Table 2. Accuracy Outcomesa.
| Arm | Control (n = 356), min | Intervention (n = 327), min | Improvement in mean, % | P value |
|---|---|---|---|---|
| Mean absolute error (SD)b | ||||
| Overall | 59.3 (72) | 49.5 (66) | 16.5 | .03 |
| Colorectal Service | 74.0 (78) | 55.7 (87) | 24.8 | .004 |
| Gynecology Service | 51.9 (68) | 46.9 (55) | 9.6 | .64 |
| Mean error (SD)b | ||||
| Overall | −33.7 (87) | −3.6 (83) | 89.3 | <.001 |
| Colorectal Service | −51.7 (94) | 5.7 (103) | 89.0 | <.001 |
| Gynecology Service | −24.6 (82) | −7.5 (72) | 69.4 | .01 |
a
Sample sizes for the service-specific results are listed in Table 1.
b
In the entire sample, there was 1 case with a duration greater than 1000 minutes: a colorectal service case randomized into the intervention arm. If this case had been considered an outlier and removed, the SD for colorectal service in the intervention arm would have been reduced from 87 to 70 for the mean absolute error SD and 103 to 86 for the mean error SD.17