A prompt-based approach was highly accurate in defining clinical trial outcomes and identifying outcome changes in ClinicalTrials.gov. This approach could be expanded to identify changes between registrations and manuscripts. Although it did not achieve perfect accuracy, our prompt-based approach could help editors and peer reviewers detect likely discrepancies that warrant further review.
#ChatGPT was accurate in identifying changes in RCT outcomes on ClinicalTrials.gov, and completed the entire process (ie, matching, defining, comparing) in ~2 min per trial vs 27 min for humans
@ischoolui.bsky.social @colbyvorland.bsky.socia
#clinepi #metaresearch
peerreviewcongress.o...
3
2
0
0
