Constructing common cohorts from trials with overlapping eligibility criteria: implications for comparing effect sizes between trials
- PMID: 19737845
- PMCID: PMC3254056
- DOI: 10.1177/1740774509344440
Constructing common cohorts from trials with overlapping eligibility criteria: implications for comparing effect sizes between trials
Abstract
Background: Comparing findings from separate trials is necessary to choose among treatment options, however differences among study cohorts may impede these comparisons.
Purpose: As a case study, to examine the overlap of study cohorts in two large randomized controlled clinical trials that assess interventions to reduce risk of major cardiovascular disease events in adults with type 2 diabetes in order to explore the feasibility of cross-trial comparisons
Methods: The Action for Health in Diabetes (Look AHEAD) and The Action to Control Cardiovascular Risk in Diabetes (ACCORD) trials enrolled 5145 and 10,251 adults with type 2 diabetes, respectively. Look AHEAD assesses the efficacy of an intensive lifestyle intervention designed to produce weight loss; ACCORD tests pharmacological therapies for control of glycemia, hyperlipidemia, and hypertension. Incidence of major cardiovascular disease events is the primary outcome for both trials. A sample was constructed to include participants from each trial who appeared to meet eligibility criteria and be appropriate candidates for the other trial's interventions. Demographic characteristics, health status, and outcomes of members and nonmembers of this constructed sample were compared.
Results: Nearly 80% of Look AHEAD participants were projected to be ineligible for ACCORD; ineligibility was primarily due to better glycemic control or no early history of cardiovascular disease. Approximately 30% of ACCORD participants were projected to be ineligible for Look AHEAD, often for reasons linked to poorer health. The characteristics of participants projected to be jointly eligible for both trials continued to reflect differences between trials according to factors likely linked to retention, adherence, and study outcomes.
Limitations: Accurate ascertainment of cross-trial eligibility was hampered by differences between protocols.
Conclusions: Despite several similarities, the Look AHEAD and ACCORD cohorts represent distinct populations. Even within the subsets of participants who appear to be eligible and appropriate candidates for trials of both modes of intervention, differences remained. Direct comparisons of results from separate trials of lifestyle and pharmacologic interventions are compromised by marked differences in enrolled cohorts.
References
-
- Longford NT. Selection bias and treatment heterogeneity in clinical trials. Statist Med. 1999;30:1467–74. - PubMed
-
- Tishler CL, Bartholomae S, Rhodes AR. Personality profiles of normal healthy research volunteers: a potential concern for clinical drug trial investigators? Med Hypoth. 2005;65:1–7. - PubMed
-
- Look AHEAD Research Group. Look AHEAD: Action for Health in Diabetes. Design and methods for a clinical trial of weight loss for the prevention of cardiovascular disease in type 2 diabetes. Controlled Clin Trials. 2003;24:610–28. - PubMed
-
- Buse JB, Bigger JT, Byington RP, et al. Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial: design and methods. Am J Cardiol. 2007;99:21i–33i. - PubMed
Publication types
MeSH terms
Substances
Grants and funding
- DK57078/DK/NIDDK NIH HHS/United States
- U01 DK057151/DK/NIDDK NIH HHS/United States
- U01 DK057135/DK/NIDDK NIH HHS/United States
- U01 DK057219/DK/NIDDK NIH HHS/United States
- U01 DK057154/DK/NIDDK NIH HHS/United States
- DK57002/DK/NIDDK NIH HHS/United States
- U01 DK057182/DK/NIDDK NIH HHS/United States
- U01 DK057136/DK/NIDDK NIH HHS/United States
- DK57178/DK/NIDDK NIH HHS/United States
- U01 DK057177/DK/NIDDK NIH HHS/United States
- DK57135/DK/NIDDK NIH HHS/United States
- N01-HC-957179/HC/NHLBI NIH HHS/United States
- DK56992/DK/NIDDK NIH HHS/United States
- N01 HC095184/HL/NHLBI NIH HHS/United States
- DK57151/DK/NIDDK NIH HHS/United States
- Y01 HC001010/HC/NHLBI NIH HHS/United States
- DK57171/DK/NIDDK NIH HHS/United States
- DK57131/DK/NIDDK NIH HHS/United States
- DK57149/DK/NIDDK NIH HHS/United States
- U01 DK056992/DK/NIDDK NIH HHS/United States
- U01-DK057136-08S1/DK/NIDDK NIH HHS/United States
- N01 HC095178/HL/NHLBI NIH HHS/United States
- U01 DK057171/DK/NIDDK NIH HHS/United States
- Y01 HC009035/HC/NHLBI NIH HHS/United States
- N01 HC095181/HL/NHLBI NIH HHS/United States
- IAA #Y-HC-1010/HC/NHLBI NIH HHS/United States
- DK57182/DK/NIDDK NIH HHS/United States
- U01 DK057002/DK/NIDDK NIH HHS/United States
- N01-HC-95184/HC/NHLBI NIH HHS/United States
- N01 HC095182/HL/NHLBI NIH HHS/United States
- U01 DK057078/DK/NIDDK NIH HHS/United States
- DK57008/DK/NIDDK NIH HHS/United States
- N01-HC-95182/HC/NHLBI NIH HHS/United States
- N01 HC095183/HL/NHLBI NIH HHS/United States
- N01-HC-95183/HC/NHLBI NIH HHS/United States
- U01 DK057131/DK/NIDDK NIH HHS/United States
- ImNIH/Intramural NIH HHS/United States
- DK57136/DK/NIDDK NIH HHS/United States
- N01-HC-95178/HC/NHLBI NIH HHS/United States
- DK57154/DK/NIDDK NIH HHS/United States
- DK57219/DK/NIDDK NIH HHS/United States
- DK57177/DK/NIDDK NIH HHS/United States
- U01 DK056990/DK/NIDDK NIH HHS/United States
- U01 DK057178/DK/NIDDK NIH HHS/United States
- IAA #Y1-HC-9035/HC/NHLBI NIH HHS/United States
- U01 DK057008/DK/NIDDK NIH HHS/United States
- DK56990/DK/NIDDK NIH HHS/United States
- N01-HC-95181/HC/NHLBI NIH HHS/United States
- U01 DK057149/DK/NIDDK NIH HHS/United States
LinkOut - more resources
Full Text Sources
Research Materials