GPT-4 performing with superior scores on medical oncology examination questions
1. The large language model, ChatGPT-4, answered 85.0% of examination-style multiple-choice questions on medical oncology correctly, a performance superior to ...
Tag: openai
Large language models may be effective in assessing clinical acuity of adult patients in the emergency department
1. The large language model, GPT-4, was capable of assessing clinical acuity when presented with pairs of patient histories obtained ...
Generative artificial intelligence comparable in terms of clinical accuracy and report quality for chest radiographs
1. Generative artificial intelligence (AI) and radiologist reports received comparable ratings of clinical accuracy and report quality, that were significantly ...
