The results were disappointing: out of 100 random pediatric cases diagnosed by ChatGPT, accuracy was only 17%.
Experts emphasize that the diagnosis of childhood diseases is especially difficult because it requires taking into account all the patient’s symptoms as well as his age.
In recent years, more and more people are considering large-scale language models as a potential tool for medical diagnosis. The study recruited 100 random pediatric cases for diagnosis using ChatGPT.
To simplify the process, researchers used the same approach for each case, asking ChatGPT questions about “differential diagnosis” and “definitive diagnosis.”
Chatbot responses were evaluated by two pediatricians not involved in the study and classified as “correct,” “incorrect,” or “missing diagnoses.”
Only 11 of the 17 correct ChatGPT responses had clinical relevance to the correct diagnosis but still contained errors.
The researchers concluded that ChatGPT cannot be used clearly as a diagnostic tool at this time, but its accuracy could be improved with more targeted training.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
