Monte Carlo validation of the Dorfman-Berbaum-Metz method using normalized pseudovalues and less data-based model simplification

Acad Radiol. 2005 Dec;12(12):1534-41. doi: 10.1016/j.acra.2005.07.012.


Rationale and objectives: Two problems of the Dorfman-Berbaum-Metz (DBM) method for analyzing multireader receiver operating characteristic (ROC) studies are that it tends to be conservative and that it can produce AUC estimates outside the parameter space--ie, greater than one or less than zero. Recently it has been shown that the problem of AUC (or other accuracy) estimates outside the parameter space can be eliminated by using normalized pseudovalues, and it has been suggested that less data-based model simplification be used. Our purpose is to empirically investigate if these two modifications--normalized pseudovalues and less data-based model simplification--result in improved performance.

Materials and methods: We examine the performance of the DBM procedure using the two proposed modifications for discrete and continuous ratings in a null simulation study comparing modalities with respect to the ROC area. The simulation study includes 144 different combinations of reader and case sample sizes, normal/abnormal case sample ratios, and variance components. The ROC area is estimated using parametric and nonparametric estimation.

Results: The DBM procedure with both modifications performs better than either the original DBM procedure or the DBM procedure with only one of the modifications. For parametric estimation with discrete rating data, use of both modifications resulted in the mean type I error (0.043) closest to the nominal .05 level and the smallest range (0.050) and standard deviation (0.0108) across the 144 type I error rates.

Conclusions: We recommend that normalized pseudovalues and less data-based model simplification be used with the DBM procedure.

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • Algorithms*
  • Computer Simulation
  • Data Interpretation, Statistical*
  • Models, Statistical*
  • Monte Carlo Method
  • Quality Assurance, Health Care / methods*
  • ROC Curve*
  • Radiography / methods*
  • Sample Size