Clinical validation of machine learning models for periodontal disease using established metabolic risk factors

Year 2026, Volume: 9 Issue: 2 , 469 - 475 , 12.03.2026

Fatma Soysal , Fatma Öner

https://doi.org/10.32322/jhsm.1845570

https://izlik.org/JA76KW29NW

Abstract

Aims: Artificial Intelligence (AI)-based models are increasingly applied in periodontal research; however, their clinical validity relative to classical statistical approaches remains insufficiently evaluated. This study was designed as a methodological validation exercise, using well-established metabolic risk factors for periodontitis to benchmark model behavior against known biological relationships. It aimed to compare classical statistical models and AI-based analytical approaches in their ability to reproduce established associations between metabolic markers, hemoglobin A1c (HbA1c), and body-mass index (BMI), and periodontal outcomes.
Methods: A cross-sectional methodological comparison was conducted using data from 1,852 adults in the NHANES 2009-2010 dataset. Periodontal pocket depth (PD) and periodontal disease status were modeled using classical linear and logistic regression, AI-optimized linear regression, random forest, deep learning, and a pseudo-multi-state logistic model (MSM). Models were evaluated with respect to stability, interpretability, and biological plausibility, in addition to numerical performance.
Results: HbA1c demonstrated a modest but statistically significant association with PD and disease probability across all modeling approaches, whereas BMI showed a statistically detectable but clinically negligible contribution. Classical linear regression and AI-assisted linear models yielded stable, clinically interpretable results. Deep learning achieved slightly improved numeric performance but did not reveal additional nonlinear structure. Random forest models showed unstable and clinically implausible prediction patterns. Probability-based models consistently demonstrated a monotonic increase in periodontal disease risk with increasing HbA1c.
Conclusion: For biologically modest and predominantly linear metabolic-periodontal relationships, traditional statistical models remain robust, interpretable, and clinically reliable. AI-based methods offer limited added value beyond incremental numerical refinement, underscoring the importance of aligning analytical complexity with biological signal strength when validating analytical approaches in periodontal epidemiology.

Keywords

Periodontal disease , machine learning , HbA1c , metabolic risk factors

References

• Gasner NS, Schure RS. Periodontal disease. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2025.
• Hashim NT, Babiker R, Padmanabhan V, et al. The global burden of periodontal disease: a narrative review on unveiling socioeconomic and health challenges. Int J Environ Res Public Health. 2025;22(4):624. doi: 10.3390/ijerph22040624
• Hajishengallis G. Periodontitis: from microbial immune subversion to systemic inflammation. Nat Rev Immunol. 2015;15(1):30 44. doi:10. 1038/nri3785
• Tattar R, da Costa BDC, Neves VCM. The interrelationship between periodontal disease and systemic health. Br Dent J. 2025;239(2):103 108. doi:10.1038/s41415-025-8642-2
• Alexa I, Dumitrescu R, Alexa VT, et al. Cross-sectional comparative assessment of periodontal status in diabetic and non-diabetic individuals within a Romanian cohort. J Clin Med. 2025;14(22):8199. doi:10.3390/jcm14228199
• Graziani F, Gennai S, Solini A, Petrini M. A systematic review and meta-analysis of epidemiologic observational evidence on the effect of periodontitis on diabetes: an update of the EFP-AAP review. J Clin Periodontol. 2018;45(2):167 187. doi:10.1111/jcpe.12837
• Zainal Abidin Z, Zainuren ZA, Noor E, Mohd Nor NS, Mohd Saffian S, Abdul Halim R. Periodontal health status of children and adolescents with diabetes mellitus: a systematic review and meta-analysis. Aust Dent J. 2021;66(Suppl 1):S15 S26. doi:10.1111/adj.12845
• Zhao D, Sun Y, Li X, et al. Association between periodontitis and HbA1c levels in non-diabetic patients: a systematic review and meta-analysis. Healthcare. 2023;11(19):2649. doi:10.3390/healthcare11192649
• Chapple ILC, Bouchard P, Cagetti MG, et al. Interaction of lifestyle, behaviour or systemic diseases with dental caries and periodontal diseases: consensus report of group 2 of the joint EFP/ORCA workshop on the boundaries between caries and periodontal diseases. J Clin Periodontol. 2017;44(Suppl 18):S39 S51. doi:10.1111/jcpe.12685
• Genco RJ, Borgnakke WS. Risk factors for periodontal disease. Periodontol 2000. 2013;62(1):59 94. doi:10.1111/j.1600-0757.2012.00457.x
• Marruganti C, Suvan JE, D’Aiuto F. Periodontitis and metabolic diseases (diabetes and obesity): tackling multimorbidity. Periodontol 2000. 2023;93(1):7 22. doi:10.1111/prd.12536
• Buduneli N, Bıyıkoğlu B, İlgenli T, et al. Is obesity a possible modifier of periodontal disease as a chronic inflammatory process? A case–control study. J Periodontal Res. 2014;49(4):465 471. doi:10.1111/jre.12125
• Jiang F, Jiang Y, Zhi H, et al. Artificial Intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4): 230 243. doi:10.1136/svn-2017-000101
• Kueper JK, Terry AL, Zwarenstein M, Lizotte DJ. Artificial Intelligence and primary care research: a scoping review. Ann Fam Med. 2020;18(3): 250 258. doi:10.1370/afm.2518
• Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. Brief Bioinform. 2018; 19(6):1236 1246. doi:10.1093/bib/bbx044
• Eloranta S, Boman M. Predictive models for clinical decision making: deep dives in practical machine learning. J Intern Med. 2022;292(2): 278 295. doi:10.1111/joim.13483
• Vallabhuni S, Debasis K. Hybrid deep learning for IoT-based health monitoring with physiological event extraction. Digit Health. 2025;11: 1 28. doi:10.1177/20552076251337848
• Fu H, Zhang D, Li Y. NHANES-based analysis of the correlation between leisure-time physical activity, serum cotinine levels, and periodontitis risk. BMC Oral Health. 2024;24(1):466. doi:10.1186/s12903-024-04141-9
• Taylor GW, Borgnakke WS. Periodontal disease: associations with diabetes, glycemic control and complications. Oral Dis. 2008;14(3):191 203. doi:10.1111/j.1601-0825.2008.01442.x
• Papapanou PN, Sanz M, Buduneli N, et al. Periodontitis: consensus report of workgroup 2 of the 2017 World Workshop on the Classification of Periodontal and Peri Implant Diseases and Conditions. J Periodontol. 2018;89(Suppl 1):S173 S182. doi:10.1002/JPER.17-0721
• Keller A, Rohde JF, Raymond K, Heitmann BL. Association between periodontal disease and overweight and obesity: a systematic review. J Periodontol. 2015;86(6):766 776. doi:10.1902/jop.2015.140589
• Suvan J, Petrie A, Moles DR, et al. Body-mass index as a predictive factor of periodontal therapy outcomes. J Dent Res. 2014;93(1):49 54. doi:10. 1177/0022034513511084
• Shmueli G. To explain or to predict? Stat Sci. 2010;25(3):289 310. doi:10. 1214/10 STS330
• Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY, van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019;110:12 22. doi:10.1016/j.jclinepi.2019.02.004
• Revilla León M, Gómez Polo M, Barmak AB, et al. Artificial intelligence models for diagnosing gingivitis and periodontal disease: a systematic review. J Prosthet Dent. 2023;130(6):816 824. doi:10.1016/j.prosdent. 2022.01.026
• Vu GT, Mayya V, Mandhidi B, et al. Application of machine learning to predict periodontal disease in US adults: a cross-sectional analysis of NHANES 2009–2014. Health Inform J. 2025;31(4):1 21. doi:10.1177/ 14604582251394617
• Steyerberg EW, Vickers AJ, Cook NR, et al. Assessing the performance of prediction models. Epidemiology. 2010;21(1):128 138. doi:10.1097/EDE.0b013e3181c30fb2