US researchers concluded in a study that ChatGPT, a language model developed using artificial intelligence (AI), is 72% accurate in making general clinical decisions. The report was published in a reputable journal Journal of Medical Internet Research.
The study indicated that the popular chat program obtained “good results in both primary and emergency care and in various specializations.” It seems ChatGPT “conducts a comprehensive assessment of decision support from the outset of working with the patient and throughout the entire care scenario“From differential diagnosis to testing, diagnosis and treatment,” said Mark Sochi, one of the paper’s authors.
Program accuracy was measured using a system that records chatbot responses. And the researchers found it ChatGPT provides an accuracy of 60.3% in identifying a differential diagnosis based solely on HPI (current disease history), PE (physical examination) and ROS (revision of systems) on the other hand, 76.9% accuracy in final diagnosis with additional information managementsuch as related diagnostic tests.
from here, It was concluded that ChatGPT had an average performance of 71.8% across all question typesIt thus positions itself as a potential ally of health professionals in the context of clinical diagnosis.
“There are no real benchmarks, but we estimate that ChatGPT performance is at the level of someone who has just graduated from medical school, such as an intern or resident.stated the study authors.
More Stories
“Those who go to museums but do not see an oak tree in the countryside should blush.”
Michoacana Science and Engineering Fair 2024, When the Call Ends – El Sol de Zamora
Dr. Miguel Kiwi, winner of the National Science Award, gives his opinion on nanoscience in Chile