PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 25, 2026European Radiology Experimental2 citationsOpen Access

Can AI write reports like a radiologist? A blinded evaluation of large language model-generated lumbar spine MRI reports

View Full Paper
MZMoreno ZanardoIRCCS Policlinico San DonatoDADomenico AlbanoUniversity of MilanVMValentina MolinariUniversity of Milan

Key Points

  • This research evaluates the quality of lumbar spine MRI reports generated by AI compared to those by radiologists.
  • Blinded evaluation of reports generated by AI and radiologists
  • Comparison of clinical relevance, findings, and structure
  • Subjective scoring by clinicians
  • Radiologist-written reports scored higher in clinical relevance and structure
  • LLM-generated reports were clinically coherent and comparable in style
  • Clinicians sometimes misclassified AI reports as human-written

Abstract

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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Zanardo et al. (2026) studied this question.

synapsesocial.com/papers/699e9106f5123be5ed04e41bhttps://doi.org/10.1186/s41747-026-00682-6
Ask AI
Helpful
Bookmark
Share
View Full Paper