Overtreatment in Restorative Dentistry: Decision Making by Last-Year Dental Students

Knowledge and attitudes toward evidence-based cariology and restorative dentistry among Egyptian dental practitioners: a cross-sectional survey

BACKGROUND

This is the first study to assess Egyptian dental practitioners' knowledge about conservative caries management approaches and investigate whether this knowledge transfers into clinical practice and the barriers to translating research into evidence-based practice.

METHODS

A sample of dental practitioners was surveyed using an online questionnaire. Convenience and snowball sampling were used to collect data from February to June 2022. We included graduated dentists from Egyptian universities who practiced in Egypt. Data were analyzed with descriptive statistics, and the associations between variables were checked using Kruskal Wallis and Chi-Square tests.

RESULTS

This study included 396 participants from throughout Egypt. There were significant correlations between specialty and participants' knowledge and behaviors toward evidence-based caries management (p = 0.002) and between specialization and tools used to detect carious lesions (p < 0.001). Most participants (59.1%) used G.V Black's classification, and (80.8%) removed caries based on the feature of dentin hardness and color, whereas (67%) removed caries until hard dentine remained. The participants' primary hurdle to staying up-to-date was their belief that the newly gained information would not be clinically applicable due to a lack of equipment or working in low-economic areas. Patient-related barriers were the major obstacles for participants in implementing evidence-based practice.

CONCLUSION

Egyptian dentists did not fully embrace minimal invasive approaches for caries management, and practitioners' experiences continue to shape decision-making. It emphasizes the imperative to practically educate dentists using effective knowledge translation dissemination to promote evidence adoption in daily practice and advocate value-based dental care to address the economic crisis's impact on Egypt's healthcare.

Artificial intelligence-based diagnostics of molar-incisor-hypomineralization (MIH) on intraoral photographs

OBJECTIVE

The aim of this study was to develop and validate a deep learning-based convolutional neural network (CNN) for the automated detection and categorization of teeth affected by molar-incisor-hypomineralization (MIH) on intraoral photographs.

MATERIALS AND METHODS

The data set consisted of 3241 intraoral images (767 teeth with no MIH/no intervention, 76 with no MIH/atypical restoration, 742 with no MIH/sealant, 815 with demarcated opacity/no intervention, 158 with demarcated opacity/atypical restoration, 181 with demarcated opacity/sealant, 290 with enamel breakdown/no intervention, 169 with enamel breakdown/atypical restoration, and 43 with enamel breakdown/sealant). These images were divided into a training (N = 2596) and a test sample (N = 649). All images were evaluated by an expert group, and each diagnosis served as a reference standard for cyclic training and evaluation of the CNN (ResNeXt-101-32 × 8d). Statistical analysis included the calculation of contingency tables, areas under the receiver operating characteristic curve (AUCs) and saliency maps.

RESULTS

The developed CNN was able to categorize teeth with MIH correctly with an overall diagnostic accuracy of 95.2%. The overall SE and SP amounted to 78.6% and 97.3%, respectively, which indicate that the CNN performed better in healthy teeth compared to those with MIH. The AUC values ranging from 0.873 (enamel breakdown/sealant) to 0.994 (atypical restoration/no MIH).

CONCLUSION

It was possible to categorize the majority of clinical photographs automatically by using a trained deep learning-based CNN with an acceptably high diagnostic accuracy.

CLINICAL RELEVANCE

Artificial intelligence-based dental diagnostics may support dental diagnostics in the future regardless of the need to improve accuracy.