Table 3 Classification results of the logistic regression model with three features for training data and independent test data, calculated as means of 100 repetitions (100 cycles). Values in brackets: 95% confidence interval.
From: Assessing preoperative risk of STR in skull meningiomas using MR radiomics and machine learning
Training data | Test data | |
|---|---|---|
AUC | 0.901 [0.879, 0.926] | 0.900 [0.786, 0.976] |
Accuracy | 0.875 [0.856, 0.896] | 0.881 [0.778, 0.963] |
Kappa | 0.629 [0.562, 0.692] | 0.644 [0.348, 0.899] |
Sensitivity | 0.675 [0.600, 0.760] | 0.692 [0.333, 1.000] |
Specificity | 0.933 [0.919, 0.953] | 0.936 [0.857, 1.000] |
