The aim of this systematic review and meta-analysis was to examine the association between sarcopenia and all-cause mortality among community-dwelling older people. A systematic review was performed using three electronic databases (EMBASE, MEDLINE and the Cochrane Library) to identify prospective cohort studies from January 2009 to February 2017 examining sarcopenia as a predictor of all-cause mortality among community-dwelling older people. We conducted a pooled analysis of mortality associated with sarcopenia, and subgroup analyses based on measurements of muscle mass and length of follow-up by employing a random-effects model. Sensitivity analyses were performed evaluate the cause of high heterogeneity. In addition, methodological quality, heterogeneity and publication bias were evaluated. Of 1703 studies identified, 6 studies incorporating 7367 individuals were included in the meta-analysis for all-cause mortality. The pooled hazard ratios (HRs) of all-cause mortality from the combination of included studies suggested participants with sarcopenia had a significantly higher rate of mortality (pooled HR 1.60, 95%CI 1.24-2.06, I2=27.8%, p=0.216) than participants without sarcopenia. The subgroup analysis for length of follow-up suggested studies with a follow-up period of less than 5 years found a higher risk of all-cause mortality (pooled HR 2.09, 95%CI 1.21-3.60) than studies with a follow-up period of 5 years or more (pooled HR 1.52, 95%CI 1.14-2.01). A subgroup of anthropometric measures was found to identify higher mortality risks (pooled HR 2.26, 95%CI 1.30-3.92) than a subgroup of dual-energy x-ray (DXA) absorptiometry (pooled HR 1.82, 95%CI 1.04-3.18) factors or a subgroup of bioelectrical impedance analysis (BIA) factors (pooled HR 1.31, 95%CI 1.15-1.49). Sarcopenia is a predictor of all-cause mortality among community-dwelling older people. Therefore, it is important to diagnose sarcopenia and to intervene, in order to reduce mortality rates in the elderly.