Bias in trials comparing paired continuous tests can cause researchers to choose the wrong screening modality

BMC Medical Research Methodology

Volumn 9, Issue 1, 2009, Pages

  Glueck, Deborah H ^a   Lamb, Molly M ^a   O'Donnell, Colin I ^a   Ringham, Brandy M ^a   Brinton, John T ^a   Muller, Keith E ^b   Lewin, John M ^c   Alonzo, Todd A ^d   Pisano, Etta D ^e  

^a Food Science and Human Nutrition   (United States)

^b UNIVERSITY OF FLORIDA   (United States)

^c Diversified Radiology of Colorado   (United States)

^d UNIVERSITY OF SOUTHERN CALIFORNIA   (United States)

^e NORTH CAROLINA STATE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AREA UNDER THE CURVE; ARTICLE; CANCER DIAGNOSIS; DECISION SUPPORT SYSTEM; DIAGNOSIS, MEASUREMENT AND ANALYSIS; DIAGNOSTIC ERROR; EPIDEMIOLOGY; HUMAN; MASS SCREENING; METHODOLOGY; PERSONNEL; ROC CURVE; SENSITIVITY AND SPECIFICITY; STATISTICAL MODEL;

AREA UNDER CURVE; BIAS (EPIDEMIOLOGY); DECISION SUPPORT TECHNIQUES; DIAGNOSTIC ERRORS; EARLY DETECTION OF CANCER; HUMANS; LABORATORY TECHNIQUES AND PROCEDURES; MASS SCREENING; MODELS, STATISTICAL; RESEARCH PERSONNEL; ROC CURVE; SENSITIVITY AND SPECIFICITY;

EID: 61849088827     PISSN: None     EISSN: 14712288     Source Type: Journal    
DOI: 10.1186/1471-2288-9-4     Document Type: Article

References (18)

1. Diagnostic performance of digital versus film mammography for breast-cancer screening. ED Pisano C Gatsonis E Hendrick M Yaffe JK Baum S Acharyya EF Conant LL Fajardo L Basett C D'Orsi R Jong M Rebner, N Engl J Med 2005 353 1773 1783 10.1056/NEJMoa052911 16169887
2. Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer. WA Berg JD Blume JB Cormack EB Mendelson D Lehrer M Böhm-Vélez ED Pisano RA Jong WP Evans MJ Morton MC Mahoney LH Larsen RG Barr DM Farria HS Marques K Boparai for the ACRIN 6666 Investigators, J Am Med Assoc 2008 299 2151 2163 10.1001/jama.299.18.2151
3. Sources of variation and bias in studies of diagnostic accuracy: a systematic review. P Whiting AW Rutjes JB Reitsma AS Glas PM Bossuyt J Kleijnen, Ann Intern Med 2004 140 189 202 14757617
4. MS Pepe, The Statistical Evaluation of Medical Test for Classification and Prediction New York: Oxford University Press 2003
5. New approach for testing the significance of differences between ROC curves measured from correlated data. C Metz P Wang HA Kronman, Information Processing In Medical Imaging The Hague, the Netherlands: Nijihoff, Deconinck F, 1984 432 445
6. TM Apostol, Calculus: Multivariable Calculus and Linear Algebra, With Applications to Differential Equations and Probability New York: Wiley and Sons Second 1969 II
7. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. ER DeLong DM DeLong DL Clarke-Pearson, Biometrics 1988 44 837 845 10.2307/2531595 3203132
8. Assessment of radiologic tests: control of bias and other design considerations. CB Begg BJ McNeil, Radiology 1988 167 565 569 3357976
9. A proposed design and analysis for comparing digital and analog mammography: special ROC methods for cancer screening. SG Baker P Pinsky, J Am Stat Assoc 2001 96 421 428 10.1198/016214501753168136
10. A non-inferiority test for diagnostic accuracy based on the paired partial areas under ROC curves. CR Li CT Liao JP Liu, Stat Med 2008 10 1762 1776 10.1002/sim.3121
11. The robustness of the 'binormal' assumptions used in fitting ROC curves. JA Hanley, Med Decis Making 1988 8 197 203 10.1177/0272989X8800800308 3398748
12. Assessment of diagnostic tests when disease verification is subject to selection bias. CB Begg RA Greenes, Biometrics 1983 39 207 215 10.2307/2530820 6871349
13. Biases in the assessment of diagnostic tests. CB Begg, Stat Med 1987 6 411 423 10.1002/sim.4780060402 3114858
14. Construction of receiver operating characteristic curves when disease verification is subject to selection bias. R Gray CB Begg RA Greenes, Med Decis Making 1984 4 151 164 10.1177/0272989X8400400204 6472063
15. ROC curve estimation when covariates affect the verification process. C Rodenberg X-H Zhou, Biometrics 2000 56 1256 1262 10.1111/j.0006-341X.2000.01256. x 11129488
16. Assessing accuracy of a continuous screening test in the presence of verification bias. TA Alonzo MS Pepe, J R Stat Soc Ser C Appl Stat 2005 54 173 190 10.1111/j.1467-9876.2005.00477.x
17. Verification bias-corrected estimators of the relative true and false positive rates of two binary screening tests. TA Alonzo, Stat Med 2005 24 403 417 10.1002/sim.1959 15543634
18. X-H Zhou NA Obuchowski DK McClish, Statistical Methods in Diagnostic Medicine New York: John Wiley and Sons 2002