Construction of A Nomogram Prognosis Prediction Model for the Prognosis of Ovarian Yolk Sac Tumors Based on SEER Database

CHU Ying; WANG Yi-xuan; HUA Zhen-dan; ZHENG Jia-hui; WANG Zan-hong

doi:10.12280/gjfckx.20240966

Abstract：Objective:To analyze the relevant influencing factors of tumor-specific survival in patients with ovarian yolk sac tumor(OYST)and construct a nomogram prediction model for the tumor-specific survival rate of OYST patients.Methods:A total of 358 patients diagnosed with OYST from January 2000 to December 2020 were screened from the SEER database.They were randomly divided into a training set(266 cases)and a validation set(92 cases)at a ratio of 3∶1.Univariate and multivariate competing risk analyses were used to identify the independent influencing factors of tumor-specific survival.A nomogram prediction models for the 1-year,3-year,and 5-year tumor-specific survival rates was constructed.The discrimination,accuracy,and practicality of the model were evaluated by the concordance index(C-index),area under the curve(AUC)of the receiver operating characteristic curve,calibration curves,Hosmer-Lemeshow goodness—of-fit test,and decision curve analysis.A risk stratification system was established to divide the patients into high-and low-risk groups,and the Kaplan-Meier curve was used to analyze the survival differences between the two groups.Results:Multivariate competing risk analysis showed that age,surgery,and regional lymph node dissection were independent influencing factors for tumor-specific survival in OYST patients.Based on this,a nomogram prediction model was constructed.The C-indices of the training set and validation set were 0.829(95％CI:0.825-0.833)and 0.808(95％CI:0.804-0.812),respectively.The AUCs for predicting the 1-year,3-year,and 5-year tumor-specific survival rates were 0.927,0.833,0.815 and 0.982,0.880,0.745,respectively.The Calibration curve and Hosmer-Lemeshow goodness-of-fit test showed good consistency between the predicted and actual tumor-specific survival rates of OYST patients.The clinical decision analysis indicated that the model had certain clinical practicality.The Kaplan-Meier curve showed that the tumor-specific survival rate of the high-risk group was significantly lower than that of the low—risk group(P＜0.000 1).Conclusions:The constructed nomogram prediction model for the tumor-specific survival rate of OYST patients has good discrimination and accuracy,which can help clinicians evaluate the prognosis of patients and develop individualized treatment plans to improve the prognosis of patients.