Insights into latent class analysis of diagnostic test performance.

Latent class analysis is used to assess diagnostic test accuracy when a gold standard assessment of disease is not available but results of multiple imperfect tests are. We consider the simplest setting, where 3 tests are observed and conditional independence (CI) is assumed. Closed-form expressions for maximum likelihood parameter estimates are derived. They show explicitly how observed 2- and 3-way associations between test results are used to infer disease prevalence and test true- and false-positive rates. Although interesting and reasonable under CI, the estimators clearly have no basis when it fails. Intuition for bias induced by conditional dependence follows from the analytic expressions. Further intuition derives from an Expectation Maximization (EM) approach to calculating the estimates. We discuss implications of our results and related work for settings where more than 3 tests are available. We conclude that careful justification of assumptions about the dependence between tests in diseased and nondiseased subjects is necessary in order to ensure unbiased estimates of prevalence and test operating characteristics and to provide these estimates clinical interpretations. Such justification must be based in part on a clear clinical definition of disease and biological knowledge about mechanisms giving rise to test results.

[1]  M S Pepe,et al.  Using a combination of reference tests to assess the accuracy of a new diagnostic test. , 1999, Statistics in medicine.

[2]  S D Walter,et al.  Estimation of test error rates, disease prevalence and relative risk from misclassified data: a review. , 1988, Journal of clinical epidemiology.

[3]  P S Albert,et al.  Latent Class Modeling Approaches for Assessing Diagnostic Error without a Gold Standard: With Applications to p53 Immunohistochemical Assays in Bladder Tumors , 2001, Biometrics.

[4]  M. Pepe The Statistical Evaluation of Medical Tests for Classification and Prediction , 2003 .

[5]  S. Hui,et al.  Evaluation of diagnostic tests without gold standards , 1998, Statistical methods in medical research.

[6]  Jim Young,et al.  The clinical diagnosis of acute bacterial rhinosinusitis in general practice and its therapeutic consequences. , 2003, Journal of clinical epidemiology.

[7]  Stan Lipovetsky,et al.  Latent Variable Models and Factor Analysis , 2001, Technometrics.

[8]  A. P. Dawid,et al.  Maximum Likelihood Estimation of Observer Error‐Rates Using the EM Algorithm , 1979 .

[9]  D. Bartholomew Latent Variable Models And Factor Analysis , 1987 .

[10]  L. Joseph,et al.  Bayesian Approaches to Modeling the Conditional Dependence Between Multiple Diagnostic Tests , 2001, Biometrics.

[11]  Patrick Van der Stuyft,et al.  A comparative study of the effectiveness of diagnostic tests for visceral leishmaniasis. , 2004, The American journal of tropical medicine and hygiene.

[12]  P. Albert,et al.  A Cautionary Note on the Robustness of Latent Class Models for Estimating Diagnostic Error without a Gold Standard , 2004, Biometrics.

[13]  Margaret S. Pepe,et al.  Assessing the Accuracy of a New Diagnostic Test When a Gold Standard Does Not Exist , 1998 .

[14]  P. Moayyedi,et al.  New approaches to enhance the accuracy of the diagnosis of reflux disease , 2004, Gut.

[15]  W Miller,et al.  Using a combination of reference tests to assess the accuracy of a diagnostic test by A. Alonzo and M. Pepe, Statistics in Medicine 1999; 18: 2987–3003 , 2001, Statistics in medicine.

[16]  S D Walter,et al.  Effects of dependent errors in the assessment of diagnostic test performance. , 1997, Statistics in medicine.

[17]  M. Tan,et al.  Random effects models in latent class analysis for evaluating accuracy of diagnostic tests. , 1996, Biometrics.

[18]  M. Ferraz,et al.  Sensitivity and specificity of different diagnostic criteria for Behçet's disease according to the latent class approach. , 1995, British journal of rheumatology.