Evaluation of the predictors of tooth loss using artificial intelligence-based machine learning approach: A retrospective study.

Background: A common and persistent inflammatory condition impacting the supportive structures of teeth, periodontal disease presents notable challenges in dental healthcare. It leads to various clinical issues, including the loss of clinical attachment, increased pocket depth, and tooth mobility. The global prevalence of periodontitis is substantial, with an estimated 20%-50% of the world's population affected, particularly in developing countries. Furthermore, periodontitis often culminates in tooth loss, affecting overall health and the quality of life, particularly in aging populations. Early intervention and accurate prediction of tooth loss are crucial for improving oral health outcomes. Conventional prognostic models have their constraints in sensitivity, prompting the exploration of alternative approaches. Machine learning, an evolving field in artificial intelligence, has gained prominence in various domains, including healthcare. In this study, we examined the potential of machine learning to predict tooth loss based on diverse parameters, including age, systemic diseases (such as diabetes and hypertension), grades of tooth mobility, oral hygiene habits, and more. Materials and Methods: Data from 200 patients were collected, categorized by gender, age, and mobility grades, with 45 having diabetes, 36 with hypertension, and the remaining free of these systemic diseases. The Orange machine learning tool was employed to analyze these data. The free and open-source data visualization and machine learning platform offers user-friendly visual programming for predictive modeling and data analysis. Results: This study showed that machine learning models produced highly accurate predictions, with an area under the curve of 1.000 for several algorithms, such as Naive Bayes, AdaBoost, Random Forest, and Neural Network. Accuracy, precision, recall, and specificity values consistently exceeded 95%, demonstrating the potential of machine learning in predicting tooth loss. Conclusion: By analyzing comprehensive datasets, machine learning models can enhance the accuracy and objectivity of tooth loss prediction. While challenges remain, such as data quality and privacy concerns, integrating machine learning algorithms in dentistry can revolutionize dental healthcare, improve patient outcomes, and reshape the future of periodontics.