Identifying predictors of tooth loss using a rule‐based machine learning approach: A retrospective study at university‐setting clinics

Abstract

BackgroundThis study aimed to identify predictors associated with tooth loss in a large periodontitis patient cohort in the university setting using the machine learning approach.MethodsInformation on periodontitis patients and 18 factors identified at the initial visit was extracted from electronic health records. A two‐step machine learning pipeline was proposed to develop the tooth loss prediction model. The primary outcome is tooth loss count. The prediction model was built on significant factors (single or combination) selected by the RuleFit algorithm, and these factors were further adopted by the count regression model. Model performance was evaluated by root‐mean‐squared error (RMSE). Associations between predictors and tooth loss were also assessed by a classical statistical approach to validate the performance of the machine learning model.ResultsIn total, 7840 patients were included. The machine learning model predicting tooth loss count achieved RMSE of 2.71. Age, smoking, frequency of brushing, frequency of flossing, periodontal diagnosis, bleeding on probing percentage, number of missing teeth at baseline, and tooth mobility were associated with tooth loss in both machine learning and classical statistical models.ConclusionThe two‐step machine learning pipeline is feasible to predict tooth loss in periodontitis patients. Compared to classical statistical methods, this rule‐based machine learning approach improves model explainability. However, the model's generalizability needs to be further validated by external datasets.

Multifactorial analysis of factors influencing premolar mobility in stage III/IV grade C periodontitis patients ≤35 years of age: A cross-sectional study

“…Mobility represents the extent of tooth movement in response to external forces and serves as a crucial clinical indicator for assessing periodontal disease severity, predicting tooth prognosis, and formulating treatment strategies. In a comprehensive study on patients with periodontitis, Chun-Teh Lee et al employed machine learning techniques to identify predictive factors associated with tooth loss, revealing mobility as a signi cant predictor of tooth loss (number of teeth with mobility degree 1, OR = 1.831, P = 0.001; number of teeth with mobility degree 2/3, OR = 1.210, P < 0.001) (Lee et al, 2023). According to a retrospective study on aggressive periodontitis, teeth with a degree of mobility of 1 exhibited a 4.71-fold greater risk of tooth loss than nonmobile teeth, while those with a degree of mobility of 2 had a 6.12-fold greater risk, and those with a degree of mobility of 3 had a 16.7-fold greater risk (Shi et al, 2020).…”