Objective To investigate the predictive value of preoperative platelet-to-lymphocyte ratio (PLR) combined with neutrophil-to-lymphocyte ratio (NLR) in the prognosis of patients with epithelial ovarian tumor debulking.Methods The clinical data of 192 patients with epithelial ovarian tumor debulking who were treated in the hospital from January 2016 to March 2020 were retrospectively analyzed, and the levels of PLR and NLR 7 days before surgery were recorded. The patients were followed up for 2 years after operation, and the patients were recorded as the recurrence group and the non-recurrence group according to whether the patients had recurrence or not. Risk factors for postoperative recurrence of epithelial ovarian tumors was analyzed. Receiver operating characteristic curve (ROC) was used to analyze the predictive value of preoperative PLR, NLR, and their combination on postoperative recurrence of epithelial ovarian tumors. Based on the regression coefficients of the above-mentioned independent risk factors, a risk assessment model for postoperative recurrence of epithelial ovarian tumors was constructed.Results As of the end of follow-up, 74 of 192 patients with epithelial ovarian tumor debulking had recurrence, and the remaining 118 patients had no recurrence. Stage Ⅲ, lymph node metastasis, the proportion of poorly differentiated cases, carbohydrate antigen 125 (CA125), PLR, and NLR in the recurrence group were higher than those in the non-recurrence group (P < 0.05). Logistic multivariate regression analysis showed that stage Ⅲ [O^R = 2.724 (95% CI: 1.121, 6.620) ], CA125 [O^R = 3.480 (95% CI: 1.432, 8.457) ], PLR [O^R = 3.916 (95% CI: 1.611, 9.516) ], and NLR [O^R = 4.204 (95% CI: 1.730, 10.217) ] were risk factors for postoperative recurrence of epithelial ovarian cancer (P < 0.05). ROC curve results showed that the sensitivities of preoperative PLR, NLR, and their combination in predicting postoperative recurrence of epithelial ovarian cancer were 74.32%, 67.57% and 68.92%, respectively; the specificities were 66.10%, 73.73% and 91.53%, respectively; the AUC values were 0.707, 0.737 and 0.795, respectively. The sensitivity and specificity of the risk assessment model were 75.64% and 86.84%, the AUC was 0.812, and the HH-L test result was 0.097. When the critical value was 5, the specificity and sensitivity of the risk assessment model were higher, which were 0.662 and 0.784, respectively.Conclusion The preoperative levels of PLR and NLR are closely related to the prognosis of patients with epithelial ovarian tumor debulking. The combination of the two has good predictive performance in predicting the prognosis of patients, and the risk assessment model based on risk factors has a certain predictive value.