Performance of three artificial intelligence (AI)-based large language models in standardized testing; implications for AI-assisted dental education.

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). 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. 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). 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.

Sabri H ，Saleh MHA ，Hazrati P ，Merchant K ，Misch J ，Kumar PS ，Wang HL ，Barootchi S ... -  《-》

Using large language models (ChatGPT, Copilot, PaLM, Bard, and Gemini) in Gross Anatomy course: Comparative analysis.

The increasing application of generative artificial intelligence large language models (LLMs) in various fields, including medical education, raises questions about their accuracy. The primary aim of our study was to undertake a detailed comparative analysis of the proficiencies and accuracies of six different LLMs (ChatGPT-4, ChatGPT-3.5-turbo, ChatGPT-3.5, Copilot, PaLM, Bard, and Gemini) in responding to medical multiple-choice questions (MCQs), and in generating clinical scenarios and MCQs for upper limb topics in a Gross Anatomy course for medical students. Selected chatbots were tested, answering 50 USMLE-style MCQs. The questions were randomly selected from the Gross Anatomy course exam database for medical students and reviewed by three independent experts. The results of five successive attempts to answer each set of questions by the chatbots were evaluated in terms of accuracy, relevance, and comprehensiveness. The best result was provided by ChatGPT-4, which answered 60.5% ± 1.9% of questions accurately, then Copilot (42.0% ± 0.0%) and ChatGPT-3.5 (41.0% ± 5.3%), followed by ChatGPT-3.5-turbo (38.5% ± 5.7%). Google PaLM 2 (34.5% ± 4.4%) and Bard (33.5% ± 3.0%) gave the poorest results. The overall performance of GPT-4 was statistically superior (p < 0.05) to those of Copilot, GPT-3.5, GPT-Turbo, PaLM2, and Bard by 18.6%, 19.5%, 22%, 26%, and 27%, respectively. Each chatbot was then asked to generate a clinical scenario for each of the three randomly selected topics-anatomical snuffbox, supracondylar fracture of the humerus, and the cubital fossa-and three related anatomical MCQs with five options each, and to indicate the correct answers. Two independent experts analyzed and graded 216 records received (0-5 scale). The best results were recorded for ChatGPT-4, then for Gemini, ChatGPT-3.5, and ChatGPT-3.5-turbo, Copilot, followed by Google PaLM 2; Copilot had the lowest grade. Technological progress notwithstanding, LLMs have yet to mature sufficiently to take over the role of teacher or facilitator completely within a Gross Anatomy course; however, they can be valuable tools for medical educators.

Mavrych V ，Ganguly P ，Bolgova O 《-》

Performance of artificial intelligence on Turkish dental specialization exam: can ChatGPT-4.0 and gemini advanced achieve comparable results to humans?

AI-powered chatbots have spread to various fields including dental education and clinical assistance to treatment planning. The aim of this study is to assess and compare leading AI-powered chatbot performances in dental specialization exam (DUS) administered in Turkey and compare it with the best performer of that year. DUS questions for 2020 and 2021 were directed to ChatGPT-4.0 and Gemini Advanced individually. DUS questions were manually entered into AI-powered chatbot in their original form, in Turkish. The results obtained were compared with each other and the year's best performers. Candidates who score at least 45 points on this centralized exam are deemed to have passed and are eligible to select their preferred department and institution. The data was statistically analyzed using Pearson's chi-squared test (p < 0.05). ChatGPT-4.0 received 83.3% correct response rate on the 2020 exam, while Gemini Advanced received 65% correct response rate. On the 2021 exam, ChatGPT-4.0 received 80.5% correct response rate, whereas Gemini Advanced received 60.2% correct response rate. ChatGPT-4.0 outperformed Gemini Advanced in both exams (p < 0.05). AI-powered chatbots performed worse in overall score (for 2020: ChatGPT-4.0, 65,5 and Gemini Advanced, 50.1; for 2021: ChatGPT-4.0, 65,6 and Gemini Advanced, 48.6) when compared to overall scores of the best performer of that year (68.5 points for year 2020 and 72.3 points for year 2021). This poor performance also includes the basic sciences and clinical sciences sections (p < 0.001). Additionally, periodontology was the clinical specialty in which both AI-powered chatbots achieved the best results, the lowest performance was determined in the endodontics and orthodontics. AI-powered chatbots, namely ChatGPT-4.0 and Gemini Advanced, passed the DUS by exceeding the threshold score of 45. However, they still lagged behind the top performers of that year, particularly in basic sciences, clinical sciences, and overall score. Additionally, they exhibited lower performance in some clinical specialties such as endodontics and orthodontics.

Sismanoglu S ，Capan BS 《BMC Medical Education》

Evaluating Bard Gemini Pro and GPT-4 Vision Against Student Performance in Medical Visual Question Answering: Comparative Case Study.

The rapid development of large language models (LLMs) such as OpenAI's ChatGPT has significantly impacted medical research and education. These models have shown potential in fields ranging from radiological imaging interpretation to medical licensing examination assistance. Recently, LLMs have been enhanced with image recognition capabilities. This study aims to critically examine the effectiveness of these LLMs in medical diagnostics and training by assessing their accuracy and utility in answering image-based questions from medical licensing examinations. This study analyzed 1070 image-based multiple-choice questions from the AMBOSS learning platform, divided into 605 in English and 465 in German. Customized prompts in both languages directed the models to interpret medical images and provide the most likely diagnosis. Student performance data were obtained from AMBOSS, including metrics such as the "student passed mean" and "majority vote." Statistical analysis was conducted using Python (Python Software Foundation), with key libraries for data manipulation and visualization. GPT-4 1106 Vision Preview (OpenAI) outperformed Bard Gemini Pro (Google), correctly answering 56.9% (609/1070) of questions compared to Bard's 44.6% (477/1070), a statistically significant difference (χ2₁=32.1, P<.001). However, GPT-4 1106 left 16.1% (172/1070) of questions unanswered, significantly higher than Bard's 4.1% (44/1070; χ2₁=83.1, P<.001). When considering only answered questions, GPT-4 1106's accuracy increased to 67.8% (609/898), surpassing both Bard (477/1026, 46.5%; χ2₁=87.7, P<.001) and the student passed mean of 63% (674/1070, SE 1.48%; χ2₁=4.8, P=.03). Language-specific analysis revealed both models performed better in German than English, with GPT-4 1106 showing greater accuracy in German (282/465, 60.65% vs 327/605, 54.1%; χ2₁=4.4, P=.04) and Bard Gemini Pro exhibiting a similar trend (255/465, 54.8% vs 222/605, 36.7%; χ2₁=34.3, P<.001). The student majority vote achieved an overall accuracy of 94.5% (1011/1070), significantly outperforming both artificial intelligence models (GPT-4 1106: χ2₁=408.5, P<.001; Bard Gemini Pro: χ2₁=626.6, P<.001). Our study shows that GPT-4 1106 Vision Preview and Bard Gemini Pro have potential in medical visual question-answering tasks and to serve as a support for students. However, their performance varies depending on the language used, with a preference for German. They also have limitations in responding to non-English content. The accuracy rates, particularly when compared to student responses, highlight the potential of these models in medical education, yet the need for further optimization and understanding of their limitations in diverse linguistic contexts remains critical.

Roos J ，Martin R ，Kaczmarczyk R 《-》

Evaluating Large Language Models for the National Premedical Exam in India: Comparative Analysis of GPT-3.5, GPT-4, and Bard.

Large language models (LLMs) have revolutionized natural language processing with their ability to generate human-like text through extensive training on large data sets. These models, including Generative Pre-trained Transformers (GPT)-3.5 (OpenAI), GPT-4 (OpenAI), and Bard (Google LLC), find applications beyond natural language processing, attracting interest from academia and industry. Students are actively leveraging LLMs to enhance learning experiences and prepare for high-stakes exams, such as the National Eligibility cum Entrance Test (NEET) in India. This comparative analysis aims to evaluate the performance of GPT-3.5, GPT-4, and Bard in answering NEET-2023 questions. In this paper, we evaluated the performance of the 3 mainstream LLMs, namely GPT-3.5, GPT-4, and Google Bard, in answering questions related to the NEET-2023 exam. The questions of the NEET were provided to these artificial intelligence models, and the responses were recorded and compared against the correct answers from the official answer key. Consensus was used to evaluate the performance of all 3 models. It was evident that GPT-4 passed the entrance test with flying colors (300/700, 42.9%), showcasing exceptional performance. On the other hand, GPT-3.5 managed to meet the qualifying criteria, but with a substantially lower score (145/700, 20.7%). However, Bard (115/700, 16.4%) failed to meet the qualifying criteria and did not pass the test. GPT-4 demonstrated consistent superiority over Bard and GPT-3.5 in all 3 subjects. Specifically, GPT-4 achieved accuracy rates of 73% (29/40) in physics, 44% (16/36) in chemistry, and 51% (50/99) in biology. Conversely, GPT-3.5 attained an accuracy rate of 45% (18/40) in physics, 33% (13/26) in chemistry, and 34% (34/99) in biology. The accuracy consensus metric showed that the matching responses between GPT-4 and Bard, as well as GPT-4 and GPT-3.5, had higher incidences of being correct, at 0.56 and 0.57, respectively, compared to the matching responses between Bard and GPT-3.5, which stood at 0.42. When all 3 models were considered together, their matching responses reached the highest accuracy consensus of 0.59. The study's findings provide valuable insights into the performance of GPT-3.5, GPT-4, and Bard in answering NEET-2023 questions. GPT-4 emerged as the most accurate model, highlighting its potential for educational applications. Cross-checking responses across models may result in confusion as the compared models (as duos or a trio) tend to agree on only a little over half of the correct responses. Using GPT-4 as one of the compared models will result in higher accuracy consensus. The results underscore the suitability of LLMs for high-stakes exams and their positive impact on education. Additionally, the study establishes a benchmark for evaluating and enhancing LLMs' performance in educational tasks, promoting responsible and informed use of these models in diverse learning environments.

Farhat F ，Chaudhry BM ，Nadeem M ，Sohail SS ，Madsen DØ ... -  《-》