Periodontitis and Metabolic Syndrome: Statistical and Machine Learning Analytics

Objectives: To analyze the associations of periodontitis with Metabolic syndrome (MetS) components, consequences, and related conditions, while controlling for socio-demographics, health-related habits among a nationally representative sample of young and middle-aged adults.
Methods: We analyzed data from the Dental, Oral, Medical Epidemiological (DOME) records-based big data study that combines comprehensive socio-demographic, medical, and dental databases of a nationally representative sample of military personnel.
Results: The current research included 57,496 records of patients fulfilling the inclusion criteria. The prevalence of periodontitis in the study population was 9.79 % (5630/57,496).
The following parmeters retained a significant positive association with periodontitis subsequent multivarite analysis (from the highest to the lowest): brushing teeth once a day or more (OR=2.985 (2.739-3.257)), Obstructive Sleep Apnea (OSA) (OR=2.188 (1.545-3.105)), consumption of cariogenic diet (OR=1.652 (1.536-1.776)), non-alcoholoc fatty liver diseases (NAFLD) (OR=1.483 (1.171-1.879)), smoking (OR=1.176 (1.047-1.322)), and age (OR=1.040 (1.035-1.046)).
The following parmeters retained a significant negative association(protective effect) with periodontitis subsequent multivarite analysis (from the highest to the lowest): the mean number of decayed teeth (OR=0.980 (0.970-0.991)), north America birth country compared to native Israelis (OR= 0.775 (0.608-0.988)), urban non-Jewish (OR=0.442 (0.280-0.698)) and urban Jewish (OR=0.395 (0.251-0.620)) compared to rural locality of residence.
We also performed features importance based on XGBoost algorithm with periodontitis set as the target variable, and received an accuracy of 0.86. Among the major features selected by the XGBoost as predictors for periodontitis were OSA and NAFLD as the most important systemic conditions.
Conclusions: Assessment and treatment should consider all of the risk factors for periodontitis and adjust the treatment approach, it will be beneficial for monitoring periodontal disease therapy, in particular to focus on high-risk populations.