Skip to main content
. 2022 Aug 11;10:944790. doi: 10.3389/fpubh.2022.944790

Table 4.

Comparison of models in predicting the probability of ICU p-LOS of obesity patients with sepsis.

Predictive model AUROC P -value IDI P -value
Training set APACHE IV 0.647 (0.631–0.663) <0.001 0.099 (0.087–0.112) <0.001
SOFA 0.670 (0.654–0.685) <0.001 0.083 (0.070–0.096) <0.001
Nomogram 0.742 (0.727–0.756)
Internal validation set APACHE IV 0.655 (0.631–0.678) <0.001 0.085 (0.067–0.103) <0.001
SOFA 0.648 (0.624–0.671) <0.001 0.089 (0.071–0.107) <0.001
Nomogram 0.730 (0.708–0.752)
External validation set APACHE IV graphic file with name fpubh-10-944790-i0001.jpg graphic file with name fpubh-10-944790-i0001.jpg graphic file with name fpubh-10-944790-i0001.jpg graphic file with name fpubh-10-944790-i0001.jpg
SOFA 0.558 (0.535–0.581) <0.001 0.196 (0.180–0.212) <0.001
Nomogram 0.778 (0.760–0.797)

AUROC, area under the receiver operating characteristic curve; CI, confidence interval; IDI, integrated discrimination improvement; APACHE IV, acute physiology and chronic health evaluation IV; ICU, intensive care unit; p-LOS, prolonged length of stay.