未分化甲状腺癌预后随机生存森林模型的构建及预测效果分析  

Establishment of random survival forest model of the prognosis of anaplastic thyroid cancer and its predictive efficacy analysis

作　　者：乔菲菲[1] 侯庆[2] 吴雨雷[1] Qiao Feifei;Hou Qing;Wu Yulei(Department of Head&Neck Surgery Ward 2,Shanxi Province Cancer Hospital,Shanxi Hospital Affiliated to Cancer Hospital,Chinese Academy of Medical Sciences,Cancer Hospital Affiliated to Shanxi Medical University,Taiyuan 030013,China;Department of Radiotherapy Biology,Shanxi Province Cancer Hospital,Shanxi Hospital Affiliated to Cancer Hospital,Chinese Academy of Medical Sciences,Cancer Hospital Affiliated to Shanxi Medical University,Taiyuan 030013,China)

机构地区：[1]山西省肿瘤医院、中国医学科学院肿瘤医院山西医院、山西医科大学附属肿瘤医院头颈外科二病区,太原030013 [2]山西省肿瘤医院、中国医学科学院肿瘤医院山西医院、山西医科大学附属肿瘤医院放射生物室,太原030013

出　　处：《肿瘤研究与临床》2023年第8期596-604,共9页Cancer Research and Clinic

摘　　要：目的探讨未分化甲状腺癌(ATC)预后的影响因素,评估构建的随机生存森林(RSF)模型在ATC预后预测中的应用价值。方法选择2004-2015年美国国立癌症研究所的监测、流行病学和最终结果(SEER)数据库中经组织病理学诊断为ATC的患者707例,采用简单随机法将所有患者分为训练集(495例)和验证集(212例)。采用单因素Cox比例风险模型分析影响训练集患者总生存(OS)的相关因素。采用基于最小赤池信息量准则(AIC)的多因素Cox比例风险模型分析上述变量并进行筛选,基于筛选出的变量构建预测OS的传统Cox模型;采用RSF算法对单因素Cox回归分析中P<0.05的变量进行分析,筛选重要的5个特征,纳入基于最小AIC的多因素Cox比例风险模型,采用筛选出的变量构建预测OS的RSF-Cox模型。采用时间依赖受试者工作特征(tROC)曲线及曲线下面积(AUC)、校正曲线、决策曲线、综合Brier评分(IBS),通过训练集和验证集来评估各模型预测OS的效能。结果单因素Cox回归分析显示,年龄、是否接受化疗、淋巴结转移情况、是否接受放疗、手术方式、肿瘤浸润程度、肿瘤数量、肿瘤长径和诊断时年份这9个变量是ATC预后的影响因素(均P<0.05)。基于最小AIC(4855.8)的多因素Cox回归分析显示,年龄较小(61~70岁比>80岁:HR=0.732,95%CI 0.560~0.957,P=0.023;≤50岁比>80岁:HR=0.561,95%CI 0.362~0.870,P=0.010)、接受化疗(是比否:HR=0.623,95%CI 0.502~0.773,P<0.001)、接受放疗(是比否:HR=0.695,95%CI 0.559~0.866,P=0.001)、接受手术(叶切除比未手术或未知:HR=0.712,95%CI 0.541~0.939,P=0.016;全切或次全切比未手术或未知:HR=0.535,95%CI 0.436~0.701,P<0.001)、肿瘤长径(≤2 cm比>6 cm:HR=0.495,95%CI 0.262~0.938,P=0.031;>2 cm且≤4 cm比>6 cm:HR=0.714,95%CI 0.520~0.980,P=0.037;>4 cm且≤6 cm比>6 cm:HR=0.699,95%CI 0.545~0.897,P=0.005)是ATC患者OS的独立保护因素;淋巴结转移(N1未知比N0:HR=1.664,95%CI 1.158~2.390,P=0.006;N1b比N0:HR=1Objective To investigate the factors influencing the prognosis of anaplastic thyroid cancer(ATC)and to evaluate the application value of established random survival forest(RSF)model in the prognosis prediction of ATC.Methods A total of 707 ATC patients diagnosed by histopathology in the Surveillance,Epidemiology and End Results(SEER)database of the National Cancer Institute from 2004 to 2015 were selected and randomly divided into the training set(495 cases)and the validation set(212 cases).Univariate Cox regression risk model was used to analyze the related factors affecting overall survival(OS)of patients in the training set.The multivariate Cox proportional risk model based on the minimum Akaike information criterion(AIC)was used to analyze the above variables and then the variables were screened out.The traditional Cox model for predicting OS was constructed based on the screened variables.The RSF algorithm was used to analyze the variables with P<0.05 in the univariate Cox regression analysis,and 5 important features were selected.Multivariate Cox proportional risk model was selected based on the minimum AIC.Then the RSF-Cox model for predicting OS was constructed by using screened variables.The time-dependent receiver operating characteristic(tROC)curve and the area under the curve(AUC),calibration curve,decision curve and integrated Brier score(IBS)in the training set and the validation set were used to evaluate the prediction performance of the models.Results Univariate Cox regression analysis showed that age,chemotherapy,lymph node metastasis,radiotherapy,surgical method,tumor infiltration degree,tumor number,tumor diameter and diagnosis time were factors affecting the prognosis of ATC(all P<0.05).Multivariate Cox regression analysis based on minimal AIC(4855.8)showed that younger age(61-70 years vs.>80 years:HR=0.732,95%CI 0.56-0.957,P=0.023;≤50 years vs.>80 years:HR=0.561,95%CI 0.362-0.87,P=0.010),receiving chemotherapy(receiving or not:HR=0.623,95%CI 0.502-0.773,P<0.001),receiving radiotherapy(recei

关 键 词：甲状腺肿瘤 生存率分析 随机森林 预后 

分 类 号：R736.1[医药卫生—肿瘤]