Factors related to the selection of surgical versus percutaneous revascularization in diabetic patients with multivessel coronary artery disease in the BARI 2D (Bypass Angioplasty Revascularization Investigation in Type 2 Diabetes) trial

Abstract

Objectives: We evaluated demographic, clinical, and angiographic factors influencing the selection of coronary artery bypass graft (CABG) surgery versus percutaneous coronary intervention (PCI) in diabetic patients with multivessel coronary artery disease (CAD) in the BARI 2D (Bypass Angioplasty Revascularization Investigation in Type 2 Diabetes) trial.

Background: Factors guiding selection of mode of revascularization for patients with diabetes mellitus and multivessel CAD are not clearly defined.

Methods: In the BARI 2D trial, the selected revascularization strategy, CABG or PCI, was based on physician discretion, declared independent of randomization to either immediate or deferred revascularization if clinically warranted. We analyzed factors favoring selection of CABG versus PCI in 1,593 diabetic patients with multivessel CAD enrolled between 2001 and 2005.

Results: Selection of CABG over PCI was declared in 44% of patients and was driven by angiographic factors including triple vessel disease (odds ratio [OR]: 4.43), left anterior descending stenosis >or=70% (OR: 2.86), proximal left anterior descending stenosis >or=50% (OR: 1.78), total occlusion (OR: 2.35), and multiple class C lesions (OR: 2.06) (all p < 0.005). Nonangiographic predictors of CABG included age >or=65 years (OR: 1.43, p = 0.011) and non-U.S. region (OR: 2.89, p = 0.017). Absence of prior PCI (OR: 0.45, p < 0.001) and the availability of drug-eluting stents conferred a lower probability of choosing CABG (OR: 0.60, p = 0.003).

Conclusions: The majority of diabetic patients with multivessel disease were selected for PCI rather than CABG. Preference for CABG over PCI was largely based on angiographic features related to the extent, location, and nature of CAD, as well as geographic, demographic, and clinical factors. (Bypass Angioplasty Revascularization Investigation in Type 2 Diabetes [BARI 2D]; NCT00006305).

Figure 1. Multivessel CAD Patients Selected for CABG within Clinical Site by Region

Percentage of CABG-intended patients per site for US sites versus non-US sites. Q1 = first quartile; Q3 = third quartile; Med = median.

Figure 2. Likelihood of Intended CABG by Myocardial Jeopardy Index in US and non-US Sites

Percentage of CABG-intended patients by myocardial jeopardy index (MJI) quartiles in US and non-US regions, among patients without prior PCI (n=1308). Note that for each quartile of MJI, non-US patients were more likely to be selected for CABG.

Figure 3. Adjusted Odds Ratio of CABG Selection

Plot of independent predictors of the selection of CABG over PCI in diabetic patients with stable multivessel coronary disease. The red rectangles depict adjusted odds ratios; the horizontal lines depict the 95% confidence interval.