Table 3.
Results of the emotional management guidance assessment of ChatGPT-4.0.
| Language | Clinical Problem Questions (n=154), n | Simulated Patient Questions (n=32), n | Total (N=186), n | P value | |||||||||
|
|
Grade 1 | Grade 2 | Grade 3 | Grade 1 | Grade 2 | Grade 3 | Grade 1 | Grade 2 | Grade 3 |
|
|||
|
|
|
|
|
|
|
|
|
|
|
|
|||
| Chinese | 5 | 73 | 0 | 2 | 14 | 0 | 7 | 87 | 0 | .08a | |||
| English | 5 | 71 | 0 | 3 | 13 | 0 | 8 | 84 | 0 |
|
|||
| Total | 10 | 144 | 0 | 5 | 27 | 0 | 15 | 171 | 0 | .75b | |||
aP value across the grades of each section.
bP value between the grades of different working languages.