Reviewed and revised 26 August 2015
- Subgroup analysis involves assessing an association between an intervention (or other factor) and a subset of the patients that were exposed
- Subgroup analysis can be decided upon a priori or performed post hoc
- identification of associations within particular subgroups is the usual method of investigation in observational studies
RANDOMISED CONTROL TRIALS
- an RCT provides a comparison of the test subjects and the controls
- when there is particular interest in the results of treatment in a certain section of trial participants, a subgroup analysis is performed
- subgroups are examined to see if they are liable to a greater benefit or risk from treatment
- subgroup analysis is often unreliable due to problems of multiplicity and small numbers of patients studied
- inferences based on comparisons between subgroups in RCTs must be approached more cautiously than those based on the main comparison
- false positive or false negative effects
- chance differences in observed effects
- lack of power to perform the analysis
- floor or ceiling effects
- issues relating to multiple statistical testing (if enough subroup analyses are performed one will eventually be postive by chance alone!)
- over-reporting and under-reporting
- Industry funded randomised controlled trials, in the absence of statistically significant primary outcomes, are more likely to report subgroup analyses than non-industry funded trials
CREDIBILITY OF A SUBGROUP ANALYSIS FINDING
The result is more credible when the claim meets the following:
- comes from a within-study comparison
- has a significant interaction
- is unequivocally specified a priori
- is one of a small number of hypotheses tested
- presents a large difference of effects
- is supported by the external evidence, and
- has compelling biological rationale
- subgroup analysis results derived from a sound clinical trial are not necessarily valid
- do not accept the validity of subgroup analysis results without due consideration
- subgroup analyses are generally considered hypothesis generating rather than practice changing
References and Links
- Cook DI, Gebski VJ, Keech AC. Subgroup analysis in clinical trials. Med J Aust. 2004 Mar 15;180(6):289-91. PMID: 15012568.
- Guillemin F. Primer: the fallacy of subgroup analysis. Nat Clin Pract Rheumatol. 2007 Jul;3(7):407-13. PMID: 17599075.
- Rothwell PM. Treating individuals 2. Subgroup analysis in randomised controlled trials: importance, indications, and interpretation. Lancet. 2005 Jan 8-14;365(9454):176-86. PMID: 15639301.
- Sun X et al. The influence of study characteristics on reporting of subgroup analyses in randomised controlled trials: systematic review. BMJ. 2011 Mar 28;342:d1569. PMC6173170.
- Sun X, Briel M, Walter SD, Guyatt GH. Is a subgroup effect believable? Updating criteria to evaluate the credibility of subgroup analyses. BMJ. 2010 Mar 30;340:c117. PMID: 20354011.
- Study to Prospectively Evaluate Reamed Intramedullary Nails in Tibial Fractures (SPRINT) Investigators. Is a subgroup claim believable? A user’s guide to subgroup analyses in the surgical literature. J Bone Joint Surg Am. 2011 Feb 2;93(3):e8. PMC3028449.
- Yusuf S, Wittes J, Probstfield J, Tyroler HA. Analysis and interpretation of treatment effects in subgroups of patients in randomized clinical trials. JAMA. 1991 Jul 3;266(1):93-8. PMID: 2046134.