Sarcouncil Journal of Medical Sciences

Abstract: Introduction: Artificial intelligence (AI) is a field of computer science that aims to simulate human intelligence through technological advancement. It has found numerous applications across various domains. ChatGPT and Gemini, two significant models developed by OpenAI and Google AI, are employed effectively in numerous domains. The objective of this study was to conduct a comparative analysis of the responses generated by ChatGPT and Gemini in response to questions pertaining to ear, nose, and throat diseases (ENT). Methods: In order to compare the success of artificial intelligence systems, multiple-choice questions were selected from the examinations used during endoscopy nursing assistant training. The answers provided by the artificial intelligence models Gemini and Chat GPT 4.0, which are subheadings of anatomy, neurology, and infection, were then compared. Results In the comparison made for Gemini, the mean infection score was found to be significantly higher than the mean scores for neurology and anatomy (F=7.66, p=0.002). Similarly, in the comparison made for Chat GPT, the mean anatomy score was observed to be significantly higher than the mean scores for neurology and infection (F=7.23, p=0.003). Conclusion: In the comparison conducted for Gemini, it was observed that the mean infection score was markedly higher than the mean scores for neurology and anatomy. In the comparison conducted for Chat GPT, it was noted that the mean anatomy score was significantly higher than the mean scores for neurology and infection