The hierarchical metaregression approach and learning from clinical evidence

The hierarchical metaregression (HMR) approach is a multiparameter Bayesian approach for meta-analysis, which generalizes the standard mixed effects models by explicitly modeling the data collection process in the meta-analysis. The HMR allows to investigate the potential external validity of experimental results as well as to assess the internal validity of the studies included in a systematic review. The HMR automatically identifies studies presenting conflicting evidence and it downweights their influence in the meta-analysis. In addition, the HMR allows to perform cross-evidence synthesis, which combines aggregated results from randomized controlled trials to predict effectiveness in a single-arm observational study with individual participant data (IPD). In this paper, we evaluate the HMR approach using simulated data examples. We present a new real case study in diabetes research, along with a new R package called jarbes (just a rather Bayesian evidence synthesis), which automatizes the complex computations involved in the HMR.

[1]  E. Chelimsky,et al.  Cross-design Synthesis: A New Form of Meta-analysis for Combining Results from Randomized Clinical Trials and Medical-practice Databases , 1993, International Journal of Technology Assessment in Health Care.

[2]  Dimitris Mavridis,et al.  Combining randomized and non‐randomized evidence in network meta‐analysis , 2017, Statistics in medicine.

[3]  Martyn Plummer,et al.  JAGS: A program for analysis of Bayesian graphical models using Gibbs sampling , 2003 .

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

[5]  Christian Ohmann,et al.  Combining randomized and non‐randomized evidence in clinical research: a review of methods and applications , 2015, Research synthesis methods.

[6]  Douglas G Altman,et al.  The effects of excluding patients from the analysis in randomised controlled trials: meta-epidemiological study , 2009, BMJ : British Medical Journal.

[7]  Sherri Rose,et al.  An Overview of Statistical Approaches for Comparative Effectiveness Research , 2017 .

[8]  C. Ohmann,et al.  Bayesian evidence synthesis for exploring generalizability of treatment effects: a case study of combining randomized and non‐randomized results in diabetes , 2016, Statistics in medicine.

[9]  Cynthia P Iglesias,et al.  A bias-adjusted evidence synthesis of RCT and observational data: the case of total hip replacement. , 2017, Health economics.

[10]  David G. Armstrong,et al.  Long-Term Prognosis of Diabetic Foot Patients and Their Limbs , 2012, Diabetes Care.

[11]  D. Spiegelhalter,et al.  Bayesian Approaches to Clinical Trials and Health-Care Evaluation: Spiegelhalter/Clinical Trials and Health-Care Evaluation , 2004 .

[12]  Bradley P Carlin,et al.  Incorporation of individual‐patient data in network meta‐analysis for multiple continuous endpoints, with application to diabetes treatment , 2015, Statistics in medicine.

[13]  David J Spiegelhalter,et al.  Bias modelling in evidence synthesis , 2009, Journal of the Royal Statistical Society. Series A,.

[14]  Pablo Emilio Verde,et al.  bamdit: An R Package for Bayesian Meta-Analysis of Diagnostic Test Data , 2018 .

[15]  S. Normand,et al.  Meta‐analysis of rate ratios with differential follow‐up by treatment arm: inferring comparative effectiveness of medical devices , 2015, Statistics in medicine.