国际妇产科学杂志

国际妇产科学杂志 ›› 2025, Vol. 52 ›› Issue (3): 342-349.doi: 10.12280/gjfckx.20240966

• 妇科肿瘤研究: 论著 • 上一篇    下一篇

基于SEER数据库构建卵巢卵黄囊瘤预后列线图预测模型

褚莹, 王艺璇, 花震丹, 郑佳慧, 王赞宏()   

  1. 030032 太原，山西医科大学第三医院（山西白求恩医院 山西医学科学院 同济山西医院）（褚莹，花震丹，郑佳慧，王赞宏）；大同市第一人民医院妇产科（王艺璇）
  • 收稿日期:2024-10-26 出版日期:2025-06-15 发布日期:2025-06-19
  • 通讯作者: 王赞宏 E-mail:wangzanhong@126.com
  • 基金资助:
    中央引导地方科技发展基金(YDZJSX2022B012)

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()   

  1. Third Hospital of Shanxi Medical University (Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital), Taiyuan 030032, China (CHU Ying, HUA Zhen-dan, ZHENG Jia-hui, WANG Zan-hong;Department of Obstetrics and Gynecology, Datong First People′s Hospital, Datong 037004, Shanxi Province, China (WANG Yi-xuan)
  • Received:2024-10-26 Published:2025-06-15 Online:2025-06-19
  • Contact: WANG Zan-hong E-mail:wangzanhong@126.com

RichHTML

11

PDF (PC)

14

摘要：

目的：分析卵巢卵黄囊瘤（ovarian yolk sac tumor，OYST）患者肿瘤特异性生存期的相关影响因素，构建OYST患者肿瘤特异性生存率的列线图预测模型。方法：从监测、流行病学和结局（The Surveillance, Epidemiology, and End Results，SEER）数据库中筛选2000年1月—2020年12月诊断为OYST的患者共358例，将其按3:1的比例随机分为训练集（266例）和验证集（92例）。采用单因素和多因素竞争风险分析肿瘤特异性生存期的独立影响因素，构建1年、3年、5年肿瘤特异性生存率的列线图预测模型，并通过一致性指数（C指数）、受试者工作特征曲线下面积（area under the curve，AUC）、校准曲线、Hosmer-Lemeshow拟合优度检验、决策曲线分析评估模型的区分度、准确性及实用性。通过建立风险分层系统，将患者分成高、低风险人群，采用Kaplan-Meier曲线分析2组人群的生存差异。结果：多因素竞争风险分析结果显示，年龄、手术和区域淋巴结清扫是OYST患者肿瘤特异性生存期的独立影响因素。据此构建列线图预测模型，训练集和验证集的C指数分别为0.829（95%CI：0.825~0.833）和0.808（95%CI：0.804~0.812），预测1年、3年、5年肿瘤特异性生存率的AUC分别为0.927、0.833、0.815和0.982、0.880、0.745。校准曲线及Hosmer-Lemeshow拟合优度检验显示模型预测的OYST患者肿瘤特异性生存率与实际生存率具有较好的一致性。临床决策分析曲线表明该模型有一定的临床实用性。Kaplan-Meier曲线显示高风险人群的肿瘤特异性生存率显著低于低风险人群（均P<0.000 1）。结论：构建的OYST患者肿瘤特异性生存率的列线图预测模型具有良好的区分度和准确度，可帮助临床医师评估患者预后，制定个体化治疗方案改善患者预后。

关键词: 卵巢肿瘤, 内胚层窦瘤, 存活率, 列线图, SEER规划, 预后, 风险调节

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.

Key words: Ovarian neoplasms, Endodermal sinus tumor, Survival rate, Nomograms, SEER program, Prognosis, Risk adjustment