I am doing a multilabel classification using two different classifiers with a dataset of 7 labels and 20 features. I have computed the accuracy, sensitivity, specificity, and area under the curve (AUC) metrics. Now, I want to report the P values and confidence intervals for AUC. I got this article, which is applicable for a binary classification problem. But, how can we implement this in multi-label settings?
Kindly provide some suggestions on this?
Thank you in advance!