Fatemeh Masaebi, Zahra Ghorbani, Mehdi Azizmohammad Looha, Marzie Deghatipour, Morteza Mohammadzadeh, M. G. Ahsaie, Fariba Asadi, Farid Zayeri
{"title":"利用随机森林算法识别儿童早期恒牙龋齿因素","authors":"Fatemeh Masaebi, Zahra Ghorbani, Mehdi Azizmohammad Looha, Marzie Deghatipour, Morteza Mohammadzadeh, M. G. Ahsaie, Fariba Asadi, Farid Zayeri","doi":"10.3389/fdmed.2024.1359379","DOIUrl":null,"url":null,"abstract":"Early permanent dental caries can pose a serious threat to oral health in the coming years. This study aimed to investigate the key factors influencing early dental caries in permanent teeth among first-grade Iranian children.A cross-sectional study involving 778 randomly selected first-grade children from public schools in Tehran, Iran, was conducted between November 2017 and January 2018. The oral health of the children, evaluated by two trained dentists, was recorded based on the DMFT index. Information on maternal education, gender, dmft index, brushing frequency, dental visits, flossing, and sweet consumption was also collected. The Random Forest method was employed to identify factors associated with early permanent dental caries, and its performance was compared with logistic regression using the Area Under the Curve (AUC) index.Logistic regression, represented by odds ratios (OR), revealed a significant association between early permanent dental caries and dmft index [OR1.13, 95% CI (1.07, 1.20), p-value <0.001], maternal education [OR = 2.04, 95% CI (1.15, 3.62), p-value <0.05], and sweet consumption [OR = 0.59, 95% CI (0.36, 0.98), p-value <0.05]. Random Forest analysis indicated that male gender, higher maternal education, and lower sweet consumption were associated with increased likelihood of being caries-free. Notably, Random Forest demonstrated superior performance (AUC = 0.81) compared to logistic regression (AUC = 0.72).Early permanent dental caries can be effectively managed by caring primary teeth and reducing consumption of sweet. Maternal education emerged as a pivotal factor in mitigating the risk of early permanent dental caries. Therefore, prioritizing these factors and preventing permanent teeth caries in childhood can be remarkably influential in reducing future caries. The usage of the Random Forest algorithm is highly recommended for identifying relevant risk factors associated with early permanent teeth.","PeriodicalId":502488,"journal":{"name":"Frontiers in Dental Medicine","volume":"18 48","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Identifying early permanent teeth caries factors in children using random forest algorithm\",\"authors\":\"Fatemeh Masaebi, Zahra Ghorbani, Mehdi Azizmohammad Looha, Marzie Deghatipour, Morteza Mohammadzadeh, M. G. Ahsaie, Fariba Asadi, Farid Zayeri\",\"doi\":\"10.3389/fdmed.2024.1359379\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Early permanent dental caries can pose a serious threat to oral health in the coming years. This study aimed to investigate the key factors influencing early dental caries in permanent teeth among first-grade Iranian children.A cross-sectional study involving 778 randomly selected first-grade children from public schools in Tehran, Iran, was conducted between November 2017 and January 2018. The oral health of the children, evaluated by two trained dentists, was recorded based on the DMFT index. Information on maternal education, gender, dmft index, brushing frequency, dental visits, flossing, and sweet consumption was also collected. The Random Forest method was employed to identify factors associated with early permanent dental caries, and its performance was compared with logistic regression using the Area Under the Curve (AUC) index.Logistic regression, represented by odds ratios (OR), revealed a significant association between early permanent dental caries and dmft index [OR1.13, 95% CI (1.07, 1.20), p-value <0.001], maternal education [OR = 2.04, 95% CI (1.15, 3.62), p-value <0.05], and sweet consumption [OR = 0.59, 95% CI (0.36, 0.98), p-value <0.05]. Random Forest analysis indicated that male gender, higher maternal education, and lower sweet consumption were associated with increased likelihood of being caries-free. Notably, Random Forest demonstrated superior performance (AUC = 0.81) compared to logistic regression (AUC = 0.72).Early permanent dental caries can be effectively managed by caring primary teeth and reducing consumption of sweet. Maternal education emerged as a pivotal factor in mitigating the risk of early permanent dental caries. Therefore, prioritizing these factors and preventing permanent teeth caries in childhood can be remarkably influential in reducing future caries. The usage of the Random Forest algorithm is highly recommended for identifying relevant risk factors associated with early permanent teeth.\",\"PeriodicalId\":502488,\"journal\":{\"name\":\"Frontiers in Dental Medicine\",\"volume\":\"18 48\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-04-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Dental Medicine\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/fdmed.2024.1359379\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Dental Medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fdmed.2024.1359379","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
恒牙早期龋齿会在未来几年对口腔健康构成严重威胁。本研究旨在调查影响伊朗一年级儿童恒牙早期龋齿的关键因素。2017 年 11 月至 2018 年 1 月期间,进行了一项横断面研究,随机选取了伊朗德黑兰公立学校的 778 名一年级儿童参与研究。儿童的口腔健康状况由两名经过培训的牙医进行评估,并根据 DMFT 指数进行记录。此外,还收集了有关母亲教育程度、性别、DMFT 指数、刷牙频率、看牙、使用牙线和食用甜食的信息。采用随机森林法确定与早期恒牙龋齿相关的因素,并使用曲线下面积(AUC)指数将其性能与逻辑回归进行比较。以几率比(OR)表示的逻辑回归显示,早期恒牙龋齿与dmft指数[OR1.13,95% CI (1.07,1.20),p值<0.001]、母亲教育程度[OR = 2.04,95% CI (1.15,3.62),p值<0.05]和甜食摄入量[OR = 0.59,95% CI (0.36,0.98),p值<0.05]之间存在显著关联。随机森林分析表明,男性性别、较高的母亲教育程度和较低的甜食摄入量与无龋的可能性增加有关。值得注意的是,与逻辑回归(AUC = 0.72)相比,随机森林的性能更优(AUC = 0.81)。产妇教育是降低早期恒牙龋齿风险的关键因素。因此,优先考虑这些因素并在儿童时期预防恒牙龋齿,对减少未来的龋齿有显著影响。强烈建议使用随机森林算法来识别与早期恒牙相关的风险因素。
Identifying early permanent teeth caries factors in children using random forest algorithm
Early permanent dental caries can pose a serious threat to oral health in the coming years. This study aimed to investigate the key factors influencing early dental caries in permanent teeth among first-grade Iranian children.A cross-sectional study involving 778 randomly selected first-grade children from public schools in Tehran, Iran, was conducted between November 2017 and January 2018. The oral health of the children, evaluated by two trained dentists, was recorded based on the DMFT index. Information on maternal education, gender, dmft index, brushing frequency, dental visits, flossing, and sweet consumption was also collected. The Random Forest method was employed to identify factors associated with early permanent dental caries, and its performance was compared with logistic regression using the Area Under the Curve (AUC) index.Logistic regression, represented by odds ratios (OR), revealed a significant association between early permanent dental caries and dmft index [OR1.13, 95% CI (1.07, 1.20), p-value <0.001], maternal education [OR = 2.04, 95% CI (1.15, 3.62), p-value <0.05], and sweet consumption [OR = 0.59, 95% CI (0.36, 0.98), p-value <0.05]. Random Forest analysis indicated that male gender, higher maternal education, and lower sweet consumption were associated with increased likelihood of being caries-free. Notably, Random Forest demonstrated superior performance (AUC = 0.81) compared to logistic regression (AUC = 0.72).Early permanent dental caries can be effectively managed by caring primary teeth and reducing consumption of sweet. Maternal education emerged as a pivotal factor in mitigating the risk of early permanent dental caries. Therefore, prioritizing these factors and preventing permanent teeth caries in childhood can be remarkably influential in reducing future caries. The usage of the Random Forest algorithm is highly recommended for identifying relevant risk factors associated with early permanent teeth.