Exploring Heterogeneity in Randomized Trials Via Meta-Analysis
- PDF / 1,068,890 Bytes
- 14 Pages / 504 x 720.24 pts Page_size
- 11 Downloads / 176 Views
Drug Information Journal, Vol. 33. pp. 211-224. 1999 Printed in h e USA. All rights reserved.
EXPLORING HETEROGENEITY IN RANDOMIZED TRIALS VIA META-ANALYSIS* CHRISTOPHER H.SCHMID,PHD Assistant Professor and Senior Statistician, Biostatistics Research Center, New England Medical Center and Tufts University School of Medicine, Boston, Massachusetts
Meta-analysis of clinical trials with heterogeneous results provides an opportunity to learn a great deal about variations in treatment effectiveness. Rather than computing a single summary estimate of a series of trials, it may be more informative to explore the effect that different study characteristics may make on treatment efficacy. Regression analysis offers a tool for these analyses. This paper outlines and applies hierarchical Bayesian models for this purpose, presenting two examples of mta-regression using summary data, in one of which results are compared with those from analysis of complete individual patient data. When covariates are not readily available, the event rate in the control group can become a surrogate covariate. An empirical study of 115 meta-analyses shows that this control rate is significantly correlated with the odds ratio about IS% of the time. This suggests that investigators should search for the causes of heterogeneity related to patient characteristics and treatment protocols to determine when treatment is most beneficial and that they should plan to study this heterogeneity in clinical trials. Key Words: Bayesian models; Control rate; Expectation-Maximization algorithm; Hierarchical models; Meta-regression
INTRODUCTION MEDICINE INCREASINGLY REQUIRES hard evidence in the form of a scientific study to support the implementation of a new practice or treatment. This drive toward evidencebased medicine has spawned a proliferation of randomized controlled trials (RCTs) and observational studies in clinical medicine.
*This work was supported by grant R01-HS08532 from the Agency for Health Care Policy and Research. Presented at the DIA Workshop “Global Statistical Challenges and Strategies in the Pharmaceutical Industry,” March 15-17, 1998, Hilton Head, South Carolina. Reprint address: Christopher H. Schmid. PhD, Assistant Professor and Senior Statistician, Biostatistics Research Center, New England Medical Center, Box 63, 750 Washington St., Boston, MA 021 1 1 .
The need to develop clear recommendations out of this wealth of information has placed a premium on the art of synthesizing the often disparate results of these studies. A variety of public and private organizations have set out to address this need. The federal Agency for Health Care Policy and Research (AHCPR) has set up 12 Evidence Based Practice Centers (EPCs) in the United States to facilitate the synthesis of information in topic areas. The international Cochrane Collaboration also promotes systematic reviews of medical research by sponsoring review groups of experts who conduct objective, scientific studies of the available data. These reviews, which often include the applica
Data Loading...
