BACKGROUND: Hospitalized infants requiring cardiopulmonary resuscitation (CPR) represent a high-risk group. Recent data on risk factors for mortality following CPR in this population are lacking. AIMS: We hypothesized that infant demographic characteristics, diagnoses, and levels of cardiopulmonary support at the time of CPR requirement would be associated with survival to hospital discharge following CPR. STUDY DESIGN: Retrospective cohort study. SUBJECTS: All infants receiving CPR on day of life 2 to 120 admitted to 348 Pediatrix Medical Group neonatal intensive care units from 1997 to 2012. OUTCOMES MEASURES: We collected data on demographics, interventions, center volume, and death prior to NICU discharge. We evaluated predictors of death after CPR using multivariable logistic regression with generalized estimating equations to account for clustering of the data by center. RESULTS: Our cohort consisted of 2231 infants receiving CPR. Of these, 1127 (51%) survived to hospital discharge. Lower gestational age, postnatal age, 5-min APGAR, congenital anomaly, and markers of severity of illness were associated with higher mortality. Mortality after CPR did not change significantly over time (Cochran-Armitage test for trend p=0.35). CONCLUSIONS: Mortality following CPR in infants is high, particularly for less mature, younger infants with congenital anomalies and those requiring cardiopulmonary support prior to CPR. Continued focus on at risk infants may identify targets for CPR prevention and improve outcomes.