Bayesian nonparametric ROC regression modeling

The receiver operating characteristic (ROC) curve is the most widely used measure for evaluating the discriminatory performance of a continuous biomarker. Incorporating covariates in the analysis can potentially enhance information gath- ered from the biomarker, as its discriminatory ability may depend on these. In this paper we propose a dependent Bayesian nonparametric model for conditional ROC estimation. Our model is based on dependent Dirichlet processes, where the covariate-dependent ROC curves are indirectly modeled using probability models for related probability distributions in the diseased and healthy groups. Our ap- proach allows for the entire distribution in each group to change as a function of the covariates, provides exact posterior inference up to a Monte Carlo error, and can easily accommodate multiple continuous and categorical predictors. Simula- tion results suggest that, regarding the mean squared error, our approach performs better than its competitors for small sample sizes and nonlinear scenarios. The proposed model is applied to data concerning diagnosis of diabetes.

[1]  K. Zou,et al.  Smooth non-parametric receiver operating characteristic (ROC) curves for continuous diagnostic tests. , 1997, Statistics in medicine.

[2]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[3]  Paul H. C. Eilers,et al.  Flexible smoothing with B-splines and penalties , 1996 .

[4]  Wesley O Johnson,et al.  Bayesian Nonparametric Nonproportional Hazards Survival Modeling , 2009, Biometrics.

[5]  J. Danesh,et al.  Diabetes mellitus, fasting blood glucose concentration, and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies. , 2010, Lancet.

[6]  Carmen Cadarso-Suárez,et al.  Comparative study of ROC regression techniques - Applications for the computer-aided diagnostic system in breast cancer detection , 2011, Comput. Stat. Data Anal..

[7]  A. Branscum,et al.  Multivariate mixtures of Polya trees for modeling ROC data , 2008 .

[8]  Javier Roca-Pardiñas,et al.  ROC curve and covariates: extending induced methodology to the non-parametric framework , 2011, Stat. Comput..

[9]  Sataya D. Dubey,et al.  Compound gamma, beta and F distributions , 1970 .

[10]  Tianxi Cai,et al.  Semi-parametric ROC regression analysis with placement values. , 2004, Biostatistics.

[11]  D. Blackwell,et al.  Ferguson Distributions Via Polya Urn Schemes , 1973 .

[12]  M. Escobar,et al.  Bayesian Density Estimation and Inference Using Mixtures , 1995 .

[13]  S. MacEachern,et al.  A semiparametric Bayesian model for randomised block designs , 1996 .

[14]  Peter Müller,et al.  Semiparametric Bayesian classification with longitudinal markers , 2007, Journal of the Royal Statistical Society. Series C, Applied statistics.

[15]  Correcting for confounding in analyzing receiver operating characteristic curves , 1996 .

[16]  Alejandro Jara,et al.  Applied Bayesian Non-and Semi-parametric Inference using DPpackage , 2007 .

[17]  Peter Müller,et al.  DPpackage: Bayesian Semi- and Nonparametric Modeling in R , 2011 .

[18]  L. Tardella,et al.  Approximating distributions of random functionals of Ferguson‐Dirichlet priors , 1998 .

[19]  J. Sethuraman.  A CONSTRUCTIVE DEFINITION OF DIRICHLET PRIORS , 1991 .

[20]  Wesley O Johnson,et al.  Bayesian semiparametric ROC curve estimation and disease diagnosis , 2008, Statistics in medicine.

[21]  Jaroslaw Harezlak,et al.  Comparison of bandwidth selection methods for kernel smoothing of ROC curves , 2002, Statistics in medicine.

[22]  Wenceslao González-Manteiga,et al.  ROC Curves in Non‐Parametric Location‐Scale Regression Models , 2011 .

[23]  Margaret Sullivan Pepe,et al.  Distribution-free ROC analysis using binary regression techniques. , 2002, Biostatistics.

[24]  Maria De Iorio,et al.  Bayesian semiparametric inference for multivariate doubly-interval-censored data , 2010, 1101.1415.

[25]  Alaattin Erkanli,et al.  Bayesian semi‐parametric ROC analysis , 2006, Statistics in medicine.

[26]  Jianqing Fan,et al.  Local polynomial modelling and its applications , 1994 .

[27]  M. Escobar,et al.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[28]  Athanasios Kottas,et al.  Modelling stochastic order in the analysis of receiver operating characteristic data: Bayesian non‐parametric approaches , 2008 .

[29]  S. MacEachern,et al.  An ANOVA Model for Dependent Random Measures , 2004 .

[30]  Liang Peng,et al.  Local linear smoothing of receiver operating characteristic (ROC) curves , 2004 .

[31]  Todd A Alonzo,et al.  Nonparametric Bayesian estimation of the three‐way receiver operating characteristic surface , 2011, Biometrical journal. Biometrische Zeitschrift.

[32]  M S Pepe,et al.  Three approaches to regression analysis of receiver operating characteristic curves for continuous test results. , 1998, Biometrics.

[33]  S. Wild,et al.  Global prevalence of diabetes: estimates for the year 2000 and projections for 2030. , 2004, Diabetes care.

[34]  E. Bedrick,et al.  Hypothesis Tests on Mixture Model Components with Applications in Ecology and Agriculture , 2010 .

[35]  S. MacEachern.  Estimating normal means with a conjugate style dirichlet process prior , 1994 .

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

[37]  Chris Lloyd,et al.  Using Smoothed Receiver Operating Characteristic Curves to Summarize and Compare Diagnostic Systems , 1998 .

[38]  The Emerging Risk Factors Collaboration.  Diabetes mellitus, fasting blood glucose concentration, and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies , 2010, The Lancet.

[39]  S. MacEachern,et al.  Estimating mixture of dirichlet process models , 1998 .

[40]  P. Green,et al.  On Bayesian Analysis of Mixtures with an Unknown Number of Components (with discussion) , 1997 .

[41]  Fernando A. Quintana,et al.  On the Support of MacEachern’s Dependent Dirichlet Processes and Extensions , 2012 .

[42]  David Faraggi,et al.  Adjusting receiver operating characteristic curves and related indices for covariates , 2003 .

[43]  B. Turnbull,et al.  NONPARAMETRIC AND SEMIPARAMETRIC ESTIMATION OF THE RECEIVER OPERATING CHARACTERISTIC CURVE , 1996 .