The use of the area under the ROC curve in the evaluation of machine learning algorithms
Open accessThe DOI matches its Crossref record; 44 of the 47 references it cites were found in a registry or an index.
Abstract
In this paper we investigate the use of the area under the receiver operating characteristic (ROC) curve (AUC) as a performance measure for machine learning algorithms. As a case study we evaluate six machine learning algorithms (C4.5, Multiscale Classifier, Perceptron, Multi-layer Perceptron, k-Nearest Neighbours, and a Quadratic Discriminant Function) on six ''real world'' medical diagnostics data sets. We compare and discuss the use of AUC to the more conventional overall accuracy and find that AUC exhibits a number of desirable properties when compared to overall accuracy: increased sensitivity in Analysis of Variance (ANOVA) tests; a standard error that decreased as both AUC and the number of test samples increased; decision threshold independent; and it is invariant to a priori class probabilities. The paper concludes with the recommendation that AUC be used in preference to overall accuracy for ''single number'' evaluation of machine learning algorithms.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“For binary outcomes, the C-statistic is equal to area under the receiver operating characteristic curve (AUROC). 37,38”
From Evaluation of performance measures in predictive artificial intelligence models to support medical decisions: overview and guidance (2025) · cites this paper as [37]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Classification and Regression Trees.
Gordon, A. D., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984) · Biometrics · doi:10.2307/2530946 · Cited by 23,522
(1992) · Cited by 23,431
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
Hanley, J. A., & McNeil, B. J. (1982) · Radiology · doi:10.1148/radiology.143.1.7063747 · Cited by 21,856
Classification and Regression Trees.
Ryzin, J. V., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1986) · Journal of the American Statistical Association · doi:10.2307/2288003 · Cited by 20,825
Bootstrap methods: another look at the jackknife
Efron, B. (1979) · The Annals of Statistics · doi:10.1214/aos/1176344552 · Cited by 17,602
Learning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,172
Introduction to Statistical Pattern Recognition
(1990) · Elsevier eBooks · doi:10.1016/c2009-0-27872-x · Cited by 11,031
(1966) · Medical Entomology and Zoology · Cited by 10,293
Signal detection theory and psychophysics
Ingleby, J. D. (1967) · Journal of Sound and Vibration · doi:10.1016/0022-460x(67)90197-6 · Cited by 8,509
Hanley, J. A., & McNeil, B. J. (1983) · Radiology · doi:10.1148/radiology.148.3.6878708 · Cited by 7,016
Introduction to statistical pattern recognition (2nd ed.)
Fukunaga, K. (1990) · Academic Press Professional, Inc. eBooks · Cited by 3,797
Pattern Recognition Principles
(2009) · Classification Methods for Remotely Sensed Data, Second Edition · doi:10.1201/9781420090741.ch2 · Cited by 3,173
Devijver, P. A., & Kittler, J. (1982) · Prentice-Hall International eBooks · Cited by 2,910
Probability and Statistics for Engineers and Scientists.
Beckman, R. J., Walpole, R. E., & Meyers, R. H. (1973) · Journal of the American Statistical Association · doi:10.2307/2284195 · Cited by 2,835
Mullin, A. A., & Rosenblatt, F. (1963) · The American Mathematical Monthly · doi:10.2307/2312103 · Cited by 2,209 · cited 1×
“The network was trained, using the Perceptron learning algorithm (23) for”
MethodNguyen, D., & Widrow, B. (1990) · 1990 IJCNN International Joint Conference on Neural Networks · doi:10.1109/ijcnn.1990.137819 · Cited by 1,375
Fundamental Concepts in the Design of Experiments
Ziegel, E. R., Hicks, C. R., & Turner, K. V. (2000) · Technometrics · doi:10.1080/00401706.2000.10486081 · Cited by 1,303
(1982) · Cited by 1,288
Fundamental Concepts in the Design of Experiments
Ziegel, E. R., Hicks, C. R., & Turner, K. V. (2000) · Technometrics · doi:10.2307/1271115 · Cited by 1,259
Pattern Recognition Principles
Kavzoglu, T., Tso, B., & Mather, P. M. (2024) · Classification Methods for Remotely Sensed Data · doi:10.1201/9781003439172-2 · Cited by 1,053
Multisurface method of pattern separation for medical diagnosis applied to breast cytology.
Wolberg, W. H., & Mangasarian, O. L. (1990) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.87.23.9193 · Cited by 1,037
Discrimination and Classification
Loader, C. (1999) · Statistics and Computing · doi:10.1007/0-387-22732-6_8 · Cited by 928
Weiss, S. M., & Kulikowski, C. A. (1991) · Morgan Kaufmann Publishers Inc. eBooks · Cited by 898
Dorfman, D. D., & Alf, E. (1969) · Journal of Mathematical Psychology · doi:10.1016/0022-2496(69)90019-4 · Cited by 874
Using the ADAP Learning Algorithm to Forecast the Onset of Diabetes Mellitus
Smith, J. W., Everhart, J. E., Dickson, W., Knowler, W. C., & Johannes, R. S. (1988) · PubMed Central · Cited by 813
Discrimination and Classification.
Moore, B. A., & Hand, D. J. (1982) · Journal of the Royal Statistical Society. Series A (General) · doi:10.2307/2982109 · Cited by 710
ROC Analysis Applied to the Evaluation of Medical Imaging Techniques
SWETS, J. A. (1979) · Investigative Radiology · doi:10.1097/00004424-197903000-00002 · Cited by 699
Detrano, R., Janosi, A., Steinbrunn, W., Pfisterer, M., Schmid, J.-J., Sandhu, S., Guppy, K. H., Lee, S., & Froelicher, V. (1989) · The American Journal of Cardiology · doi:10.1016/0002-9149(89)90524-9 · Cited by 695
Models of Incremental Concept Formation
Gennari, J. H., Langley, P., & Fisher, D. (1988) · doi:10.21236/ada191597 · Cited by 525
Probability and Statistics for Engineers and Scientists
Robinson, J. A. (1990) · Technometrics · doi:10.1080/00401706.1990.10484698 · Cited by 463
Models of incremental concept formation
Gennari, J. H., Langley, P., & Fisher, D. (1989) · Artificial Intelligence · doi:10.1016/0004-3702(89)90046-5 · Cited by 453
Principles of neurodynamics: Yu. G. Antomonov
Ivakhnenko, A. G. (1976) · Cybernetics · doi:10.1007/bf01071380 · Cited by 318
Schaffer, C. (1993) · Machine Learning · doi:10.1023/a:1022653209073 · Cited by 310
Decision, estimation, and classification: an introduction to pattern recognition and related topics
(1989) · Choice Reviews Online · doi:10.5860/choice.27-0356 · Cited by 294
An Overview of Predictive Learning and Function Approximation
Friedman, J. H. (1994) · From Statistics to Neural Networks · doi:10.1007/978-3-642-79119-2_1 · Cited by 189
From Statistics to Neural Networks: Theory and Pattern Recognition Applications
Cherkassky, V., Friedman, J. H., & Wechsler, H. L. (1996) · CERN Document Server (European Organization for Nuclear Research) · Cited by 175
On deflection as a performance criterion in detection
Picinbono, B. (1995) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/7.395235 · Cited by 143
Fundamental Concepts in the Design of Experiments
Nelson, L. S. (1994) · Journal of Quality Technology · doi:10.1080/00224065.1994.11979544 · Cited by 129
Relationship of platelet aggregation to bleeding after cardiopulmonary bypass
Ray, M. J., Hawson, G. A. T., Just, S., McLachlan, G. J., & O’Brien, M. F. (1994) · The Annals of Thoracic Surgery · doi:10.1016/0003-4975(94)90218-6 · Cited by 102
Lovell, B. C., & Bradley, A. P. (1996) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.481538 · Cited by 59 · cited 1×
“This is a requirement for the Multiscale Classifier, (15)1 but was done for all of the learning algorithms for consistency (with no loss of generality).”
MethodSelf-citationWalker, R. F., Jackway, P., Lovell, B. C., & Longstaff, I. D. (2002) · Australian and New Zealand Intelligent Information Systems Conference (ANZIIS) · doi:10.1109/anziis.1994.396977 · Cited by 37
ROC Curves for Classification Trees
Raubertas, R. F., Rodewald, L. E., Humiston, S. G., & Szilagyi, P. G. (1994) · Medical Decision Making · doi:10.1177/0272989x9401400209 · Cited by 20
Power curves for pattern classification networks
Twomey, J. M., & Smith, A. E. (2002) · IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks · doi:10.1109/icnn.1993.298685 · Cited by 4
On the methodology for comparing learning algorithms: a case
Bradley, A. P., Lovell, B. C., Ray, M. J., & Hawson, G. A. T. (2002) · Australian and New Zealand Intelligent Information Systems Conference (ANZIIS) · doi:10.1109/anziis.1994.396954 · Cited by 3
Self-citation
Research works printed but not linked: 5
- 16. B . C . L o vell & A. P. Bradley, \The Multiscale Classier," IEEE Transactions on Pat- tern Analysis and Machine Intelligence 18 (1996), 124{137.
- 20. D. J. Hand, in Discrimination and Classi cation, John Wiley and Sons, 1981.
- 21. J. R. Quinlan, in C4.5:Programs f o r M a c hine Learning, Morgan Kaufmann, San Mateo, 1993.
- 22. M. L. Minsky & S. A. Papert, in Perceptrons, MIT Press, Cambridge, Mass, 1969.
- 29. J . H . F riedman, \Introduction to Computational Learning and Statistical Prediction," Tutorial, at the XII International Conference on Machine Learning, Lake T ahoe, CA., 1995.
Cited by
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865
An introduction to ROC analysis
Fawcett, T. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.10.010 · Cited by 21,879
“A common method is to calculate the area under the ROC curve, abbreviated AUC (Bradley, 1997; Hanley and McNeil, 1982).”
MethodThe relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559
“Often, the area under the curve is used as a simple metric to define how an algorithm performs over the whole space (Bradley, 1997; Davis et al., 2005; Goadrich et al., 2004; Kok & Domingos, 2005; Macskassy & Provost, 2005; Singla & Domingos, 2005).”
MethodChicco, D., & Jurman, G. (2020) · BMC Genomics · doi:10.1186/s12864-019-6413-7 · Cited by 6,143
Borderline-SMOTE : A New Over-Sampling Method in Imbalanced Data Sets Learning
Han, H., Wang, W.-Y., & Mao, B.-H. (2005) · Lecture notes in computer science · doi:10.1007/11538059_91 · Cited by 4,331
“ROC curve [9] is one of the popular metrics to evaluate the learners for imbalanced data sets.”
Background
Metadata
- Authors
- Bradley, A. P.
- Affiliations
- The University of Queensland (AU)
- Corresponding author
- Bradley, Andrew P.
- ORCID
- Bradley, Andrew P.
- Venue
- Pattern Recognition
- Publisher
- Elsevier BV
- Published
- 1997-07
- Volume
- 30
- Issue
- 7
- Pages
- 1145-1159
- ISSN
- 0031-3203 (ISSN-L)
- OpenAlex
- W2155653793
- Semantic Scholar
- 48ddd9101a90fe65e3061de69626741b843ff5e4
- Cited by
- 7,217
- References
- 47
- Citations by year
- 2026: 365 · 2025: 591 · 2024: 588 · 2023: 544 · 2022: 617 · 2021: 597 · 2020: 477 · 2019: 470 · 2018: 363 · 2017: 287 · 2016: 278 · 2015: 258 · 2014: 259 · 2013: 216 · 2012: 204
- FWCI
- 5.20
- Type
- journal article
- Language
- en
- Open access
- green
- eprints.qut.edu.au
- Licence
- cc-by-nc-nd
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- Locations
- Pattern Recognition (publishedVersion)
- QUT ePrints (Queensland University of Technology) (submittedVersion)
- QUT ePrints (Queensland University of Technology) (submittedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Imbalanced Data Classification Techniques
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- area under the ROC curve, receiver operating characteristic, overall accuracy, medical diagnostics, C4.5, k-nearest neighbors, multilayer perceptron, quadratic discriminant analysis, standard errors
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.