Background The decision to initially implant an implantable cardioverter-defibrillator (ICD) is informed by robust randomized controlled trials, but no such data exist to guide the decision to replace an ICD generator. In this study, we aimed to determine outcomes after ICD generator replacement. Methods All patients with ischemic or nonischemic cardiomyopathy who underwent ICD generator replacement from 2001 to 2011 at Mayo Clinic, MN, or Beth Israel Deaconess Medical Center, MA, were included. Outcomes included (1) appropriate therapy after generator replacement and (2) death before appropriate therapy after generator replacement. Cox proportional hazards modeling was used to determine the associations between patient characteristics and outcomes. Results In 1421 patients undergoing ICD generator replacement (mean±SD age 69.6±12.1 years, 81% male), appropriate therapy occurred after replacement in 435 patients (30.6%) over a mean follow-up of 2.7±2.6 years. Associated factors included lower left ventricular ejection fraction and history of appropriate therapy before generator replacement. Death before appropriate ICD therapy occurred in 336 (23.7%) patients. Older age, lower left ventricular ejection fraction, and noncardiac comorbidities, including diabetes mellitus, chronic lung disease, peripheral vascular disease, lower hemoglobin, and lower glomerular filtration rate, were associated with greater risk of death before appropriate therapy. A progressive increase in mortality was observed with aggregation of these noncardiac comorbidities. Conclusions The decision to replace the ICD should take into consideration not only left ventricular ejection fraction and history of ventricular arrhythmias, but also comorbid illnesses that may impact the duration and the quality of life.