Table 2 Performance of the four linear SVM classifiers on the test set when the features are defined using a cut-off of 0.1 on the log2 copy ratio. The features (Segments, Size and Chromosomes), considered as covariates in the four linear SVM classifiers, were defined using a cut-off of 0.1 on the log2 copy ratio. The performance of the best model for each classifier was evaluated on the test set (n = 60) in terms of accuracy, specificity, sensitivity, balanced accuracy and area under the ROC curve (AUROC). TP: true positives; TN: true negatives; FP: false positives; FN: false negatives.

From: Binary classification of copy number alteration profiles in liquid biopsy with potential clinical impact in advanced NSCLC