Skip to main content

Table 5 Post-hoc pairwise comparison of scores in AI chatbots

From: Can artificial intelligence models serve as patient information consultants in orthodontics?

 

Modified DISCERN Score

p

Flesch Reading Ease Score

p

GQS

Score

p

ChatGPT-3.5 vs. ChatGPT-4

0.597

0.371

0.165

ChatGPT-3.5 vs. Gemini

0.023†

0.001†

0.036†

ChatGPT-3.5 vs. Copilot

0.0001†

0.758

0.0001†

ChatGPT-4 vs. Gemini

0.348

0.017†

0.483

ChatGPT-4 vs. Copilot

0.0001†

0.919

0.007†

Gemini vs. Copilot

0.0001†

0.002†

0.042†

  1. †p < 0.05, Tukey’s post hoc test was used for Modified DISCERN and Flesch Reading Ease Score, and Dunn’s post hoc test was used for GQS.
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us