Table 2.
Means and SD for survey questions rated on a 5-point Likert scale, with 1 indicating “strongly disagree” and 5 indicating “strongly agree.”
| Model | Clarity | Completeness | Conciseness | Utility |
|---|---|---|---|---|
| Healthcare Provider | 4.2 ± 1.1 | 1.9 ± 1.2 | 4.1 ± 1.3 | 3.5 ± 1.5 |
| CLAIR | 4.3 ± 0.9 | 2.8 ± 1.2a | 4.1 ± 1.0 | 4.2 ± 0.7 |
| GPT4-Simple | 3.1 ± 1.5a,b | 4.1 ± 1.1a,b | 2.5 ± 1.5a,b | 3.8 ± 1.0 |
| GPT4-Complex | 3.2 ± 1.5a,b | 3.6 ± 1.1a,b | 3.6 ± 1.2c | 4.1 ± 0.8 |
Results are denoted by
a
if models had a significant effect relative to Healthcare Provider,
b
if significant to CLAIR,
c
if significant to GPT4-Simple at the P = .05 using Kruskal-Wallis H test with Dunn’s post hoc tests.