Skip to main content
. Author manuscript; available in PMC: 2021 Oct 1.
Published in final edited form as: J Surg Res. 2020 Jun 9;254:350–363. doi: 10.1016/j.jss.2020.05.007

Figure 2: A model using both preoperative and intraoperative data outperformed a model using preoperative data alone in predicting postoperative ICU stay >48 hours.

Figure 2:

A: The postoperative model had greater area under the receiver operating characteristic curve (0.88 vs. 0.87). B: The postoperative model had greater area under the precision-recall curve (0.80 vs. 0.72). The postoperative model reclassified cases that did (C) and did not (D) feature prolonged ICU stays. Red dots are patients at high-risk for prolonged ICU stay according to the postoperative model; green dots are patients at low-risk. C, D: The postoperative model correctly reclassified 6.8% of all cases. Gray areas represent regions for which predictive discrimination or precision are ≤0.2, precluding reasonable clinical application.