The potential of ChatGPT in medicine: an example analysis of nephrology specialty exams in Poland.

Jan Nicikowski Mikołaj Szczepański Miłosz Miedziaszczyk Bartosz Kudliński

Published in: Clinical kidney journal (2024)

ChatGPT-3.5 was not spectacularly successful in nephrology exams. The ChatGPT-4.0 algorithm was able to pass most of the analysed nephrology specialty exams. New generations of ChatGPT achieve similar results to humans. The best results of humans are better than those of ChatGPT-4.0.

Keyphrases

machine learning
deep learning
human health