Evidence synthesis from aggregate recurrent event data for clinical trial design and analysis

Information from historical trials is important for the design, interim monitoring, analysis, and interpretation of clinical trials. Meta-analytic models can be used to synthesize the evidence from historical data, which are often only available in aggregate form. We consider evidence synthesis methods for trials with recurrent event endpoints, which are common in many therapeutic areas. Such endpoints are typically analyzed by negative binomial regression. However, the individual patient data necessary to fit such a model are usually unavailable for historical trials reported in the medical literature. We describe approaches for back-calculating model parameter estimates and their standard errors from available summary statistics with various techniques, including approximate Bayesian computation. We propose to use a quadratic approximation to the log-likelihood for each historical trial based on 2 independent terms for the log mean rate and the log of the dispersion parameter. A Bayesian hierarchical meta-analysis model then provides the posterior predictive distribution for these parameters. Simulations show this approach with back-calculated parameter estimates results in very similar inference as using parameter estimates from individual patient data as an input. We illustrate how to design and analyze a new randomized placebo-controlled exacerbation trial in severe eosinophilic asthma using data from 11 historical trials.

[1]  Jean-Michel Marin,et al.  Approximate Bayesian computational methods , 2011, Statistics and Computing.

[2]  W. Busse,et al.  Benralizumab, an anti-interleukin 5 receptor α monoclonal antibody, versus placebo for uncontrolled eosinophilic asthma: a phase 2b randomised dose-ranging study. , 2014, The Lancet. Respiratory medicine.

[3]  G R Wood Confidence and prediction intervals for generalised linear accident models. , 2005, Accident; analysis and prevention.

[4]  J. Lawless Negative binomial and mixed Poisson regression , 1987 .

[5]  J. Bird,et al.  Mepolizumab for Severe Eosinophilic Asthma (DREAM): A Multicentre, Double-Blind, Placebo-Controlled Trial , 2013, Pediatrics.

[6]  K Ulm,et al.  A simple method to calculate the confidence interval of a standardized mortality ratio (SMR) , 1990, American journal of epidemiology.

[7]  Andrew Gelman,et al.  General methods for monitoring convergence of iterative simulations , 1998 .

[8]  Brandon M. Turner,et al.  Hierarchical Approximate Bayesian Computation , 2013, Psychometrika.

[9]  J. L. Folks,et al.  Complete sufficiency and maximum likelihood estimation for the two-parameter negative binomial distribution , 1986 .

[10]  S. Willsie Mepolizumab for Prednisone-Dependent Asthma with Sputum Eosinophilia , 2010 .

[11]  I. Pavord,et al.  Mepolizumab treatment in patients with severe eosinophilic asthma. , 2015, The New England journal of medicine.

[12]  Ana Sousa,et al.  Mepolizumab and exacerbations of refractory eosinophilic asthma. , 2009, The New England journal of medicine.

[13]  Jiqiang Guo,et al.  Stan: A Probabilistic Programming Language. , 2017, Journal of statistical software.

[14]  Tim Friede,et al.  Meta‐analysis of two studies in the presence of heterogeneity with applications in rare diseases , 2016, Biometrical journal. Biometrische Zeitschrift.

[15]  A Whitehead,et al.  Borrowing strength from external trials in a meta-analysis. , 1996, Statistics in medicine.

[16]  Bradley P Carlin,et al.  Detecting outlying trials in network meta‐analysis , 2015, Statistics in medicine.

[17]  Tim Friede,et al.  Evidence synthesis for count distributions based on heterogeneous and incomplete aggregated data , 2013, Biometrical journal. Biometrische Zeitschrift.

[18]  M. Sydes,et al.  Practical methods for incorporating summary time-to-event data into meta-analysis , 2007, Trials.

[19]  D. Spiegelhalter,et al.  Summarizing historical information on controls in clinical trials , 2010, Clinical trials.

[20]  Gagandeep Kang,et al.  Analysis of human immune responses in quasi-experimental settings: tutorial in biostatistics , 2012, BMC Medical Research Methodology.

[21]  David J Spiegelhalter,et al.  A re-evaluation of random-effects meta-analysis , 2009, Journal of the Royal Statistical Society. Series A,.

[22]  Heinz Schmidli,et al.  Using historical control information for the design and analysis of clinical trials with overdispersed count data , 2013, Statistics in medicine.

[23]  Tim Friede,et al.  Meta‐analysis of few small studies in orphan diseases , 2016, Research synthesis methods.

[24]  E. W. Barnes The Asymptotic Expansion of Integral Functions Defined by Generalised Hypergeometric Series , 1907 .

[25]  J A Anderson,et al.  Statistical analysis of exacerbation rates in COPD: TRISTAN and ISOLDE revisited , 2008, European Respiratory Journal.

[26]  Daniel Jackson,et al.  A refined method for multivariate meta-analysis and meta-regression , 2013, Statistics in medicine.

[27]  F. Garwood,et al.  i) Fiducial Limits for the Poisson Distribution , 1936 .

[28]  Nicky J Welton,et al.  Evidence Synthesis for Decision Making in Healthcare , 2012 .

[29]  S J Pocock,et al.  The combination of randomized and historical controls in clinical trials. , 1976, Journal of chronic diseases.

[30]  Nicky J Welton,et al.  Enhanced secondary analysis of survival data: reconstructing the data from published Kaplan-Meier survival curves , 2012, BMC Medical Research Methodology.

[31]  I. Pavord,et al.  Oral glucocorticoid-sparing effect of mepolizumab in eosinophilic asthma. , 2014, The New England journal of medicine.

[32]  D. Berry,et al.  Bayesian Survival Analysis With Nonproportional Hazards , 2004 .

[33]  S. Wenzel,et al.  Dupilumab in persistent asthma with elevated eosinophil levels. , 2013, The New England journal of medicine.

[34]  Rebecca M Turner,et al.  Characteristics of meta-analyses and their component studies in the Cochrane Database of Systematic Reviews: a cross-sectional, descriptive analysis , 2011, BMC medical research methodology.

[35]  Nicky J Welton,et al.  Evidence Synthesis for Decision Making in Healthcare: Welton/Evidence Synthesis for Decision Making in Healthcare , 2012 .

[36]  Paul Marjoram,et al.  Markov chain Monte Carlo without likelihoods , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[37]  A. Gelman Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper) , 2004 .

[38]  Frank Bretz,et al.  Bayesian predictive power for interim adaptation in seamless phase II/III trials where the endpoint is survival up to some specified timepoint , 2007, Statistics in medicine.

[39]  M. Parmar,et al.  Extracting summary statistics to perform meta-analyses of the published literature for survival endpoints. , 1998, Statistics in medicine.

[40]  R. Maciuca,et al.  Lebrikizumab in moderate-to-severe asthma: pooled data from two randomised placebo-controlled studies , 2015, Thorax.

[41]  M. A. Best Bayesian Approaches to Clinical Trials and Health‐Care Evaluation , 2005 .

[42]  B. Holzhauer Meta‐analysis of aggregate data on medical events , 2017, Statistics in medicine.

[43]  William J. Browne,et al.  Bayesian and likelihood-based methods in multilevel modeling 1 A comparison of Bayesian and likelihood-based methods for fitting multilevel models , 2006 .

[44]  Theo Stijnen,et al.  Meta‐analysis of summary survival curve data , 2008, Statistics in medicine.

[45]  Krishna K. Saha Interval estimation of the over‐dispersion parameter in the analysis of one‐way layout of count data , 2011, Statistics in medicine.

[46]  T Friede,et al.  Blinded Sample Size Reestimation with Negative Binomial Counts in Superiority and Non-inferiority Trials , 2010, Methods of Information in Medicine.

[47]  Dipak D. Patil,et al.  COMPARISON OF CONFIDENCE INTERVALS FOR THE POISSON MEAN: SOME NEW ASPECTS , 2012 .

[48]  Anthony O'Hagan,et al.  Assurance in clinical trial design , 2005 .

[49]  Nicky J Welton,et al.  NICE DSU Technical Support Document 2: A Generalised Linear Modelling Framework for Pairwise and Network Meta-Analysis of Randomised Controlled Trials , 2011 .

[50]  Paula R Williamson,et al.  Aggregate data meta‐analysis with time‐to‐event outcomes , 2002, Statistics in medicine.

[51]  E. Bateman,et al.  Reslizumab for inadequately controlled asthma with elevated blood eosinophil counts: results from two multicentre, parallel, double-blind, randomised, placebo-controlled, phase 3 trials. , 2015, The Lancet. Respiratory medicine.

[52]  D. Moher,et al.  CONSORT 2010 Statement: updated guidelines for reporting parallel group randomised trials , 2010, BMC medicine.

[53]  O. Keene,et al.  Analysis of exacerbation rates in asthma and chronic obstructive pulmonary disease: example from the TRISTAN study , 2007, Pharmaceutical statistics.

[54]  C. Adams,et al.  The Leeds Evaluation of Efficacy of Detoxification Study (LEEDS) prisons project pilot study: protocol for a randomised controlled trial comparing dihydrocodeine and buprenorphine for opiate detoxification , 2007, Trials.

[55]  A. Cameron,et al.  Regression Analysis of Count Data by A. Colin Cameron , 2013 .

[56]  Anthony O'Hagan,et al.  Robust meta‐analytic‐predictive priors in clinical trials with historical control information , 2014, Biometrics.