基于机器学习的上海某医院60岁及以上就诊老人根面龋风险预测模型构建

doi:10.13701/j.cnki.kqyxyj.2026.05.011

摘要/Abstract

摘要： 目的:采用机器学习算法构建老年根面龋风险预测模型,识别根面龋发病的危险因素,为临床筛查高危患者及制定预防策略提供依据。方法:选取2024~2025年上海杨浦区中心医院4826例60岁及以上的患者,经口腔检查、临床数据收集及问卷收集信息。多因素Logistic回归分析筛选危险因素,数据集7∶3分训练集与验证集,Python构建4种机器学习模型,以曲线下面积(area under curve,AUC)评估效果。结果:根面龋患病率45.3%。多因素分析显示年龄、糖尿病等7项因素关联显著(P<0.05)。4种模型AUC为0.849~0.894,Logistic回归最优,菌斑指数贡献最高。结论:Logistic回归模型预测效能良好,针对关键危险因素干预可降低老年根面龋发生率,提升口腔健康管理水平。

关键词: 老年根面龋, 机器学习, Logistic回归, 危险因素, 预测模型

Abstract: Objective: To construct a risk prediction model for root caries in the elderly using machine learning, identify risk factors, and provide a basis for clinical screening and prevention. Methods: 4,826 patients aged ≥60 from Shanghai Yangpu District Central Hospital (2024-2025) were included. Data were collected via oral examinations, clinical records, and questionnaires. Risk factors were screened by multivariate Logistic regression. The dataset was split into training (70%) and validation (30%) sets. Four machine learning models were built using Python and evaluated effectiveness based on the area under curve (AUC). Results: The prevalence of root caries was 45.3%. Multivariate analysis showed 7 factors (e.g., age, diabetes) were significantly associated (P<0.05). The four models had AUC 0.849-0.894, with Logistic regression optimal and plaque index contributed most. Conclusion: Logistic regression had good predictive performance. Intervening on key risk factors can reduce root caries incidence in the elderly and improve oral health management.

Key words: root caries in the elderly, machine learning, Logistic regression, risk factors, prediction model

王辉, 张翼. 基于机器学习的上海某医院60岁及以上就诊老人根面龋风险预测模型构建[J]. 口腔医学研究, 2026, 42(5): 426-432.

WANG Hui, ZHANG Yi. Machine Learning-based Construction of Risk Prediction Model for Root Caries in Elderly Patients Aged 60 Years and Above in Shanghai[J]. Journal of Oral Science Research, 2026, 42(5): 426-432.

参考文献

[1] Selwitz RH, Ismail AI, Pitts NB. Dental caries [J]. Lancet, 2007, 369(9555): 51-59.
[2] Vos MB, Kaar JL, Welsh JA, et al. Added sugars and cardiovascular disease risk in children: a scientific statement from the American heart association [J]. Circulation, 2017, 135(19): e1017-e1034.
[3] Novotna M, Podzimek S, Broukal Z, et al. Periodontal diseases and dental caries in children with type 1 diabetes mellitus [J]. Mediators Inflamm, 2015, 2015: 379626.
[4] Alsadat FA, Alamoudi NM, El-Housseiny AA, et al. Oral and dental manifestations of celiac disease in children: A case-control study [J]. BMC Oral Health, 2021, 21(1): 669.
[5] 王兴.第四次全国口腔健康流行病学调查报告[M].北京:人民卫生出版社,2018: 156-162.
[6] 严鑫淼,孙桃兰,卢雨航,等.基于机器学习的四川省12岁儿童龋齿预测模型[J].华西口腔医学杂志,2023, 41(6): 686-693.
[7] Battineni G, Sagaro GG, Chinatalapudi N, et al. Applications of machine learning predictive models in the chronic disease diagnosis [J]. J Pers Med, 2020, 10(2): 21.
[8] Khanagar SB, Al-Ehaideb A, Maganur PC, et al. Developments, application, and performance of artificial intelligence in dentistry-A systematic review [J]. J Dent Sci, 2021, 16(1): 508-522.
[9] Sadegh-Zadeh SA, Rahmani Qeranqayeh A, Benkhalifa E, et al. Dental caries risk assessment in children 5 years old and under via machine learning [J]. Dent J (Basel), 2022, 10(9): 164.
[10] 李国,程兴群,吴红昆.老年人根面龋危险因素研究进展[J].中国实用口腔科杂志,2021, 14(6): 734-738.
[11] 中华口腔医学会老年口腔医学专业委员会.中国老年口腔健康指南(2021)[J].中华口腔医学杂志,2021, 56 (8): 789-800.
[12] Li Y, Wang X, Zhang L, et al. Prevalence of root caries in Chinese older adults: A systematic review and meta-analysis [J]. J Dent, 2022, 116: 104215.
[13] 上海市人民政府. 2024年上海市户籍老年人口、老龄事业和养老服务工作综合统计信息[R/OL].上海:上海市人民政府,2025. https://www.shanghai.gov.cn/nw4411/20250521/9cd16db60e124efeaab01936311e8f05.html
[14] 国家卫生健康委员会.健康口腔行动方案(2019-2025 年)[Z].北京:国家卫生健康委员会,2019.
[15] Marsh PD. Dental biofilms: biology, pathophysiology, and control [J]. Periodontology 2000, 2020, 83(1): 10-27.
[16] Liu J, Li J, Chen H, et al. Relationship between plaque index and root caries in elderly patients with removable dentures [J]. BMC Oral Health, 2021, 21(1): 523.
[17] Frencken JE, van der Weijden F, van Winkelhoff AJ. Fluoride varnish for the prevention of root caries in older adults: A randomized controlled trial [J]. J Dent Res, 2020, 99(10): 1123-1129.
[18] National Institute for Health and Care Excellence (NICE). Oral health: Prevention in adults [EB/OL]. 2022.
[19] 刘敏,陈悦,李静.老年人根面龋相关危险因素分析及列线图预测模型构建[J].口腔医学,2022, 42(8): 721-725.
[20] Smith A, Johnson B, Lee K. Removable partial dentures and root caries risk: A systematic review [J]. J Prosthet Dent, 2020, 124(3): 389-395.
[21] Zhang L, Wang H, Liu Y. Effect of denture cleaning frequency on root caries in elderly patients [J]. J Oral Rehabil, 2021, 48(5): 542-548.
[22] Wu T, Sun J, Hu D, et al. Glycemic control and root caries in type 2 diabetes mellitus patients: A 5-year cohort study [J]. J Diabetes Res, 2022, 2022: 9876543.
[23] American Diabetes Association. Standards of medical care in diabetes-2023 [J]. Diabetes Care, 2023, 46(S1): S1-S291.
[24] Tonetti MS, Greenwell H, Kornman K. Staging and grading of periodontitis: Framework and proposal of a new classification and case definition [J]. J Periodontol, 2018, 89(S1): S159-S172.
[25] Wang Y, Li Q, Zhang H. Prevalence of gingival recession and its association with root caries in Chinese elderly: A cross-sectional study [J]. Gerodontology, 2020, 37(3): 321-327.
[26] Petersen PE, Bourgeois D, Ogawa H, et al. Oral health in older people: A comprehensive narrative review [J]. BMC Oral Health, 2019, 19(1): 202.
[27] Mohd Yusof E, Ismail IH, Abdul Rahim AH, et al. The risk factors and interventions of dental caries in the elderly: A narrative review [J]. Compendium of Oral Science, 2023, 10(2): 9-22.
[28] Goodwin JL. Logistic regression in dental research: Strengths, limitations, and applications [J]. J Dent Res, 2019, 98(12): 1365-1371.
[29] Shen C, Liu Y, Wang J, et al. Machine learning models for oral disease prediction: A systematic review [J]. J Dent Sci, 2022, 17(2): 612-623.
[30] Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: Data mining, inference, and prediction [M]. 2nd ed. New York: Springer, 2021.
[31] Wang L, Chen M, Li X, et al. Artificial intelligence in root caries diagnosis: A pilot study using deep learning [J]. J Dent, 2023, 128: 104456.
[32] Moher D, Liberati A, Tetzlaff J, et al. Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement [J]. PLoS Med, 2009, 6(7): e1000097.
[33] Rothman KJ, Greenland S, Lash TL. Modern epidemiology [M]. 4th ed. Philadelphia: Lippincott Williams & Wilkins, 2020.
[34] World Health Organization. Global oral health status report 2022 [R]. Geneva: WHO, 2022.