Background and Aims Adenosquamous carcinoma of the pancreas (ASCP) is a rare exocrine malignant tumor, with a high malignancy grade and a poor prognosis after radical resection. However, the current prognostic model for pancreatic cancer based on TNM stage is not suitable for ASCP, and it is urgent to establish a prognostic model suitable for ASCP by combining with other clinical data. Therefore, this study was conducted to investigate the values of preoperative inflammatory- and immune-related indicators [neutrophil to lymphocyte ratio (NLR), platelet to lymphocyte ratio (PLR), lymphocyte to monocyte ratio (LMR), and systemic immune-inflammatory index (SII)] in postoperative prognostic evaluation of ASCP, and establish a prognostic model for ASCP.Methods Clinical data and follow-up records of 129 patients who underwent radical resection for ASCP in the Department of Hepatobiliary Pancreatic Surgery of Changhai Hospital Affiliated to the Naval Medical University of Chinese People's Liberation Army from September 2012 to September 2019 were retrospectively analyzed. The cutoff values of NLR, PLR, LMR and SII were determined by the minimum P-value method. The differences in prognosis between patients grouped based on the cut-off value of each indicator were compared, and the differences in baseline characteristics between high SII group and low SII group were selectively compared. The prognostic factors for patients were determined by univariate analysis and multivariate Cox regression analysis, and then a prognostic index (PI) model for prognosis prediction was established. The abilities to predict two-year survival of patients of the PI prediction model and TNM stage prediction model were analyzed and compared by the receiver operating characteristic (ROC) curve.Results The cutoff values of NLR, PLR, LMR and SII were 3.46, 85.5, 4.1 and 339.7, respectively. The differences in survival between patients grouped based on the cut-off value of each indicator were all statistically significant (all P<0.05). The proportions of cases with tumor located in the pancreatic head and cases with poorly differentiated tumor in high SII group were higher than those in low SII group (47.3% vs. 26.3%; 63.6% vs. 42.1%), but both differences did not reach a statistical significance (both P>0.05). Results of univariate variable analysis showed that T stage, N stage, tumor differentiation, tumor size, vessel tumor emboli, nerve invasion, NLR, PLR, LMR, and SII were all influencing factors for postoperative prognosis of ASCP patients (all P<0.05), and results multivariate Cox regression analysis revealed N stage, tumor differentiation, tumor size, nerve invasion, and SII were independent postoperative prognostic factors for ASCP patients (all P<0.05). The predictive efficacy of PI prediction model constructed based on these independent prognostic factors was superior to that of TNM stage prediction model (AUC: 0.779 vs. 0.625).Conclusions Preoperative NLR, PLR, LMR and SII are of great value in evaluating the postoperative overall survival of ASCP patients. The predictive efficacy of the PI prediction model constructed by integrating SII and other clinical factors has a better predictive efficacy.