Disadvantages of using the area under the receiver operating characteristic curve to assess imaging tests: A discussion and proposal for an alternative approach
Open Access
- 20 January 2015
- journal article
- research article
- Published by Springer Science and Business Media LLC in European Radiology
- Vol. 25 (4), 932-939
- https://doi.org/10.1007/s00330-014-3487-0
Abstract
The objectives are to describe the disadvantages of the area under the receiver operating characteristic curve (ROC AUC) to measure diagnostic test performance and to propose an alternative based on net benefit. We use a narrative review supplemented by data from a study of computer-assisted detection for CT colonography. We identified problems with ROC AUC. Confidence scoring by readers was highly non-normal, and score distribution was bimodal. Consequently, ROC curves were highly extrapolated with AUC mostly dependent on areas without patient data. AUC depended on the method used for curve fitting. ROC AUC does not account for prevalence or different misclassification costs arising from false-negative and false-positive diagnoses. Change in ROC AUC has little direct clinical meaning for clinicians. An alternative analysis based on net benefit is proposed, based on the change in sensitivity and specificity at clinically relevant thresholds. Net benefit incorporates estimates of prevalence and misclassification costs, and it is clinically interpretable since it reflects changes in correct and incorrect diagnoses when a new diagnostic test is introduced. ROC AUC is most useful in the early stages of test assessment whereas methods based on net benefit are more useful to assess radiological tests where the clinical context is known. Net benefit is more useful for assessing clinical impact. • The area under the receiver operating characteristic curve (ROC AUC) measures diagnostic accuracy. • Confidence scores used to build ROC curves may be difficult to assign. • False-positive and false-negative diagnoses have different misclassification costs. • Excessive ROC curve extrapolation is undesirable. • Net benefit methods may provide more meaningful and clinically interpretable results than ROC AUC.Keywords
This publication has 29 references indexed in Scilit:
- Evaluation of Markers and Risk Prediction ModelsMedical Decision Making, 2013
- Comparing Areas under Receiver Operating Characteristic Curves: Potential Impact of the “Last” Experimentally Measured Operating PointRadiology, 2008
- “Binary” and “Non-Binary” Detection Tasks: Are Current Performance Measures Optimal?Academic Radiology, 2007
- Evaluating the added predictive ability of a new marker: From area under the ROC curve to reclassification and beyondStatistics in Medicine, 2007
- Computed Tomographic Colonography: Assessment of Radiologist Performance With and Without Computer-Aided DetectionGastroenterology, 2006
- Multireader, multicase receiver operating characteristic analysis:: an empirical comparison of five methods1Academic Radiology, 2004
- Receiver Operating Characteristic (ROC) Curve: Practical Review for RadiologistsKorean Journal of Radiology, 2004
- Application of Treatment Thresholds to Diagnostic-test EvaluationMedical Decision Making, 1997
- Some methodological questions concerning receiver operating characteristic (ROC) analysis as a method for assessing image quality in radiologyJournal of Digital Imaging, 1990
- Analyzing a Portion of the ROC CurveMedical Decision Making, 1989