基于临床特征与^(18)F-FDG PET/CT代谢参数预测浸润性肺腺癌高级别亚型列线图模型的建立与验证  

Development and validation of a nomogram combining clinical and ^(18)F-FDG PET/CT parameters for prediction of high-grade patterns in invasive lung adenocarcinoma

作　　者：郭悦[1] 朱辉[1] 陈旭[1] 秦嵩[1] 刘甫庚[1] Guo Yue;Zhu Hui;Chen Xu;Qin Song;Liu Fugeng(Department of Nuclear Medicine,Beijing Hospital,National Center of Gerontology,Institute of Geriatric Medicine,Chinese Academy of Medical Sciences,Beijing 100730,China)

机构地区：[1]北京医院核医学科,国家老年医学中心,中国医学科学院老年医学研究院,北京100730

出　　处：《中华医学杂志》2025年第4期284-290,共7页National Medical Journal of China

基　　金：中央高水平医院临床科研业务费(BJ-2021-186、BJ-2024-190)。

摘　　要：目的:建立并验证基于临床特征与^(18)氟-脱氧葡萄糖正电子发射计算机断层扫描(^(18)F-FDG PET/CT)代谢参数的浸润性肺腺癌患者含有高级别亚型(HGP)的列线图预测模型。方法:回顾性收集2017年10月至2022年3月于北京医院确诊浸润性肺腺癌且治疗前行^(18)F-FDG PET/CT的311例患者的临床资料。按照是否含HGP将患者分为HGP组196例与非HGP组115例。采用简单随机分组方法按7∶3比例将患者分为训练集和验证集。在训练集建立HGP预测模型并绘制列线图。在训练集及验证集中以受试者工作特征(ROC)曲线下面积(AUC)评价模型预测能力,采用Hosmer-Lemeshow检验评估模型的拟合优度,校准曲线评价实际概率和列线图预测概率一致性,决策曲线分析(DCA)评估列线图模型临床实用性。结果:311例患者年龄为(65.6±10.9)岁,男148例(47.6%)。训练集217例,其中HGP组141例(65.0%);验证集94例,其中HGP组55例(58.5%)。训练集中HGP组和非HGP组间性别、验证集中两组间癌胚抗原(CEA)、训练集及验证集两组间吸烟史、临床分期、细胞角蛋白19片段(CYFRA21-1)、最大标准摄取值(SUV_(max))、平均标准摄取值(SUV_(mean))、肿瘤代谢体积(MTV)、糖酵解总量(TLG)和肿瘤最大径(D_(max))差异均有统计学意义(均P<0.05)。将性别、临床分期、CYFRA21-1、SUV mean及TLG纳入浸润性肺腺癌患者临床及PET/CT参数HGP预测模型,训练集中该模型AUC(95%CI)为0.888(0.844~0.932),灵敏度、特异度分别为85.1%、79.0%;验证集AUC(95%CI)为0.925(0.872~0.977),灵敏度、特异度分别为83.6%、89.7%。上述模型在训练集(χ^(2)=8.247,P=0.410)和验证集(χ^(2)=1.636,P=0.990)中均具有良好拟合度。校准曲线显示训练集和验证集中模型预测概率和实际发生概率均有良好一致性。DCA显示该列线图模型可为浸润性肺腺癌患者临床及PET/CT参数预测HGP提供较好的临床净获益。结论:基于临床特征及^(18)F-FDG PET/CT代�Objective To establish and validate a nomogram based on clinical characteristics and metabolic parameters derived from ^(18)F-fluorodeoxyglucose positron emission tomography and computed tomography(^(18)F-FDG PET/CT)for prediction of high-grade patterns(HGP)in invasive lung adenocarcinoma.Methods The clinical and PET/CT image data of 311 patients who were confirmed invasive lung adenocarcinoma and underwent pre-treatment ^(18)F-FDG PET/CT scan in Beijing Hospital between October 2017 and March 2022 were retrospectively collected.The enrolled patients were divided into HGP group(196 patients)and non-HGP group(115 patients)according to the presence and absence of HGP.The data were divided into training set and validation set at 7∶3 ratio using R statistical software and simple random allocation.A nomogram prediction model was constructed in training set.The area under the curve(AUC)of receiver operating characteristic(ROC)was depicted in the training and validation set respectively for assessing the prediction efficacy.The goodness of fit,consistency between predicted and observed probability and clinical usefulness of the model were evaluated by Hosmer-Lemeshow test,calibration curve and decision curve analysis(DCA).Results The age of 311 patients were(65.6±10.9)years and included 148 males(47.6%).In training set of 217 patients,141(65.0%)contained HGP while in validation set of 94 patients,55(58.5%)contained HGP.Gender in training set,serum carcino-embryonic antigen(CEA)in validation set,smoking history,clinical stage,cytokeratin fragments(CYFRA21-1),maximum standardized uptake value(SUV_(max)),mean standardized uptake value(SUV mean),metabolic tumor volume(MTV),total lesion glycolysis(TLG)and maximum diameter(D_(max))in both sets showed significant differences between HGP and non-HGP groups(all P<0.05).The variables integrated in the model were gender,clinical stage,CYFRA21-1,SUV mean and TLG.The AUC(95%CI)of the ROC curve in training and validation set were 0.888(0.844-0.932)and 0.925(0.872-0.977),the sensit

关 键 词：肺肿瘤 肺腺癌 正电子发射计算机断层扫描 ^(18)F-脱氧葡萄糖 列线图 

分 类 号：R73[医药卫生—肿瘤]