Incidence, risk factors, and predictive modeling of pulmonary infection after high-risk surgery for lung cancer: a retrospective case-control study.

IF 2.1 3区 医学 Q3 RESPIRATORY SYSTEM
Journal of thoracic disease Pub Date : 2025-06-30 Epub Date: 2025-06-10 DOI:10.21037/jtd-2024-2276
Jiajia Ma, Bei Xue, Zhengmin Zhang, Liping Yao, Xiaoxin Liu
{"title":"Incidence, risk factors, and predictive modeling of pulmonary infection after high-risk surgery for lung cancer: a retrospective case-control study.","authors":"Jiajia Ma, Bei Xue, Zhengmin Zhang, Liping Yao, Xiaoxin Liu","doi":"10.21037/jtd-2024-2276","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The hierarchical operation management system is one of the core medical systems. Graded management based on the degree of surgical risk, difficulty, resource consumption, and ethical risks can help ensure the quality and safety of the surgery. With the progress of medical technology and the continuous development of medical standards, the proportion of lung cancer patients who underwent high-risk surgery was increasing rapidly. The purpose of this study is to explore the incidence, risk factors, and prediction models of pulmonary infection after high-risk surgery for lung cancer based on machine learning algorithms.</p><p><strong>Methods: </strong>This study included individuals who underwent lung cancer high-risk surgery at Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine from January 2021 to December 2023. Five machine learning algorithms including least absolute shrinkage and selection operator (LASSO)-assisted logistic regression (LR), artificial neural network (ANN), support vector machine (SVM), random forest (RF), and eXtreme gradient boosting (XGB) were adopted to explore risk factors and prediction models of pulmonary infection after high-risk surgery for lung cancer.</p><p><strong>Results: </strong>A cohort of 2,650 patients were eligible for the study after application of the exclusion criteria, with an overall incidence of postoperative pulmonary infection at 9.66% (256/2,650). LASSO regression screened out eight characteristic variables including daily smoking, history of diabetes, diffusing capacity of the lung for carbon monoxide percentage of predicted (DLCO%Pred), airway resistance percentage of predicted (Raw%Pred), maximum tumor diameter, perioperative oral nutritional supplements (ONS) supplement, postoperative urinary catheter, and pleural adhesion degree. The risk prediction model of postoperative pulmonary infection was constructed using these eight clinical features. The area under the curve (AUC) range of the five models was 0.893-0.936. The XGB model outperformed the others, with an AUC of 0.936 [95% confidence interval (CI): 0.923-0.949]. The LR model had an AUC of 0.927 (95% CI: 0.921-0.939), second only to the XGB model, which was converted into a nomogram for model visualization.</p><p><strong>Conclusions: </strong>The establishment of a risk prediction model based on machine learning can help clinical nursing staff identify high-risk patients for pulmonary infection after lung cancer high-risk surgery. The nomogram is expected to be an effective tool for nursing staff to manage the risk of pulmonary infection after lung cancer high-risk surgery.</p>","PeriodicalId":17542,"journal":{"name":"Journal of thoracic disease","volume":"17 6","pages":"3702-3715"},"PeriodicalIF":2.1000,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12268473/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of thoracic disease","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.21037/jtd-2024-2276","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/6/10 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RESPIRATORY SYSTEM","Score":null,"Total":0}
引用次数: 0

Abstract

Background: The hierarchical operation management system is one of the core medical systems. Graded management based on the degree of surgical risk, difficulty, resource consumption, and ethical risks can help ensure the quality and safety of the surgery. With the progress of medical technology and the continuous development of medical standards, the proportion of lung cancer patients who underwent high-risk surgery was increasing rapidly. The purpose of this study is to explore the incidence, risk factors, and prediction models of pulmonary infection after high-risk surgery for lung cancer based on machine learning algorithms.

Methods: This study included individuals who underwent lung cancer high-risk surgery at Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine from January 2021 to December 2023. Five machine learning algorithms including least absolute shrinkage and selection operator (LASSO)-assisted logistic regression (LR), artificial neural network (ANN), support vector machine (SVM), random forest (RF), and eXtreme gradient boosting (XGB) were adopted to explore risk factors and prediction models of pulmonary infection after high-risk surgery for lung cancer.

Results: A cohort of 2,650 patients were eligible for the study after application of the exclusion criteria, with an overall incidence of postoperative pulmonary infection at 9.66% (256/2,650). LASSO regression screened out eight characteristic variables including daily smoking, history of diabetes, diffusing capacity of the lung for carbon monoxide percentage of predicted (DLCO%Pred), airway resistance percentage of predicted (Raw%Pred), maximum tumor diameter, perioperative oral nutritional supplements (ONS) supplement, postoperative urinary catheter, and pleural adhesion degree. The risk prediction model of postoperative pulmonary infection was constructed using these eight clinical features. The area under the curve (AUC) range of the five models was 0.893-0.936. The XGB model outperformed the others, with an AUC of 0.936 [95% confidence interval (CI): 0.923-0.949]. The LR model had an AUC of 0.927 (95% CI: 0.921-0.939), second only to the XGB model, which was converted into a nomogram for model visualization.

Conclusions: The establishment of a risk prediction model based on machine learning can help clinical nursing staff identify high-risk patients for pulmonary infection after lung cancer high-risk surgery. The nomogram is expected to be an effective tool for nursing staff to manage the risk of pulmonary infection after lung cancer high-risk surgery.

肺癌高危手术后肺部感染的发生率、危险因素和预测模型:一项回顾性病例对照研究
背景:分级操作管理系统是核心医疗系统之一。根据手术风险程度、难度、资源消耗、伦理风险等进行分级管理,确保手术质量和安全。随着医疗技术的进步和医疗标准的不断发展,肺癌患者接受高危手术的比例正在迅速增加。本研究旨在探讨基于机器学习算法的肺癌高危手术后肺部感染的发生率、危险因素及预测模型。方法:本研究纳入了2021年1月至2023年12月在上海交通大学医学院附属上海胸科医院接受肺癌高危手术的患者。采用最小绝对收缩和选择算子(LASSO)辅助逻辑回归(LR)、人工神经网络(ANN)、支持向量机(SVM)、随机森林(RF)、极限梯度增强(XGB)等5种机器学习算法探讨肺癌高危手术后肺部感染的危险因素及预测模型。结果:应用排除标准后,2650例患者入选研究,术后肺部感染的总发生率为9.66%(256/ 2650)。LASSO回归筛选出8个特征变量,包括每日吸烟、糖尿病史、肺弥散能力预测一氧化碳百分比(DLCO%Pred)、预测气道阻力百分比(Raw%Pred)、最大肿瘤直径、围手术期口服营养补充剂(ONS)补充、术后导尿管、胸膜粘连程度。利用这8个临床特征构建术后肺部感染风险预测模型。5种模型的曲线下面积(AUC)范围为0.893 ~ 0.936。XGB模型优于其他模型,AUC为0.936[95%置信区间(CI): 0.923-0.949]。LR模型的AUC为0.927 (95% CI: 0.921-0.939),仅次于XGB模型,将其转换为nomogram用于模型可视化。结论:建立基于机器学习的风险预测模型可以帮助临床护理人员识别肺癌高危手术后肺部感染的高危患者。该图有望成为护理人员管理肺癌高危手术后肺部感染风险的有效工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of thoracic disease
Journal of thoracic disease RESPIRATORY SYSTEM-
CiteScore
4.60
自引率
4.00%
发文量
254
期刊介绍: The Journal of Thoracic Disease (JTD, J Thorac Dis, pISSN: 2072-1439; eISSN: 2077-6624) was founded in Dec 2009, and indexed in PubMed in Dec 2011 and Science Citation Index SCI in Feb 2013. It is published quarterly (Dec 2009- Dec 2011), bimonthly (Jan 2012 - Dec 2013), monthly (Jan. 2014-) and openly distributed worldwide. JTD received its impact factor of 2.365 for the year 2016. JTD publishes manuscripts that describe new findings and provide current, practical information on the diagnosis and treatment of conditions related to thoracic disease. All the submission and reviewing are conducted electronically so that rapid review is assured.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信