Generalized linear mixed models for multi-reader multi-case studies of diagnostic tests

• Published in: Statistical methods in medical research Vol. 26; no. 3; pp. 1373 - 1388
• Main Authors: Liu, Wei, Pantoja-Galicia, Norberto, Zhang, Bo, Kotz, Richard M, Pennello, Gene, Zhang, Hui, Jacob, Jessie, Zhang, Zhiwei
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.06.2017; Sage Publications Ltd
• Subjects: Algorithms; Area Under Curve; Breast cancer; Breast Neoplasms - diagnosis; Cancer; Computer simulation; Diagnostic systems; Diagnostic tests; Diagnostic Tests, Routine - methods; Economic models; Estimates; Female; Humans; Inference; Likelihood Functions; Linear Models; Maximization; Monte Carlo Method; Monte Carlo simulation; Normality; Random effects; Readers; ROC Curve; Simulation; random effect; diagnostic medicine; ROC curve; EM algorithm; pseudo-likelihood; AUC
• ISSN: 0962-2802; 1477-0334
• DOI: 10.1177/0962280215579476

Diagnostic tests are often compared in multi-reader multi-case (MRMC) studies in which a number of cases (subjects with or without the disease in question) are examined by several readers using all tests to be compared. One of the commonly used methods for analyzing MRMC data is the Obuchowski–Rockette (OR) method, which assumes that the true area under the receiver operating characteristic curve (AUC) for each combination of reader and test follows a linear mixed model with fixed effects for test and random effects for reader and the reader–test interaction. This article proposes generalized linear mixed models which generalize the OR model by incorporating a range-appropriate link function that constrains the true AUCs to the unit interval. The proposed models can be estimated by maximizing a pseudo-likelihood based on the approximate normality of AUC estimates. A Monte Carlo expectation-maximization algorithm can be used to maximize the pseudo-likelihood, and a non-parametric bootstrap procedure can be used for inference. The proposed method is evaluated in a simulation study and applied to an MRMC study of breast cancer detection.