Screening for coronary artery disease in patients with type 2 diabetes: a meta-analysis and trial sequential analysis

Objective To evaluate the efficacy of coronary artery disease screening in asymptomatic patients with type 2 diabetes and assess the statistical reliability of the findings. Methods Electronic databases (MEDLINE, EMBASE, Cochrane Library and clinicaltrials.org) were reviewed up to July 2016. Randomised controlled trials evaluating coronary artery disease screening in asymptomatic patients with type 2 diabetes and reporting cardiovascular events and/or mortality were included. Data were summarised with Mantel-Haenszel relative risk. Trial sequential analysis (TSA) was used to evaluate the optimal sample size to detect a 40% reduction in outcomes. Main outcomes were all-cause mortality and cardiac events (non-fatal myocardial infarction and cardiovascular death); secondary outcomes were non-fatal myocardial infarction, myocardial revascularisations and heart failure. Results One hundred thirty-five references were identified and 5 studies fulfilled the inclusion criteria and totalised 3315 patients, 117 all-cause deaths and 100 cardiac events. Screening for coronary artery disease was not associated with decrease in risk for all-cause deaths (RR 0.95(95% CI 0.66 to 1.35)) or cardiac events (RR 0.72(95% CI 0.49 to 1.06)). TSA shows that futility boundaries were reached for all-cause mortality and a relative risk reduction of 40% between treatments could be discarded. However, there is not enough information for firm conclusions for cardiac events. For secondary outcomes no benefit or harm was identified; optimal sample sizes were not reached. Conclusion Current available data do not support screening for coronary artery disease in patients with type 2 diabetes for preventing fatal events. Further studies are needed to assess the effects on cardiac events. PROSPERO CRD42015026627.