Answers are grounded in this paper and cite their sources.
A blinded evaluation finds AI-generated reports clinically coherent but less relevant than radiologist-written ones.
LLM-generated reports are clinically coherent and stylistically comparable to those written by expert radiologists. Radiologist-written reports scored significantly higher for clinical relevance, findings, and structure. LLM-generated reports were sometimes misclassified as human-written by clinicians.
No takes yet. Share an insight, caveat, or question.
Zanardo et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: