基于SEER数据库建立非精原细胞瘤预后模型列线图  

Construction of a nomogram prognostic prediction model for non-seminoma based on SEER database

作　　者：杨啸宇 奉友刚[1] YANG Xiaoyu;FENG Yougang(Department of Urology,Suining Central Hospital,Sichuan 629000,China)

机构地区：[1]遂宁市中心医院泌尿外科,遂宁629000

出　　处：《现代泌尿生殖肿瘤杂志》2024年第3期155-160,共6页Journal of Contemporary Urologic and Reproductive Oncology

摘　　要：目的 探讨影响非精原细胞肿瘤患者疾病特异生存率(DSS)的独立预后因素,并建立列线图模型预测其1年、3年、5年的DSS。方法 从监测、流行病学和最终结果(SEER)数据库获取2010年至2018年的非精原细胞肿瘤患者临床病理资料,以7∶3比例随机分配为训练集和验证集。通过单因素及多因素Cox回归分析筛选独立预后因素,构建列线图模型并进行内部验证。使用列线图得分风险分层生存分析评价模型的预测效能。结果 纳入3 747例非精原细胞瘤患者,其中训练集2 622例,验证集1 125例。多因素Cox回归分析显示确诊年龄35~44岁、大于44岁、未婚、肿瘤最大直径>7 cm、未手术、肿瘤、淋巴结和转移(TNM)分期Ⅲ期是影响DSS的独立预后危险因素、未放疗是影响DSS的独立预后保护因素。列线图模型一致性指数(C-index)为0.865(训练集)和0.880(验证集),训练集及验证集1年、3年、5年受试者工作特征(ROC)曲线下面积(AUC)值均大于0.8。高风险组与低风险组生存分析差异有统计学意义(P<0.001)。结论 本研究识别了影响非精原细胞肿瘤患者DSS的独立预后因素,并建立了准确的预测模型。Objective To investigate the independent prognostic factors affecting disease-specific survival(DSS)in patients with non-seminoma and to establish a nomogram model to predict 1-year,3-year,and 5-year DSS.Methods Clinical and pathological data of patients with non-seminoma from 2010 to 2018 were obtained from the Surveillance,Epidemiology,and End Results(SEER)database.Cases were randomly assigned to training and validation sets in a 7∶3 ratio.Independent prognostic factors were identified through Cox regression analysis,and a nomogram model was constructed and internally validated.The model's predictive performance was evaluated using risk stratification survival analysis based on nomogram scores.Results A total of 3747 non-seminoma patients were included,with 2622 cases in the training set and 1125 cases in the validation set.Multivariate regression analysis showed that age at diagnosis of 35-44 years,age greater than 44 years,unmarried status,tumor maximum diameter>7 cm,no surgery or tumor,node,metastasis(TNM)stageⅢwere independent prognostic risk factors affecting DSS,while no radiotherapy was an independent prognostic protective factor.The nomogram model's consistency index(C-index)was 0.865 for the training set and 0.880 for the validation set.The 1-year,3-year,and 5-year area under the receiver operating characteristic(ROC)curve values for both training and validation sets were all greater than 0.8.Survival analysis showed a statistically significant difference between high-risk and low-risk groups(P<0.001).Conclusions This study identified independent prognostic factors affecting DSS in patients with non-seminoma and established an accurate predictive model.

关 键 词：非精原细胞瘤 预后 SEER数据库 列线图 

分 类 号：R737.21[医药卫生—肿瘤]