Assessing the Usability of ChatGPT Responses Compared to Other Online Information in Hand Surgery DOI
Ophélie Lavoie-Gagné, Oscar Shen, Neal C. Chen

et al.

Hand, Journal Year: 2025, Volume and Issue: unknown

Published: April 12, 2025

ChatGPT is a natural language processing tool with potential to increase accessibility of health information. This study aimed to: (1) assess usability online medical information for hand surgery topics; and (2) evaluate the influence consensus. Three phrases were posed 20 times each Google, ChatGPT-3.5, ChatGPT-4.0: "What cause carpal tunnel syndrome?" (high consensus), tennis elbow?" (moderate "Platelet-rich plasma thumb arthritis?" (low consensus). Readability was assessed by grade level while reliability accuracy scored based on predetermined rubrics. Scores compared via Mann-Whitney U tests alpha set .05. Google responses had superior readability moderate-high consensus topics (P < .0001) an average eighth-grade reading college sophomore ChatGPT. Low poor throughout. ChatGPT-4 similar but significantly inferior ChatGPT-3.5 low .01). There no significant difference in between sources. differing coverage disease .05) procedure details/efficacy/alternatives anatomy pathophysiology. Compared does not provide readable when providing reliable While patients can modulate prompt engineering, this requires insight into their literacy additional barrier accessing Medical influences both Providers should remain aware limitations distributing

Language: Английский

Assessing the Usability of ChatGPT Responses Compared to Other Online Information in Hand Surgery DOI
Ophélie Lavoie-Gagné, Oscar Shen, Neal C. Chen

et al.

Hand, Journal Year: 2025, Volume and Issue: unknown

Published: April 12, 2025

ChatGPT is a natural language processing tool with potential to increase accessibility of health information. This study aimed to: (1) assess usability online medical information for hand surgery topics; and (2) evaluate the influence consensus. Three phrases were posed 20 times each Google, ChatGPT-3.5, ChatGPT-4.0: "What cause carpal tunnel syndrome?" (high consensus), tennis elbow?" (moderate "Platelet-rich plasma thumb arthritis?" (low consensus). Readability was assessed by grade level while reliability accuracy scored based on predetermined rubrics. Scores compared via Mann-Whitney U tests alpha set .05. Google responses had superior readability moderate-high consensus topics (P < .0001) an average eighth-grade reading college sophomore ChatGPT. Low poor throughout. ChatGPT-4 similar but significantly inferior ChatGPT-3.5 low .01). There no significant difference in between sources. differing coverage disease .05) procedure details/efficacy/alternatives anatomy pathophysiology. Compared does not provide readable when providing reliable While patients can modulate prompt engineering, this requires insight into their literacy additional barrier accessing Medical influences both Providers should remain aware limitations distributing

Language: Английский

Citations

0