Table 2:
DISCERN questionnaire and panelist scores for ChatGPT and Bing
| DISCERN Question | Scale | ChatGPT Score | Bing Score |
|---|---|---|---|
| Are the aims clear | 1=no, 3=partially, 5=yes | 5 | 5 |
| Does it achieve its aims | 1=no, 3=partially, 5=yes | 4 | 4 |
| Is it relevant | 1=no, 3=partially, 5=yes | 5 | 5 |
| Is it clear what sources of information were used to compile the publication? | 1=no, 3=partially, 5=yes | 2 | 4 |
| Is it clear when the information used or reported in the publication was produced? | 1=no, 3=partially, 5=yes | 1 | 4 |
| Is it balanced and unbiased? | 1=no, 3=partially, 5=yes | 4 | 4 |
| Does it provide details of additional sources of support and information? | 1=no, 3=partially, 5=yes | 2 | 4 |
| Does it refer to areas of uncertainty? | 1=no, 3=partially, 5=yes | 4 | 4 |
| Does it describe how each treatment works? | 1=no, 3=partially, 5=yes | 5 | 5 |
| Does it describe the benefits of each treatment? | 1=no, 3=partially, 5=yes | 5 | 5 |
| Does it describe the risks of each treatment? | 1=no, 3=partially, 5=yes | 5 | 5 |
| Does it describe what would happen if no treatment is used? | 1=no, 3=partially, 5=yes | 5 | 5 |
| Does it describe how the treatment choices affect overall quality of life? | 1=no, 3=partially, 5=yes | 5 | 5 |
| Is it clear that there may be more than one possible treatment choice? | 1=no, 3=partially, 5=yes | 5 | 4 |
| Does it provide support for shared decision-making? | 1=no, 3=partially, 5=yes | 5 | 5 |
| Based on the answers to all of the above questions, rate the overall quality of the publication as a source of information about treatment choices | 1=serious or extensive shortcomings; 3=potentially important but not serious shortcomings; 5=minimal shortcomings | 4 | 3 |
| Mean | 4.13 | 4.44 | |
| Standard Deviation | 1.31 | 0.63 |