Cardiac rehabilitation (CR) is a promising therapeutic option for chronic heart failure (HF). However, the extent to which early rehabilitation is beneficial for patients receiving critical care remains controversial. This study examined the association between the early initiation of CR and the short-term clinical outcomes of patients admitted to the intensive care unit (ICU) with acute HF. We used the Diagnosis Procedure Combination database, a nationwide inpatient database in Japan, and included patients with acute HF admitted to the ICU within 2days after hospital admission. We defined the early initiation of CR as its initiation within 2days of hospital admission. We performed an overlap weighting based on the propensity scores and inverse probability of treatment weighting analysis to compare the clinical outcomes between patients with and without early initiation of CR. Among 25,362 eligible patients, 3,582 (14.1%) received an early initiation of CR. Overlap weighting created well-balanced cohorts, which showed that the early initiation of CR was related to lower in-hospital mortality (odds ratio [OR] 0.81, 95% confidence interval [CI] 0.68 to 0.96) and shorter hospital stay. The inverse probability of treatment weighting analysis also showed that in-hospital mortality was lower in the patients with the early initiation of CR (OR 0.80, 95% CI 0.67 to 0.96). The instrumental variable analysis also demonstrated the association of the early initiation of CR with lower in-hospital mortality (OR 0.64, 95% CI 0.44 to 0.93). In conclusion, early initiation of CR after hospital admission was associated with better short-term outcomes in patients with acute HF admitted to the ICU, suggesting the potential of the early administration of CR for acute HF requiring intensive care.