Large language models (LLMs) such as OpenAI's ChatGPT, Google's Bard, and Microsoft's Bing Chat have shown potential as educational tools in the medical and dental fields. This study evaluated their effectiveness using questions from the Japanese national dental hygienist examination, focusing on textual information only. We analyzed 73 questions from the 32nd Japanese national dental hygienist examination, conducted in March 2023, using LLMs ChatGPT-3.5, GPT-4, Bard, and Bing Chat. Each question was categorized into one of nine domains. Standardized prompts were used for all LLMs, and Fisher's exact test was applied for statistical analysis. GPT-4 achieved the highest accuracy (75.3%), followed by Bing (68.5%), Bard (66.7%), and GPT-3.5 (63.0%). There were no statistically significant differences between the LLMs. The performance varied across different question categories, with all models excelling in the ‘Disease mechanism and promotion of recovery process' category (100% accuracy). GPT-4 generally outperformed other models, especially in multi-answer questions. GPT-4 demonstrated the highest overall accuracy among the LLMs tested, indicating its superior potential as an educational support tool in dental hygiene studies. The study highlights the varied performance of different LLMs across various question categories. While GPT-4 is currently the most effective, the capabilities of LLMs in educational settings are subject to continual change and improvement.

Rapid advancements in AI technology have led to significant interest in its application across various fields, including medicine and dentistry. This study aimed to assess the capabilities of ChatGPT-4V with image recognition in answering image-based questions from the Japanese National Dental Examination (JNDE) to explore its potential as an educational support tool for dental students. The dataset used questions from the JNDE, which was conducted in January 2023, with a focus on image-related queries. ChatGPT-4V was utilized, and standardized prompts, question texts, and images were input. Data and statistical analyses were conducted using Qlik Sense® and GraphPad Prism. The overall correct response rate of ChatGPT-4V for image-based JNDE questions was 35.0 %. The correct response rates were 57.1 % for compulsory questions, 43.6 % for general questions, and 28.6 % for clinical practical questions. In specialties like Dental Anesthesiology and Endodontics, ChatGPT-4V achieved correct response rates above 70 %, while response rates for Orthodontics and Oral Surgery were lower. A higher number of images in questions was correlated with lower accuracy, suggesting an impact of the number of images on correct and incorrect responses. While innovative, ChatGPT-4V’s image recognition feature exhibited limitations, especially in handling image-intensive and complex clinical practical questions, and is not yet fully suitable as an educational support tool for dental students at its current stage. Further technological refinement and re-evaluation with a broader dataset are recommended.

Soluble tumor necrosis factor receptors 1 and 2 (sTNF-R1 and sTNF-R2) are reported to protect against excessive TNF-α, a primary mediator of systemic responses to infection. This study aimed to investigate the levels of TNF-α, sTNF-R1, and sTNF-R2 in saliva and to verify whether their dynamics are associated with periodontal health. The study population comprised 28 adult patients. Probing pocket depth, clinical attachment level, and bleeding on probing were assessed, and periodontal inflamed surface area (PISA) was calculated. Stimulated saliva was collected before the oral examinations. The levels of TNF-α, sTNF-R1, sTNF-R2, and total protein (TP) in saliva samples were determined. There were significant positive correlations between TNF-α, sTNF-R1, and sTNF-R2 to TP (/TP) in stimulated saliva. Moreover, there were significant positive correlations between PISA and sTNF-R2/TP. Stepwise multiple regression analysis revealed that PISA was significantly associated with sTNF-R2/TP in saliva; however, TNF-α/TP was not significantly associated with PISA. In conclusion, this study demonstrates that significant relationships exist between the salivary levels of TNF-α and sTNF-R1, and that salivary sTNF-R2 is associated with the expansion of inflamed periodontal tissue.

OpenAI's GPT-4V and Google's Gemini Pro, being Large Language Models (LLMs) equipped with image recognition capabilities, have the potential to be utilized in future medical diagnosis and treatment, ands serve as valuable educational support tools for students. This study compared and evaluated the image recognition capabilities of GPT-4V and Gemini Pro using questions from the Japanese National Dental Examination (JNDE) to investigate their potential as educational support tools. We analyzed 160 questions from the 116th JNDE, administered in March 2023, using ChatGPT-4V, and Gemini Pro, which have image recognition functions. Standardized prompts were used for all LLMs, and statistical analysis was conducted using Fisher's exact test and the Mann–Whitney U test. For the 160 JNDE questions, the accuracy rates of GPT-4V and Gemini Pro were 35.0% and 28.1%, respectively, with GPT-4V being the highest, although not statistically significant. Across dental specialties, the accuracy rates of the GPT-4V were generally higher than those of the Gemini Pro, with some areas showing equal accuracy. Accuracy rates tended to decrease with an increased number of images within a question, suggesting that the number of images influenced the correctness of the responses. The overall superior performance of GPT-4V compared to Gemini Pro may be attributed to the continuous updates in OpenAI's model. This research demonstrates the potential of LLMs as educational support tools in dentistry, while also highlighting areas that require further technological development.

With advancements in artificial intelligence (AI), its role in education and examinations is expanding. This study aimed to evaluate the accuracy and response capability of ChatGPT-4o in solving questions from the Japanese National Dental Technician Examination (JNDTE). By analysing the AI's answers to a variety of questions, including both text-based items and those containing visual information across multiple domains, we examined the practicality of using AI as a supportive tool for learning and assessment in dental education. A total of 400 JNDTE questions (2018-2022) were analysed using ChatGPT-4o. Standardized prompts were used, and statistical analysis was conducted using Fisher's exact test. The AI demonstrated high accuracy in basic knowledge-based questions but lower accuracy in specialized topics requiring technical skills. Notably, accuracy decreased when visual elements (figures, tables, and photographs) were present. The highest accuracy was observed in 'Dental materials, laboratory equipment, and processing technology' (84.1%), while the lowest was in 'Orthodontic technology' (46.2%) and 'Pediatric dental technology' (50.0%). The AI particularly struggled with interpreting radiographic images and procedural workflows. ChatGPT-4o demonstrated reasonable proficiency with JNDTE-related knowledge, suggesting its potential application as a supplementary tool in dental education. However, its limitations in processing visual and technical content highlight the need for advancements in AI-driven image recognition and simulation-based learning. The findings of this study highlight the potential application of AI models like ChatGPT-4o as a supplementary tool in dental technician education and examination preparation. Enhancing AI-driven image recognition and simulation-based learning could improve its effectiveness in dental education and clinical training, ultimately contributing to better learning outcomes and skill development for future dental technicians.

Large language models (LLMs) are increasingly used in professional examinations, but their relative performance on dental board-style questions remains unclear. This study compared two reasoning-optimized models, GPT-o3 and GPT-5T, with a general-purpose multimodal model, GPT-4o, using 399 Japanese dental board-style multiple-choice questions from 2018 to 2022. All questions were presented in Japanese, and items originally accompanied by charts, photographs, or other figures were analyzed separately from items without visual materials. Accuracy and item-level agreement were assessed using pairwise McNemar tests, stratified analyses according to the original presence of visual materials, the Breslow–Day test for homogeneity of odds ratios, and two-proportion z-tests. GPT-5T achieved the highest overall accuracy (294/399, 73.7%), followed by GPT-o3 (257/399, 64.4%) and GPT-4o (255/399, 63.9%). Pairwise McNemar tests showed that GPT-5T outperformed both GPT-4o (Holm-adjusted p = 0.00098) and GPT-o3 (Holm-adjusted p = 0.00072), whereas GPT-o3 and GPT-4o did not differ significantly (Holm-adjusted p = 0.920). Accuracy was lower for questions originally containing visual materials than for questions without such materials across all three models (GPT-4o: 49.7% vs. 72.2%; GPT-o3: 55.1% vs. 69.8%; GPT-5T: 59.9% vs. 81.8%). The advantage of GPT-5T was more evident in questions without visual materials, and heterogeneity across question formats was observed for GPT-5T versus GPT-o3. GPT-5T showed the strongest performance in this dataset. Questions originally containing visual materials were associated with lower accuracy across all models. Because the comparison was based on distinct item groups rather than experimentally manipulated visual conditions, this result should be interpreted as a difference across question formats and may also reflect differences in item composition and difficulty between the two groups.