Evaluating ChatGPT-3.5 in allergology: performance in the Polish Specialist Examination

Abstract

Introduction:The development of Artificial Intelligence (AI) and attempts to use it in medicine are increasingly becoming the subject of more scientific research. Aim: The aim of this article is to present the effectiveness of the advanced language model, ChatGPT-3.5 in the context of the pass rate of the Polish National Specialist Examination (PES) in allergology. Additionally, it seeks to comprehend the potential applications of artificial intelligence in the field of medicine, particularly within allergology. Material and methods:The study used the latest available PES exam prepared by the Medical Research Centre in Lodz. 118 questions were asked using the openai.com platform, which allows free access to the ChatGPT-3.5 model. All questions were classified according to Bloom's taxonomy to assess their complexity and difficulty, with additional three categorisations. Each question was asked five times. Results: ChatGPT-3.5 did not pass the allergology PES, achieving a score of 52.54%. It was observed that the model performed better in answering memory questions (60%) compared to those requiring comprehension and critical thinking, where the results were slightly lower (45%). Moreover, within the categories of 'treatment' , 'immune system' and 'symptoms' , the model exceeded the passing threshold. Questions to which ChatGPT provided the correct answer significantly exhibited higher difficulty compared to those to which it provided an incorrect response. Conclusions:The results indicate that ChatGPT's pass rate in the allergology PES is considerably lower than that of resident doctors specializing in this field. The potential applications of AI in medicine require further research to effectively support clinical practice among physicians.