Exploring the risk factors and clustering patterns of periodontitis in patients with different subtypes of diabetes through machine learning and cluster analysis.

Abstract

Aim: To analyse the risk factors contributing to the prevalence of periodontitis among clusters of patients with diabetes and to examine the clustering patterns of clinical blood biochemical indicators.

Materials and methods: Data regarding clinical blood biochemical indicators and periodontitis prevalence among 1804 patients with diabetes were sourced from the National Health and Nutrition Examination Survey (NHANES) database spanning 2009 to 2014. A clinical prediction model for periodontitis risk in patients with diabetes was constructed via the XGBoost machine learning method. Furthermore, the relationships between diabetes patient clusters and periodontitis prevalence were investigated through consistent consensus clustering analysis.

Results: Seventeen clinical blood biochemical indicators emerged as superior predictors of periodontitis in patients with diabetes. Patients with diabetes were subsequently categorized into two subtypes: Cluster A presented a slightly lower periodontitis prevalence (74.80%), whereas Cluster B presented a higher prevalence risk (83.68%). Differences between the two groups were considered statistically significant at a p value of ≤0.05. There was marked variability in the associations of different cluster characteristics with periodontitis prevalence.

Conclusions: Machine learning combined with consensus clustering analysis revealed a greater prevalence of periodontitis among patients with diabetes mellitus in Cluster B. This cluster was characterized by a smoking habit, a lower education level, a higher income-to-poverty ratio, and higher levels of albumin (ALB g/L) and alanine aminotransferase (ALT U/L).