0

Recently I crossed a paper, which authors presented their ROC curve results in the following way:

44,7,0,19,18,74,15,8,27,24,2,0,0,0,2,0,0,0,0,0,0,0, 0,0,0,183,42,36,46,59,25,6,2,2,15,330,81,59,86,1 04,14,2,2,2,8,16,4,2,2,8,317,97,67,67,86,287,89,5 9,59,80,359,104,67,86,102,16,4,2,2,8,16,4,2,2,8,1 78,62,31,40,45,336,98,65,84,89,31,23,8,0,0,2,2,0, 0,0,0,0,0,0,0,0,0,3,13,324,0,114,0,0,7,0,0,0,0,0,0, 265,0,0,0,0,0,0,12,0,57,21,0,0,156,121,6,361,0

How can understand the performance over the used dataset? I checked this post and post but still I don't get it how it can be represented instead of scores by above numbers?

Mario
  • 421
  • I'll state the obvious and point out that this is a dump of numbers and not ROC curves. I was going to suggest to get in touch with the authors before I noticed that the email for contact is 13121239987@163.com. – dipetkov Jul 13 '22 at 20:24
  • 1
    @dipetkov many researchers in China use email addresses in the 163.com domain. They are all numbers, this one looks fairly legit. – Calimo Jul 13 '22 at 20:32
  • @Calimo Thanks. Then the author might appreciate to learn that something went wrong with Figure 4 of his paper because this doesn't look like a legit ROC curve. – dipetkov Jul 13 '22 at 20:36
  • 1
    Absolutely. And I would also take the rest of the paper with a grain of salt, as something obviously went very wrong in the peer review process... – Calimo Jul 14 '22 at 07:09

0 Answers0