Retrospective cohort study identifies predictors of dental implant success using AI models, improving risk assessment.
Key Points
To identify predictors of dental implant success and develop AI models to forecast implant outcomes.
Retrospective cohort study of 172 patients with 219 implants from 2020 to 2021.
Evaluated patient demographics, health factors, surgical variables, and implant characteristics.
Utilized logistic regression and machine-learning models, including Decision Tree and Random Forest, using stratified 10-fold cross-validation.
Implant success rate was 91.3%; smoking (AOR D 2.3, 95% CI 1.3–4.1, p D 0.001) and diabetes (AOR D 1.8, 95% CI 1.1–3.5, p D 0.03) were independent predictors of failure.
Flapless surgery showed a protective effect (AOR D 0.7, 95% CI 0.5–0.9, p D 0.04).
Random Forest achieved highest predictive performance (Accuracy D 87.4%, AUC D 0.91) with good calibration (Brier D 0.07).
Cite This Study
Veeraraghavan et al. (2026) studied this question.