Answers are grounded in this paper and cite their sources.
ChatGPT (GPT-3.5 and GPT-4; OpenAI) produced accurate diagnoses from transcribed radiologic findings for a majority of cases; however, hallucinations and repeatability issues were present.
No takes yet. Share an insight, caveat, or question.
Sun et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: