机器学习在龋病预测模型中的应用

doi:10.7518/gjkq.2026102

摘要/Abstract

摘要：

龋病是全球范围内最常见的口腔疾病之一，给个人健康和社会经济带来了严重影响。随着机器学习技术的快速发展，它在医疗领域中的应用也越来越受到关注，研究者们开始探索其在龋病预测中的应用。本文综述了机器学习在龋病预测模型中的应用现状，包括数据来源、特征选择、模型构建、性能评估及未来发展方向。通过对现有文献的分析，结果发现机器学习方法能够在龋病风险评估、个性化干预方案和公共健康政策制定中发挥重要作用。本综述旨在帮助读者了解机器学习在龋病预测中的潜力和挑战，促进该领域的进一步研究和应用。

关键词: 龋病, 机器学习, 风险评估

Abstract:

Caries is one of the most common oral diseases worldwide, with serious health and socioeconomic implications. With the rapid development of machine learning technology, its application in the medical field has attracted increasing attention, and researchers have begun to explore its application in caries prediction. This study reviews the application status of machine learning in caries prediction models, including data sources, feature selection, model construction, performance evaluation, and future development directions. By analyzing the existing literature, we found that machine learning methods can play an important role in caries risk assessment, personalized intervention programs, and public health policy making. This review aims to help readers understand the potential and challenges of machine learning in caries prediction and promote further research and application in this field.

Key words: dental caries, machine learning, risk assessment

中图分类号:

R781.1

方伟,王炳蔚,张军,刘景. 机器学习在龋病预测模型中的应用[J]. 国际口腔医学杂志, 2026, 53(3): 335-343.

Wei Fang,Bingwei Wang,Jun Zhang,Jing Liu. Application of machine learning in caries prediction models[J]. Int J Stomatol, 2026, 53(3): 335-343.

参考文献 64

[1]	Selwitz RH, Ismail AI, Pitts NB. Dental caries[J]. Lancet, 2007, 369(9555): 51-59.
[2]	高岩. 口腔组织病理学[M]. 8版. 北京: 人民卫生出版社, 2020: 126-127.
	Gao Y. Oral histopathology[M]. 8th ed. Beijing: People’s Medical Publishing House, 2020: 126-127.
[3]	Maklennan A, Borg-Bartolo R, Wierichs RJ, et al. A systematic review and meta-analysis on early-childhood-caries global data[J]. BMC Oral Health, 2024, 24(1): 835.
[4]	Al-Khalifa KS, Ahmed WM, Azhari AA, et al. The use of artificial intelligence in caries detection: a review[J]. Bioengineering (Basel), 2024, 11(9): 936.
[5]	Dey P, Ogwo C, Tellez M. Comparison of traditio-nal regression modeling vs. AI modeling for the prediction of dental caries: a secondary data analysis[J]. Front Oral Health, 2024, 5: 1322733.
[6]	黄港, 曹桂莹, 刘民. 1990—2019年中国龋病的疾病负担现状及变化趋势研究[J]. 中国全科医学, 2024, 27(14): 1735-1741.
	Huang G, Cao GY, Liu M. Current situation and trends in the disease burden of dental caries in China, 1990-2019[J]. Chin Gen Pract, 2024, 27(14): 1735-1741.
[7]	郑欣, 程磊, 周学东. 龋病研究的前沿与进展[J]. 中华口腔医学杂志, 2024, 59(1): 14-22.
	Zheng X, Cheng L, Zhou XD. Frontiers and advan-ces in dental caries research[J]. Chin J Stomatol, 2024, 59(1): 14-22.
[8]	Reyes LT, Knorst JK, Ortiz FR, et al. Machine lear-ning in the diagnosis and prognostic prediction of dental caries: a systematic review[J]. Caries Res, 2022, 56(3): 161-170.
[9]	Çiftçi BT, Aşantoğrol F. Utilization of machine learning models in predicting caries risk groups and oral health-related risk factors in adults[J]. BMC Oral Health, 2024, 24(1): 430.
[10]	Sadegh-Zadeh SA, Bagheri M, Saadat M. Decoding children dental health risks: a machine learning approach to identifying key influencing factors[J]. Front Artif Intell, 2024, 7: 1392597.
[11]	Kang IA, Ngnamsie Njimbouom S, Lee KO, et al. DCP: prediction of dental caries using machine lear-ning in personalized medicine[J]. Appl Sci, 2022, 12(6): 3043.
[12]	刘红艳, 韦曦, 凌均棨. 人工智能在龋病诊疗中的应用与探索[J]. 中华口腔医学杂志, 2024, 59(1): 37-44.
	Liu HY, Wei X, Ling JQ. Application and exploration of artificial intelligence for caries management[J]. Chin J Stomatol, 2024, 59(1): 37-44.
[13]	Didier AJ, Nigro A, Noori Z, et al. Application of machine learning for lung cancer survival prognos-tication-a systematic review and meta-analysis[J]. Front Artif Intell, 2024, 7: 1365777.
[14]	Nwanosike EM, Conway BR, Merchant HA, et al. Potential applications and performance of machine learning techniques and algorithms in clinical practice: a systematic review[J]. Int J Med Inform, 2022, 159: 104679.
[15]	李小娟, 韩萌, 王乐, 等. 监督与半监督学习下的数据流集成分类综述[J]. 计算机应用研究, 2021, 38 (7): 1921-1929.
	Li XJ, Han M, Wang L, et al. Overview of data stream ensemble classification based on supervised and semi-supervised learning[J]. Appl Res Comput, 2021, 38(7): 1921-1929.
[16]	Zaadnoordijk L, Besold TR, Cusack R. Lessons from infant learning for unsupervised machine lear-ning[J]. Nat Mach Intell, 2022, 4(6): 510-520.
[17]	Bala B, Behal S. AI techniques for IoT-based DDoS attack detection: taxonomies, comprehensive review and research challenges[J]. Comput Sci Rev, 2024, 52: 100631.
[18]	Ancajas CMF, Oyedele AS, Butt CM, et al. Advan-ces, opportunities, and challenges in methods for interrogating the structure activity relationships of na-tural products[J]. Nat Prod Rep, 2024, 41(10): 1543-1578.
[19]	Binetti MS, Massarelli C, Uricchio VF. Machine learning in geosciences: a review of complex environmental monitoring applications[J]. Mach Learn Knowl Extr, 2024, 6(2): 1263-1280.
[20]	殷瑞刚, 魏帅, 李晗, 等. 深度学习中的无监督学习方法综述[J]. 计算机系统应用, 2016, 25(8): 1-7.
	Yin RG, Wei S, Li H, et al. Introduction of unsupervised learning methods in deep learning[J]. Comput Sys Appl, 2016, 25(8): 1-7.
[21]	Carreras J, Yukie Kikuti Y, Miyaoka M, et al. Artificial intelligence analysis and reverse engineering of molecular subtypes of diffuse large B-cell lymphoma using gene expression data[J]. BioMedInforma-tics, 2024, 4(1): 295-320.
[22]	Ferraro M, Vieira AR. Explaining gender differen-ces in caries: a multifactorial approach to a multifactorial disease[J]. Int J Dent, 2010, 2010: 649643.
[23]	邹聚芬, 毕小琴. 成都市社区成年居民口腔健康现状调查及影响因素分析[J]. 中华现代护理杂志, 2022, 28(2): 177-183.
	Zou JF, Bi XQ. Oral health status and influencing factors of adult residents in Chengdu communities[J]. Chin J Mod Nurs, 2022, 28(2): 177-183.
[24]	Li YX, Xiang YG, Ren HX, et al. Association between periodontitis and dental caries: a systematic review and meta-analysis[J]. Clin Oral Investig, 2024, 28(6): 306.
[25]	Ng TC, Luo BW, Lam WY, et al. Updates on caries risk assessment-a literature review[J]. Dent J (Basel), 2024, 12(10): 312.
[26]	楼云飞, 俞长浩, 戴金保. 唾液pH值与年龄及口腔环境的多因素关系[J]. 中华口腔医学杂志, 1986, 21(3): 189-189.
	Lou YF, Yu CH, Dai JB. The multifactorial relationship between salivary pH value, age, and oral environment[J]. Chin J Stomatol, 1986, 21(3): 189-189.
[27]	Johansson I, Holgerson PL, Kressin NR, et al. Snac-king habits and caries in young children[J]. Caries Res, 2010, 44(5): 421-430.
[28]	Mobley C, Marshall TA, Milgrom P, et al. The contribution of dietary factors to dental caries and disparities in caries[J]. Acad Pediatr, 2009, 9(6): 410-414.
[29]	Kumar S, Tadakamadla J, Johnson NW. Effect of toothbrushing frequency on incidence and increment of dental caries: a systematic review and meta-analysis[J]. J Dent Res, 2016, 95(11): 1230-1236.
[30]	de Oliveira KMH, Nemezio MA, Romualdo PC, et al. Dental flossing and proximal caries in the primary dentition: a systematic review[J]. Oral Health Prev Dent, 2017, 15(5): 427-434.
[31]	Fenza G, Gallo M, Loia V, et al. Data set quality in machine learning: consistency measure based on group decision making[J]. Appl Soft Comput, 2021, 106: 107366.
[32]	郝爽, 李国良, 冯建华, 等. 结构化数据清洗技术综述[J]. 清华大学学报(自然科学版), 2018, 58(12): 1037-1050.
	Hao S, Li GL, Feng JH, et al. Survey of structured data cleaning methods[J]. J Tsinghua Univ (Sci Te-chnol), 2018, 58(12): 1037-1050.
[33]	卢洁. 基于微生物组大数据的龋病菌群分析及诊断模型构建[D]. 辽宁: 大连医科大学, 2021.
	Lu J. Caries microbiota analysis and diagnostic model construction based on microbiome big data[D]. Liaoning: Dalian Medical University, 2021.
[34]	胡智栩. 基于机器学习的慢性病预测关键技术研究[D]. 成都: 电子科技大学, 2022.
	Hu ZX. Research on key technologies of chronic disease prediction based on machine learning[D]. Chengdu: University of Electronic Science and Te-chnology of China, 2022.
[35]	Ebrahimi Warkiani M, Moattar MH. A comprehensive survey on recent feature selection methods for mixed data: challenges, solutions and future directions[J]. Neurocomputing, 2025, 623: 129372.
[36]	Jolliffe IT, Cadima J. Principal component analysis: a review and recent developments[J]. Philos Trans Roy Soc A Math Phys Eng Sci, 2016, 374(2065): 20150202.
[37]	Lei S. A feature selection method based on information gain and genetic algorithm[C]//2012 international conference on computer science and electro-nics engineering. IEEE, 2012: 355-358.
[38]	Chandrashekar G, Sahin F. A survey on feature selection methods[J]. Comput Electr Eng, 2014, 40(1): 16-28.
[39]	Li JD, Cheng KW, Wang SH, et al. Feature selection[J]. ACM Comput Surv, 2018, 50(6): 1-45.
[40]	Cai J, Luo JW, Wang SL, et al. Feature selection in machine learning: a new perspective[J]. Neurocomputing, 2018, 300: 70-79.
[41]	Mountrakis G, Im J, Ogole C. Support vector machines in remote sensing: a review[J]. ISPRS J Photogramm Rem Sens, 2011, 66(3): 247-259.
[42]	Chang CC, Lin CJ. LIBSVM: a library for support vector machines[J]. ACM Trans Int Sys Technol, 2011, 2(3): 27.
[43]	Loh WY. Classification and regression trees[J]. WI-REs Data Min & Knowl, 2011, 1(1): 14-23.
[44]	Quist J, Taylor L, Staaf J, et al. Random forest mo-delling of high-dimensional mixed-type data for breast cancer classification[J]. Cancers (Basel), 2021, 13(5): 991.
[45]	Mathew A, Amudha P, Sivakumari S. Deep learning techniques: an overview[M]. Singapore: Springer Singapore, 2020: 599-608.
[46]	Shi Y, Zhu Q, Guo F, et al. Easing embedding lear-ning by comprehensive transcription of heterogeneous information networks[C]//Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, London Uni-ted Kingdom. ACM, 2018: 2190-2199.
[47]	Zhang SC, Li XL, Zong M, et al. Learning kfor kNN classification[J]. ACM Trans Intell Syst Technol, 2017, 8(3): 1-19.
[48]	Ke GL, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree[C]//31st conference on neural information processing systems. NIPS, 2017: 30.
[49]	Yang SP, Berdine G. Bayesian data analysis[J]. Southwest Resp Crit Care Chron, 2020, 8(36): 74-77.
[50]	Mavrogiorgou A, Kiourtis A, Kleftakis S, et al. A catalogue of machine learning algorithms for healthcare risk predictions[J]. Sensors (Basel), 2022, 22(22): 8615.
[51]	Berrar D. Cross-validation[M]. 2nd ed. Amsterdam: Elsevier, 2025: 638-644.
[52]	Stone M. Cross-validatory choice and assessment of statistical predictions[J]. J Roy Stat Soc, 1974, 36(2): 111-133.
[53]	Seiffert C, Khoshgoftaar TM, Van Hulse J, et al. RUSBoost: a hybrid approach to alleviating class imbalance[J]. IEEE Trans Syst Man Cybern Part A Syst Hum, 2010, 40(1): 185-197.
[54]	Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning[J]. J Big Data, 2019, 6(1): 60.
[55]	Wei J, Zou K. EDA: easy data augmentation techniques for boosting performance on text classification tasks[J]. arXiv, 2019: arXiv:.
[56]	Ribani R, Marengoni M. A survey of transfer lear-ning for convolutional neural networks[C]//2019 32nd SIBGRAPI conference on graphics, patterns and images tutorials (SIBGRAPI-T). IEEE, 2019: 47-57.
[57]	Zou H, Hastie T. Addendum: regularization and va-riable selection via the elastic net[J]. J Roy Stat Soc, 2005, 67(5): 768.
[58]	Binuya ME, Engelhardt EG, Schats W, et al. Me-thodological guidance for the evaluation and upda-ting of clinical prediction models: a systematic review[J]. BMC Med Res Methodol, 2022, 22(1): 316.
[59]	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.
	Yan XM, Sun TL, Lu YH, et al. Prediction model of dental caries in 12-year-old children in Sichuan province based on machine learning[J]. West China J Stomatol, 2023, 41(6): 686-693.
[60]	Yang YH, Kim JS, Jeong SH. Prediction of dental caries in 12-year-old children using machine-lear-ning algorithms[J]. J Korean Acad Oral Health, 2020, 44(1): 55-63.
[61]	Ogwo C, Brown G, Warren J, et al. Predicting dental caries outcomes in young adults using machine learning approach[J]. BMC Oral Health, 2024, 24(1): 529.
[62]	Qu X, Zhang C, Houser SH, et al. Prediction model for early childhood caries risk based on behavioral determinants using a machine learning algorithm[J]. Comput Methods Programs Biomed, 2022, 227: 107221.
[63]	Kumari M, Subbarao N. A hybrid resampling algorithms SMOTE and ENN based deep learning mo-dels for identification of Marburg virus inhibitors[J]. Future Med Chem, 2022, 14(10): 701-715.
[64]	Samek W, Wiegand T, Müller KR. Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models[J]. arXiv, 2017: arXiv:.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed