AUTHOR=Karobari Mohmed Isaqali , Veeraraghavan Vishnu Priya , Nagarathna P. J. , Varma Sudhir Rama , Kodangattil Narayanan Jayaraj , Patil Santosh R. 

TITLE=Predictive analysis of root canal morphology in relation to root canal treatment failures: a retrospective study

JOURNAL=Frontiers in Dental Medicine

VOLUME=Volume 6 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/dental-medicine/articles/10.3389/fdmed.2025.1540038

DOI=10.3389/fdmed.2025.1540038

ISSN=2673-4915

ABSTRACT=BackgroundFailure of root canal treatment (RCT) significantly affects patient outcomes and dental practice. Understanding the association between root canal morphology and RCT outcomes can help predict treatment success. This study aimed to analyze the predictive role of root canal morphology in RCT failure.MethodsThis retrospective study included 224 patients who underwent RCT. Demographic data, tooth type, and root canal morphology were also recorded. Univariate and multivariate logistic regression analyses were performed to identify predictors of RCT failure. Additionally, machine learning algorithms were employed to develop a predictive model that was evaluated using receiver operating characteristic (ROC) curves.ResultsOf the 224 RCTs, 112 (50%) were classified as successful and 112 (50%) as failure. Severe canal curvature (p < 0.001) and presence of accessory canals (p = 0.002) were significant predictors of failure. The final predictive model demonstrated an area under the ROC curve (AUC) of 0.83, indicating good accuracy in distinguishing between successful and failed RCTs.ConclusionThese findings underscore the importance of root canal morphology in predicting RCT outcomes. Machine learning approaches can enhance clinical decision making, enabling better treatment planning for patients at a higher risk of RCT failure.