A recent study conducted by Dutch researchers found that an AI bot (ChatGPT) may be just as effective at diagnosing patients in emergency care compared to real doctors.
ChatGPT, developed by OpenAI, uses advanced language models and has previously demonstrated success in passing medical exams and displaying a better bedside manner than human doctors.
In the study, researchers analyzed the performance of the bot in an emergency department. They anonymized details of 30 patients treated at Jeroen Bosch Hospital's emergency department in 2022.
They inputted physicians' notes on patients' signs, symptoms and physical examinations into two versions of ChatGPT. The AI bot was asked to generate a list of possible diagnoses for each patient, which were compared to the doctors' lists.
The results showed an overlap of around 60% between the shortlists generated by ChatGPT and doctors.
In 87% of cases, doctors had the correct diagnosis within their top five compared to 97% for ChatGPT version 3.5 and 87% for version 4.0. (Pressrun 09/13/23) AI bot outperforms doctor in diagnosing patients in emergency room (pressrundown.com)
No comments:
Post a Comment