Systematic Review: Why sources of heterogeneity in meta-analysis should be investigated

Although meta-analysis is now well established as a method of reviewing evidence, an uncritical use of the technique can be very misleading. One common problem is the failure to investigate appropriately the sources of heterogeneity, in particular the clinical differences between the studies included. This paper distinguishes between the concepts of clinical and statistical heterogeneity and exemplifies the importance of investigating heterogeneity by using published meta-analyses of epidemiological studies of serum cholesterol concentration and clinical trials of its reduction. Although not without some dangers of speculative conclusions, prompted by overzealous inspection of the data to hand, a sensible investigation of sources of heterogeneity should increase both the scientific and the clinical relevance of the results of meta-analyses.

[1]  G H Guyatt,et al.  A Consumer's Guide to Subgroup Analyses , 1992, Annals of Internal Medicine.

[2]  A Whitehead,et al.  A general parametric approach to the meta-analysis of randomized clinical trials. , 1991, Statistics in medicine.

[3]  R F Galbraith,et al.  A note on graphical presentation of estimated odds ratios from several clinical trials. , 1988, Statistics in medicine.

[4]  S. Senn,et al.  IMPORTANCE OF TRENDS IN THE INTERPRETATION OF AN OVERALL ODDS RATIO IN THEMETA-ANALYSIS OF CLINICAL TRIALS. AUTHOR'S REPLY , 1994 .

[5]  S. Pocock,et al.  Does plasma cholesterol concentration predict mortality from coronary heart disease in elderly people? 18 year follow up in Whitehall study. , 1991, BMJ.

[6]  P. Easterbrook,et al.  Publication bias in clinical research , 1991, The Lancet.

[7]  Douglas G. Altman,et al.  Practical statistics for medical research , 1990 .

[8]  S. Pocock,et al.  The impact of stopping rules on heterogeneity of results in overviews of clinical trials. , 1992, Biometrics.

[9]  R. Collins,et al.  Blood pressure, stroke, and coronary heart disease Part 1, prolonged differences in blood pressure: prospective observational studies corrected for the regression dilution bias , 1990, The Lancet.

[10]  Earlybreastcancertrialistscol,et al.  Systemic treatment of early breast cancer by hormonal, cytotoxic, or immune therapy 133 randomised trials involving 31 000 recurrences and 24 000 deaths among 75 000 women , 1992, The Lancet.

[11]  N J Wald,et al.  By how much and how quickly does reduction in serum cholesterol concentration lower risk of ischaemic heart disease? , 1994, BMJ.

[12]  Anthony Howell,et al.  Systemic treatment of early breast cancer by hormonal, cytotoxic, or immune therapy. 133 randomised trials involving 31,000 recurrences and 24,000 deaths among 75,000 women. Early Breast Cancer Trialists' Collaborative Group. , 1992 .

[13]  U. Ravnskov,et al.  Cholesterol lowering trials in coronary heart disease: frequency of citation and outcome. , 1992, BMJ.

[14]  N. Laird,et al.  Meta-analysis in clinical trials. , 1986, Controlled clinical trials.

[15]  F. Song,et al.  Cholesterol lowering and mortality: the importance of considering initial level of risk. , 1993, BMJ.

[16]  J. Wittes,et al.  Analysis and interpretation of treatment effects in subgroups of patients in randomized clinical trials. , 1991, JAMA.

[17]  M. Parmar,et al.  Meta-analysis of the literature or of individual patient data: is there a difference? , 1993, The Lancet.

[18]  H Kragt,et al.  Importance of trends in the interpretation of an overall odds ratio in the meta-analysis of clinical trials. , 1992, Statistics in medicine.

[19]  R Peto,et al.  Why do we need systematic overviews of randomized trials? , 1987, Statistics in medicine.

[20]  K. Bailey,et al.  Inter-study differences: how should they influence the interpretation and analysis of results? , 1987, Statistics in medicine.

[21]  A Morabito,et al.  Prevention of First Bleeding in Cirrhosis , 1992, Annals of Internal Medicine.

[22]  Walker,et al.  Collaborative overview of randomised trials of antiplatelet therapy Prevention of death, myocardial infarction, and stroke by prolonged antiplatelet therapy in various categories of patients , 1994 .

[23]  J. Himes,et al.  Nutritional supplementation, psychosocial stimulation, and mental development of stunted children: the Jamaican Study , 1991, The Lancet.

[24]  T. Manolio,et al.  Cholesterol and heart disease in older persons and women. Review of an NHLBI workshop. , 1992, Annals of epidemiology.

[25]  K. Dickersin,et al.  Meta-analysis: state-of-the-science. , 1992, Epidemiologic reviews.

[26]  S. Pocock,et al.  Can meta-analyses be trusted? , 1991, The Lancet.

[27]  S G Thompson,et al.  Controversies in meta-analysis: the case of the trials of serum cholesterol reduction , 1993, Statistical methods in medical research.