基于SEER数据库的乳腺髓样癌预后分析及预测模型构建  

Construction of a prediction model for prognosis of patients with medullary breast carcinoma based on SEER data

作　　者：陈勇[1] 许正 丁锦华 CHEN Yong;XU Zheng;DING Jinhua(Department of Thyroid and Breast Surgery,Affiliated Lihuili Hospital,Ningbo University,Ningbo 315040,China)

机构地区：[1]宁波大学附属李惠利医院甲乳外科,315040

出　　处：《浙江医学》2024年第4期360-368,共9页Zhejiang Medical Journal

基　　金：浙江省医药卫生科技计划项目(2023KY1013)。

摘　　要：目的 分析典型乳腺髓样癌(TMBC)与不典型乳腺髓样癌(AMCB)的临床病理特征和预后差异,构建乳腺髓样癌(MBC)预后预测模型。方法 收集美国国家癌症研究所监测、流行病学及结局项目(SEER)数据库中2004年1月至2017年12月经病理学诊断为TMBC(2 017例)和AMCB(157例)的患者。比较两组患者临床病理特征,采用Kaplan-Meier法比较两组的总生存期(OS)和乳腺癌特异生存期(BCSS),并进行亚组分析。采用Cox回归分析影响MBC患者OS的危险因素;构建基于危险因素的OS预测模型,绘制ROC曲线、校正曲线和决策曲线评估模型的预测效能。结果 两组患者临床病理特征比较,差异均无统计学意义(均P>0.05),Kaplan-Meier生存曲线表明两组患者OS和BCSS比较,差异均无统计学意义(均P>0.05)。亚组分析显示,肿瘤直径>5 cm的亚组中AMCB患者OS较差。Cox单因素分析表明年龄、婚姻状况、原发侧、美国癌症联合委员会(AJCC)分期、淋巴结状态、孕激素受体、放化疗、肿瘤大小是MBC预后的危险因素,Cox多因素分析表明年龄、婚姻状况、AJCC分期、淋巴结状态、化疗、肿瘤大小是独立危险因素。基于独立危险因素构建预测MBC 1、3、5年OS的预后模型。ROC曲线、校正曲线和决策曲线均显示该模型有良好的预测效能。结论 TMBC与AMCB的临床病理特征和预后相似,构建MBC预后预测模型可有效预测MBC患者预后。Objective To construct a prediction model for prognosis of patients with medullary breast carcinoma(MBC) based on the analysis of the clinical pathological characteristics and differences of prognosis of tipical medullary breast cancinoma(TMBC) and atypital medullary cancinoma of the breast(AMCB).Methods The clinical data of patients diagnosed as MCB from January 2004 to December 2017 were obtained from the surveillance,epidemiology and end results(SEER) database,including 2 017 cases of TMBC and 157 cases of AMCB.The clinicopathological characteristics of the two groups were compared;the overall survival(OS) and breast cancer-specific survival(BCSS) were analyzed with Kaplan-Meier and compare between the two groups.The factors influencing the OS of MBC patients were identified with Cox regression analyses,based of which a prediction model for prognosis of MBC patients was constructed.The predictive performance of the model was evaluated by ROC curve,calibration curve and decision curve analysis(DCA).Results There were no significant differences in clinical and pathological characteristics between the two groups(all P>0.05);and Kaplan-Meier curves indicated that there were no significant differences in OS and BCSS between the two groups(all P>0.05).Subgroup analysis revealed that AMCB patients with tumor diameter >5 cm had poorer OS.Univariate Cox analysis showed that age,marital status,primary side,American Joint Committee on Cancer(AJCC) stage,lymph node status,progesterone receptor,radiotherapy,chemotherapy and tumor size were significantly associated with the prognosis of MBC patients.Multivariate Cox analysis showed that age,marital status,AJCC stage,lymph node status,chemotherapy,and tumor size were independent prognosis factors of MBC patients.A prediction model for 1-,3-and 5-year OS of MBC patients was constructed based on independent prognosis factors.The ROC curves,calibration curves and DCA all demonstrated that the model exhibited good predictive performance.Conclusion The clinical pathological chara

关 键 词：乳腺髓样癌 典型乳腺髓样癌 不典型乳腺髓样癌 预测模型 监测、流行病学及结局数据库 

分 类 号：R737.9[医药卫生—肿瘤] O212.1[医药卫生—临床医学]