Skip to main content
. Author manuscript; available in PMC: 2015 Feb 1.
Published in final edited form as: Obstet Gynecol. 2014 Feb;123(2 0 1):279–287. doi: 10.1097/AOG.0000000000000094

Figure 4.

Figure 4

Comparing accuracy of the models’ predictions, experts’ predictions and the preoperative stress test results using Receiver Operating Characteristic (ROC) curves in predicting De novo stress urinary incontinence (SUI)for 32 random patients selected from the Outcomes Following Vaginal Prolapse Repair and Midurethral Sling dataset. The model was significantly more accurate than experts who had knowledge of the same patient characteristics and preoperative prolapse reduction stress test results. The model was also significantly more accurate than the preoperative prolapse reduction stress test alone.