Predictors of long-term mortality with cardiac resynchronization therapy in mild heart failure patients with left bundle branch block

Background Hypothesis Cardiac resynchronization therapy (CRT) is highly beneficial in patients with heart failure (HF) and left bundle branch block (LBBB); however, up to 30% of patients in this selected group are nonresponders. We hypothesized that clinical and echocardiographic variables can be used to develop a simple mortality risk stratification score in CRT. Methods Results Best-subsets proportional-hazards regression analysis was used to develop a simple clinical risk score for all-cause mortality in 756 patients with LBBB allocated to the CRT with defibrillator (CRT-D) group enrolled in the multicenter automatic defibrillator implantation trial with cardiac resynchronization therapy. The score was used to assess the mortality risk within the CRT-D group and the associations with mortality reduction with CRT-D vs implantable cardioverter defibrillator (ICD) in each risk category. Four clinical variables comprised the risk score: age >= 65, creatinine >= 1.4 mg/dL, history of coronary artery bypass graft, and left ventricular ejection fraction (LVEF) < 26%. Every 1 point increase in the score was associated with 2-fold increased mortality within the CRT-D arm (P < 0.001). CRT-D was associated with mortality reduction as compared with ICD only in patients with moderate risk: score 0 (HR = 0.80, P = 0.615), score 1 (HR = 0.54, P = 0.019), score 2 (HR = 0.54, P = 0.016), score 3-4 risk factors (HR = 1.08, P = 0.811); however, the device by score interaction was not significant (P = 0.306). The score was also significantly predictive of left ventricular reverse remodeling (P < 0.001). Conclusions Four clinical variables can be used for improved mortality risk stratification in mild HF patients with LBBB implanted with CRT-D.