Fast Implementation of DeLong’s Algorithm for Comparing the Areas Under Correlated Receiver Operating Characteristic Curves

By Xu Sun, Weichao Xu. 2014

544 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Luke S. Zettlemoyer
3. Percy Liang
4. Jianfeng Gao
5. Caiming Xiong
6. Richard Socher
7. Quoc V. Le
8. Samuel R. Bowman

In Statistics and Probability

1. Carl Sabottke
2. Andrew Y. Ng
3. B. Spieler

In Signal Processing

1. Carl Sabottke
2. Andrew Y. Ng
3. B. Spieler
4. Yoshua Bengio
5. Qiang Yang

Citations in the corpus

• CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison (2019, methodology): “For each pathology, we also test whether the AUC of the best-performing approach is significantly greater than the AUC of the worst-performing approach us-ing the one-sided DeLongs test for two correlated ROC curves (DeLong, DeLong, and Clarke-Pearson 1988).”
• The Effect of Image Resolution on Deep Learning in Radiography. (2020, methodology): “The DeLong method was used to calculate variance of the AUC for the validation set images (10,11).”