Predictive Modeling of Short-Term Poor Prognosis of Successful Reperfusion after Endovascular Treatment in Patients with Anterior Circulation Acute Ischemic Stroke
Table 7
Predictive performance of the model based on different patients with the severity of stroke.
Sets
AUC (95%CI)
Sensitivity (95%CI)
Specificity (95%CI)
PPV (95%CI)
NPV (95%CI)
Training set
Mild stroke
0.691 (0.564–0.818)
0.484 (0.308–0.660)
0.853 (0.769–0.937)
0.600 (0.408–0.792)
0.784 (0.690–0.878)
Moderate stroke
0.799 (0.739–0.860)
0.727 (0.640–0.815)
0.806 (0.740–0.872)
0.727 (0.640–0.815)
0.806 (0.740–0.872)
Moderate to severe stroke
0.857 (0.548–1.000)
1.000 (1.000–1.000)
0.333 (0.000–0.867)
0.778 (0.506–1.000)
1.000 (1.000–1.000)
Testing set
Mild stroke
0.905 (0.772–1.000)
0.714 (0.380–1.000)
0.963 (0.892–1.000)
0.833 (0.535–1.000)
0.929 (0.833–1.000)
Moderate stroke
0.836 (0.761–0.911)
0.682 (0.544–0.819)
0.767 (0.660–0.874)
0.682 (0.544–0.819)
0.767 (0.660–0.874)
Moderate to severe stroke
1.000 (1.000–1.000)
1.000 (1.000–1.000)
1.000 (1.000–1.000)
1.000 (1.000–1.000)
1.000 (1.000–1.000)
Abbreviations: AUC, area under the curve; PPV, positive predictive value; NPV, negative predictive value.