Was the Coronavirus Disease 2019 Pandemic Associated with an Increased Rate of Cracked Teeth?

Artificial intelligence in endodontics: Data preparation, clinical applications, ethical considerations, limitations, and future directions

Artificial intelligence (AI) is emerging as a transformative technology in healthcare, including endodontics. A gap in knowledge exists in understanding AI's applications and limitations among endodontic experts. This comprehensive review aims to (A) elaborate on technical and ethical aspects of using data to implement AI models in endodontics; (B) elaborate on evaluation metrics; (C) review the current applications of AI in endodontics; and (D) review the limitations and barriers to real-world implementation of AI in the field of endodontics and its future potentials/directions. The article shows that AI techniques have been applied in endodontics for critical tasks such as detection of radiolucent lesions, analysis of root canal morphology, prediction of treatment outcome and post-operative pain and more. Deep learning models like convolutional neural networks demonstrate high accuracy in these applications. However, challenges remain regarding model interpretability, generalizability, and adoption into clinical practice. When thoughtfully implemented, AI has great potential to aid with diagnostics, treatment planning, clinical interventions, and education in the field of endodontics. However, concerted efforts are still needed to address limitations and to facilitate integration into clinical workflows.

Incidence of Middle Mesial Canals in Mandibular Molars during Root Canal Treatment and Nonsurgical Retreatment

INTRODUCTION

Large-scale clinical studies on the incidence of middle mesial canals (MMCs) in nonsurgical root canal treatment (RCT) and retreatment of mandibular molars are lacking. The primary aim of this observational study was to determine the incidence of MMCs in mandibular first and second molars that received RCT or nonsurgical retreatment (NSRetx). The secondary aim was to determine factors associated with incidence of MMCs.

METHODS

Included were 3018 mandibular molars that received RCT (n = 1624) or NSRetx (n = 1394) by 3 endodontists in a private practice. Demographic and procedural data were collected. Bivariate and multivariable (Poisson regression model) analyses were performed.

RESULTS

Incidence of MMCs was 8.8% (n = 267). Although the bivariate analysis showed that NSRetx was significantly associated with incidence of MMCs, this association did not reach the threshold for statistical significance after controlling for all covariates (P = .07). Multivariable analysis on the entire cohort showed that incidence of MMCs was significantly associated with younger age (risk ratio [RR] = 1.62; 95% confidence interval [CI], 1.28-2.06), male gender (RR = 1.48; 95% CI, 1.18-1.85), preoperative cone-beam computed tomography (CBCT) (RR = 1.48; 95% CI, 1.17-1.89), and first molar (RR = 2.30; 95% CI:1.74-3.05). Subgroup multivariable analyses revealed that incidence of MMCs was associated with male gender only in the RCT group (RR = 2.26; 95% CI, 1.55-3.30) but not in the NSRetx group (RR = 1.11; 95% CI, 0.82, 1.50); and with preoperative CBCT only in the NSRetx group (RR = 1.78; 95% CI, 1.28, 2.50) but not in the RCT group (RR = 1.10; 95% CI, 0.71, 1.69). Associations with younger age and first molar remained unchanged.

CONCLUSIONS

Overall incidence of MMCs was 8.8%. Incidence of MMCs was significantly higher in younger patients and in mandibular first molars but was not associated with the type of treatment.

Artificial Intelligence for Detection of External Cervical Resorption Using Label-Efficient Self-Supervised Learning Method

INTRODUCTION

The aim of this study was to leverage label-efficient self-supervised learning (SSL) to train a model that can detect ECR and differentiate it from caries.

METHODS

Periapical (PA) radiographs of teeth with ECR defects were collected. Two board-certified endodontists reviewed PA radiographs and cone beam computed tomographic (CBCT) images independently to determine presence of ECR (ground truth). Radiographic data were divided into 3 regions of interest (ROIs): healthy teeth, teeth with ECR, and teeth with caries. Nine contrastive SSL models (SimCLR v2, MoCo v2, BYOL, DINO, NNCLR, SwAV, MSN, Barlow Twins, and SimSiam) were implemented in the assessment alongside 7 baseline deep learning models (ResNet-18, ResNet-50, VGG16, DenseNet, MobileNetV2, ResNeXt-50, and InceptionV3). A 10-fold cross-validation strategy and a hold-out test set were employed for model evaluation. Model performance was assessed via various metrics including classification accuracy, precision, recall, and F1-score.

RESULTS

Included were 190 PA radiographs, composed of 470 ROIs. Results from 10-fold cross-validation demonstrated that most SSL models outperformed the transfer learning baseline models, with DINO achieving the highest mean accuracy (85.64 ± 4.56), significantly outperforming 13 other models (P < .05). DINO reached the highest test set (ie, 3 ROIs) accuracy (84.09%) while MoCo v2 exhibited the highest recall and F1-score (77.37% and 82.93%, respectively).

CONCLUSIONS

This study showed that AI can assist clinicians in detecting ECR and differentiating it from caries. Additionally, it introduced the application of SSL in detecting ECR, emphasizing that SSL-based models can outperform transfer learning baselines and reduce reliance on large, labeled datasets.

Flare-ups After Nonsurgical Retreatments: Incidence, Associated Factors, and Prediction

INTRODUCTION

The aims of this study were to determine the incidence, associated factors, and predictability of flare-ups after nonsurgical retreatments (NSRetx).

METHODS

All patients (n = 3,666) who received NSRetx by 3 endodontists in 2 endodontic offices during a period of 6 years (2016-2022) were included. Demographic, diagnostic, and procedural data were collected. A flare-up was defined as moderate-severe pain with/without swelling that took place within 14 days of initiation of NSRetx and resulted in an unscheduled appointment. Bivariate analyses on the entire cohort and multivariable analyses on cases with complete dataset (n = 2,846) were performed to identify significant associations. A Random Forest algorithm was used to make a prediction model.

RESULTS

Incidence of flare-ups was 3.95% (n = 145). Increased risk of flare-ups was associated with diabetes (adjusted odds ratio [AOR] = 2.01; 95% confidence interval [CI], 1.01-3.97), mandibular teeth (AOR = 1.67; 95% CI, 1.11-2.52), moderate-severe preoperative pain on percussion (AOR = 2.13; 95% CI, 1.31-3.50), and pain on palpation (AOR = 1.63; 95% CI, 1.01-2.64). Lower risk of flare-up was associated with high blood pressure (AOR = 0.44; 95% CI, 0.21-0.82) (P < .05). The prediction model was not able to predict flare-ups with sufficient confidence (precision = 0.13).

CONCLUSIONS

Incidence of flare-ups following NSRetx was low (∼4%) and had a weak but significant association with the history of diabetes. Moderate-severe pain on percussion, pain on palpation (any intensity), and mandibular teeth had a significant association with flare-ups. The history of high blood pressure was associated with lower risk of flare-ups. Flare-ups were difficult to predict in this clinical setting.

The prevalence, characteristics, and risk factors of external cervical resorption: a retrospective practice-based study

OBJECTIVES

External cervical root resorption (ECR) is a poorly understood and aggressive form of resorption. The purpose of this study was to examine the prevalence, characteristics, and risk factors associated with the occurrence of ECR in patients seeking endodontic care from private practice settings.

MATERIALS AND METHODS

Records of 343 patients with 390 teeth diagnosed with ECR were identified from 3 private endodontic practices from 2008 to 2022. The patients' demographic information, systemic conditions, and dental history were recorded. The characteristics of the cases including Heithersay classification, pulpal and periapical status, and their management were documented. The association between case severity and potential predisposing factors was examined using chi-square analysis.

RESULTS

The overall prevalence of ECR among patients seeking endodontic care was low (< 1%). However, there was a greater than twofold increase in the pooled prevalence from 2016 to 2021 (0.99%) compared to the data from 2010 to 2015 (0.46%). The most commonly affected teeth were anterior teeth (48.7%). Class II (30.0%) and class III (45.4%) defects were the most often identified. Patients with a history of trauma or orthodontic treatment were significantly more likely to be diagnosed with severe cervical resorption (class III or IV) (p < 0.05).

CONCLUSIONS

There has been an increase in the prevalence of ECR in patients seeking endodontic care. A history of orthodontic treatment and traumatic dental mechanical injuries may predict the severity of resorption.

CLINICAL RELEVANCE

The upward trend in the occurrence of ECR warrants close monitoring of the patients at high risk of developing the condition to facilitate early detection and management.