Although ChatGPT-4.0 shows potential in supporting blood cell classification activities, its performance remains inadequate for adoption as a standalone diagnostic tool or as replacement for the current generation of hematological digital imaging software.
Evaluating the accuracy of ChatGPT in classifying normal and abnormal blood cell morphology
Negrini, Davide;Pighi, Laura;Tosi, Marco;Lippi, Giuseppe
2025-01-01
Abstract
Although ChatGPT-4.0 shows potential in supporting blood cell classification activities, its performance remains inadequate for adoption as a standalone diagnostic tool or as replacement for the current generation of hematological digital imaging software.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
