Evaluating Data from Closely Related Clinical Trials


In the drug development process, clinical trials are conducted for different diseases or indications. Generally, the assessment of drug effectiveness is performed by only utilizing data from clinical trials within a particular indication. However, in some cases, different indications are closely related. They may be etiologically or pathophysiologically similar. Even if the indications are less closely related, the general purpose of therapy may be very similar. Evaluating data from all of these related studies together enables researchers to access the information, and give a systematic overview of the treatment effect in a broader scope. In this paper, we use an example in the allergy therapeutic area to illustrate a Bayesian approach to synthesizing evidence from trials aimed at closely related indications. This approach accounts for the heterogeneity of treatment effects across different indications as well as across different studies. It also allows us to quantify the treatment benefit difference between different indications in a more meaningful way. Demonstration of beneficial drug effects on different indications in the context of all related data can cross-substantiate a claim of effectiveness for each indication and hence strengthen the evidence of treatment efficacy.

This is a preview of subscription content, access via your institution.


  1. 1.

    Food and Drug Administration. Guidance for Industry-Providing Clinical Evidence of Effectiveness for Human Drugs and Biological Products. Bethesda, MD; US Department of Health and Human Services, Food and Drug Administration; 1998.

    Google Scholar 

  2. 2.

    Allen IE, Kupelnick B, Kumashiro M, Luo D, Ross S, Wolin M. Efficacy of Interleukin-2 in the treatment of metastatic melanoma: Systematic review and metaanalysis. Cancer Therapeut. 1998;3:168–173.

    Google Scholar 

  3. 3.

    Dersimonian R, Laird N. Meta-analysis in clinical trials. Controll Clin Trials. 1986;7:177–188.

    CAS  Article  Google Scholar 

  4. 4.

    Tweedie RZ, Mengersen KL. Lung cancer and passive smoking: Reconciling the biochemical and epidemiological approach. Br J Cancer. 1992;66:700–705.

    CAS  Article  Google Scholar 

  5. 5.

    Gelman A, Carlin JB, Stern HS, Rubin DB. Bayesian Data Analysis. New York, NY: Chapman & Hall; 1995.

    Book  Google Scholar 

  6. 6.

    Chalmers TC. Problems induced by meta-analysis. Stat Med. 1991;10:971–980.

    CAS  Article  Google Scholar 

  7. 7.

    DuMouchel W. Bayesian Meta-analysis. In: Berry D, ed. Statistical Methods for Pharmacology. New York, NY: Marcel Dekker, 1990:509–529.

    Google Scholar 

  8. 8.

    He Z, Sun D. Hierarchical Bayesian estimation of hunting success rates with spatial correlations. Biometrics. 2000;56:360–367.

    CAS  Article  Google Scholar 

  9. 9.

    Carlin JB. Meta-analysis for 2 x 2 tables: a Bayesian approach. Stat Med. 1992;11:141–158.

    CAS  Article  Google Scholar 

  10. 10.

    Ibrahim JG, Chen M. Prior distributions and Bayesian computation for proportional hazards models. Indian J Stat. 1998;60:48–64.

    Google Scholar 

  11. 11.

    Spiegelhalter DJ, Thomas A, Best N, Gilks WR. BUGS Examples, Version 0.50. Technical report. Cambridge, England: Institute of Public Health; 1995.

    Google Scholar 

  12. 12.

    Spiegelhalter DJ, Freedman LS, Darmar MK. Bayesian approaches to randomized trials. J Roy Stat Soc. 1994;357–416.

    Google Scholar 

  13. 13.

    Begg CB, Pilote L. A model for incorporating historic controls into a meta-analysis. Biometrics. 1991; 47:899–906.

    CAS  Article  Google Scholar 

  14. 14.

    Olkin I. Meta-analysis: methods for combining independent studies. Stat Sci. 1992;7:226.

    Article  Google Scholar 

  15. 15.

    Light R, Pillemer D. Summing Up: The Science of Reviewing Research. Cambridge, MA: Harvard University Press; 1984.

    Google Scholar 

  16. 16.

    Dural S, Tweedie R. Trim and fill: A simple funnel-plot-based method of testing and adjusting for publication bias in meta-analysis. Biometrics. 2000;56: 450–463.

    Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Dr. Steven Sun PHD.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Sun, S., Suresh, R. Evaluating Data from Closely Related Clinical Trials. Ther Innov Regul Sci 35, 1317–1326 (2001). https://doi.org/10.1177/009286150103500428

Download citation

Key Words

  • Meta-analysis
  • Clinical trials
  • Bayesian analysis
  • Hierarchical models
  • Random effects model