Objectives: We here attempted to evaluate the prediction of different "ABO" blood groups for postsurgical gastric cancer-specific mortality by using data from the ongoing Fujian prospective investigation of cancer (FIESTA) study. Methods: Initially, a total of 3413 patients with gastric cancer were consecutively enrolled between January 2000 and December 2010 to receive radical gastrectomy, and they were followed up until December 2015. Study patients were divided into the "O+" group and the blood type "O-" group. Results: Of 2781 eligible patients, 1116 (40.1%) were in the "O+" group and 1665 (59.9%) in the "O-" group, with mortality rate of being 45.0% (n = 502) and 45.3% (n = 755), respectively. A 1: 1 propensity score match between the "O+" and the "O-" groups was used. After adjustment, neutrophil-lymphocyte ratio (NLR), lymphocyte-monocyte ratio (LMR), high total cholesterol and high low-density lipoprotein cholesterol, had non-overlapping 95% confidence intervals between the "O+" and the "O-" groups and simultaneously had detectable statistical significance in either group only. A forward method in the multivariate-adjusted COX model was employed and there were five shared risk factors between both groups, including diabetes mellitus, low high-density lipoprotein cholesterol, regional lymph node metastasis, tumor size and TNM stage. Further nomogram plot revealed that presurgical risk factors selected can better predict the risk of early gastric cancer-specific mortality (C-index: 0.737 for the "O-" group and 0.751 for the "O+" group). Conclusions: Our findings indicated that the prognostic factors differed between postsurgical gastric cancer patients with "O+" and "O-" blood types.