0
$\begingroup$

So I trained a model based on a medical dataset and and I got an AUROC for detecting cancer in brain images as about 0.96 and i noticed that the youden index is 0.1 but i want to increase it to 0.5 , is there a way to do it ? heres what i thought of

  1. Oversampling the minority classes
  2. freeze the encoder and train the classificaiton head with oversampling , not sure why random sampling gives a very low youden index , is there any logic to justify oversampling increases youden index?
Improve this question
$\endgroup$

0

Reset to default