Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation
University of Waterloo · Ottawa Hospital · +9 more institutions
Abstract
Optimal performance is desired for decision-making in any field with binary classifiers and diagnostic tests, however common performance measures lack depth in information. The area under the receiver operating characteristic curve (AUC) and the area under the precision recall curve are too general because they evaluate all decision thresholds including unrealistic ones. Conversely, accuracy, sensitivity, specificity, positive predictive value and the F1 score are too specific-they are measured at a single threshold that is optimal for some instances, but not others, which is not equitable. In between both approaches, we propose deep ROC analysis to measure performance in multiple groups of predicted risk…
Citation impact
- FWCI
- 34.16
- Percentile
- 100%
- References
- 60
Authors
12- AMAndre M. CarringtonCorresponding
University of Waterloo, Ottawa Hospital
- DGDouglas G. Manuel
University of Ottawa, Ottawa Hospital, Institute for Clinical Evaluative Sciences
- PWPaul W. Fieguth
University of Waterloo
- TRTim Ramsay
University of Ottawa, Ottawa Hospital
- VOVenet Osmani
University of Trento, Fondazione Bruno Kessler
Topics & keywords
- Receiver operating characteristic
- Precision and recall
- Binary classification
- Classifier (UML)
- False positive rate
- Pattern recognition (psychology)
- Binary number
- Correlation