significant associated factors were identified by machine learning algorithm with the largest AUC. The calibration curve and decision curve were plotted based on the largest AUC machine learning algorithm. Figure 1 shows the research process. Results Participants characteristics Table 1 presents characteristics of the participants, including residence, gender, and the 16 variables selected through the questionnaire survey. All the variables included in the study were categorical variables. Among the included variables, there were statistically significant differences in the untreated caries prevalence rates of different conditions of variables such as gender, residence, father's education attainment, mother's education attainment, brushing teeth frequency, floss frequency, self-evaluation of oral condition, have a toothache in the past year, and oral health knowledge. Table 1 Univariate analysis of factors associated to untreated caries > 0. Variables N(%) untreated caries > 0(%) OR(95% CI) P-value Gender 1.377 (1.131–1.677) 0.001 male 826(50.34) 311(37.65) female 815(49.66) 370(45.40) Residence 1.573 (1.289–1.920) < 0.001 urban 753(45.89) 268(35.59) rural 888(54.11) 413(46.51) Whether they are only children or not 0.772 (0.573–1.041) 0.090 yes 213(12.98) 77(36.15) no 1428(87.02) 604(42.30) Father's education attainment 0.793 (0.690–0.911) 0.001 lowest 4(0.24) 1(25.00) relatively low 1056(64.35) 477(45.17) medium 356(21.69) 120(33.71) high 225(13.71) 83(36.89) Mother's education attainment 0.743 (0.646–0.853) < 0.001 lowest 30(1.83) 17(56.67) relatively low 1105(67.34) 494(44.71) medium 293(17.85) 99(33.79) high 213(12.98) 71(33.33) Brushing teeth frequency 1.248 (1.055–1.476) 0.010 ≥ 2 times a day 840(51.19) 319(37.98) once a day 734(44.73) 333(45.37) not brushing teeth every day 63(3.84) 28(44.44) never 4(0.24) 1(25.00) Fluoride toothpaste 1.465 (0.344–6.242) 0.230 yes 295(17.98) 138(46.78) no 126(7.68) 53(42.06) unknown 1212(73.86) 487(40.18) never use toothpaste 8(0.49) 3(37.50) Floss frequency 0.805 (0.679–0.954) 0.013 never 1143(69.65) 498(43.57) occasionally 443(27.00) 163(36.79) use weekly 30(1.83) 13(43.33) use daily 25(1.52) 7(28.00) Dessert frequency 1.089 (0.949–1.249) 0.227 at least once a day 400(24.38) 162(40.50) at least once a week 803(48.93) 324(40.35) < 3 times a month 438(26.69) 195(44.52) Sweet drink frequency 1.117 (0.968–1.290) 0.130 at least once a day 604(36.81) 238(39.40) at least once a week 796(48.51) 335(42.09) < 3 times a month 241(14.69) 108(44.81) Sweet milk frequency 1.089 (0.952–1.245) 0.213 at least once a day 669(40.77) 271(40.51) at least once a week 677(41.26) 276(40.77) < 3 times a month 295(17.98) 134(45.42) Tobacco frequency 0.911 (0.561–1.482) 0.708 daily 3(0.18) 1(33.33) weekly 1(0.06) 1(100.00) rarely 36(2.19) 16(44.44) never 1601(97.56) 663(41.41) Self-evaluation of oral condition 1.503 (1.316–1.717) < 0.001 fine 78(4.75) 27(34.62) relatively good 432(26.33) 138(31.94) normal 915(55.76) 395(43.17) relatively bad 189(11.52) 100(52.91) very bad 27(1.65) 21(77.78) Tooth trauma 0.961 (0.831–1.111) 0.587 injured 305(18.59) 134(43.93) uninjured 876(53.38) 356(40.64) cannot remember clearly 460(28.03) 191(41.52) Have a toothache in the past year 0.692 (0.605–0.790) < 0.001 often 36(2.19) 29(80.56) occasionally 770(46.92) 365(47.40) never 586(35.71) 193(32.94) cannot remember clearly 249(15.17) 94(37.75) Visit a dentist 0.897 (0.737–1.091) 0.276 have visited 822(50.09) 352(42.82) never 819(49.91) 329(40.17) Oral health knowledge 0.742 (0.647–0.849) < 0.001 low 296(18.04) 153(51.69) middle 700(42.66) 293(41.86) high 645(39.31) 235(36.43) Oral health attitude 0.836 (0.678–1.032) 0.095 low 27(1.65) 13(48.15) middle 340(20.72) 153(45.00) high 1274(77.64) 515(40.42) Performance of different models Cross-validation results The optimal range of hyperparameters was sought. The optimal hyperparameters were obtained through cross-validation, and the combination of the optimal hyperparameters was used for training the final model. During the search process, the accuracy, precision, specificity, sensitivity, and F1 score of 6 models, as well as the AUC under 5-fold cross-validation were obtained. As shown in Fig. 2 , from the results of the 5-fold cross-validation, the model with the smallest AUC was Logistic Regression (0.619 ± 0.017), and the one with the largest AUC was the Random Forest (0.785 ± 0.013). Model prediction results As shown in Table 2 . The AUC values obtained by training the model on the training set of Decision Tree(DTM), Random Forest(RF), Xtreme Gradient Boosting(XGBoost), Gradient Boosting Decision Tree(GBDT), Light Gradient Boosting Machine(LightGBM), and Logistic Regression were 0.839, 0.875, 0.888, 0.799, 0.905 and 0.633, respectively. The AUC values obtained by training the model on the test set of Decision Tree(DTM), Random Forest(RF), Xtreme Gradient Boosting(XGBoost), Gradient Boosting Decision Tree(GBDT), Light Gradient Boosting Machine(LightGBM), and Logistic Regression were 0.773, 0.785, 0.807, 0.733, 0.800 and 0.644, respectively. Table 2 The AUC of six machine algorithm models in the training set and the test set. Training set Test set DTM 0.839 0.773 Random Forest 0.875 0.785 XGBoost 0.888 0.807 GBDT 0.799 0.733 LightGBM 0.905 0.800 Logistic Regression 0.633 0.644 The test performance of six models This study employed six machine learning classifiers for classification learning. Overall, the AUC of Decision Tree (DTM), Random Forest (RF), Xtreme Gradient Boosting (XGBoost), Gradient Boosting Decision Tree (GBDT), and Light Gradient Boosting Machine (LightGBM) were 70.5%−78.5%. Logistic Regression performed the worst on accuracy (0.592), precision (0.582), sensitivity (0.549), specificity (0.631), F1 Score (0.564), and the AUC(0.619). Random Forest performed the best on accuracy (0.707), precision (0.698), specificity (0.714), F1 Score (0.698), and the AUC (0.785). Light Gradient Boosting Machine (LightGBM) performed the best on sensitivity (0.718) (Table 3 ). Table 3 Comparison of 5-fold cross-validation results of different machine algorithm models. DTM Random Forest XGBoost GBDT LightGBM Logistic Regression AUC 0.705 (0.658–0.751) 0.785 (0.759–0.811) 0.765 (0.724–0.806) 0.716 (0.684–0.748) 0.763 (0.731–0.796) 0.619 (0.585–0.653) Accuracy 0.658 (0.602–0.713) 0.707 (0.685–0.728) 0.696 (0.664–0.727) 0.654 (0.637–0.671) 0.698 (0.662–0.734) 0.592 (0.559–0.624) Precision 0.642 (0.575–0.708) 0.698 (0.673–0.724) 0.676 (0.646–0.705) 0.644 (0.605–0.683) 0.676 (0.631–0.721) 0.582 (0.534–0.629) Specificity 0.656 (0.630–0.693) 0.714 (0.695–0.737) 0.684 (0.669–0.703) 0.673 (0.647–0.709) 0.679 (0.659–0.706) 0.631 (0.610–0.661) Sensitivity 0.660 (0.641–0.685) 0.699 (0.675–0.730) 0.708 (0.683–0.740) 0.633 (0.616–0.657) 0.718 (0.705–0.734) 0.549 (0.544–0.555) F1 Score 0.650 (0.597–0.703) 0.698 (0.666–0.730) 0.691 (0.652–0.730) 0.637 (0.612–0.663) 0.696 (0.667–0.725) 0.564 (0.545–0.583) Variable importance of Random Forest In the Random Forest model, The ranking of the contribution degree of variables to the model was as follows: self-evaluation of oral condition, have a toothache in the past year, oral health knowledge, father's education attainment, mother's education attainment, floss frequency, residence, gender, brushing teeth frequency (Fig. 3 ). Calibration curve and Decision curve of Random Forest The calibration curve is plotted based on the predicted rate and the actual occurrence rate to determine if the observed probability is consistent with the model's predicted probability. Figure 4 showed the calibration curve of the Random Forest model. The calibration curve of the model was close to the standard line, indicating that the machine learning model performed well and was reliable and effective. The decision curve of the random forest model was shown in Fig. 4 . The vertical axis represents net benefit, and the horizontal axis represents the threshold probability. The black solid line and the gray dashed line are respectively regarded as the two extreme lines representing all negative and all positive cases. The net benefit was higher than the extreme curve, it indicated that the random forest model's judgment was good. Discussion In this study, we utilized machine learning methods to establish a preliminary prediction model for untreated dental caries among adolescents based on questionnaire surveys. The sample of our study was large and representative. The data acquisition method through questionnaires is straightforward and highly conducive to the promotion of the prediction model in remote and impoverished areas where advanced technologies are not accessible. Our research findings are helpful for the formulation of oral public health policies and the allocation of resources. By leveraging machine learning technology, we aimed to enhance the efficiency of screening adolescents with untreated dental caries, especially through a simple questionnaire survey. It is crucial to identify adolescents who have not received treatment for dental caries, especially the most vulnerable ones. This helps to uphold the principle of fairness in universal health coverage, giving more attention to those who truly need it [ 27 ] . Our research identified the key factors that influence untreated caries in adolescents. Nine variables were included in the machine learning model. The AUC of the random forest model was the largest. The top three most important variables in the random forest model were self-evaluation of oral condition, have a toothache in the past year and oral health knowledge. High levels of dental awareness and self-efficacy are associated with self-reported satisfaction with oral health [ 28 ] . Toothache is the intuitive perception of the oral health condition, toothache and self-assessment of oral health go hand in hand. Self-perception of oral health affects the use of dental services [ 29 – 33 ] . Children who suffered from frequent toothaches in the past year were more likely to visit the dentist [ 33 ] . Oral health knowledge is significant for promoting oral health [ 34 ] . Insufficient oral health knowledge and misunderstandings prevent women from seeking dental care [ 35 ] . Better oral health knowledge has a protective effect on specific issues of oral health-related quality of life [ 36 ] . The other six variables included in this model have also been proven to be associated with caries in previous studies. Parents' good educational achievement is associated with better oral health for offspring [ 37 ] . Male had a higher prevalence of untreated caries in the U.S. [ 8 ] . Nevertheless, researches on caries in school-age children in China have revealed that girls are more susceptible to developing caries [ 38 , 39 ] . The use of dental floss is associated with proximal caries [ 40 ] . Individuals who brush their teeth infrequently afford higher risk for the caries increment than those brushing more frequently [ 41 , 42 ] . Furthermore, we employed six machine learning algorithms and evaluated their performance systematically. We determined that the random forest algorithm was the most performant model by hyperparameter tuning and model selection. Compared with other algorithms, it exhibited better predictive performance. Parameter optimization and algorithm selection play a crucial role in enhancing the performance of model. Random Forest performed the best on accuracy, precision, specificity, F1 Score and the area under the ROC curve (AUC). With the application of artificial learning and machine learning in various disciplines, their use in the medical field has also rapidly grown. Almost all types of clinical predictions can be achieved through machine learning [ 43 ] . Machine learning is widely applied in clinical diagnosis, precise treatment, and health monitoring [ 44 ] . Further research on the caries predictive models based on the related factors of caries will be helpful for the formulation of oral public health policies. This study has several limitations. Firstly, the cross-sectional design is inherently limited in its ability to establish causal relationships, this type of design can merely unveil the correlations that exist among variables. Secondly, the independent dataset has not undergone external validation. As such, further verification of the model's robustness and generalization ability is needed. Thirdly, some of the data were derived from questionnaire surveys, and these data may be influenced by the subjective cognitive biases and recall biases of the participants. Finally, the dental plaque microecology, saliva, and genes related to caries were not included in the study. In light of the limitations of the present study, several enhancements could be implemented for future research endeavors. Longitudinal investigations explore more profoundly the causal associations between relevant variables and caries. Incorporating more objective indicators, such as plaque microecology, salivary markers, radiological images, and genes, enriches the research scope. Additionally, the predictive model developed will then be subjected to external validation using another dataset. These efforts aim to offer scientific basis for the prevention and treatment of caries. Conclusion In conclusion, we utilized machine learning methods to establish a preliminary prediction model for untreated caries among adolescents based on questionnaire surveys. The random forest model performed the best. Factors such as self-evaluation of oral condition, have a toothache in the past year, oral health knowledge, parents' education attainment, floss frequency, residence, gender, and brushing teeth frequency had impact on untreated caries. The prediction model provides clearer decision-making guidance for the prevention of caries. Abbreviations DMF Decayed-Missing-Filled ML Machine Learning CPI community periodontal index WHO World Health Organization DTM Decision Tree RF Random Forest XGBoost Xtreme Gradient Boosting GBDT Gradient Boosting Decision Tree LightGBM Light Gradient Boosting Machine LR Logistic Regression ROC Receiver Operating Characteristic Curve AUC Area Under the ROC Curve Declarations Ethical Approval and Consent to Participate The study passed ethical review by the Ethics Committee of the Stomatological Hospital, Southern Medical University on March 24, 2020 (Approval No.: 2020–08). This study was conducted in accordance with the Declaration of Helsinki. Informed consent was obtained from legal guardians of all adolescents included in the study. Consent for publication Not applicable. Availability of data and materials The data that support the findings of this study are available on request from the corresponding author [Li J]. The data are not publicly available due to them containing information that could compromise research participant privacy. Competing interests The authors declare no conflicts of interest in this work. Funding Guangdong General Higher Education Key Area Special Project, Guangdong Provincial Department of Education (2024ZDZX2031) Science research cultivation program of stomatological hospital, Southern medical university (PY2023021) Guangzhou Science and Technology Bureau Project- “Research and Demonstration Application of Diagnosis and Recognition of Pit and Fissure Sealing on Permanent Molar for Children Based on Big Data and Artificial Intelligence” (2025B03J0150). Author Contributions All authors made important contributions to the work reported. SQY contributed to the conception, study design, execution, and drafting of the manuscript; LXJ contributed to data visualization and interpretation of statistical results; ZHC, YH, and DFL contributed to investigation and acquiasition of data; JBL contributed to project administration, review, editing, supervision and funding acquisition. All authors gave final approval of the version to be published; have agreed on the journal to which the article has been submitted; and agreed to take responsibility and be accountable for all aspects of the work. Acknowledgments The authors would like to thank all of the adolescents and their parents/grandparents, and all the staff who participants in the surveys. References Kassebaum NJ, Bernabé E, Dahiya M, Bhandari B, Murray CJ, Marcenes W (2015) Global burden of untreated caries: a systematic review and metaregression. J Dent Res 94(5):650–658. 10.1177/0022034515573272 Selwitz RH, Ismail AI, Pitts NB (2007) Dental caries. Lancet 369(9555):51–59. 10.1016/S0140-6736(07)60031-2 Jackson SL, Vann WF Jr, Kotch JB, Pahel BT, Lee JY (2011) Impact of poor oral health on children's school attendance and performance. Am J Public Health 101(10):1900–1906. 10.2105/AJPH.2010.200915 Petersen PE, Bourgeois D, Ogawa H, Estupinan-Day S, Ndiaye C (2005) The global burden of oral diseases and risks to oral health. Bull World Health Organ 83(9):661–669 Bashir NZ (2022) Update on the prevalence of untreated caries in the US adult population, 2017–2020. J Am Dent Assoc 153(4):300–308. 10.1016/j.adaj.2021.09.004 Eid SA, Khattab NMA, Elheeny AAH (2020) Untreated dental caries prevalence and impact on the quality of life among 11 to14-year-old Egyptian schoolchildren: a cross-sectional study. BMC Oral Health. ;20(1):83. Published 2020 Mar 19. 10.1186/s12903-020-01077-8 Vieira-Andrade RG, Pordeus IA, Ramos-Jorge ML et al (2022) Risk indicators of untreated dental caries incidence among preschoolers: a prospective longitudinal study. Braz Oral Res 36:e064 Published 2022 May 2. 10.1590/1807-3107bor-2022.vol36.0064 Gupta N, Vujicic M, Yarbrough C, Harrison B (2018) Disparities in untreated caries among children and adults in the U.S., 2011–2014. BMC Oral Health. ;18(1):30. Published 2018 Mar 6. 10.1186/s12903-018-0493-7 Ortiz FR, Reyes LT, Ardenghi TM (2022) Social Economic Disadvantage and Untreated Dental Caries: Findings from a Cohort Study in Adolescents. Caries Res 56(3):179–186. 10.1159/000525238 Griffin SO, Thornton-Evans G, Wei L, Griffin PM (2021) Disparities in Dental Use and Untreated Caries Prevalence by Income. JDR Clin Trans Res 6(2):234–241. 10.1177/2380084420934746 Lin M, Thornton-Evans G, Griffin SO, Wei L, Junger M, Espinoza L (2019) Increased Dental Use May Affect Changes in Treated and Untreated Dental Caries in Young Children. JDR Clin Trans Res 4(1):49–57. 10.1177/2380084418793410 Edelstein BL (2002) Disparities in oral health and access to care: findings of national surveys. Ambul Pediatr 2(2 Suppl):141–147. 10.1367/1539-4409(2002)002%3C0141:diohaa%3E2.0.co;2 Edelstein BL, Chinn CH (2009) Update on disparities in oral health and access to dental care for America's children. Acad Pediatr 9(6):415–419. 10.1016/j.acap.2009.09.010 Costa MD, Chapanski VDR, Crema AFA, Menoncin BLV, Höfelmann DA, Fraiz FC (2022) Untreated early childhood caries: the role of parental eating behavior. Braz Oral Res 36:e010 Published 2022 Jan 14. 10.1590/1807-3107bor-2022.vol36.0010 Sadiq N, Probst JC, Martin AB, Khan MM, Merchant AT (2021) Untreated Dental Caries May be Associated with Subsequent Mortality among Working-Age Adults: Evidence from NHANES III. Community Dent Oral Epidemiol 49(4):377–383. 10.1111/cdoe.12612 Bomfim RA (2024) Machine learning to predict untreated dental caries in adolescents. BMC Oral Health 24(1):316 Published 2024 Mar 9. 10.1186/s12903-024-04073-4 Peng X, Liu Y, Zhang B et al (2024) A preliminary prediction model of pediatric Mycoplasma pneumoniae pneumonia based on routine blood parameters by using machine learning method. BMC Infect Dis. ;24(1):707. Published 2024 Jul 18. 10.1186/s12879-024-09613-5 Peiffer-Smadja N, Rawson TM, Ahmad R et al (2020) Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clin Microbiol Infect 26(5):584–595. 10.1016/j.cmi.2019.09.009 Theodosiou AA, Read RC (2023) Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician. J Infect 87(4):287–294. 10.1016/j.jinf.2023.07.006 Peng HT, Siddiqui MM, Rhind SG, Zhang J, da Luz LT, Beckett A (2023) Artificial intelligence and machine learning for hemorrhagic trauma care. Mil Med Res 10(1):6 Published 2023 Feb 16. 10.1186/s40779-023-00444-0 Shaohong Huang (2020) The Report on Fourth Oral Health Epidemiology Survey in Guangdong Province. Southern Publishing Media Group Organization WH (2013) Oral Health Surveys: Basic Methods. World Health Organization Jiang L, Huang S, Reissmann DR, Schmalz G, Li J (2025) Identification of Risk Group for Root Caries and Analysis of Associated Factors in Older Adults Using Unsupervised Machine Learning Clustering. Clin Interv Aging 20:483–493 Published 2025 Apr 24. 10.2147/CIA.S520229 Tian T, Yang Z, Li S et al (2024) Cross-sectional survey and analysis of factors influencing the prevalence of dental caries among older individuals aged 65–74 in Guangdong Province in 2021. BMC Oral Health. ;24(1):948. Published 2024 Aug 16. 10.1186/s12903-024-04624-9 Hosmer DW Jr, Lemeshow S, Sturdivant RX (2013) Applied logistic regression. Wiley Cai G, Huang F, Gao Y et al (2024) Artificial intelligence-based models enabling accurate diagnosis of ovarian cancer using laboratory tests in China: a multicentre, retrospective cohort study. Lancet Digit Health 6(3):e176–e186. 10.1016/S2589-7500(23)00245-5 da Cunha IP, de Lacerda VR, da, Silveira Gaspar G et al (2022) Factors associated with the absence of Brazilians in specialized dental centers. BMC Oral Health. ;22(1):364. Published 2022 Aug 26. 10.1186/s12903-022-02402-z Allen F, Fan SY, Loke WM, Na TM, Keng Yan GL, Mittal R (2022) The relationship between self-efficacy and oral health status of older adults. J Dent 122:104085. 10.1016/j.jdent.2022.104085 Herkrath FJ, Vettore MV, Werneck GL (2018) Contextual and individual factors associated with dental services utilisation by Brazilian adults: A multilevel analysis. PLoS ONE 13(2):e0192771 Published 2018 Feb 8. 10.1371/journal.pone.0192771 Xu M, Cheng M, Gao X et al (2020) Factors associated with oral health service utilization among adults and older adults in China, 2015–2016. Community Dent Oral Epidemiol 48(1):32–41. 10.1111/cdoe.12497 Rebelo Vieira JM, Rebelo MAB, Martins NMO, Gomes JFF, Vettore MV (2019) Contextual and individual determinants of non-utilization of dental services among Brazilian adults. J Public Health Dent 79(1):60–70. 10.1111/jphd.12295 Xu M, Yuan C, Sun X, Cheng M, Xie Y, Si Y (2018) Oral health service utilization patterns among preschool children in Beijing, China. BMC Oral Health. ;18(1):31. Published 2018 Mar 6. 10.1186/s12903-018-0494-6 Gao X, Ding M, Xu M et al (2020) Utilization of dental services and associated factors among preschool children in China. BMC Oral Health 20(1):9 Published 2020 Jan 8. 10.1186/s12903-019-0996-x Naidu RS, Nunn JH (2020) Oral Health Knowledge, Attitudes and Behaviour of Parents and Caregivers of Preschool Children: Implications for Oral Health Promotion. Oral Health Prev Dent 18(2):245–252 Published 2020 Jul 4. 10.3290/j.ohpd.a43357 Williams TM, Babalola AE, Bolarinwa O et al (2025) Oral health knowledge, perceptions and attitudes of pregnant women in Sub-Saharan Africa: a systematic review. BMC Oral Health 25(1):937 Published 2025 Jun 6. 10.1186/s12903-025-06249-y Gardner J, Huang B, Ip RHL (2023) Oral health knowledge is associated with oral health-related quality of life: a survey of first-year undergraduate students enrolled in an American university. BMC Oral Health. ;23(1):961. Published 2023 Dec 3. 10.1186/s12903-023-03721-5 Ruhe T, Broadbent JM, Schluter PJ et al (2023) Parents' education and Pasifika children's oral health in Aotearoa/New Zealand: A national linked data study using Aotearoa/New Zealand's integrated data infrastructure. Community Dent Oral Epidemiol 51(5):936–944. 10.1111/cdoe.12791 Wang X, Chen H, Hou R et al (2023) Effect of dietary patterns on dental caries among 12–15 years-old adolescents: a cross-sectional survey. BMC Oral Health 23(1):845 Published 2023 Nov 9. 10.1186/s12903-023-03566-y Chen Z, Zhu J, Zhao J et al (2023) Dental caries status and its associated factors among schoolchildren aged 6–8 years in Hangzhou, China: a cross-sectional study. BMC Oral Health. ;23(1):94. Published 2023 Feb 14. 10.1186/s12903-023-02795-5 de Oliveira KMH, Nemezio MA, Romualdo PC, da Silva RAB, de Paula E, Silva FWG, Küchler EC (2017) Dental Flossing and Proximal Caries in the Primary Dentition: A Systematic Review. Oral Health Prev Dent 15(5):427–434. 10.3290/j.ohpd.a38780 Brusius CD, Alves LS, Maltz M (2023) Association between toothbrushing frequency and dental caries and tooth loss in adolescents: a cohort study. Braz Oral Res 37:e127 Published 2023 Dec 15. 10.1590/1807-3107bor-2023.vol37.0127 Holmes RD (2016) Tooth brushing frequency and risk of new carious lesions. Evid Based Dent 17(4):98–99. 10.1038/sj.ebd.6401196 Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25(1):44–56. 10.1038/s41591-018-0300-7 Goecks J, Jalili V, Heiser LM, Gray JW (2020) How Machine Learning Will Transform Biomedicine. Cell 181(1):92–101. 10.1016/j.cell.2020.03.022 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7975886","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":544466783,"identity":"d396056f-6fb5-4de7-aae4-93fe2cc922d3","order_by":0,"name":"Siqi Yan","email":"","orcid":"","institution":"Stomatological Hospital, School of Stomatology, Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Siqi","middleName":"","lastName":"Yan","suffix":""},{"id":544466784,"identity":"41a36050-1408-454f-8504-bedae296f72d","order_by":1,"name":"Linxin Jiang","email":"","orcid":"","institution":"University of Leipzig","correspondingAuthor":false,"prefix":"","firstName":"Linxin","middleName":"","lastName":"Jiang","suffix":""},{"id":544466785,"identity":"f60d857d-8f90-4306-bdb1-6d433a4f363d","order_by":2,"name":"Zhuohang Chen","email":"","orcid":"","institution":"Stomatological Hospital, School of Stomatology, Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zhuohang","middleName":"","lastName":"Chen","suffix":""},{"id":544466786,"identity":"9cb61f53-3274-4efa-a8bf-30bfca9c4dcc","order_by":3,"name":"Yu He","email":"","orcid":"","institution":"Stomatological Hospital, School of Stomatology, Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"He","suffix":""},{"id":544466787,"identity":"089aba57-209b-4f92-aac4-d24bdb439b6c","order_by":4,"name":"Dingfang Luo","email":"","orcid":"","institution":"Stomatological Hospital, School of Stomatology, Southern Medical University","correspondingAuthor":false,"prefix":"","firstName":"Dingfang","middleName":"","lastName":"Luo","suffix":""},{"id":544466788,"identity":"56346c9f-19b2-40e1-8169-8d38fd4eef94","order_by":5,"name":"Jianbo Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwUlEQVRIiWNgGAWjYFACxgaDBzwH5Nj4mw8Qq4X5QEECzwFjPoljCcRqYUv4kMBwIHEeQ44BcRp0+88YbkiQuZPexnDGgOFHxTbCWswOnDE2SOB5ltvG3FbA2HPmNhFaDvaYAbUczm1jOLyBmbGNGC2Hecx/ALWkszEkGBCp5RhbAsiWBDaGFGK1nGE+APKLYRswkA8S55fzBxsMPvbckZfvbz744EcFEVrAgLEHQh8gUj0I/CBB7SgYBaNgFIw8AAAdpEFyl7AWKAAAAABJRU5ErkJggg==","orcid":"","institution":"Stomatological Hospital, School of Stomatology, Southern Medical University","correspondingAuthor":true,"prefix":"","firstName":"Jianbo","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-10-29 05:38:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7975886/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7975886/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96206687,"identity":"e00fca1b-a7a9-4de8-8f40-0d99d8e6ac5f","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"tif","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":255240,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.tif","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/5e947aab5e94b0916fc8cbc6.tif"},{"id":96206688,"identity":"f666bb3e-007a-46ee-b467-c2ac78493f6c","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1487293,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/de2239c718c6005ce62925be.docx"},{"id":96252513,"identity":"c6c49bdd-c8f3-4080-ad5b-7aa4c574c231","added_by":"auto","created_at":"2025-11-19 07:41:06","extension":"tif","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":918190,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/1aee3705d6ccf5763af878b4.tif"},{"id":96252441,"identity":"e46462ba-8250-46c7-a246-2c32af65ab34","added_by":"auto","created_at":"2025-11-19 07:40:57","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24607,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/6bd758855947d43ca04a7cc9.docx"},{"id":96252553,"identity":"5bec3709-8b77-4033-b68d-33e936301a1d","added_by":"auto","created_at":"2025-11-19 07:41:11","extension":"tif","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":417880,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/95f7f3915ddb39ee9f2a2764.tif"},{"id":96252526,"identity":"8e1d59c4-cda9-4c94-8be7-a3ca6aa3c353","added_by":"auto","created_at":"2025-11-19 07:41:07","extension":"docx","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12176,"visible":true,"origin":"","legend":"","description":"","filename":"Table2.docx","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/7e0bf42e37ed38f8accb7d07.docx"},{"id":96206700,"identity":"d4776810-ded4-4cd9-934d-19572f5cdcef","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"tif","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":169482,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.tif","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/6a75eb458b27d05f46fadcf4.tif"},{"id":96206709,"identity":"867cc584-a28a-4449-ac16-e1a8b988aae6","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"docx","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13435,"visible":true,"origin":"","legend":"","description":"","filename":"Table3.docx","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/d67047fbbdc8d1867928e0c3.docx"},{"id":96206689,"identity":"c90e3510-e46f-4747-b4d5-58b058738823","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"json","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7978,"visible":true,"origin":"","legend":"","description":"","filename":"7559ff0584694b668eb22ea59e0a46ea.json","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/c071c6e824477f718b9441db.json"},{"id":96206705,"identity":"d2550320-e20f-47aa-8db2-5611e7a6902a","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"xml","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":173190,"visible":true,"origin":"","legend":"","description":"","filename":"7559ff0584694b668eb22ea59e0a46ea1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/4f20fbf2ae5da0ef9b099ad7.xml"},{"id":96206716,"identity":"76eb8107-65a5-4772-bcd1-4da0505c4d38","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"tif","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":255240,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.tif","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/847eb0d85253829eea631697.tif"},{"id":96206710,"identity":"12320666-aaa4-4255-9a38-468c37fb5953","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"tif","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":918190,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/d61b9444cc7106eb8c9b53f5.tif"},{"id":96252883,"identity":"c2519c1c-f98f-44d1-9415-1d80cc542dd9","added_by":"auto","created_at":"2025-11-19 07:41:36","extension":"tif","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":417880,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/bb54a7fd222819b02e69074e.tif"},{"id":96206714,"identity":"0372347e-5773-447a-aba4-f05a84d1a3ae","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"tif","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":169482,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.tif","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/74dff1c54aee8be2db603295.tif"},{"id":96206715,"identity":"ba338a15-d0dc-41f4-8a31-3e7028344b71","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":255240,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/26f3497f2aed0a795de4f0ba.jpeg"},{"id":96206707,"identity":"3dd13e07-9144-4eb9-8394-5a21e11efea4","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"jpeg","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":918190,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/780a27cc63e323af4dbad037.jpeg"},{"id":96206713,"identity":"43c14c11-264f-487c-9c84-b811bd8027fc","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"jpeg","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":417880,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/41c9d4aa4c5b6228c94cc502.jpeg"},{"id":96253016,"identity":"8994d908-9cce-42d6-a23f-8be7137936ed","added_by":"auto","created_at":"2025-11-19 07:41:47","extension":"jpeg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":169482,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/72471c5bba15fbe6f463ba22.jpeg"},{"id":96206691,"identity":"f1b06a77-7f9b-491b-a827-30171288955a","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33303,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/568d9b525053369ff82bcb57.png"},{"id":96206697,"identity":"22ef07c5-8ead-4ebf-b813-c3385dfc1f2d","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110045,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/ef875ec6ad6f666a63279554.png"},{"id":96206701,"identity":"435166c0-acab-4c0b-91b8-861f51eaa286","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42933,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/e790ddd376895fd4ccaf441a.png"},{"id":96206717,"identity":"734100ba-2cf3-449b-9f2e-4bf409505404","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29306,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/835726e112e8ebd7ed2b7fb0.png"},{"id":96206698,"identity":"63c0df1b-b6e0-4d3c-a158-0286d083e13c","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33303,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/c0cf3350b3ab3352a2fc2523.png"},{"id":96206693,"identity":"228f9620-226e-4baa-a7d5-000799dac4e5","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110045,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/7fe7ccb8c0b9b2c346461dec.png"},{"id":96206704,"identity":"4e99cdf6-9235-4969-8147-f006ed366a8f","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42933,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/61dafca4ebd293b250e5d3a6.png"},{"id":96206712,"identity":"ea8b0453-d9a6-451c-b35f-a9c4e6d0c42d","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29306,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/d0be6f5740f7abca1e4175f0.png"},{"id":96206702,"identity":"b7fc6857-5c65-4ae0-82cd-e83939ee5f00","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"xml","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":170202,"visible":true,"origin":"","legend":"","description":"","filename":"7559ff0584694b668eb22ea59e0a46ea1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/572053a88818157369dfc72a.xml"},{"id":96206699,"identity":"e5d77579-7c66-4342-a48b-a9150cec735a","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"html","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":181647,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/534cc4ef9fd4794cc88e7635.html"},{"id":96206685,"identity":"138a9fcb-dae7-455f-85de-4a39ceec2e99","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":448006,"visible":true,"origin":"","legend":"\u003cp\u003eThe process of sample collection and data analysis\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/2677605dca0b7853b141d996.png"},{"id":96206696,"identity":"ac246b44-17df-4ebb-8eec-db5e7b9b9c1e","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":1109115,"visible":true,"origin":"","legend":"\u003cp\u003eThe results of the 5-fold cross-validation for 6 models.\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/81ae5c2f774f38f346090561.png"},{"id":96206686,"identity":"539e89ea-7fd7-4eda-ace3-a13cfbf36d47","added_by":"auto","created_at":"2025-11-18 17:23:52","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":491083,"visible":true,"origin":"","legend":"\u003cp\u003eVariable importance of Random Forest.\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/462552ae398faf029c3172ca.png"},{"id":96206706,"identity":"144a8f4e-0db8-4fff-a913-e71d9a4630a8","added_by":"auto","created_at":"2025-11-18 17:23:53","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":234373,"visible":true,"origin":"","legend":"\u003cp\u003eThe calibration curve and decision curve of Random Forest.\u003c/p\u003e","description":"","filename":"Figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/6b2bb1532751ce1d5a9fe2c8.png"},{"id":98777250,"identity":"40d53855-6468-479d-9377-9fb9e3f1eede","added_by":"auto","created_at":"2025-12-22 12:26:24","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3434547,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7975886/v1/191c188f-4d8c-4638-925f-35c842e35227.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A preliminary prediction model of untreated dental caries by using machine learning method: a population-based cross-sectional survey","fulltext":[{"header":"Introduction","content":"\u003cp\u003eThe common caries evaluation index is DMF (decayed-missing-filled) index, which reflects the past and present caries experience. Most epidemiological studies only focus on DMF index\u003csup\u003e[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]\u003c/sup\u003e. While treated caries do not contribute to the current medical burden, untreated caries can spread into the pulp, causing pain and infection\u003csup\u003e[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]\u003c/sup\u003e, and affecting children's growth, general health and academic achievement\u003csup\u003e[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]\u003c/sup\u003e. Therefore, untreated dental caries has imposed a serious health and economic burden on individuals and health care systems\u003csup\u003e[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]\u003c/sup\u003e, and predicting untreated caries is arguably more important for the assessment of the medical burden of caries and for the planning of oral public health services.\u003c/p\u003e\u003cp\u003eUntreated caries is disproportionately distributed among people with lower socioeconomic status, which has a significant negative impact on schoolchildren's quality of life\u003csup\u003e[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/sup\u003e. Low income is a significant risk factors of untreated caries\u003csup\u003e[\u003cspan additionalcitationids=\"CR8 CR9 CR10 CR11 CR12\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]\u003c/sup\u003e. Children from low-income families have the highest number of oral diseases and visit the dentist the most frequently for pain relief. However, these children visit the dentist the least often overall. Fewer preventive dental visits increase the disease burden of low-income children. Terrible oral health condition and lack of oral health services for low-income preschoolers, who are twice as likely to develop caries as high-income children in future\u003csup\u003e[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]\u003c/sup\u003e. Untreated carious cavities is associated with lower tooth brushing frequency\u003csup\u003e[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/sup\u003e. Low life quality is a risk indicator for the new lesions of untreated dental caries after 2 years\u003csup\u003e[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]\u003c/sup\u003e. Recent dental visit contributes to increases in treated caries\u003csup\u003e[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]\u003c/sup\u003e. Toothache is s risk factor for untreated dental caries\u003csup\u003e[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]\u003c/sup\u003e. Low maternal educational attainment also affects untreated caries\u003csup\u003e[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]\u003c/sup\u003e. The literature on untreated caries related behaviors investigated parental eating behaviors and tooth brushing frequency. Positive parental diet behaviors can reduce the effect of negative parental behaviors on the prevalence of untreated caries in young children\u003csup\u003e[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]\u003c/sup\u003e. Oral health cognition and attitude towards caries influence untreated caries\u003csup\u003e[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]\u003c/sup\u003e. The most influential factors on untreated caries are the use of dental floss, unhealthy food consumption, self-declared race and exposure to fluoridated water\u003csup\u003e[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eExploring new disease diagnosis models based on big data and machine learning algorithms has achieved remarkable results in disease risk prediction and diagnosis\u003csup\u003e[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]\u003c/sup\u003e. Artificial intelligence based on machine learning has been proven by numerous studies to have promising performance in disease prediction\u003csup\u003e[\u003cspan additionalcitationids=\"CR19\" citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/sup\u003e. Machine learning methods will help predict those teenagers at higher risk of dental caries\u003csup\u003e[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eIn this study, data from a cross-sectional study of untreated caries in 12 year old adolescents in Guangdong Province will be analyzed. The age of 12 is the recommended age for the investigation of permanent tooth caries by the World Health Organization. The aim of this study is to apply machine learning methods to predict adolescents with untreated caries, the related factors are further explored to provide a scientific basis for accurately identifying high-risk group and optimizing prevention policies for oral health of adolescents.\u003c/p\u003e"},{"header":"Materials and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eStudy population\u003c/h2\u003e\u003cp\u003eThe data of this study were derived from the 2021 Oral Health Monitoring Project for Key Populations in Guangdong Province, China, which was a representative cross-sectional study.\u003c/p\u003e\u003cp\u003eThe inclusion criteria entailed participants who were 12-year-old residents of Guangdong Province (who had lived there for at least six months prior to the survey month) and willing to cooperate with the investigators and maintain good compliance. In addition, their legal guardians had the ability to understand the study and the willingness to sign the relevant informed consent letter.\u003c/p\u003e\u003cp\u003eThe exclusion criteria were as follows: legal guardian could not understand and refused to participate in the study; participants with oral disease or major systematic disease which would affect the data integrity and/or the safety of participants.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eEthical consideration\u003c/h3\u003e\n\u003cp\u003eThe study passed ethical review by the Ethics Committee of the Stomatological Hospital, Southern Medical University on March 24, 2020 (Approval No.: 2020\u0026ndash;08). This study was conducted in accordance with the Declaration of Helsinki. Informed consent was obtained from legal guardians of all adolescents as well as the adolescents themselves included in the study.\u003c/p\u003e\n\u003ch3\u003eStudy design\u003c/h3\u003e\n\u003cp\u003eThe formula for calculating the sample size was: N\u0026thinsp;=\u0026thinsp;deff \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\frac{{{\\text{\u0026mu;}}_{\\text{\u0026alpha;}\\text{/2}}}^{\\text{2}}\\text{p(1\u0026minus;p)}}{{\\text{\u0026delta;}}^{\\text{2}}}\\)\u003c/span\u003e\u003c/span\u003e. The design effect (deff) was set at 2.5. The significance level α was set at 0.05, corresponding to a \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\text{\u0026mu;}\\)\u003c/span\u003e\u003c/span\u003e-value of 1.96 at the cumulative probability of α/2 for the standard normal distribution. The allowable relative error(δ) of the expected prevalence (p) was controlled at 10%, prevalence of untreated caries in 12-year-olds adolescents in the 4th Oral Health Survey of Guangdong province was 37.81%\u003csup\u003e[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]\u003c/sup\u003e. According to this calculation, the minimum sample size required for the investigation was 1580 participants.\u003c/p\u003e\u003cp\u003eThe research samples were sampled by stratified random sampling, and 13 monitoring districts were selected. Each monitoring district had approximately 120 to 140 adolescents sampled. There were 7 rural monitoring districts and 6 urban monitoring districts. The number of male and female was nearly equal. A total of 1,641 participants were ultimately included, exceeding the minimum sample size requirement.\u003c/p\u003e\n\u003ch3\u003eClinical examination\u003c/h3\u003e\n\u003cp\u003eThe examiners were guided by a standard examiner until the kappa values of inter-examiner were \u0026gt;\u0026thinsp;0.8 before examination. The participants were examined on portable dental chairs with lights. Caries examination was performed on each participant with a community periodontal index (CPI) probe and a plane mirror. The diagnostic criteria of dental caries were based on the oral health survey methods of World Health Organization (WHO) (5th edition)\u003csup\u003e[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]\u003c/sup\u003e. The kappa values of inter-examiner were calculated by repeated examination of 5% of participants.\u003c/p\u003e\n\u003ch3\u003eQuestionnaire survey\u003c/h3\u003e\n\u003cp\u003eBefore questionnaire survey, the training of questionnaire investigators included clarifying the purpose of the questionnaire, unifying the questionnaire filling method and standardizing the questioning procedure. Trained investigators conducted one-on-one questionnaires on the participants, each participant completed a questionnaire. The questionnaire, previously deployed in national surveys, shows robust reliability and validity\u003csup\u003e[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e, \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]\u003c/sup\u003e. The variables included in this study mainly fell into five categories: (1) basic demographic information, including gender and whether you are only children or not; (2) socioeconomic status, including household registration type and parental education level; (3) lifestyle related to caries, including oral hygiene habits, sweets consumption frequency, and tobacco consumption; (4) oral health-related experiences, including toothache, tooth trauma, self-evaluation of oral condition, and dental visit; (5) oral health knowledge and attitudes.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eStatistical analysis\u003c/h2\u003e\u003cp\u003eIn terms of algorithms, six common machine learning algorithms were used to build models separately by using Python 3.11: Decision Tree (DTM), Random Forest (RF), Xtreme Gradient Boosting (XGBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), and Logistic Regression. The training process of the model consisted of four stages: dataset construction, data processing, training and validation, and prediction.\u003c/p\u003e\u003cp\u003eIt was divided into the training set and the test set in a ratio of 7:3. To obtain a more stable model and reduce overfitting, a 5-fold cross-validation was conducted on the data. The data was divided into five subsets of similar size, among which four subsets were used as the training sets for establishing and optimizing the model, and one subset was used as the test set for verifying the model's efficiency. A total of five repeated tests were conducted, and the optimal hyperparameters were finally obtained. The final model was trained using the combination of the optimal hyperparameters.\u003c/p\u003e\u003cp\u003eThe metrics used to evaluate the performance of each machine learning algorithm in stratified 5-fold cross-validation included the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, precision, specificity, sensitivity, and F1 score. The average AUC value was calculated from five repetitions of the model training process, and the other evaluation metrics were also obtained in the same way. AUC is a performance metric used to evaluate the quality of the learner. An AUC value between 0.7 and 0.9 indicates a certain level of accuracy in real diagnosis, and an AUC greater than 0.9 indicates high accuracy\u003csup\u003e[\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]\u003c/sup\u003e. The higher the AUC value, the better the classification performance of the model\u003csup\u003e[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eThe most significant associated factors were identified by machine learning algorithm with the largest AUC. The calibration curve and decision curve were plotted based on the largest AUC machine learning algorithm.\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows the research process.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cb\u003eParticipants characteristics\u003c/b\u003e\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e presents characteristics of the participants, including residence, gender, and the 16 variables selected through the questionnaire survey. All the variables included in the study were categorical variables. Among the included variables, there were statistically significant differences in the untreated caries prevalence rates of different conditions of variables such as gender, residence, father's education attainment, mother's education attainment, brushing teeth frequency, floss frequency, self-evaluation of oral condition, have a toothache in the past year, and oral health knowledge.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cdiv class=\"gridtable\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eUnivariate analysis of factors associated to untreated caries \u0026gt; 0.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVariables\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eN(%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003euntreated caries \u0026gt; 0(%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eOR(95% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eGender\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.377 (1.131–1.677)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e0.001\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e826(50.34)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e311(37.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003efemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e815(49.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e370(45.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eResidence\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.573 (1.289–1.920)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e\u0026lt; 0.001\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eurban\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e753(45.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e268(35.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erural\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e888(54.11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e413(46.51)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eWhether they are only children or not\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.772 (0.573–1.041)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.090\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eyes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e213(12.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e77(36.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1428(87.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e604(42.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eFather's education attainment\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.793 (0.690–0.911)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e0.001\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003elowest\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4(0.24)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1(25.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erelatively low\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1056(64.35)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e477(45.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emedium\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e356(21.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e120(33.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehigh\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e225(13.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e83(36.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eMother's education attainment\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.743 (0.646–0.853)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e\u0026lt; 0.001\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003elowest\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e30(1.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e17(56.67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erelatively low\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1105(67.34)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e494(44.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emedium\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e293(17.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e99(33.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehigh\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e213(12.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e71(33.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eBrushing teeth frequency\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.248 (1.055–1.476)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e0.010\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e≥ 2 times a day\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e840(51.19)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e319(37.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eonce a day\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e734(44.73)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e333(45.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enot brushing teeth every day\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e63(3.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e28(44.44)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enever\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4(0.24)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1(25.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eFluoride toothpaste\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.465 (0.344–6.242)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.230\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eyes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e295(17.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e138(46.78)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e126(7.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e53(42.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eunknown\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1212(73.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e487(40.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enever use toothpaste\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e8(0.49)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3(37.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eFloss frequency\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.805 (0.679–0.954)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e0.013\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enever\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1143(69.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e498(43.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eoccasionally\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e443(27.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e163(36.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003euse weekly\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e30(1.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13(43.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003euse daily\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e25(1.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7(28.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eDessert frequency\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.089 (0.949–1.249)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.227\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eat least once a day\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e400(24.38)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e162(40.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eat least once a week\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e803(48.93)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e324(40.35)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026lt; 3 times a month\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e438(26.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e195(44.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSweet drink frequency\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.117 (0.968–1.290)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.130\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eat least once a day\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e604(36.81)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e238(39.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eat least once a week\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e796(48.51)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e335(42.09)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026lt; 3 times a month\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e241(14.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e108(44.81)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSweet milk frequency\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.089 (0.952–1.245)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.213\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eat least once a day\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e669(40.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e271(40.51)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eat least once a week\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e677(41.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e276(40.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026lt; 3 times a month\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e295(17.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e134(45.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTobacco frequency\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.911 (0.561–1.482)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.708\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003edaily\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3(0.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1(33.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eweekly\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1(0.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1(100.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erarely\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36(2.19)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e16(44.44)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enever\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1601(97.56)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e663(41.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSelf-evaluation of oral condition\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.503 (1.316–1.717)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e\u0026lt; 0.001\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003efine\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e78(4.75)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e27(34.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erelatively good\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e432(26.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e138(31.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e915(55.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e395(43.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003erelatively bad\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e189(11.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e100(52.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003every bad\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e27(1.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e21(77.78)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTooth trauma\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.961 (0.831–1.111)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.587\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003einjured\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e305(18.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e134(43.93)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003euninjured\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e876(53.38)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e356(40.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ecannot remember clearly\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e460(28.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e191(41.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eHave a toothache in the past year\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.692 (0.605–0.790)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e\u0026lt; 0.001\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eoften\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36(2.19)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29(80.56)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eoccasionally\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e770(46.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e365(47.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enever\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e586(35.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e193(32.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ecannot remember clearly\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e249(15.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e94(37.75)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eVisit a dentist\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.897 (0.737–1.091)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.276\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehave visited\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e822(50.09)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e352(42.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003enever\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e819(49.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e329(40.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eOral health knowledge\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.742 (0.647–0.849)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e\u0026lt; 0.001\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003elow\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e296(18.04)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e153(51.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emiddle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e700(42.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e293(41.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehigh\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e645(39.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e235(36.43)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eOral health attitude\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.836 (0.678–1.032)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.095\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003elow\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e27(1.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13(48.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emiddle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e340(20.72)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e153(45.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehigh\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1274(77.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e515(40.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\u003c/div\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003ePerformance of different models\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eCross-validation results\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe optimal range of hyperparameters was sought. The optimal hyperparameters were obtained through cross-validation, and the combination of the optimal hyperparameters was used for training the final model. During the search process, the accuracy, precision, specificity, sensitivity, and F1 score of 6 models, as well as the AUC under 5-fold cross-validation were obtained. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, from the results of the 5-fold cross-validation, the model with the smallest AUC was Logistic Regression (0.619 ± 0.017), and the one with the largest AUC was the Random Forest (0.785 ± 0.013).\u003c/p\u003e\u003cp\u003e\u003cb\u003eModel prediction results\u003c/b\u003e\u003c/p\u003e\u003cp\u003eAs shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The AUC values obtained by training the model on the training set of Decision Tree(DTM), Random Forest(RF), Xtreme Gradient Boosting(XGBoost), Gradient Boosting Decision Tree(GBDT), Light Gradient Boosting Machine(LightGBM), and Logistic Regression were 0.839, 0.875, 0.888, 0.799, 0.905 and 0.633, respectively. The AUC values obtained by training the model on the test set of Decision Tree(DTM), Random Forest(RF), Xtreme Gradient Boosting(XGBoost), Gradient Boosting Decision Tree(GBDT), Light Gradient Boosting Machine(LightGBM), and Logistic Regression were 0.773, 0.785, 0.807, 0.733, 0.800 and 0.644, respectively.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cdiv class=\"gridtable\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eThe AUC of six machine algorithm models in the training set and the test set.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTraining set\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eTest set\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDTM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.839\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.773\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRandom\u003c/p\u003e\u003cp\u003eForest\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.875\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.785\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.888\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.807\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGBDT\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.799\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.733\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLightGBM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.905\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.800\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLogistic Regression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.633\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.644\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\u003c/div\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eThe test performance of six models\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThis study employed six machine learning classifiers for classification learning. Overall, the AUC of Decision Tree (DTM), Random Forest (RF), Xtreme Gradient Boosting (XGBoost), Gradient Boosting Decision Tree (GBDT), and Light Gradient Boosting Machine (LightGBM) were 70.5%−78.5%.\u003c/p\u003e\u003cp\u003eLogistic Regression performed the worst on accuracy (0.592), precision (0.582), sensitivity (0.549), specificity (0.631), F1 Score (0.564), and the AUC(0.619). Random Forest performed the best on accuracy (0.707), precision (0.698), specificity (0.714), F1 Score (0.698), and the AUC (0.785). Light Gradient Boosting Machine (LightGBM) performed the best on sensitivity (0.718) (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cdiv class=\"gridtable\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eComparison of 5-fold cross-validation results of different machine algorithm models.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDTM\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRandom\u003c/p\u003e\u003cp\u003eForest\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eGBDT\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eLightGBM\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eLogistic Regression\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAUC\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.705 (0.658–0.751)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.785 (0.759–0.811)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.765 (0.724–0.806)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.716 (0.684–0.748)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.763 (0.731–0.796)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.619 (0.585–0.653)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.658 (0.602–0.713)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.707 (0.685–0.728)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.696 (0.664–0.727)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.654 (0.637–0.671)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.698 (0.662–0.734)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.592 (0.559–0.624)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.642 (0.575–0.708)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.698 (0.673–0.724)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.676 (0.646–0.705)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.644 (0.605–0.683)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.676 (0.631–0.721)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.582 (0.534–0.629)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.656 (0.630–0.693)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.714 (0.695–0.737)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.684 (0.669–0.703)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.673 (0.647–0.709)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.679 (0.659–0.706)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.631 (0.610–0.661)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.660 (0.641–0.685)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.699 (0.675–0.730)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.708 (0.683–0.740)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.633 (0.616–0.657)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.718 (0.705–0.734)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.549 (0.544–0.555)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eF1 Score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.650 (0.597–0.703)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.698 (0.666–0.730)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.691 (0.652–0.730)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.637 (0.612–0.663)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.696 (0.667–0.725)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.564 (0.545–0.583)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\u003c/div\u003e\n\u003ch3\u003eVariable importance of Random Forest\u003c/h3\u003e\n\u003cp\u003eIn the Random Forest model, The ranking of the contribution degree of variables to the model was as follows: self-evaluation of oral condition, have a toothache in the past year, oral health knowledge, father's education attainment, mother's education attainment, floss frequency, residence, gender, brushing teeth frequency (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\n\u003ch3\u003eCalibration curve and Decision curve of Random Forest\u003c/h3\u003e\n\u003cp\u003eThe calibration curve is plotted based on the predicted rate and the actual occurrence rate to determine if the observed probability is consistent with the model's predicted probability. Figure\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e showed the calibration curve of the Random Forest model. The calibration curve of the model was close to the standard line, indicating that the machine learning model performed well and was reliable and effective.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThe decision curve of the random forest model was shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. The vertical axis represents net benefit, and the horizontal axis represents the threshold probability. The black solid line and the gray dashed line are respectively regarded as the two extreme lines representing all negative and all positive cases. The net benefit was higher than the extreme curve, it indicated that the random forest model's judgment was good.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this study, we utilized machine learning methods to establish a preliminary prediction model for untreated dental caries among adolescents based on questionnaire surveys. The sample of our study was large and representative. The data acquisition method through questionnaires is straightforward and highly conducive to the promotion of the prediction model in remote and impoverished areas where advanced technologies are not accessible. Our research findings are helpful for the formulation of oral public health policies and the allocation of resources.\u003c/p\u003e\u003cp\u003eBy leveraging machine learning technology, we aimed to enhance the efficiency of screening adolescents with untreated dental caries, especially through a simple questionnaire survey. It is crucial to identify adolescents who have not received treatment for dental caries, especially the most vulnerable ones. This helps to uphold the principle of fairness in universal health coverage, giving more attention to those who truly need it\u003csup\u003e[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eOur research identified the key factors that influence untreated caries in adolescents. Nine variables were included in the machine learning model. The AUC of the random forest model was the largest. The top three most important variables in the random forest model were self-evaluation of oral condition, have a toothache in the past year and oral health knowledge. High levels of dental awareness and self-efficacy are associated with self-reported satisfaction with oral health\u003csup\u003e[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]\u003c/sup\u003e. Toothache is the intuitive perception of the oral health condition, toothache and self-assessment of oral health go hand in hand. Self-perception of oral health affects the use of dental services\u003csup\u003e[\u003cspan additionalcitationids=\"CR30 CR31 CR32\" citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/sup\u003e. Children who suffered from frequent toothaches in the past year were more likely to visit the dentist\u003csup\u003e[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/sup\u003e. Oral health knowledge is significant for promoting oral health\u003csup\u003e[\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]\u003c/sup\u003e. Insufficient oral health knowledge and misunderstandings prevent women from seeking dental care\u003csup\u003e[\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]\u003c/sup\u003e. Better oral health knowledge has a protective effect on specific issues of oral health-related quality of life\u003csup\u003e[\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]\u003c/sup\u003e. The other six variables included in this model have also been proven to be associated with caries in previous studies. Parents' good educational achievement is associated with better oral health for offspring\u003csup\u003e[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]\u003c/sup\u003e. Male had a higher prevalence of untreated caries in the U.S.\u003csup\u003e[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]\u003c/sup\u003e. Nevertheless, researches on caries in school-age children in China have revealed that girls are more susceptible to developing caries\u003csup\u003e[\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e, \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]\u003c/sup\u003e. The use of dental floss is associated with proximal caries\u003csup\u003e[\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]\u003c/sup\u003e. Individuals who brush their teeth infrequently afford higher risk for the caries increment than those brushing more frequently\u003csup\u003e[\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eFurthermore, we employed six machine learning algorithms and evaluated their performance systematically. We determined that the random forest algorithm was the most performant model by hyperparameter tuning and model selection. Compared with other algorithms, it exhibited better predictive performance. Parameter optimization and algorithm selection play a crucial role in enhancing the performance of model. Random Forest performed the best on accuracy, precision, specificity, F1 Score and the area under the ROC curve (AUC). With the application of artificial learning and machine learning in various disciplines, their use in the medical field has also rapidly grown. Almost all types of clinical predictions can be achieved through machine learning\u003csup\u003e[\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e]\u003c/sup\u003e. Machine learning is widely applied in clinical diagnosis, precise treatment, and health monitoring\u003csup\u003e[\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]\u003c/sup\u003e. Further research on the caries predictive models based on the related factors of caries will be helpful for the formulation of oral public health policies.\u003c/p\u003e\u003cp\u003eThis study has several limitations. Firstly, the cross-sectional design is inherently limited in its ability to establish causal relationships, this type of design can merely unveil the correlations that exist among variables. Secondly, the independent dataset has not undergone external validation. As such, further verification of the model's robustness and generalization ability is needed. Thirdly, some of the data were derived from questionnaire surveys, and these data may be influenced by the subjective cognitive biases and recall biases of the participants. Finally, the dental plaque microecology, saliva, and genes related to caries were not included in the study.\u003c/p\u003e\u003cp\u003eIn light of the limitations of the present study, several enhancements could be implemented for future research endeavors. Longitudinal investigations explore more profoundly the causal associations between relevant variables and caries. Incorporating more objective indicators, such as plaque microecology, salivary markers, radiological images, and genes, enriches the research scope. Additionally, the predictive model developed will then be subjected to external validation using another dataset. These efforts aim to offer scientific basis for the prevention and treatment of caries.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn conclusion, we utilized machine learning methods to establish a preliminary prediction model for untreated caries among adolescents based on questionnaire surveys. The random forest model performed the best. Factors such as self-evaluation of oral condition, have a toothache in the past year, oral health knowledge, parents' education attainment, floss frequency, residence, gender, and brushing teeth frequency had impact on untreated caries. The prediction model provides clearer decision-making guidance for the prevention of caries.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eDMF \u0026nbsp; \u0026nbsp; Decayed-Missing-Filled\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eML \u0026nbsp; \u0026nbsp;Machine Learning\u003c/p\u003e\n\u003cp\u003eCPI \u0026nbsp; \u0026nbsp; community periodontal index\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eWHO \u0026nbsp; \u0026nbsp; World Health Organization\u003c/p\u003e\n\u003cp\u003eDTM \u0026nbsp; \u0026nbsp;Decision Tree\u003c/p\u003e\n\u003cp\u003eRF \u0026nbsp; \u0026nbsp;Random Forest\u003c/p\u003e\n\u003cp\u003eXGBoost \u0026nbsp; \u0026nbsp;Xtreme Gradient Boosting\u003c/p\u003e\n\u003cp\u003eGBDT \u0026nbsp; \u0026nbsp;Gradient Boosting Decision Tree\u003c/p\u003e\n\u003cp\u003eLightGBM \u0026nbsp; \u0026nbsp;Light Gradient Boosting Machine\u003c/p\u003e\n\u003cp\u003eLR \u0026nbsp; \u0026nbsp;Logistic Regression\u003c/p\u003e\n\u003cp\u003eROC \u0026nbsp; \u0026nbsp;Receiver Operating Characteristic Curve\u003c/p\u003e\n\u003cp\u003eAUC \u0026nbsp; \u0026nbsp;Area Under the ROC Curve\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthical Approval and Consent to Participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study passed ethical review by the Ethics Committee of the Stomatological Hospital, Southern Medical University on March 24, 2020 (Approval No.: 2020\u0026ndash;08). This study was conducted in accordance with the Declaration of Helsinki. Informed consent was obtained from legal guardians of all adolescents included in the study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data that support the findings of this study are available on request from the corresponding author [Li J]. The data are not publicly available due to them containing information that could compromise research participant privacy.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no conflicts of interest in this work.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGuangdong General Higher Education Key Area Special Project, Guangdong Provincial Department of Education (2024ZDZX2031)\u003c/p\u003e\n\u003cp\u003eScience research cultivation program of stomatological hospital, Southern medical university (PY2023021)\u003c/p\u003e\n\u003cp\u003eGuangzhou Science and Technology Bureau Project- \u0026ldquo;Research and Demonstration Application of Diagnosis and Recognition of Pit and Fissure Sealing on Permanent Molar for Children Based on Big Data and Artificial Intelligence\u0026rdquo; (2025B03J0150).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor Contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors made important contributions to the work reported. SQY contributed to the conception, study design, execution, and drafting of the manuscript; LXJ contributed to data visualization and interpretation of statistical results; ZHC, YH, and DFL contributed to investigation and acquiasition of data; JBL contributed to project administration, review, editing, supervision and funding acquisition. All authors gave final approval of the version to be published; have agreed on the journal to which the article has been submitted; and agreed to take responsibility and be accountable for all aspects of the work.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgments\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors would like to thank all of the adolescents and their parents/grandparents, and all the staff who participants in the surveys.\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eKassebaum NJ, Bernab\u0026eacute; E, Dahiya M, Bhandari B, Murray CJ, Marcenes W (2015) Global burden of untreated caries: a systematic review and metaregression. J Dent Res 94(5):650\u0026ndash;658. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/0022034515573272\u003c/span\u003e\u003cspan address=\"10.1177/0022034515573272\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSelwitz RH, Ismail AI, Pitts NB (2007) Dental caries. Lancet 369(9555):51\u0026ndash;59. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/S0140-6736(07)60031-2\u003c/span\u003e\u003cspan address=\"10.1016/S0140-6736(07)60031-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJackson SL, Vann WF Jr, Kotch JB, Pahel BT, Lee JY (2011) Impact of poor oral health on children's school attendance and performance. Am J Public Health 101(10):1900\u0026ndash;1906. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2105/AJPH.2010.200915\u003c/span\u003e\u003cspan address=\"10.2105/AJPH.2010.200915\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePetersen PE, Bourgeois D, Ogawa H, Estupinan-Day S, Ndiaye C (2005) The global burden of oral diseases and risks to oral health. Bull World Health Organ 83(9):661\u0026ndash;669\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBashir NZ (2022) Update on the prevalence of untreated caries in the US adult population, 2017\u0026ndash;2020. J Am Dent Assoc 153(4):300\u0026ndash;308. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.adaj.2021.09.004\u003c/span\u003e\u003cspan address=\"10.1016/j.adaj.2021.09.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEid SA, Khattab NMA, Elheeny AAH (2020) Untreated dental caries prevalence and impact on the quality of life among 11 to14-year-old Egyptian schoolchildren: a cross-sectional study. BMC Oral Health. ;20(1):83. Published 2020 Mar 19. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-020-01077-8\u003c/span\u003e\u003cspan address=\"10.1186/s12903-020-01077-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eVieira-Andrade RG, Pordeus IA, Ramos-Jorge ML et al (2022) Risk indicators of untreated dental caries incidence among preschoolers: a prospective longitudinal study. Braz Oral Res 36:e064 Published 2022 May 2. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1590/1807-3107bor-2022.vol36.0064\u003c/span\u003e\u003cspan address=\"10.1590/1807-3107bor-2022.vol36.0064\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGupta N, Vujicic M, Yarbrough C, Harrison B (2018) Disparities in untreated caries among children and adults in the U.S., 2011\u0026ndash;2014. BMC Oral Health. ;18(1):30. Published 2018 Mar 6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-018-0493-7\u003c/span\u003e\u003cspan address=\"10.1186/s12903-018-0493-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eOrtiz FR, Reyes LT, Ardenghi TM (2022) Social Economic Disadvantage and Untreated Dental Caries: Findings from a Cohort Study in Adolescents. Caries Res 56(3):179\u0026ndash;186. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1159/000525238\u003c/span\u003e\u003cspan address=\"10.1159/000525238\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGriffin SO, Thornton-Evans G, Wei L, Griffin PM (2021) Disparities in Dental Use and Untreated Caries Prevalence by Income. JDR Clin Trans Res 6(2):234\u0026ndash;241. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/2380084420934746\u003c/span\u003e\u003cspan address=\"10.1177/2380084420934746\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLin M, Thornton-Evans G, Griffin SO, Wei L, Junger M, Espinoza L (2019) Increased Dental Use May Affect Changes in Treated and Untreated Dental Caries in Young Children. JDR Clin Trans Res 4(1):49\u0026ndash;57. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/2380084418793410\u003c/span\u003e\u003cspan address=\"10.1177/2380084418793410\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEdelstein BL (2002) Disparities in oral health and access to care: findings of national surveys. Ambul Pediatr 2(2 Suppl):141\u0026ndash;147. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1367/1539-4409(2002)002%3C0141:diohaa%3E2.0.co;2\u003c/span\u003e\u003cspan address=\"10.1367/1539-4409(2002)002%3C0141:diohaa%3E2.0.co;2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEdelstein BL, Chinn CH (2009) Update on disparities in oral health and access to dental care for America's children. Acad Pediatr 9(6):415\u0026ndash;419. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.acap.2009.09.010\u003c/span\u003e\u003cspan address=\"10.1016/j.acap.2009.09.010\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCosta MD, Chapanski VDR, Crema AFA, Menoncin BLV, H\u0026ouml;felmann DA, Fraiz FC (2022) Untreated early childhood caries: the role of parental eating behavior. Braz Oral Res 36:e010 Published 2022 Jan 14. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1590/1807-3107bor-2022.vol36.0010\u003c/span\u003e\u003cspan address=\"10.1590/1807-3107bor-2022.vol36.0010\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSadiq N, Probst JC, Martin AB, Khan MM, Merchant AT (2021) Untreated Dental Caries May be Associated with Subsequent Mortality among Working-Age Adults: Evidence from NHANES III. Community Dent Oral Epidemiol 49(4):377\u0026ndash;383. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/cdoe.12612\u003c/span\u003e\u003cspan address=\"10.1111/cdoe.12612\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBomfim RA (2024) Machine learning to predict untreated dental caries in adolescents. BMC Oral Health 24(1):316 Published 2024 Mar 9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-024-04073-4\u003c/span\u003e\u003cspan address=\"10.1186/s12903-024-04073-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePeng X, Liu Y, Zhang B et al (2024) A preliminary prediction model of pediatric Mycoplasma pneumoniae pneumonia based on routine blood parameters by using machine learning method. BMC Infect Dis. ;24(1):707. Published 2024 Jul 18. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12879-024-09613-5\u003c/span\u003e\u003cspan address=\"10.1186/s12879-024-09613-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePeiffer-Smadja N, Rawson TM, Ahmad R et al (2020) Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clin Microbiol Infect 26(5):584\u0026ndash;595. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.cmi.2019.09.009\u003c/span\u003e\u003cspan address=\"10.1016/j.cmi.2019.09.009\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTheodosiou AA, Read RC (2023) Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician. J Infect 87(4):287\u0026ndash;294. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jinf.2023.07.006\u003c/span\u003e\u003cspan address=\"10.1016/j.jinf.2023.07.006\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePeng HT, Siddiqui MM, Rhind SG, Zhang J, da Luz LT, Beckett A (2023) Artificial intelligence and machine learning for hemorrhagic trauma care. Mil Med Res 10(1):6 Published 2023 Feb 16. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s40779-023-00444-0\u003c/span\u003e\u003cspan address=\"10.1186/s40779-023-00444-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eShaohong Huang (2020) The Report on Fourth Oral Health Epidemiology Survey in Guangdong Province. Southern Publishing Media Group\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eOrganization WH (2013) Oral Health Surveys: Basic Methods. World Health Organization\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJiang L, Huang S, Reissmann DR, Schmalz G, Li J (2025) Identification of Risk Group for Root Caries and Analysis of Associated Factors in Older Adults Using Unsupervised Machine Learning Clustering. Clin Interv Aging 20:483\u0026ndash;493 Published 2025 Apr 24. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2147/CIA.S520229\u003c/span\u003e\u003cspan address=\"10.2147/CIA.S520229\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTian T, Yang Z, Li S et al (2024) Cross-sectional survey and analysis of factors influencing the prevalence of dental caries among older individuals aged 65\u0026ndash;74 in Guangdong Province in 2021. BMC Oral Health. ;24(1):948. Published 2024 Aug 16. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-024-04624-9\u003c/span\u003e\u003cspan address=\"10.1186/s12903-024-04624-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHosmer DW Jr, Lemeshow S, Sturdivant RX (2013) Applied logistic regression. Wiley\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCai G, Huang F, Gao Y et al (2024) Artificial intelligence-based models enabling accurate diagnosis of ovarian cancer using laboratory tests in China: a multicentre, retrospective cohort study. Lancet Digit Health 6(3):e176\u0026ndash;e186. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/S2589-7500(23)00245-5\u003c/span\u003e\u003cspan address=\"10.1016/S2589-7500(23)00245-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eda Cunha IP, de Lacerda VR, da, Silveira Gaspar G et al (2022) Factors associated with the absence of Brazilians in specialized dental centers. BMC Oral Health. ;22(1):364. Published 2022 Aug 26. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-022-02402-z\u003c/span\u003e\u003cspan address=\"10.1186/s12903-022-02402-z\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAllen F, Fan SY, Loke WM, Na TM, Keng Yan GL, Mittal R (2022) The relationship between self-efficacy and oral health status of older adults. J Dent 122:104085. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jdent.2022.104085\u003c/span\u003e\u003cspan address=\"10.1016/j.jdent.2022.104085\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHerkrath FJ, Vettore MV, Werneck GL (2018) Contextual and individual factors associated with dental services utilisation by Brazilian adults: A multilevel analysis. PLoS ONE 13(2):e0192771 Published 2018 Feb 8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1371/journal.pone.0192771\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0192771\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXu M, Cheng M, Gao X et al (2020) Factors associated with oral health service utilization among adults and older adults in China, 2015\u0026ndash;2016. Community Dent Oral Epidemiol 48(1):32\u0026ndash;41. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/cdoe.12497\u003c/span\u003e\u003cspan address=\"10.1111/cdoe.12497\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRebelo Vieira JM, Rebelo MAB, Martins NMO, Gomes JFF, Vettore MV (2019) Contextual and individual determinants of non-utilization of dental services among Brazilian adults. J Public Health Dent 79(1):60\u0026ndash;70. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/jphd.12295\u003c/span\u003e\u003cspan address=\"10.1111/jphd.12295\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXu M, Yuan C, Sun X, Cheng M, Xie Y, Si Y (2018) Oral health service utilization patterns among preschool children in Beijing, China. BMC Oral Health. ;18(1):31. Published 2018 Mar 6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-018-0494-6\u003c/span\u003e\u003cspan address=\"10.1186/s12903-018-0494-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGao X, Ding M, Xu M et al (2020) Utilization of dental services and associated factors among preschool children in China. BMC Oral Health 20(1):9 Published 2020 Jan 8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-019-0996-x\u003c/span\u003e\u003cspan address=\"10.1186/s12903-019-0996-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNaidu RS, Nunn JH (2020) Oral Health Knowledge, Attitudes and Behaviour of Parents and Caregivers of Preschool Children: Implications for Oral Health Promotion. Oral Health Prev Dent 18(2):245\u0026ndash;252 Published 2020 Jul 4. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3290/j.ohpd.a43357\u003c/span\u003e\u003cspan address=\"10.3290/j.ohpd.a43357\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWilliams TM, Babalola AE, Bolarinwa O et al (2025) Oral health knowledge, perceptions and attitudes of pregnant women in Sub-Saharan Africa: a systematic review. BMC Oral Health 25(1):937 Published 2025 Jun 6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-025-06249-y\u003c/span\u003e\u003cspan address=\"10.1186/s12903-025-06249-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGardner J, Huang B, Ip RHL (2023) Oral health knowledge is associated with oral health-related quality of life: a survey of first-year undergraduate students enrolled in an American university. BMC Oral Health. ;23(1):961. Published 2023 Dec 3. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-023-03721-5\u003c/span\u003e\u003cspan address=\"10.1186/s12903-023-03721-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRuhe T, Broadbent JM, Schluter PJ et al (2023) Parents' education and Pasifika children's oral health in Aotearoa/New Zealand: A national linked data study using Aotearoa/New Zealand's integrated data infrastructure. Community Dent Oral Epidemiol 51(5):936\u0026ndash;944. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/cdoe.12791\u003c/span\u003e\u003cspan address=\"10.1111/cdoe.12791\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang X, Chen H, Hou R et al (2023) Effect of dietary patterns on dental caries among 12\u0026ndash;15 years-old adolescents: a cross-sectional survey. BMC Oral Health 23(1):845 Published 2023 Nov 9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-023-03566-y\u003c/span\u003e\u003cspan address=\"10.1186/s12903-023-03566-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChen Z, Zhu J, Zhao J et al (2023) Dental caries status and its associated factors among schoolchildren aged 6\u0026ndash;8 years in Hangzhou, China: a cross-sectional study. BMC Oral Health. ;23(1):94. Published 2023 Feb 14. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12903-023-02795-5\u003c/span\u003e\u003cspan address=\"10.1186/s12903-023-02795-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ede Oliveira KMH, Nemezio MA, Romualdo PC, da Silva RAB, de Paula E, Silva FWG, K\u0026uuml;chler EC (2017) Dental Flossing and Proximal Caries in the Primary Dentition: A Systematic Review. Oral Health Prev Dent 15(5):427\u0026ndash;434. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3290/j.ohpd.a38780\u003c/span\u003e\u003cspan address=\"10.3290/j.ohpd.a38780\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBrusius CD, Alves LS, Maltz M (2023) Association between toothbrushing frequency and dental caries and tooth loss in adolescents: a cohort study. Braz Oral Res 37:e127 Published 2023 Dec 15. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1590/1807-3107bor-2023.vol37.0127\u003c/span\u003e\u003cspan address=\"10.1590/1807-3107bor-2023.vol37.0127\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHolmes RD (2016) Tooth brushing frequency and risk of new carious lesions. Evid Based Dent 17(4):98\u0026ndash;99. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/sj.ebd.6401196\u003c/span\u003e\u003cspan address=\"10.1038/sj.ebd.6401196\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTopol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25(1):44\u0026ndash;56. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41591-018-0300-7\u003c/span\u003e\u003cspan address=\"10.1038/s41591-018-0300-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGoecks J, Jalili V, Heiser LM, Gray JW (2020) How Machine Learning Will Transform Biomedicine. Cell 181(1):92\u0026ndash;101. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.cell.2020.03.022\u003c/span\u003e\u003cspan address=\"10.1016/j.cell.2020.03.022\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Untreated dental caries, Adolescents, Machine learning, Caries prevention, Cross-sectional epidemiological survey","lastPublishedDoi":"10.21203/rs.3.rs-7975886/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7975886/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjectives\u003c/h2\u003e\u003cp\u003eThis study aimed to establish a preliminary prediction model for untreated dental caries among adolescents by using machine learning method.\u003c/p\u003e\u003ch2\u003eMaterials and Methods\u003c/h2\u003e\u003cp\u003eData were obtained from a cross-sectional epidemiological survey involving 1,641 adolescents aged 12 years in Guangdong, Southern China. Demographic information, socioeconomic status, and caries-related behaviors were collected via a structured questionnaire. A preliminary prediction model was developed using six machine learning (ML) algorithms. The performance of each algorithm was evaluated through stratified 5-fold cross-validation, with the following metrics: area under the receiver operating characteristic (ROC) curve (AUC), accuracy, precision, specificity, sensitivity, and F1 score. Variable importance rankings were generated, and calibration and decision curves were plotted.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eAmong six machine learning algorithms, random forest performed the best, which demonstrated an AUC, accuracy, precision, specificity, sensitivity, and F1 score of 0.785 (0.759\u0026ndash;0.811), 0.707 (0.685\u0026ndash;0.728), 0.698 (0.673\u0026ndash;0.724), 0.714 (0.695\u0026ndash;0.737), 0.699 (0.675\u0026ndash;0.730), and 0.698 (0.666\u0026ndash;0.730) in stratified 5-fold cross-validation. The top three important variables: self-evaluation of oral condition, have a toothache in the past year, and oral health knowledge.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e\u003cp\u003eThe prediction model based on random forest algorithm could help discriminate adolescents with untreated dental caries, which will assist healthcare providers in the individual management of caries in adolescents.\u003c/p\u003e","manuscriptTitle":"A preliminary prediction model of untreated dental caries by using machine learning method: a population-based cross-sectional survey","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-18 17:23:47","doi":"10.21203/rs.3.rs-7975886/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f7766f4d-5dde-43ad-99c6-bffb6d7b4a45","owner":[],"postedDate":"November 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-21T23:08:32+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-18 17:23:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7975886","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7975886","identity":"rs-7975886","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}