This retrospective single-center study evaluated adults with cardiogenic shock supported with veno-arterial extracorporeal membrane oxygenation (VA ECMO) from 2011 to 2023 to identify predictors of in-hospital mortality among those who survived to decannulation. Continuous and categorical variables were analyzed using Wilcoxon rank-sum test, chi-squared test, or Fisher’s exact tests. Poisson regression was used to identify independent predictors of mortality. Of 588 patients who received VA ECMO, 419 (71%) survived to decannulation. Of these, 320 (77%) survived to discharge, and 99 (23%) died post-decannulation. Patients who died were older (66 vs. 60 years; p < 0.001) and more likely to have chronic kidney disease (42% vs. 27%; p = 0.003), hypertension (79% vs. 67%; p = 0.028), and prior stroke (14% vs. 6.6%; p = 0.017). Extracorporeal membrane oxygenation duration was longer (4.9 vs. 3.9 days; p = 0.013), and Impella use was more frequent (24% vs. 16%; p = 0.049). The leading cause of death was withdrawal of care (42%). Age, extracorporeal cardiopulmonary resuscitation (ECPR), and post-cardiotomy shock were the only independent predictors of in-hospital mortality (relative risk [RR], 1.06; 95% confidence interval [CI], 1.01–1.10; p = 0.010). Nearly one in four patients who survived ECMO decannulation died before discharge. Older age, longer time on ECMO, and comorbidities were more prevalent among non-survivors. These findings underscore the need for improved post-decannulation risk stratification.