ROC Curves: Assessment of Clinical Test Accuracy
The number and complexity of measurements or indicators of the clinical performance of laboratory tests have increased considerably in recent years. So many different quantities, terms and plots have been suggested that even persons interested in and familiar with the issues find the array confusing. This need not be the case. By defining the fundamental issues and then making logical distinctions, we can identify order in this field. When I first began thinking about test performance and usefulness, I failed to appreciate a simple but important distinction which I now recognize and wish to promote. This is the distinction between accuracy and efficacy. Failure to maintain this simple distinction clouds the fundamental issues, contributes to the complex terms and quantities we are now burdened with, and obscures the source of problems with use of the test.
KeywordsRadar Decis Weinstein
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
J.A. Swets and R.M. Pickett, Evaluation of diagnostic systems. Methods from signal detection theory, Academic Press, New York, 1–93 (1982).Google Scholar
C.E. Metz, Basic principles of ROC analysis. Seminars, Nucl. Med.
8: 283 (1978).Google Scholar
P.S. Norman, L.M. Lichtenstein and K. Ishizaka, Diagnostic tests in ragweed hay fever, J. Allergy Clin. Immunol.
52: 210 (1973).PubMedCrossRefGoogle Scholar
E.T. Fossel, J.M. Carr and J. McDonagh, Detection of malignant tumors. Water suppressed proton nuclear magnetic resonance spectroscopy of plasma. N. Engl. J. Med.
315: 1369 (1986).PubMedCrossRefGoogle Scholar
Medical News and Perspectives, ‘Oncolipids’ offer promise as universal screening tool for cancer, J. Am. Med. Assn.
257: 1849 (1987).CrossRefGoogle Scholar
J.A. Swets, The relative operating characteristic in psychology, Science
182: 990 (1973).PubMedCrossRefGoogle Scholar
C.E. Metz, ROC methodology in radiologic imaging. Invest. Radiol.
21: 720 (1986).PubMedCrossRefGoogle Scholar
J.R. Beck and E.K. Shultz, The use of relative operating characteristic (ROC) curves in test performance evaluation, Arch. Pathol. Lab. Med.
110: 13 (1986).PubMedGoogle Scholar
B.J. McNeil et al., Primer on certain elements of medical decision making. New Engl. J. Med.
293: 211 (1975).Google Scholar
B.J. McNeil and J.A. Hanley, Statistical approached to the analysis of receiver operating characteristic (ROC) curves, Med. Decis. Making
4: 137 (1984).PubMedCrossRefGoogle Scholar
C. Weinstein and H.V. Fineberg: Clinical decision analysis, W.B. Saunders, Philadelphia: 114 (1980).Google Scholar
D.A. Turner, An intuitive approach to receiver operating characteristic curve analysis, J. Nucl. Med.
19: 213 (1978).PubMedGoogle Scholar
© Plenum Press, New York 1988