Are ChatGPT's knowledge and interpretation ability comparable to those of medical students in Korea for taking a parasitology examination?: a descriptive study

This study aimed to compare the knowledge and interpretation ability of ChatGPT, a language model of artificial general intelligence, with those of medical students in Korea by administering a parasitology examination to both ChatGPT and medical students. The examination consisted of 79 items and was administered to ChatGPT on January 1, 2023. The examination results were analyzed in terms of ChatGPT's overall performance score, its correct answer rate by the items' knowledge level, and the acceptability of its explanations of the items. ChatGPT's performance was lower than that of the medical students, and ChatGPT's correct answer rate was not related to the items' knowl-edg level. However, ther was relationship beween acceptable explanations and crrect answers. In conclusion, ChatGPT's knowledge and Are ChatGPT's knowle dge a nd interpretation ability comparable to those of medical students in Koeainterpretationfor takingabilitya for thiparas itologyparasitology examination?:examinationa wre notdescriptiveyet studycomparable to those of medical students in Korea.

Automated summary

This study aimed to compare the knowledge and interpretation ability of ChatGPT, an artificial general intelligence language model, with those of medical students in Korea by administering a parasitology examination. The results showed that ChatGPT's performance was lower than that of the medical students, and there was no correlation between its correct answer rate and the knowledge level of the items. However, there was a relationship between acceptable explanations and correct answers. Overall, ChatGPT's knowledge and interpretation ability were not comparable to those of medical students in Korea.