Artificial intelligence (AI) models have been increasingly integrated into dental education for assessment and learning support. However, their accuracy and reliability in assessment of dental knowledge requires further evaluation. This study aimed to assess and compare the accuracy and response consistency of five AI language models– ChatGPT-4, Grok XI, Gemini, Qwen 2.5 and DeepSeek-V3– using standardised dental multiple-choice questions (MCQs). A set of 150 MCQs from two textbooks was used. Each AI model was tested twice, 10 days apart, using identical questions. Accuracy was determined by comparing responses to reference answers, and consistency was measured using Cohen’s kappa and McNemar’s test. The inter-model agreement was also analysed. ChatGPT-4 showed the highest accuracy (91.3%) in both assessments, followed by Grok XI (90.7–92.7%) and Qwen 2.5 (89.3%). Gemini and DeepSeek performed slightly lower (86.7–88.7%). ChatGPT, Grok XI and Gemini demonstrated strong consistency, whereas Qwen 2.5 and DeepSeek exhibited more variation between test administrations. No significant differences were found in inter-model agreement (p > 0.05). All five AI models showed high levels of accuracy in answering dental MCQs, and three of the models, ChatGPT-4, Grok XI and Gemini had strong test-retest reliability. These AI models show promise as educational tools, though continued evaluation and refinement are needed for broader clinical or academic applications.

Introduction: Artificial intelligence (AI), particularly large language models (LLMs), is transforming healthcare education and clinical decision-making. While models like ChatGPT and Claude have demonstrated utility in medical contexts, their performance in dental diagnostics remains underexplored; additionally, the potential of emerging platforms, like Manus, is yet to be evaluated. Objective: To compare the diagnostic accuracy and consistency of the ChatGPT, Claude, and Manus—using authentic, case-based dental scenarios. Methods: A set of 117 multiple-choice questions based on validated clinical dental vignettes spanning various specialities was administered to each model under standardised conditions at two separate time points. Responses were scored against expert-validated answer keys. Inter-rater reliability was assessed using Cohen's kappa, and statistical comparisons were made using the chi-square, McNemar, and t-tests. Results: Claude and Manus consistently outperformed ChatGPT across both testing phases. In the second round, Claude and Manus achieved a diagnostic accuracy of 92.3%, compared to ChatGPT's 76.9%. Claude and Manus also demonstrated higher intra-model consistency (Cohen's kappa = 0.714 and 0.782, respectively) than ChatGPT (kappa = 0.560). Although the numerical trends favoured Claude and Manus, pairwise differences in accuracy did not reach statistical significance. Conclusion: Claude and Manus demonstrated numerically higher diagnostic performance and greater response stability compared with ChatGPT; however, these differences did not reach statistical significance and should therefore be interpreted cautiously. This variability across models highlights the need for larger-scale evaluations. These findings underscore the importance of considering both accuracy and consistency when selecting AI tools for integration into dental practice and curricula.

The maxillary sinus exhibits significant anatomical variation, influenced by sex, age and laterality. Understanding these morphological characteristics is essential for effective diagnostic and surgical planning in dentistry and maxillofacial procedures. Comprehensive Comprehensive cone-beam computed tomography (CBCT)-based evaluations in Saudi populations remain limited. This study aimed to assess maxillary sinus anatomical features and dimensions using CBCT imaging in a Saudi subpopulation, examining associations with sex, side and age. A retrospective, cross-sectional analysis was conducted on 1018 CBCT scans (2036 sinuses) of adults aged ≥ 18 years, obtained between January 2024 and January 2025 at a leading dental centre in Ha’il, Saudi Arabia. Sinus parameters, comprising width, length, area, perimeter, septa, fluid, and mucosal thickening, were measured. Statistical tests evaluated associations with sex, age and laterality. Sinus fluid was the most frequent abnormality and was significantly more common in male and older adults (p < 0.001). Sinus dimensions (width, length, area, perimeter) were significantly larger in male than in female (p < 0.001) and decreased progressively with age, particularly after the fifth decade. Bilateral dimensions were strongly correlated (ρ > 0.55, p < 0.001), confirming anatomical symmetry. Maxillary sinus morphology varied significantly with sex and age in this Saudi population. Male and younger individuals exhibited larger sinus dimensions, and sinus pathology was more common in older adults. These findings underscore the value of CBCT imaging for individualised treatment planning and highlight the need for population-specific anatomical references in clinical and forensic contexts. These findings have implications for surgical planning and sex estimation in forensic cases.

Needle stick injuries (NSIs) pose a significant occupational hazard to healthcare professionals, including dental students. Despite the availability of guidelines and preventive strategies, knowledge, training, and compliance remain inadequate among dental students. Therefore, this study aimed to evaluate the Prospective gain of an educational pack in reducing NSIs and improving knowledge of attitudes towards, and compliance with NSI prevention and management guidelines among dental students. A prospective audit design was employed over four weeks, involving fourth-, fifth-, and sixth-year dental students. The study consisted of three phases: pre-assessment, educational intervention, and post-assessment. Baseline knowledge, attitudes, and practices were evaluated using a structured questionnaire. Self-reported compliance with safe sharps handling practices has been designated as the primary outcome. The educational pack, comprising presentations, comparative data, interactive scenarios, and guidelines, was delivered during the intervention phase. Post-intervention assessments used the same questionnaire to measure changes in outcomes. Data were analysed using SPSS, and statistical significance was set at p ≤ 0.05. Post-intervention, the incidence of NSIs significantly decreased, with self-reported cases reducing from 17.2% to 4.3%. Knowledge scores improved markedly, with the percentage of correct answers to key questions rising from 34.5% to 93.1% among sixth-year students (p = 0.032). Gender-based analysis revealed statistically significant improvements in scores for both male and female students, with female students achieving higher post-assessment scores for key questions (e.g. 93.8% vs 75.6%, p = 0.014). Students with lower GPAs demonstrated the greatest improvement, with scores increasing from 14.3% to 100% in some areas (p = 0.022). The findings underscore the change following the intervention of structured infection control training in reducing NSIs and improving adherence to guidelines. Integrating such programs into dental curricula is vital for fostering a culture of safety and compliance in clinical practice. This study aligns with Saudi Vision 2030, emphasising the importance of enhancing healthcare quality and occupational safety through targeted educational interventions.

Artificial intelligence (AI) integration in diagnostic medicine has advanced accuracy and efficiency, particularly in pathology. This study assessed the diagnostic performance of three large language models (LLMs)—ChatGPT (GPT-4-turbo), Grok (xAI), and MANUS—in interpreting histopathology slides of oral lesions. A comparative diagnostic study was conducted using 100 high-resolution slides representing diverse oral pathologies. Images were sourced from a validated textbook and reviewed by two board-certified oral pathologists who provided consensus diagnoses. Each slide was analysed twice by the three AI models using standardized prompts. Diagnostic accuracy, intra-model consistency, inter-model concordance, and agreement with human experts were evaluated using descriptive statistics, Cohen’s kappa, McNemar’s test, and chi-square analysis. All AI models demonstrated high diagnostic accuracy. In the second round, Grok achieved the highest accuracy (97%), followed by MANUS (96%) and ChatGPT (94%). ChatGPT showed the highest intra-model consistency (κ = 0.918), while MANUS and Grok displayed substantial agreement (κ = 0.790 and 0.740). Expert pathologists achieved 98% accuracy. Comparisons between AI models and human diagnoses showed moderate to substantial agreement, with MANUS most aligned with experts. Most misclassifications occurred in histologically ambiguous cases, with no significant differences between AI models. Multimodal LLMs demonstrated strong diagnostic capabilities, consistency, and alignment with expert reasoning in oral histopathology interpretation. Grok was the most accurate, ChatGPT the most consistent, and MANUS the most expert-aligned. These findings support AI integration into digital pathology for diagnostic support, education, and quality assurance, with further validation in clinical datasets recommended.

Orthognathic surgery is essential for addressing severe dentofacial deformities, improving both function and aesthetics. In Ha'il, Saudi Arabia, the decision-making process for this surgery is influenced by a range of medical, psychological, and social factors. This study examined the key factors influencing patients' decisions to undergo orthognathic surgery in Ha'il. A cross-sectional study was conducted from 2019-2023, involving 27 patients in Ha'il who either required or had undergone orthognathic surgery. Data were collected through structured interviews covering demographics, medical history, consultation experiences, and decision influences. Statistical analyses, including chi-square tests and logistic regression models, were performed with a significance level of p < 0.05. Among the participants, 59.3% were male, and Class III malocclusion was the most prevalent deformity (59.3%). Aesthetic concerns were the primary motivator for 48.1% of patients, while functional concerns drove 18.5%. Only 44.4% of participants reported receiving comprehensive information about the surgery's risks and benefits. Healthcare professionals were the main decision influencers, cited by 51.9% of participants, while social stigma impacted 25.9%. Cultural beliefs had minimal influence on the decision-making process. The decision to undergo orthognathic surgery in Ha'il is predominantly driven by aesthetic concerns, with healthcare professionals playing a crucial role in patient education. Cultural beliefs have little influence, though social stigma is a notable factor. Enhancing patient education could improve decision-making, aligning with Saudi Vision 2030's healthcare goals.