GPT-4:

Eunbeen Jo1, Sanghoun Song2, Jong-Ho Kim3,4

  • 1Department of Medical Informatics, Korea University College of Medicine, Seoul, Republic of Korea.

PubMed
概括

像GPT-4这样的大型语言模型在心脏病咨询中显示出与人类专家相比的医疗准确性. 然而,人类专家在细微的临床判断和特定的查询类型中表现出色,表明AI改进的领域.