Skip to main content
. 2024 Mar 7;31(6):1388–1396. doi: 10.1093/jamia/ocae041

Table 3.

Means and SD for survey questions rated on a 5-point Likert scale, with 1 indicating “strongly disagree” and 5 indicating “strongly agree.”

AI-generated summaries mean (SD) Human-generated summaries mean (SD) P
Clarity: The summary is logical and easy to understand. 4.2 (1.1) 4.1 (1.1) .176
Completeness: There are no important topics in the comments that the summary misses. 3.4 (1.2) 2.7 (1.2) .001
Accuracy: There are no points in the summary that are not actually found in the comments. 4.5 (0.7) 4.5 (0.7) .499
Usefulness: The summary would be helpful to me as I tried to improve the alert. 4.0 (1.1) 3.9 (0.8) .011