非小细胞肺癌放射性肺损伤预测模型的临床可应用性分析  

Clinical applicability analysis of predictive models for radiation-induced lung injury in non-small cell lung cancer

作　　者：郭峰 张朦 杜傲男[1] 沈文彬[1] 陈宏林[1] 王强[1] GUO Feng;ZHANG Meng;DU Aonan;SHEN Wenbin;CHEN Honglin;WANG Qiang(Department of Radiation Oncology,Xuzhou Cancer Hospital,Xuzhou 221005 China)

机构地区：[1]徐州市肿瘤医院放疗科,江苏徐州221005

出　　处：《中国辐射卫生》2025年第1期126-134,共9页Chinese Journal of Radiological Health

基　　金：彭城英才--医学重点人才课题(XWRCHT20220044);徐州医科大学科技园科技创新课题(CXCYYB202416);徐州市卫生健康委医学科技创新项目(XWKYHT20220112)。

摘　　要：目的 构建并验证一种放射性肺损伤(RILI)风险的模型,评估其在临床实践中的可行性。方法 纳入共计125名非小细胞肺癌(NSCLC)患者的临床数据,将其分为训练组(88例)和验证组(38例)。通过单因素和多因素逻辑回归分析结合最小收缩与选择算子(Lasso)回归筛选关键预测因子,建立预测模型,并通过列线图、受试者工作特征曲线(ROC)、校准曲线及决策曲线分析模型的性能。结果 模型筛选出的关键变量包括肿瘤体积(P=0.017)、东部肿瘤协作组体力状态评分(P=0.035)、靶区最低剂量的95%(P=0.028)、双肺接受20 Gy辐射剂量的体积百分比(P <0.001)和中性粒细胞-淋巴细胞比值(P=0.021)。ROC曲线显示模型在训练组和验证组的曲线下面积(AUC)分别为0.987和0.992,具有良好的预测能力。校准曲线和决策曲线进一步验证了模型的准确性和临床实用性。结论 本研究构建的预测模型能够较为准确地预测NSCLC患者放疗后RILI的发生风险,具有潜在的临床应用价值。Objective To develop and validate a model to predict the risk of radiation-induced lung injury(RILI)and as-sess its clinical feasibility.Methods Clinical data from 125 patients with non-small cell lung cancer(NSCLC)were in-cluded in the study.The patients were divided into training group(88 cases)and validation group(38 cases).Key predictive factors were identified using univariate and multivariate logistic regression analyses combined with least absolute shrinkage and selection operator(LASSO)regression.A predictive model was constructed and evaluated using a nomogram,receiver operating characteristic(ROC)curve,calibration curve,and decision curve analysis.Results The key variables identified by the model were tumor volume(P=0.017),Eastern Cooperative Oncology Group performance status score(P=0.035),95%of the minimum dose to the target volume(P=0.028),percentage of bilateral lung volume receiving 20 Gy of radiation(P<0.001),and neutrophil-to-lymphocyte ratio(P=0.021).The ROC curve showed that the areas under the curve(AUC)for the model in the training and validation groups were 0.987 and 0.992,respectively,indicating good predictive ability.The calibration curve and decision curve further confirmed the accuracy and clinical practicability of the model.Conclusion The predictive model proposed in this study can accurately assess the risk of developing RILI in patients with NSCLC who have undergone radiotherapy,demonstrating its potential value in clinical practice.

关 键 词：非小细胞肺癌 放射性肺损伤 预测模型 

分 类 号：R818[医药卫生—放射医学]