Trialling a Large Language Model (ChatGPT) in General Practice With the Applied Knowledge Test: Observational Study Demonstrating Opportunities and Limitations in Primary Care

• Published in: JMIR medical education Vol. 9; p. e46599
• Main Authors: Thirunavukarasu, Arun James, Hassan, Refaat, Mahmood, Shathar, Sanghera, Rohan, Barzangi, Kara, El Mukashfi, Mohanned, Shah, Sachin
• Format: Journal Article
• Language: English
• Published: Canada JMIR Publications 21.04.2023
• Subjects: Accuracy; Chatbots; Deep learning; Design; Large language models; Medical research; Multimedia; Observational studies; Original Paper; Primary care; Statistical analysis; United Kingdom > UK; chatbot; deep learning; decision support techniques; natural language processing; ChatGPT; general practice; AI; primary care; family medicine; large language model; artificial intelligence

Large language models exhibiting human-level performance in specialized tasks are emerging; examples include Generative Pretrained Transformer 3.5, which underlies the processing of ChatGPT. Rigorous trials are required to understand the capabilities of emerging technology, so that innovation can be...