Construction of a Survival Prediction Model of Uterine Carcinosarcoma Pa-tients Based on SEER Database
Objective:To establish a nomogram to predict overall survival(OS)of Uterine carcinosarcoma(UCS)patients.Methods:A total of 2635 UCS patients were selected from the Surveillance,Epidemiology and End Results(SEER)database between 2000 and 2020.The patients were randomly divided into a training cohort and a validation cohort in a 7∶3 ratio.Univariate Cox regression analysis,Lasso regression and multivariate Cox analysis was conducted to screen for independent risk factors affecting OS in UCS patients.We established a no-mogram for predicting the 1-and 3-year OS of UCS patients and evaluate the discrimination and calibration of the nomogram using receiver operating characteristic curve(ROC),calibration plots and decision curve analysis(DCA).According to the nomogram scores,patients were divided into low,medium,and high-risk groups and compared with the International Federation of Gynecology and Obstetrics(FIGO)staging system.Results:Age,race,tumor size,tumor stage,surgery,radiotherapy,chemotherapy and lymph node metastasis were identified as independent prognostic factors affecting patient OS(P＜0.05),and the above eight key variables were selected to establish the nomogram for predicting 1-and 3-year OS in UCS patients.The C-index and the area under the ROC curve(AUC)values of both the training and validation cohorts were greater than 0.7,indicating good discriminative capabilities of the nomogram.The calibration curves showed high consistency between the predicted probability and actual survival results.Moreover,the DCA curves suggested the clinical utility and application value of the model were superior to those of the FIGO staging system.The total risk score of each patient was calculated ac-cording to the nomogram model.UCS patients were divided into the low-risk group(score＜80),middle-risk group(score 80-130),and high-risk group(score＞130).Kaplan-Meier survival analysis demonstrated that the nomo-gram had a good ability to identify high-risk individuals.Conclusions;The model is a useful tool for accurately predicting OS in UCS patients and can assist in making individualized interventions by providing valuable prognos-tic information.
万方数据
维普
