Table 3:

Time Spent Per Case

Group	Time spent per case (seconds)
	Physicians + GPT-4	Physicians + Conventional Resources	Difference (95% CI)	P-value
All Participants	519 (371, 668)	565 (456, 788)	−81.9 (−195.1, 31.3)	0.15
Level of Training
Attending	533 (389, 672)	563 (435, 778)	−73 (−204 to 58)	0.26
Resident	478 (356, 654)	565 (458, 800)	−76 (−284, 131)	0.45
ChatGPT Experience
Less than monthly	556 (415, 742)	572 (474, 778)	−46 (−219, 127)	0.59
More than monthly	462 (305, 627)	556 (427, 810)	−140 (−294, 13)	0.07

Continuous variables are expressed as median (interquartile range). Differences between groups are reported from the multilevel analysis accounting for clustering of cases by participant.