Developing Predictive Models for Periodontitis Progression Using Artificial Intelligence: A Longitudinal Cohort Study
Camila Pinheiro Furquim, Lannawill Caruth, Ganesh Chandrasekaran, Andrew J. Cucchiara, Michael J. Kallan, Lynn Martin, Magda Feres, Kyle Bittinger, Kimon Divaris, Joseph Glessner, Alpdoğan Kantarcı, William V. Giannobile, Shefali S. Verma, Flavia Teles
Abstract
AIM: To construct predictive models of periodontitis progression by applying Machine Learning (ML) to baseline data from a study of periodontitis progression. MATERIALS AND METHODS: Logistic regression (LR), multi-layer perceptron (MLP) and probabilistic graphic model (PGM) were utilised on data from a multi-centre longitudinal study in which periodontally healthy (n = 113) and periodontitis participants (n = 302) were examined bi-monthly for 12 months without treatment. Periodontal examination was performed, and salivary levels of 10 analytes were determined. Clinical and demographic parameters and analytes levels were input into the model. The performance of 14 models was compared using the area under the receiver operating characteristic curve (AUROC), and feature importance was assessed using SHapley Additive exPlanations (SHAP). RESULTS: The PGM model (Clinical measures, saliva IL-1β, age, sex) demonstrated the best overall performance (AUROC = 0.88), compared to LR (AUROC = 0.72) and MLP (AUROC = 0.58). Although MLP had a lower Brier score (0.12), its sensitivity was 0, limiting its clinical utility. In contrast, PGM achieved a balanced sensitivity (0.55) and specificity (0.81). Feature importance analyses highlighted the number of deep periodontal pockets as a key driver of model predictions in both PGM and MLP. CONCLUSIONS: ML models can predict periodontitis progression, supporting early detection strategies. Our integrative approach, combining clinical data with salivary biomarkers such as IL-1β, improved predictive accuracy.