Table 4 A comparison of the Likert, modified DISCERN, GQS and FRES scores of four different chatbots
From: Can artificial intelligence models serve as patient information consultants in orthodontics?
ChatGPT-3.5 | ChatGPT-4 | Gemini | Copilot | p | ||
|---|---|---|---|---|---|---|
Likert Score | mean ± SD | 4.15 ± 0.75 | 4.5 ± 0.61 | 4.1 ± 0.72 | 4.35 ± 0.81 | 0.259‡ |
median (IQR) | 4 (4-5) | 5 (4-5) | 4 (4-5) | 5 (4-5) | ||
Modified DISCERN Score | mean ± SD | 18.65 ± 2.25 | 19.7 ± 2.15 | 21.1 ± 2.63 | 25.4 ± 3.39 | 0.0001† |
GQS Score | mean ± SD | 3.5 ± 0.61 | 3.8 ± 0.62 | 3.95 ± 0.69 | 4.4 ± 0.68 | 0.001‡ |
median (IQR) | 3 (3-4) | 4 (3-4) | 4 (3,25 − 4) | 4,5 (4-5) | ||
Flesch Reading Ease Score | mean ± SD | 38.39 ± 11.56 | 43.88 ± 10.13 | 54.12 ± 10.27 | 41.72 ± 10.74 | 0.0001† |