Background and importance Interpretation of subgroup analysis (SA) is potentially important for treatment decisions in medical practice. SA can provide clinicians with a better perspective on the individualised treatment of patients. However, SA can introduce analytical challenges, which may result in denial of a beneficial treatment or even receiving a potentially harmful or ineffective treatment.
Aim and objectives The aim of this study was to assess the credibility of subgroup claims in haematology randomised clinical trials (RCT).
Material and methods A systematic review of Medline of haematology phase III RCT published between January 2013 and October 2019 was carried to identify SA reported. Claims of subgroup effect were classified according to their strength, as: strong claim, claim of a likely effect or suggestion of a possible effect based on the Sun et al 2009 classification. To evaluate the credibility of subgroup claims for RCT primary outcomes, ‘the 10 criteria for assessing the credibility of a subgroup claim’ by Sun et al 2012 were applied.
Results 98 studies reported SA. Of these, 24 RCT reported 46 claims of subgroup difference. 44 were claims for the primary outcome: 25 were strong claims, 17 suggestions of a possible effect and two claims of a likely effect. The authors included subgroup variables for the primary outcome measured at baseline for 38 claims (n=86.36%), used the subgroup variable as a stratification factor at randomisation for 15 (34.09%), clearly prespecified their hypothesis for 11 (25%), the subgroup effect was one of a small number of hypothesised effects tested for 17 (38.36%), carried out a test of interaction that was statistically significant for 18 (40.91%), documented replication of a subgroup effect with previously related studies for 11 (25%), identified consistency of a subgroup effect across related outcome for 10 (22.72%) and provided a biological rationale for the effect for 8 (18.18%). 34/44 claims for the primary outcome met 4 or fewer of the 10 credibility criteria.
Conclusion and relevance Subgroup claims reported in haematology RCT lack credibility, even when claims were strong. Subgroup analysis should be carried out because of the potential information they can provide but researchers should be more cautious before claiming the existence of a subgroup effect.
Conflict of interest No conflict of interest