RESUMO
INTRODUCTION: The emerging rise in novel computer technologies and automated data analytics has the potential to change the course of dental education. In line with our long-term goal of harnessing the power of AI to augment didactic teaching, the objective of this study was to quantify and compare the accuracy of responses provided by ChatGPT (GPT-4 and GPT-3.5) and Google Gemini, the three primary large language models (LLMs), to human graduate students (control group) to the annual in-service examination questions posed by the American Academy of Periodontology (AAP). METHODS: Under a comparative cross-sectional study design, a corpus of 1312 questions from the annual in-service examination of AAP administered between 2020 and 2023 were presented to the LLMs. Their responses were analyzed using chi-square tests, and the performance was juxtaposed to the scores of periodontal residents from corresponding years, as the human control group. Additionally, two sub-analyses were performed: one on the performance of the LLMs on each section of the exam; and in answering the most difficult questions. RESULTS: ChatGPT-4 (total average: 79.57%) outperformed all human control groups as well as GPT-3.5 and Google Gemini in all exam years (p < .001). This chatbot showed an accuracy range between 78.80% and 80.98% across the various exam years. Gemini consistently recorded superior performance with scores of 70.65% (p = .01), 73.29% (p = .02), 75.73% (p < .01), and 72.18% (p = .0008) for the exams from 2020 to 2023 compared to ChatGPT-3.5, which achieved 62.5%, 68.24%, 69.83%, and 59.27% respectively. Google Gemini (72.86%) surpassed the average scores achieved by first- (63.48% ± 31.67) and second-year residents (66.25% ± 31.61) when all exam years combined. However, it could not surpass that of third-year residents (69.06% ± 30.45). CONCLUSIONS: Within the confines of this analysis, ChatGPT-4 exhibited a robust capability in answering AAP in-service exam questions in terms of accuracy and reliability while Gemini and ChatGPT-3.5 showed a weaker performance. These findings underscore the potential of deploying LLMs as an educational tool in periodontics and oral implantology domains. However, the current limitations of these models such as inability to effectively process image-based inquiries, the propensity for generating inconsistent responses to the same prompts, and achieving high (80% by GPT-4) but not absolute accuracy rates should be considered. An objective comparison of their capability versus their capacity is required to further develop this field of study.
RESUMO
INTRODUCTION: This in vitro study aimed to evaluate the ability of air-powder abrasion to decontaminate dental implants. MATERIALS AND METHODS: Twenty-six implants were inoculated with a Streptococcus sanguinis biofilm media in a novel periimplantitis defect model. Six implants served as controls, and 20 implants were disinfected with either the Cavitron JET Plus or the AIR-FLOW PERIO air-powder abrasion units. Residual bacteria were cultured, and colony forming units (CFUs) were totaled at 24 hours. RESULTS: As expected, negative control implant cultures showed no evidence of viable bacteria. Bacterial growth was observed on all positive control cultures, whereas only 15% of the experimental cultures displayed evidence of viable bacteria. The average CFU per streak for the positive control was 104 compared with a maximum of 10 and 4 CFUs for the Cavitron JET Plus and AIR-FLOW PERIO, respectively. There was a 99.9% reduction in bacteria for both air-powder abrasion instruments. CONCLUSION: Air-powder abrasion is an effective technique for the decontamination of dental implants, and the Cavitron JET Plus and AIR-FLOW PERIO are equally successful at eliminating viable bacteria from implant surfaces.