| 徐婧姝,何依月,高婧婧,等.基于LASSO-Cox回归构建并验证局部晚期鼻咽癌远处转移风险列线图模型：468例患者回顾性研究[J].肿瘤学杂志,2026,32(4):325-334. |
| 基于LASSO-Cox回归构建并验证局部晚期鼻咽癌远处转移风险列线图模型：468例患者回顾性研究 |
| Development and Validation of a LASSO-Cox Regression-Based Nomogram for Predicting Distant Metastasis in Locally Advanced Nasopharyngeal Carcinoma： a Retrospective Study of 468 Patients |
| 投稿时间：2025-12-25 |
| DOI：10.11735/j.issn.1671-170X.2026.04.B008 |
|
 |
| 中文关键词: 鼻咽肿瘤 局部晚期 远处转移 LASSO-Cox回归 预测模型 列线图 |
| 英文关键词:nasopharyngeal neoplasms locally advanced distant metastasis LASSO-Cox regression prediction model Nomogram |
| 基金项目:国家自然科学基金（82172804）；江苏省卫健委重点项目（K2019028）；南京市科技计划项目（2022SX00001663）；南京医科大学鼻咽癌专病队列研究（NMUC2021011A） |
|
| 摘要点击次数: 13 |
| 全文下载次数: 9 |
| 中文摘要: |
| 摘 要：［目的］ 构建并验证一个整合了传统临床分期、营养状况、炎症指标及治疗方法的预测模型，以精准识别放化疗后的高风险鼻咽癌患者，指导临床个体化治疗决策的制定。［方法］ 回顾性收集2018年1月至2021年12月初诊的468例Ⅲ~Ⅳa期鼻咽癌患者资料，按7∶3比例随机分为训练集（n=327）和验证集（n=141）。对所有连续变量（如年龄、血小板与淋巴细胞比值、白蛋白等）进行z-标准化处理，以消除量纲影响。通过最小绝对收缩和选择算子（least absolute shrinkage and selection operator，LASSO）筛选预测变量，并在构建Cox比例风险模型前对连续变量与Log（风险）关系进行检验及必要转换，同时对高度相关的炎症指标进行共线性处理。采用Schoenfeld残差检验验证Cox模型的比例风险假定。采用受试者工作特征（receiver operating characteristic，ROC）曲线确定风险评分截断值，并据此将患者分为高风险组和低风险组。采用Kaplan-Meier法绘制生存曲线，并用Log-rank检验比较两组间无远处转移生存（distant metastasis-free survival，DMFS）的差异。通过校准曲线及决策曲线分析（decision curve analysis，DCA）对模型的准确性和临床实用性进行验证。［结果］ LASSO-Cox回归筛选结果显示，年龄、治疗前血小板与淋巴细胞比值、治疗前白蛋白、治疗前淋巴细胞与中性粒细胞比值、T分期和靶向治疗是DMFS的独立预后因素。构建的列线图模型在训练集和验证集2年、2.5年、3年的ROC曲线下面积（area under the curve，AUC）分别为0.778、0.747、0.747和0.731、0.724、0.724，校准曲线显示预测与实际结果具有良好一致性，临床决策曲线证实模型具临床实用性。基于风险评分进行分层，训练集中的高风险与低风险组患者3年DMSF率分别为74.2%和93.6%，差异有统计学意义（χ2=23.686，P<0.001），表明该模型具有良好的风险分层能力。［结论］ 基于 LASSO-Cox 回归构建的列线图模型，能够利用局部晚期鼻咽癌患者的治疗前基线特征有效预测接受放化疗患者的远处转移风险，具有良好的预测准确性和潜在临床应用价值。 |
| 英文摘要: |
| Abstract：［Objective］ To develop and validate a predictive model integrating conventional clinical staging， nutritional status， inflammatory markers， and treatment modalities for precisely identifying high-risk patients with locally advanced nasopharyngeal carcinoma (LA-NPC) after chemoradiotherapy. ［Methods］ Clinical data from 468 patients newly diagnosed with stage Ⅲ~Ⅳa NPC between January 2018 and December 2021 were retrospectively collected and randomly divided into a training cohort (n=327) and a validation cohort (n=141) at a 7∶3 ratio. All continuous variables (e.g.， age， platelet-to-lymphocyte ratio， albumin) were z-score standardized. Candidate predictors were selected using least absolute shrinkage and selection operator(LASSO) regression. Before constructing the Cox proportional hazards model， the relationships between continuous variables and log (relative risk) were examined and transformed when necessary， and multicollinearity among highly correlated inflammatory indices was addressed. The proportional hazards assumption was verified using Schoenfeld residuals. The optimal risk score cutoff was determined by receiver operating characteristic (ROC) curve analysis， and patients were stratified into high- and low-risk groups accordingly. Distant metastasis-free survival (DMFS) was compared between groups using the Kaplan-Meier method and log-rank test. Model calibration and clinical utility were assessed by calibration curves and decision curve analysis (DCA). ［Results］ LASSO-Cox regression identified age， pretreatment platelet-to-lymphocyte ratio， albumin， lymphocyte-to-neutrophil ratio， T stage， and targeted therapy as independent prognostic factors for DMFS. The Nomogram achieved area under the ROC curve (AUC) values of 0.778， 0.747， and 0.747 at 2， 2.5， and 3 years in the training cohort， and 0.731， 0.724， and 0.724 in the validation cohort， respectively. Calibration curves showed good agreement between predicted and observed outcomes， and DCA confirmed the model’s clinical applicability. Based on risk score stratification， the 3-year DMFS rates in the high- and low-risk groups of the training cohort were 74.2% and 93.6% (χ2=23.686， P<0.001)， demonstrating excellent risk discrimination. ［Conclusion］ The LASSO-Cox-based Nomogram， utilizing baseline pretreatment characteristics， effectively predicts distant metastasis risk in LA-NPC patients undergoing chemoradiotherapy， exhibiting favorable predictive accuracy and potential clinical value. |
|
在线阅读
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|