Bayesian regression for group testing data

Group testing involves pooling individual specimens (e.g., blood, urine, swabs, etc.) and testing the pools for the presence of a disease. When individual covariate information is available (e.g., age, gender, number of sexual partners, etc.), a common goal is to relate an individual's true disease status to the covariates in a regression model. Estimating this relationship is a nonstandard problem in group testing because true individual statuses are not observed and all testing responses (on pools and on individuals) are subject to misclassification arising from assay error. Previous regression methods for group testing data can be inefficient because they are restricted to using only initial pool responses and/or they make potentially unrealistic assumptions regarding the assay accuracy probabilities. To overcome these limitations, we propose a general Bayesian regression framework for modeling group testing data. The novelty of our approach is that it can be easily implemented with data from any group testing protocol. Furthermore, our approach will simultaneously estimate assay accuracy probabilities (along with the covariate effects) and can even be applied in screening situations where multiple assays are used. We apply our methods to group testing data collected in Iowa as part of statewide screening efforts for chlamydia, and we make user-friendly R code available to practitioners.

[1]  P. Sly,et al.  Pooled biological specimens for human biomonitoring of environmental chemicals: Opportunities and limitations , 2014, Journal of Exposure Science and Environmental Epidemiology.

[2]  Dani Gamerman,et al.  Sampling from the posterior distribution in generalized linear mixed models , 1997, Stat. Comput..

[3]  P. Hall,et al.  New approaches to nonparametric and semiparametric regression for univariate and multivariate group testing data , 2014 .

[4]  W. Johnson,et al.  A Bayesian Approach to Estimate OJD Prevalence From Pooled Fecal Samples of Variable Pool Size , 2010 .

[5]  K. Ault,et al.  Gonorrhea and chlamydia infection among women visiting family planning clinics: racial variation in prevalence and predictors. , 2005, Perspectives on sexual and reproductive health.

[6]  A. Meister,et al.  Nonparametric Regression Analysis for Group Testing Data , 2011 .

[7]  S Vansteelandt,et al.  Regression Models for Disease Prevalence with Diagnostic Tests on Pools of Serum Samples , 2000, Biometrics.

[8]  N. Speybroeck,et al.  Estimating the prevalence of infections in vector populations using pools of samples , 2012, Medical and veterinary entomology.

[9]  R. Christensen,et al.  A New Perspective on Priors for Generalized Linear Models , 1996 .

[10]  Joshua M Tebbs,et al.  Optimal retesting configurations for hierarchical group testing , 2015, Journal of the Royal Statistical Society. Series C, Applied statistics.

[11]  M Xie,et al.  Regression analysis of group testing samples , 2001, Statistics in medicine.

[12]  J. Ibrahim,et al.  Power prior distributions for regression models , 2000 .

[13]  T. Quinn,et al.  Performance of the APTIMA Combo 2 Assay for Detection of Chlamydia trachomatis and Neisseria gonorrhoeae in Female Urine and Endocervical Swab Specimens , 2003, Journal of Clinical Microbiology.

[14]  C. Farrington.  Estimating prevalence by group testing using generalized linear models. , 1992, Statistics in medicine.

[15]  Mark Gilbert,et al.  Pooled nucleic acid testing increases the diagnostic yield of acute HIV infections in a high-risk population compared to 3rd and 4th generation HIV enzyme immunoassays. , 2014, Journal of clinical virology : the official publication of the Pan American Society for Clinical Virology.

[16]  Joanna Lynn Lewis,et al.  Cost savings and increased efficiency using a stratified specimen pooling strategy for Chlamydia trachomatis and Neisseria gonorrhoeae. , 2012, Sexually transmitted diseases.

[17]  J. Pliskin,et al.  Feasibility and cost–benefit of implementing pooled screening for HCVAg in small blood bank settings , 2007, Transfusion medicine.

[18]  Chunling Liu,et al.  Optimality of group testing in the presence of misclassification. , 2012, Biometrika.

[19]  S. Chib,et al.  Bayesian analysis of binary and polychotomous response data , 1993 .

[20]  Hae-Young Kim,et al.  Comparison of Group Testing Algorithms for Case Identification in the Presence of Test Error , 2007, Biometrics.

[21]  Aurore Delaigle,et al.  Nonparametric methods for group testing data, taking dilution into account , 2015 .

[22]  J. Tebbs,et al.  Group testing regression model estimation when case identification is a goal , 2013, Biometrical journal. Biometrische Zeitschrift.

[23]  P. Holland,et al.  Hepatitis B virus (HBV) DNA screening of blood donations in minipools with the COBAS AmpliScreen HBV test , 2005, Transfusion.

[24]  Adam J. Branscum,et al.  Informative g-Priors for Logistic Regression , 2014 .

[25]  Joshua M Tebbs,et al.  Group Testing Regression Models with Fixed and Random Effects , 2009, Biometrics.

[26]  Joseph L. Gastwirth,et al.  Screening with Cost-Effective Quality Control: Potential Applications to HIV and Drug Testing , 1994 .

[27]  Joshua M Tebbs,et al.  Regression models for group testing data with pool dilution effects. , 2013, Biostatistics.

[28]  Joshua M Tebbs,et al.  Two‐Dimensional Informative Array Testing , 2012, Biometrics.

[29]  Wesley O Johnson,et al.  Identifiability of Models for Multiple Diagnostic Testing in the Absence of a Gold Standard , 2010, Biometrics.

[30]  Xianzheng Huang,et al.  An improved test of latent‐variable model misspecification in structural measurement error models for group testing data , 2009, Statistics in medicine.

[31]  R. Dorfman.  The Detection of Defective Members of Large Populations , 1943 .

[32]  Christopher S. McMahan,et al.  Informative Dorfman Screening , 2012, Biometrics.

[33]  Joshua M Tebbs,et al.  Group testing in heterogeneous populations by using halving algorithms , 2012, Journal of the Royal Statistical Society. Series C, Applied statistics.