Methods for evaluating the performance of diagnostic tests in the absence of a gold standard: a latent class model approach

In many areas of medical research, 'gold standard' diagnostic tests do not exist and so evaluating the performance of standardized diagnostic criteria or algorithms is problematic. In this paper we propose an approach to evaluating the operating characteristics of diagnoses using a latent class model. By defining 'true disease' as our latent variable, we are able to estimate sensitivity, specificity and negative and positive predictive values of the diagnostic test. These methods are applied to diagnostic criteria for depression using Baltimore's Epidemiologic Catchment Area Study Wave 3 data.

[1]  R. Murray,et al.  Further exploration of a latent class typology of schizophrenia , 1996, Schizophrenia Research.

[2]  S. Zeger,et al.  Latent Class Model Diagnosis , 2000, Biometrics.

[3]  A. Pickles,et al.  Analyzing twin resemblance in multisymptom data: Genetic applications of a latent class model for symptoms of conduct disorder in juvenile boys , 1993, Behavior genetics.

[4]  K. Kendler,et al.  Latent class analysis of Temperance Board registrations in Swedish male–male twin pairs born 1902 to 1949: searching for subtypes of alcoholism , 1998, Psychological Medicine.

[5]  W. Eaton,et al.  The Epidemiologic Catchment Area Program of the National Institute of Mental Health. , 1981, Public health reports.

[6]  K. Bucholz,et al.  Evaluation of ADHD typology in three contrasting samples: a latent class approach. , 1999, Journal of the American Academy of Child and Adolescent Psychiatry.

[7]  G. Casella,et al.  Explaining the Gibbs Sampler , 1992 .

[8]  T Reich,et al.  Can we subtype alcoholism? A latent class analysis of data from relatives of alcoholics in a multicenter family study of alcoholism. , 1996, Alcoholism, clinical and experimental research.

[9]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  T. Kohlmann,et al.  Latent class analysis in medical research , 1996, Statistical methods in medical research.

[11]  R. Kessler,et al.  The identification and validation of distinct depressive syndromes in a population-based sample of female twins. , 1996, Archives of general psychiatry.

[12]  M. Stephens.  Dealing with label switching in mixture models , 2000 .

[13]  P. Sullivan,et al.  Typology of common psychiatric syndromes , 1998, British Journal of Psychiatry.

[14]  S. Faraone,et al.  Measuring diagnostic accuracy in the absence of a "gold standard". , 1994, The American journal of psychiatry.

[15]  M A Young,et al.  Evaluating diagnostic criteria: a latent class paradigm. , 1982, Journal of psychiatric research.

[16]  M. Taylor,et al.  The prevalence of schizophrenia: a reassessment using modern diagnostic criteria. , 1978, The American journal of psychiatry.

[17]  Quantification of fluorescence properties of lymphocytes in peripheral blood mononuclear cell suspensions using a latent class model. , 1993, Cytometry.

[18]  A. McCutcheon,et al.  Latent Class Analysis of Anxiety and Depression , 1989 .

[19]  An evaluation of the structure of schizophrenia spectrum personality disorders , 1994 .

[20]  L. Robins,et al.  National Institute of Mental Health Diagnostic Interview Schedule. Its history, characteristics, and validity. , 1981, Archives of general psychiatry.

[21]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[22]  A. McCutcheon,et al.  DSM–III Major Depressive Disorder in the Community , 1989, British Journal of Psychiatry.

[23]  D. Fergusson,et al.  The prevalence and risk factors associated with abusive or hazardous alcohol consumption in 16-year-olds. , 1995, Addiction.

[24]  P Bolton,et al.  Latent-class analysis of recurrence risks for complex phenotypes with selection and measurement error: a twin and family history study of autism. , 1995, American journal of human genetics.

[25]  S. Chib,et al.  Understanding the Metropolis-Hastings Algorithm , 1995 .

[26]  K. Kendler,et al.  The structure of psychosis: latent class analysis of probands from the Roscommon Family Study. , 1998, Archives of general psychiatry.

[27]  Inequality in health and health service use for mothers of young children in south west England. Survey Team of the Avon Longitudinal Study of Pregnancy and Childhood Team. , 1997, Journal of epidemiology and community health.

[28]  A. Pulver,et al.  Extended latent class approach to the study of familial/sporadic forms of a disease: Its application to the study of the heterogeneity of schizophrenia , 1994, Genetic epidemiology.

[29]  R. Kessler,et al.  Social phobia subtypes in the National Comorbidity Survey. , 1998, The American journal of psychiatry.

[30]  J. Forbes,et al.  Development of a Neonatal Case-mix Classification , 1988, Medical care.

[31]  Scott L. Zeger,et al.  Latent Variable Regression for Multiple Discrete Outcomes , 1997 .

[32]  F. Volkmar,et al.  Evaluation of diagnostic criteria for autism using latent class models. , 1995, Journal of the American Academy of Child and Adolescent Psychiatry.

[33]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[34]  P. Sullivan,et al.  The epidemiology and classification of bulimia nervosa , 1998, Psychological Medicine.