Skip to main content
Intended for healthcare professionals
Restricted access
Research article
First published online April 7, 2026
Request permissions

Data-Driven Tooth Selection Enhances Partial-Mouth Periodontal Screening

N. Lin, C. Wang, […], Y. Shan, and Z. Wu https://orcid.org/0000-0002-6951-1218 [email protected]+1View all authors and affiliations
OnlineFirst
https://doi.org/10.1177/00220345261432570

Abstract

The high prevalence of periodontitis has imposed a significant global disease burden. Epidemiologic surveys rely on full-mouth periodontal examination (FMPE) or partial-mouth periodontal examination (PMPE). While FMPE is resource-intensive, the efficiency of PMPE remains questionable. Moreover, the value of subpopulation-tailored PMPE protocols is still unassessed. To address these gaps, we developed an interpretable, data-driven framework that ranks the importance of teeth using SHapley Additive exPlanations (SHAP) values from machine learning models. Using data from the National Health and Nutrition Examination Survey 2009–2014, XGBoost (XGB) and LightGBM (LGB) were trained on maximum interproximal probing depth and clinical attachment loss across 28 teeth from adults aged 35 y and older. Absolute SHAP values were aggregated separately for each model to calculate global tooth importance. The top 10 teeth were then evaluated and benchmarked against the Community Periodontal Index (CPI) and modified Ramfjord protocol. Primary outcomes included quadratic weighted kappa (QWK) for diagnostic agreement with FMPE and the inflation factor (IF) for prevalence estimation bias. The XGB-derived protocol (FDI 47, 27, 17, 26, 37, 16, 42, 46, 36, 41) achieved QWK = 0.85 and IF = 127.29% in the external validation set, with significantly lower IF than CPI (P = 0.003), indicating its potential to replace CPI. Further optimization for age- and gender-specific protocols occasionally yielded localized improvements, such as males aged 55 to 64 y (teeth 17, 16, 27, 47, 26, 33, 45, 37, 43, 25), while the unified XGB-derived protocol remained robust across all strata. These findings support the general use of a unified, data-driven protocol for large-scale epidemiological surveys. SHAP-guided tooth selection offers an interpretable and efficient alternative to traditional PMPE, bridging the gap between accuracy and feasibility in large-scale periodontal surveys.

Get full access to this article

View all access and purchase options for this article.

Get Access

Data availability statement

The NHANES data are accessible via https://wwwn.cdc.gov/nchs/nhanes/, and the analysis code for tooth selection is available on GitHub at https://github.com/LinNanzhen/Data-Driven-Tooth-Selection-Enhances-Partial-Mouth-Periodontal-Screening.git.

References

Alawaji YN, Mostafa N, Carvalho RM, Alshammari A, Aleksejuniene J. 2022. Accuracy and precision of using partial-mouth recordings to study the prevalence, extent and risk associations of untreated periodontitis. Saudi Dent J. 34(2):142–149. https://doi.org/10.1016/j.sdentj.2021.12.005
Google Scholar
Albandar JM. 2002. Global risk factors and risk indicators for periodontal diseases. Periodontol 2000. 29(1):177–206. https://doi.org/10.1034/j.1600-0757.2002.290109.x
Google Scholar
Albandar JM. 2011. Underestimation of periodontitis in NHANES surveys. J Periodontol. 82(3):337–341. https://doi.org/10.1902/jop.2011.100638
Google Scholar
Alsulaiman AA, et al. 2018. Incisor malalignment and the risk of periodontal disease progression. Am J Orthod Dentofacial Orthop. 153(4):512–522. https://doi.org/10.1016/j.ajodo.2017.08.015
Google Scholar
Centers for Disease Control and Prevention. 2025. Age adjustment - health, United States. National Center for Health Statistics; [updated 2025 Jun 9; accessed 2025 Oct 24]. https://www.cdc.gov/nchs/hus/sources-definitions/age-adjustment.htm
Google Scholar
Chilukoti SV, Shan L, Tida VS, Maida AS, Hei X. 2024. A reliable diabetic retinopathy grading via transfer learning and ensemble learning with quadratic weighted kappa metric. BMC Med Inf Decis Making. 24(1):37. https://doi.org/10.1186/s12911-024-02446-x
Google Scholar
Díaz-Vallejo M, et al. 2024. Analyses of the variable selection using correlation methods: an approach to the importance of statistical inferences in the modelling process. Ecol Modell. 498:110893. https://doi.org/10.1016/j.ecolmodel.2024.110893
Google Scholar
Efthimiou O, et al. 2024. Developing clinical prediction models: a step-by-step guide. BMJ. 386:e078276. https://doi.org/10.1136/bmj-2023-078276
Google Scholar
Eickholz P, et al. 2025. Prevalence of the periodontal status in Germany: results of the 6th German Oral Health Study (DMS • 6). Quintessence Int. 56(11):S40–S47. https://doi.org/10.3290/j.qi.b5981979
Google Scholar
Eke PI, Borgnakke WS, Genco RJ. 2020. Recent epidemiologic trends in periodontitis in the USA. Periodontol 2000. 82(1):257–267. https://doi.org/10.1111/prd.12323
Google Scholar
Eke PI, et al. 2015. Update on prevalence of periodontitis in adults in the United States: NHANES 2009 – 2012. J Periodontol. 86(5):611–622. https://doi.org/10.1902/jop.2015.140520
Google Scholar
Eke PI, Page RC, Wei L, Thornton-Evans G, Genco RJ. 2012. Update of the case definitions for population-based surveillance of periodontitis. J Periodontol. 83(12):1449–1454. https://doi.org/10.1902/jop.2012.110664
Google Scholar
Fahmy AS, et al. 2022. An explainable machine learning approach reveals prognostic significance of right ventricular dysfunction in nonischemic cardiomyopathy. JACC Cardiovasc Imaging. 15(5):766–779. https://doi.org/10.1016/j.jcmg.2021.11.029
Google Scholar
Fu H, Li X, Zhang R, Zhu J, Wang X. 2025. Global burden of periodontal diseases among the working-age population from 1990–2021: results from the Global Burden of Disease Study 2021. BMC Public Health. 25(1):1316. https://doi.org/10.1186/s12889-025-22566-x
Google Scholar
Gul SS. 2024. Prevalence and severity of circumferential alveolar bone loss using CBCT images: a retrospective study of 20,620 surfaces of 5155 teeth. Diagnostics (Basel). 14(5):507. https://doi.org/10.3390/diagnostics14050507
Google Scholar
Jepsen S, Deschner J, Braun A, Schwarz F, Eberhard J. 2011. Calculus removal and the prevention of its formation. Periodontol 2000. 55(1):167–188. https://doi.org/10.1111/j.1600-0757.2010.00382.x
Google Scholar
Jordan AR, Micheelis W, editors. 2016. Fünfte Deutsche Mundgesundheitsstudie (DMS V) [The Fifth German Oral Health Study; in German]. Deutscher Zahnärzte Verlag DÄV.
Google Scholar
Jordan RA, et al. 2014. The Fifth German oral health study (Fünfte Deutsche Mundgesundheitsstudie, DMS V) – rationale, design, and methods. BMC Oral Health. 14:161. https://doi.org/10.1186/1472-6831-14-161
Google Scholar
Kang B, et al. 2024. Reliability of partial-mouth periodontal examinations for diagnosing periodontal disease. J Periodontal Implant Sci. 55(4):273–284. https://doi.org/10.5051/jpis.2403400170
Google Scholar
Kapila YL. 2021. Oral health’s inextricable connection to systemic health: special populations bring to bear multimodal relationships and factors connecting periodontal disease to systemic diseases and conditions. Periodontol 2000. 87(1):11–16. https://doi.org/10.1111/prd.12398
Google Scholar
Kinane DF, Stathopoulou PG, Papapanou PN. 2017. Periodontal diseases. Nat Rev Dis Primers. 3(1):17038. https://doi.org/10.1038/nrdp.2017.38
Google Scholar
Marcilio WE, Eler DM. 2020. From explanations to feature selection: assessing SHAP values as feature selection mechanism. In: 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI); 2020 Nov 7–10; Virtual Conference. IEEE. p 340–347. https://doi.org/10.1109/SIBGRAPI51738.2020.00053
Google Scholar
Matthews DC, Tabesh M. 2004. Detection of localized tooth-related factors that predispose to periodontal infections. Periodontol 2000. 34(1):136–150. https://doi.org/10.1046/j.0906-6713.2003.003429.x
Google Scholar
Mombelli A, Meier C. 2001. On the symmetry of periodontal disease. J Clin Periodontol. 28(8):741–745. https://doi.org/10.1034/j.1600-051x.2001.280804.x
Google Scholar
Ngai T, et al. 2024. Assessing polyomic risk to predict Alzheimer’s disease using a machine learning model. Alzheimers Dement. 20(12):8700–8714. https://doi.org/10.1002/alz.14319
Google Scholar
Nohara Y, Matsumoto K, Soejima H, Nakashima N. 2022. Explanation of machine learning models using Shapley additive explanation and application for real data in hospital. Comput Methods Programs Biomed. 214:106584. https://doi.org/10.1016/j.cmpb.2021.106584
Google Scholar
Oh M-Y, et al. 2025. Machine learning–based explainable automated nonlinear computation scoring system for health score and an application for prediction of perioperative stroke: retrospective study. J Med Internet Res. 27:e58021. https://doi.org/10.2196/58021
Google Scholar
Owens JD, Dowsett SA, Eckert GJ, Zero DT, Kowolik MJ. 2003. Partial-mouth assessment of periodontal disease in an adult population of the United States. J Periodontol. 74(8):1206–1213. https://doi.org/10.1902/jop.2003.74.8.1206
Google Scholar
Perez-Lebel A, Varoquaux G, Le Morvan M, Josse J, Poline J-B. 2022. Benchmarking missing-values approaches for predictive models on health databases. Gigascience. 11:giac013. https://doi.org/10.1093/gigascience/giac013
Google Scholar
Ponce-Bobadilla AV, Schmitt V, Maier CS, Mensing S, Stodtmann S. 2024. Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development. Clin Transl Sci. 17(11):e70056. https://doi.org/10.1111/cts.70056
Google Scholar
Sreenivasan PK, Prasad KVV, Javali SB. 2016. Oral health practices and prevalence of dental plaque and gingivitis among Indian adults. Clin Exp Dent Res. 2(1):6–17. https://doi.org/10.1002/cre2.15
Google Scholar
Su X, et al. 2023. The association between sex hormones and periodontitis among American adults: a cross-sectional study. Front Endocrinol (Lausanne). 14:1125819. https://doi.org/10.3389/fendo.2023.1125819
Google Scholar
Suh B, Yu H, Cha J-K, Choi J, Kim J-W. 2025. Explainable deep learning approaches for risk screening of periodontitis. J Dent Res. 104(1):45–53. https://doi.org/10.1177/00220345241286488
Google Scholar
Susin C, Vecchia CFD, Oppermann RV, Haugejorden O, Albandar JM. 2004. Periodontal attachment loss in an urban population of Brazilian adults: effect of demographic, behavioral, and environmental risk indicators. J Periodontol. 75(7):1033–1041. https://doi.org/10.1902/jop.2004.75.7.1033
Google Scholar
Tay JRH, Holtfreter B, Baumeister S, Peres MA, Nascimento GG. 2025. Application of the 2018 Periodontal Status Classification to Epidemiological Survey Data (ACES) framework to estimate the periodontitis prevalence in the United States. J Clin Periodontol. 52(7):1032–1043. https://doi.org/10.1111/jcpe.14132
Google Scholar
Tonetti MS, Greenwell H, Kornman KS. 2018. Staging and grading of periodontitis: framework and proposal of a new classification and case definition. J Periodontol. 89(suppl 1):S159–S172. https://doi.org/10.1002/jper.18-0006
Google Scholar
Tran DT, et al. 2014. Assessment of partial-mouth periodontal examination protocols for periodontitis surveillance. J Clin Periodontol. 41(9):846–852. https://doi.org/10.1111/jcpe.12285
Google Scholar
Vandenbroucke JP, et al. 2007. Strengthening the Reporting of Observational Studies in Epidemiology (STROBE): explanation and elaboration. PLoS Med. 4(10):e297. https://doi.org/10.1371/journal.pmed.0040297
Google Scholar
Walter E, et al. 2025. Predictive modeling for step II therapy response in periodontitis - model development and validation. NPJ Digit Med. 8(1):445. https://doi.org/10.1038/s41746-025-01828-3
Google Scholar
Wu L, Zhang S, Zhao L, Ren Z, Hu C. 2022. Global, regional, and national burden of periodontitis from 1990 to 2019: results from the Global Burden of Disease study 2019. J Periodontol. 93(10):1445–1454. https://doi.org/10.1002/jper.21-0469
Google Scholar

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

|

Also from Sage