Key result
ChatGPT responses to hand surgery queries had significantly inferior readability compared to Google (P<0.0001), with no significant difference in accuracy between sources.
Why the study?
ChatGPT has the potential to increase accessibility of health information, but the usability of online medical information for hand surgery topics and the influence of medical consensus needed assessment.
Does ChatGPT provide more usable medical information compared to Google for hand surgery topics?
Population
Three phrases posed 20 times each regarding hand surgery topics
Comparison
Google vs ChatGPT-3.5 vs ChatGPT-4.0
Authors
Loading...
ChatGPT yields less readable hand surgery information than Google at similar accuracy; leaves open whether consensus or prompting improves patient accessibility.
Cross-Sectional
Does ChatGPT provide more usable medical information compared to Google for hand surgery topics?
p-value: p=<.0001
ChatGPT provides less readable medical information compared to Google for hand surgery topics, highlighting a potential health literacy barrier for patients using AI tools.
Lavoie‐Gagne et al. (2025) conducted a cross-sectional in Hand surgery topics. ChatGPT (3.5 and 4.0) vs. Google was evaluated on Readability (grade level) (p=<.0001). ChatGPT responses to hand surgery queries had significantly inferior readability compared to Google (P<0.0001), with no significant difference in accuracy between sources.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: