Background: The rapid advancement of artificial intelligence (AI) in healthcare has opened new opportunities, yet the clinical validation of AI tools in dentistry remains limited. Objectives: This study aimed to assess the performance of ChatGPT in generating accurate and complete responses to academic dental questions across multiple specialties, comparing the capabilities of GPT-4 and GPT-3.5 models. Methodology: A panel of academic specialists from eight dental specialties collaboratively developed 48 clinical questions, classified by consensus as easy, medium, or hard, and as requiring either binary (yes/no) or descriptive responses. Each question was sequentially entered into both GPT-4 and GPT-3.5 models, with instructions to provide guideline-based answers. The AI-generated responses were independently evaluated by the specialists for accuracy (6-point Likert scale) and completeness (3-point Likert scale). Descriptive and inferential statistics were applied, including Mann–Whitney U and Kruskal–Wallis tests, with significance set at p < 0.05. Results: GPT-4 consistently outperformed GPT-3.5 in both evaluation domains. The median accuracy score was 6.0 for GPT-4 and 5.0 for GPT-3.5 (p = 0.02), while the median completeness score was 3.0 for GPT-4 and 2.0 for GPT-3.5 (p < 0.001). GPT-4 demonstrated significantly higher overall accuracy (5.29 ± 1.1) and completeness (2.44 ± 0.71) compared to GPT-3.5 (4.5 ± 1.7 and 1.69 ± 0.62, respectively; p = 0.024 and <0.001). When stratified by specialty, notable improvements with GPT-4 were observed in Periodontology, Endodontics, Implantology, and Oral Surgery, particularly in completeness scores. Conclusions: In academic dental settings, GPT-4 provided more accurate and complete responses than GPT-3.5. Despite both models showing potential, their clinical application should remain supervised by human experts.

To describe oral healthcare services administered during the lockdown in the Eastern Mediterranean region and to investigate the role of socio-professional characteristics of dental practitioners or their self-reported COVID-19 infection.

Objective: This study aimed to assess the effects of povidone-iodine, salt base water (Himalaya), and normal saline on soft tissue healing and pain alleviation as post-extraction mouthwashes in the dental clinic of Taibah Dental Hospital in Saudi Arabia. Methods: In the present study, the effects of various mouthwashes, including normal saline, Himalaya natural salt mouthwash, and diluted betadine solution was compared regarding the extraction socket healing and improved patient experience. The pain and edema were assessed using a visual analogue scale, and soft tissue healing was assessed using the Landry and Turnbull criteria. Results: On the first day, nearly all the study participants experienced the same level of discomfort, which then progressively subsided over five days. The wounds were examined for soft tissue healing on day three and seven following surgery and revealed no difference between the groups. Conclusion: Despite the fact that all mouthwash types produced equal beneficial effects, there was no statistically significant difference in the effect of using various types of mouthwash on the acceleration of soft tissue healing or the reduction of pain after uncomplicated exodontia.

Objectives: To estimate how accurately individual panoramic radiographic signs predict postoperative inferior alveolar nerve (IAN) injury after mandibular third molar surgery, treating postoperative neurosensory injury, intraoperative nerve exposure and CBCT-defined canal contact as three separate target conditions rather than one. Methods: MEDLINE, Embase, Scopus, the Cochrane Library and Google Scholar were searched to 24 June 2025. Risk of bias was assessed with QUADAS-2 and, for randomised trials, RoB 2. Sensitivity and specificity were pooled by sign using DerSimonian–Laird random-effects models and re-examined with a bivariate random-effects model. Results: Thirty-seven studies were included; ten contributed two × two data, nine against postoperative neurosensory injury and one against intraoperative exposure. Diversion of the canal discriminated best (specificity 0.95, 95% CI 0.90–0.98; diagnostic odds ratio 8.18, 95% CI 3.31–20.20) but was insensitive (0.27). Only darkening of the root and diversion of the canal withstood removal of any single study. Negative predictive values of 94.2–96.7% added just 0.2–2.5 percentage points beyond pre-test probability, whereas diversion of the canal raised estimated risk from about 5% to 25%. Heterogeneity was substantial (I² 91–98% for specificity), no contributing study was at low risk of bias in all four QUADAS-2 domains, and the reference standard was at high risk in seven of ten. Conclusions: Panoramic signs serve risk stratification and are informative when present rather than when absent. The pooled estimates are provisional and should not be transferred to individual practice without allowance for heterogeneity and bias.