ObjectiveTo develop and validate a 3-year recurrence prediction score (RPS) system for predicting the baseline risk of recurrence of stage I–II endometrial carcinoma.MethodsWe reviewed 427 patients with International Federation of Gynecology and Obstetrics staging I–II endometrial carcinoma underwent surgery without any adjuvant therapy from 2005 to 2013. The patients were divided into 2 groups: the test cohort (n=251) comprising those who underwent surgery in odd-numbered years, and the validation cohort (n=176) comprising those who underwent surgery in even-numbered years. Multivariate analysis was performed using 7 candidate predictors to identify the risk factors for 3-year recurrence-free interval (RFI) in the test cohort. Each risk factor was scored based on logistic regression analyses of the test data set, and the sum of the risk factor scores was defined as the RPS system. We then applied the system in the validation cohort.ResultsMultivariate analysis revealed that the significant risk factors were age ≥60 years, pathological type II, positive cervical stromal invasion, and positive peritoneal cytology. In the test cohort, the 3-year RFI rates were 100%, 95.8%, 79.9%, and 33.3% for RPSs of 0, 1, 2, and 3, respectively. In the validation cohort, the 3-year RFI was significantly higher in the low-RPS group (RPS 0 or 1) than in the high-RPS group (RPS 2 or 3) (95.2% vs. 79.9%, p<0.01).ConclusionsThe RPS system shows significant reproducibility for predicting the baseline risk of recurrence. The system could potentially impact the choice of adjuvant therapy for stage I–II endometrial carcinoma.