{"title":"使用机器学习预测儿童行为结果。","authors":"Samir P V, Aruna Kumari G, Nandini Biradar, Kodali Srija, Debasmita Das, Sukabhogi Anusha","doi":"10.6026/973206300211555","DOIUrl":null,"url":null,"abstract":"<p><p>Behavioural management in paediatric dentistry is essential for treatment success, yet predicting a child's behavior remains a challenge. This study used machine learning models on data from 120 children aged 4-10 years, incorporating clinical and historical variables such as age, dental history and parental anxiety. Among the models tested, Random Forest achieved the highest accuracy (87.5%) in predicting behavior based on the Frankl scale. Key predictors of negative behavior included younger age, high parental anxiety and prior negative dental experiences. These findings highlight the potential of machine learning to support behavior guidance planning and improve clinical outcomes.</p>","PeriodicalId":8962,"journal":{"name":"Bioinformation","volume":"21 6","pages":"1555-1558"},"PeriodicalIF":1.9000,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12449484/pdf/","citationCount":"0","resultStr":"{\"title\":\"Behavioral outcome prediction among children using machine learning.\",\"authors\":\"Samir P V, Aruna Kumari G, Nandini Biradar, Kodali Srija, Debasmita Das, Sukabhogi Anusha\",\"doi\":\"10.6026/973206300211555\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Behavioural management in paediatric dentistry is essential for treatment success, yet predicting a child's behavior remains a challenge. This study used machine learning models on data from 120 children aged 4-10 years, incorporating clinical and historical variables such as age, dental history and parental anxiety. Among the models tested, Random Forest achieved the highest accuracy (87.5%) in predicting behavior based on the Frankl scale. Key predictors of negative behavior included younger age, high parental anxiety and prior negative dental experiences. These findings highlight the potential of machine learning to support behavior guidance planning and improve clinical outcomes.</p>\",\"PeriodicalId\":8962,\"journal\":{\"name\":\"Bioinformation\",\"volume\":\"21 6\",\"pages\":\"1555-1558\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2025-06-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12449484/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bioinformation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.6026/973206300211555\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioinformation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.6026/973206300211555","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}
Behavioral outcome prediction among children using machine learning.
Behavioural management in paediatric dentistry is essential for treatment success, yet predicting a child's behavior remains a challenge. This study used machine learning models on data from 120 children aged 4-10 years, incorporating clinical and historical variables such as age, dental history and parental anxiety. Among the models tested, Random Forest achieved the highest accuracy (87.5%) in predicting behavior based on the Frankl scale. Key predictors of negative behavior included younger age, high parental anxiety and prior negative dental experiences. These findings highlight the potential of machine learning to support behavior guidance planning and improve clinical outcomes.