Flexible Bayesian additive joint models with an application to type 1 diabetes research

The joint modeling of longitudinal and time-to-event data is an important tool of growing popularity to gain insights into the association between a biomarker and an event process. We develop a general framework of flexible additive joint models that allows the specification of a variety of effects, such as smooth nonlinear, time-varying and random effects, in the longitudinal and survival parts of the models. Our extensions are motivated by the investigation of the relationship between fluctuating disease-specific markers, in this case autoantibodies, and the progression to the autoimmune disease type 1 diabetes. Using Bayesian P-splines, we are in particular able to capture highly nonlinear subject-specific marker trajectories as well as a time-varying association between the marker and event process allowing new insights into disease progression. The model is estimated within a Bayesian framework and implemented in the R-package bamlss.

[1]  J. Ibrahim,et al.  A Bayesian semiparametric joint hierarchical model for longitudinal and survival data. , 2003, Biometrics.

[2]  E. Bonifacio,et al.  Primary Dietary Intervention Study to Reduce the Risk of Islet Autoimmunity in Children at Increased Risk for Type 1 Diabetes , 2011, Diabetes Care.

[3]  An-Min Tang,et al.  Semiparametric Bayesian inference on skew–normal joint modeling of multivariate longitudinal and survival data , 2015, Statistics in medicine.

[4]  Stefan Lang,et al.  Simultaneous selection of variables and smoothing parameters in structured additive regression models , 2008, Comput. Stat. Data Anal..

[5]  Robin Henderson,et al.  Joint modelling of repeated measurements and time-to-event outcomes: flexible model specification and exact likelihood inference , 2014, Journal of the Royal Statistical Society. Series B, Statistical methodology.

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

[7]  Hedi Peterson,et al.  AIRE-Deficient Patients Harbor Unique High-Affinity Disease-Ameliorating Autoantibodies , 2016, Cell.

[8]  Nadja Klein,et al.  Bayesian structured additive distributional regression for multivariate responses , 2015 .

[9]  J. Ibrahim,et al.  A Flexible B‐Spline Model for Multiple Longitudinal Biomarkers and Survival , 2005, Biometrics.

[10]  Clifford M. Hurvich,et al.  Smoothing parameter selection in nonparametric regression using an improved Akaike information criterion , 1998 .

[11]  D. Rizopoulos,et al.  Impact of longitudinal exposure to mycophenolic acid on acute rejection in renal-transplant recipients using a joint modeling approach. , 2013, Pharmacological research.

[12]  Anastasios A. Tsiatis,et al.  Joint Modeling of Longitudinal and Time-to-Event Data : An Overview , 2004 .

[13]  E. Bonifacio.  Predicting Type 1 Diabetes Using Biomarkers , 2015, Diabetes Care.

[14]  Xiao Song,et al.  Semiparametric Approaches for Joint Modeling of Longitudinal and Survival Data with Time‐Varying Coefficients , 2008, Biometrics.

[15]  S. Wood.  Generalized Additive Models: An Introduction with R , 2006 .

[16]  S. Wood.  Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models , 2011 .

[17]  E. Bonifacio,et al.  Autoantibody appearance and risk for development of childhood diabetes in offspring of parents with type 1 diabetes: the 2-year analysis of the German BABYDIAB Study. , 1999, Diabetes.

[18]  Geert Verbeke,et al.  A Two‐Part Joint Model for the Analysis of Survival and Longitudinal Binary Data with Excess Zeros , 2008, Biometrics.

[19]  B. Berkhout,et al.  Has the Rate of CD4 Cell Count Decline before Initiation of Antiretroviral Therapy Changed over the Course of the Dutch HIV Epidemic among MSM? , 2013, PloS one.

[20]  D. Thomas,et al.  Simultaneously modelling censored survival data and repeatedly measured covariates: a Gibbs sampling approach. , 1996, Statistics in medicine.

[21]  Ana-Maria Staicu,et al.  Functional Additive Mixed Models , 2012, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[22]  Alan Y. Chiang,et al.  Generalized Additive Models: An Introduction With R , 2007, Technometrics.

[23]  F. Harrell,et al.  Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors , 2005 .

[24]  Bradley P. Carlin,et al.  Multilevel Bayesian Models for Survival Times and Longitudinal Patient-Reported Outcomes With Many Zeros , 2012 .

[25]  Dimitris Rizopoulos,et al.  A Bayesian semiparametric multivariate joint model for multiple longitudinal outcomes and a time‐to‐event , 2011, Statistics in medicine.

[26]  Matthias Schmid,et al.  Boosting joint models for longitudinal and time‐to‐event data , 2016, Biometrical journal. Biometrische Zeitschrift.

[27]  Dimitris Rizopoulos,et al.  The R Package JMbayes for Fitting Joint Models for Longitudinal and Time-to-Event Data using MCMC , 2014, 1404.7625.

[28]  Jane-Ling Wang,et al.  Modeling Longitudinal Data with Nonparametric Multiplicative Random Effects Jointly with Survival Data , 2008, Biometrics.

[29]  L. Fahrmeir,et al.  PENALIZED STRUCTURED ADDITIVE REGRESSION FOR SPACE-TIME DATA: A BAYESIAN PERSPECTIVE , 2004 .

[30]  Geoff Jones,et al.  Book Review: Joint Models for Longitudinal and Time-to-Event Data: With Applications in R, by Dimitris Rizopoulos , 2013 .

[31]  Naisyin Wang,et al.  Modelling short‐ and long‐term characteristics of follicle stimulating hormone as predictors of severe hot flashes in the Penn Ovarian Aging Study , 2015, Journal of the Royal Statistical Society. Series C, Applied statistics.

[32]  M. Rewers,et al.  Age of Islet Autoantibody Appearance and Mean Levels of Insulin, but Not GAD or IA-2 Autoantibodies, Predict Age of Diagnosis of Type 1 Diabetes , 2011, Diabetes Care.

[33]  Xingqiu Zhao,et al.  Bayesian variable selection and estimation in semiparametric joint models of multivariate longitudinal and survival data , 2017, Biometrical journal. Biometrische Zeitschrift.

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

[35]  Ralf Bender,et al.  Generating survival times to simulate Cox proportional hazards models , 2005, Statistics in medicine.

[36]  E. Bonifacio,et al.  Predictors of Progression From the Appearance of Islet Autoantibodies to Early Childhood Diabetes: The Environmental Determinants of Diabetes in the Young (TEDDY) , 2015, Diabetes Care.

[37]  S. Wood,et al.  Smoothing Parameter and Model Selection for General Smooth Models , 2015, 1511.03864.

[38]  Å. Lernmark,et al.  Staging Presymptomatic Type 1 Diabetes: A Scientific Statement of JDRF, the Endocrine Society, and the American Diabetes Association , 2015, Diabetes Care.

[39]  E. Brown,et al.  ASSESSING THE ASSOCIATION BETWEEN TRENDS IN A BIOMARKER AND RISK OF EVENT WITH AN APPLICATION IN PEDIATRIC HIV/AIDS. , 2009, The annals of applied statistics.

[40]  Joseph G Ibrahim,et al.  Joint modeling of survival and longitudinal non‐survival data: current methods and issues. Report of the DIA Bayesian joint modeling working group , 2015, Statistics in medicine.

[41]  A. Ziegler,et al.  On the appearance of islet associated autoimmunity in offspring of diabetic mothers: a prospective study from birth , 1993, Diabetologia.

[42]  E. Bonifacio,et al.  Seroconversion to multiple islet autoantibodies and risk of progression to diabetes in children. , 2013, JAMA.

[43]  Yongseok Park,et al.  Real‐Time Individual Predictions of Prostate Cancer Recurrence Using Joint Models , 2013, Biometrics.

[44]  Xihong Lin,et al.  Semiparametric Modeling of Longitudinal Measurements and Time‐to‐Event Data–A Two‐Stage Regression Calibration Approach , 2008, Biometrics.

[45]  S. Lang,et al.  Bayesian P-Splines , 2004 .

[46]  J. Ramsay,et al.  The historical functional linear model , 2003 .

[47]  Lei Liu,et al.  Joint modeling longitudinal semi‐continuous data and survival, with application to longitudinal medical cost data , 2009, Statistics in medicine.

[48]  Ciprian M Crainiceanu,et al.  Variable-Domain Functional Regression for Modeling ICU Data , 2014, Journal of the American Statistical Association.

[49]  E. Bonifacio,et al.  Brief Communication: Early Appearance of Islet Autoantibodies Predicts Childhood Type 1 Diabetes in Offspring of Diabetic Parents , 2004, Annals of Internal Medicine.

[50]  Bradley P Carlin,et al.  Separate and Joint Modeling of Longitudinal and Event Time Data Using Standard Computer Packages , 2004 .

[51]  Bradley P. Carlin,et al.  Combining Dynamic Predictions From Joint Models for Longitudinal and Time-to-Event Data Using Bayesian Model Averaging , 2013, 1303.2797.

[52]  Achim Zeileis,et al.  BAMLSS: Bayesian Additive Models for Location, Scale, and Shape (and Beyond) , 2018, Journal of Computational and Graphical Statistics.

[53]  Michael J Crowther,et al.  Simulating biologically plausible complex survival data , 2013, Statistics in medicine.

[54]  Nadja Klein,et al.  Bayesian structured additive distributional regression with an application to regional income inequality in Germany , 2015, 1509.05230.

[55]  Dimitris Rizopoulos,et al.  Joint Models for Longitudinal and Time-to-Event Data: With Applications in R , 2012 .