文章摘要
老年肺癌患者胸腔镜术后心肺并发症的列线图
Construction of a risk prediction model for thoracoscopic postoperative cardiopulmonary complications in elderly lung cancer patients based on Lasso-Logistic regression
投稿时间：2025-10-14  修订日期：2026-04-07
DOI：
中文关键词: Lasso-Logistic回归  老年  肺癌  胸腔镜  术后心肺并发症  风险预测模型
英文关键词: Lasso-Logistic Regression  Elderly  Lung cancer  Thoracoscopy  Postoperative cardiopulmonary complications  Risk prediction model
基金项目:秦皇岛市科学技术研究与发展计划202501A102
作者单位邮编
丁家宝* 秦皇岛市第一医院 066000
摘要点击次数: 180
全文下载次数: 0
中文摘要:
      目的:基于最小绝对收缩和选择算法(Lasso)-Logistic回归构建老年肺癌患者胸腔镜术后心肺并发症(PCC)的发生风险预测模型。方法:回顾性分析2023年6月-2025年6月在本院行胸腔镜手术的272例老年肺癌患者的临床资料。采用Lasso-Logistic回归筛选预测老年肺癌患者胸腔镜PCC发生的变量,以此构建列线图,再用受试者工作特征(ROC)曲线、校准曲线、Hosmer-Lemeshow拟合优度检验进行验证。结果:272例行胸腔镜手术的老年肺癌患者,共80例(构成比29.41%)发生PCC。Lasso-Logistic回归分析结果显示,冠心病(OR=3.753)、衰弱(OR=4.597)、第一秒用力呼气容积占预计值百分比(FEV1%pred)＜70%(OR=6.954)、六分钟步行距离(6MWD)＜300m(OR=3.294)、术中出血量＞200mL(OR=4.564)、术后24h内未下床活动(OR=7.125)是老年肺癌患者胸腔镜PCC发生的独立危险因素。ROC曲线下面积0.913(95%CI:0.870～0.956)。Apparent、Bias-corrected比较贴合Ideal,且Hosmer-Lemeshow拟合优度检验χ2=6.275,P=0.508。列线图预测老年肺癌患者胸腔镜PCC发生风险的灵敏度81.25%、特异度93.75%、准确度90.07%。结论:基于Lasso-Logistic回归构建预测老年肺癌患者胸腔镜PCC发生风险的列线图具有良好预测能力。
英文摘要:
      Objective: To construct a risk prediction model for thoracoscopic postoperative cardiopulmonary complications (PCC) in elderly lung cancer patients based on the Least Absolute Shrinkage and Selection Operator (Lasso) - Logistic regression. Methods: A retrospective analysis was conducted on the clinical data of 272 elderly lung cancer patients who underwent thoracoscopic surgery in our hospital from June 2023 to June 2025. Lasso Logistic regression was used to screen variables that predicted the occurrence of thoracoscopic PCC in elderly lung cancer patients, and based on this, a nomogram was constructed. Then receiver operating characteristic (ROC) curves, calibration curves, and Hosmer Lemeshow goodness of fit tests were used for validation it. Results: Among 272 elderly lung cancer patients who underwent thoracoscopic surgery, a total of 80 cases (accounting for 29.41%) developed PCC. The results of Lasso-Logistic regression analysis showed that coronary heart disease (OR=3.753), frailty (OR=4.597), percentage of predicted forced of expiratory volume in one second (FEV1% pred)<70% (OR=6.954), 6-minute walking distance (6MWD)<300m (OR=3.294), intraoperative blood loss>200mL (OR=4.564), and lack of mobilization within 24 hours after surgery (OR=7.125) were independent risk factors for thoracoscopic PCC in elderly lung cancer patients. The area under the ROC curve was 0.913 (95% CI: 0.870-0.956). Apparel and Bias-corrected fitted well with Ideal, and the Hosmer-Lemeshow goodness of fit test showed χ2=6.275, P=0.508. The sensitivity, specificity, and accuracy of the nomogram in predicting the risk of thoracoscopic PCC in elderly lung cancer patients were 81.25%, 93.75%, and 90.07%, respectively. Conclusion: The nomogram constructed based on Lasso-Logistic regression for predicting the risk of thoracoscopic PCC in elderly lung cancer patients has good predictive ability.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭