Risk prediction model construction of postoperative pulmonary infection in lung cancer patients undergoing four-level thoracoscopic surgery based on machine learning algorithms

MA Jiajia; LIU Xiaoxin; XUE Bei; FENG Jing; ZHANG Zhengmin; YAO Liping; JU Xinxing; LIU Tingting

doi:10.7619/jcmp.20245679

Journal of Clinical Medicine in Practice > 2025 > 29(6): 111-117. > DOI: 10.7619/jcmp.20245679

MA Jiajia, LIU Xiaoxin, XUE Bei, FENG Jing, ZHANG Zhengmin, YAO Liping, JU Xinxing, LIU Tingting. Risk prediction model construction of postoperative pulmonary infection in lung cancer patients undergoing four-level thoracoscopic surgery based on machine learning algorithms[J]. Journal of Clinical Medicine in Practice, 2025, 29(6): 111-117. DOI: 10.7619/jcmp.20245679

Citation:

PDF (1877 KB)

Risk prediction model construction of postoperative pulmonary infection in lung cancer patients undergoing four-level thoracoscopic surgery based on machine learning algorithms

MA Jiajia^{1, 2},
LIU Xiaoxin^{1, 2,},
XUE Bei¹,
FENG Jing¹,
ZHANG Zhengmin¹,
YAO Liping¹,
JU Xinxing^{1, 2},
LIU Tingting^{1, 2}

1.
Nursing Department, Chest Hospital Affiliated to School of Medicine of Shanghai Jiao Tong University, Shanghai, 200030
2.
School of Nursing of Shanghai Jiao Tong University, Shanghai, 200025

More Information

Received Date: November 18, 2024
Revised Date: December 25, 2024

Graphical Abstract

Abstract

Abstract

Objective
To develop and validate risk prediction models utilizing five machine learning algorithms for assessing postoperative pulmonary infection (PPI) risk in lung cancer patients undergoing grade Ⅳ thoracoscopic surgery.
Methods
A retrospective cohort study included 2, 380 lung cancer patients who underwent grade Ⅳ thoracoscopic surgery at a tertiary hospital in Shanghai (January 2022 to June 2024). Patients were stratified into training (n=1, 665) and validation (n=715) cohorts. Five machine learning algorithms—Logistic regression (LR), artificial neural network (ANN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGB)—were employed to construct predictive models. A nomogram was developed for clinical utility.
Results
Among 2, 380 patients, 226 (9.5%) developed PPI. The Least Absolute Shrinkage and Selection Operator (LASSO) regression identified eight predictive variables: daily cigarette consumption, diabetes history, preoperative diffusing capacity, maximal tumor diameter, 24-hour postoperative chest drainage volume, perioperative oral nutritional supplementation (ONS), postoperative urinary catheterization, and intraoperative pleural adhesion severity. All models demonstrated robust discrimination, with area under the curve (AUC) values ranging from 0.862 to 0.947. The XGB model achieved superior performance (AUC=0.947, 95%CI, 0.937 to 0.962), followed closely by the LR model (AUC=0.926, 95%CI, 0.918 to 0.933).
Conclusion
Machine learning-based algorithms models effectively stratify PPI risk in lung cancer patients following grade Ⅳ thoracoscopic surgery. The derived nomogram provides a practical tool for perioperative risk management by healthcare providers.
- lung cancer,
- grade four surgery,
- thoracoscopic surgery,
- pulmonary infection,
- predictive model,
- machine learning,
- nomogram,
- risk management

FullText(HTML)

References (30)

References

[1]	WHO. Global cancer burden growing, amidst mounting need for services[EB/OL]. (2023-12-27)[2024-02-27]. https://www.who.int/news/item.
[2]	QI J L, LI M L, WANG L J, et al. National and subnational trends in cancer burden in China, 2005-20: an analysis of national mortality surveillance data[J]. Lancet Public Health, 2023, 8(12): e943-e955.
[3]	CHEN S, CAO Z, PRETTNER K, et al. Estimates and projections of the global economic cost of 29 cancers in 204 countries and territories from 2020 to 2050[J]. JAMA Oncol, 2023, 9(4): 465-472.
[4]	翁文俊, 李剑锋, 侯宜军. 单孔胸腔镜联合三维血管支气管CT成像在解剖性肺段切除中的应用[J]. 实用临床医药杂志, 2022, 26(5): 14-17.
[5]	中华预防医学会医院感染控制分会第四届委员会重点部位感染防控学组. 术后肺炎预防和控制专家共识[J]. 中华临床感染病杂志, 2018, 11(1): 11-19.
[6]	WANG Y Q, LIU X, JIA Y, et al. Impact of breathing exercises in subjects with lung cancer undergoing surgical resection: a systematic review and meta-analysis[J]. J Clin Nurs, 2019, 28(5/6): 717-732.
[7]	娄洁琼, 侯旭敏, 郑悦, 等. 胸外科四级手术日间化研究与探索[J]. 中国卫生质量管理, 2024, 31(5): 29-32.
[8]	SEMENKOVICH T R, FREDERIKSEN C, HUDSON J L, et al. Postoperative pneumonia prevention in pulmonary resections: a feasibility pilot study[J]. Ann Thorac Surg, 2019, 107(1): 262-270. doi: 10.1016/j.athoracsur.2018.08.008
[9]	中华医学会呼吸病学分会感染学组. 中国成人医院获得性肺炎与呼吸机相关性肺炎诊断和治疗指南(2018年版)[J]. 中华结核和呼吸杂志, 2018, 41(4): 255-280. doi: 10.3760/cma.j.issn.1001-0939.2018.04.006
[10]	肖博, 王冲, 刘洋, 等. 胸腔镜肺叶袖式切除术与开胸肺叶袖式切除术对中心型肺癌的治疗效果对比[J]. 中国临床医生杂志, 2024, 52(7): 811-815.
[11]	DING Z, WANG X, JIANG S, et al. Risk factors for postoperative pulmonary infection in patients with non-small cell lung cancer: analysis based on regression models and construction of a nomogram prediction model[J]. Am J Transl Res, 2023, 15(5): 3375-3384.
[12]	LIU W, JIN F, WANG H M, et al. The association between double-lumen tube versus bronchial blocker and postoperative pulmonary complications in patients after lung cancer surgery[J]. Front Oncol, 2022, 12: 1011849.
[13]	仲蕾, 张会, 许静, 等. 老年2型糖尿病患者发生口腔衰弱风险的列线图预测模型构建[J]. 实用临床医药杂志, 2024, 28(16): 98-103, 108. doi: 10.7619/jcmp.20240638
[14]	AGOSTINI P J, LUGG S T, ADAMS K, et al. Risk factors and short-term outcomes of postoperative pulmonary complications after VATS lobectomy[J]. J Cardiothorac Surg, 2018, 13(1): 28.
[15]	WANG M, ZOU P. High FEV1 and BMI as protective factors in reducing the infection incidence of lung cancer in patients who underwent thoracoscopic surgery[J]. Clin Exp Reprod Med, 2018, 11(12): 13697-13704.
[16]	LEEMING J. How AI is helping the natural sciences[J]. Nature, 2021, 598(7880): S5-S7.
[17]	CECEN B, TOPATES G, KARA A, et al. Biocompatibility of silicon nitride produced via partial sintering & tape casting[J]. Ceram Int, 2021, 47(3): 3938-3945.
[18]	WANG Y, ZHU Y, XUE Q, et al. Predicting chronic pain in postoperative breast cancer patients with multiple machine learning and deep learning models[J]. J Clin Anesth, 2021, 74: 110423.
[19]	LVSCHER T F, LYON A, AMSTEIN R, et al. Artificial intelligence: the pathway to the future of cardiovascular medicine[J]. Eur Heart J, 2022, 43(7): 556-558.
[20]	GAO Z, LOU L, WANG M, et al. Application of machine learning in intelligent medical image diagnosis and construction of intelligent service process[J]. Comput Intell Neurosci, 2022, 2022: 9152605.
[21]	LI M P, LIU W C, WU J B, et al. Machine learning for the prediction of postoperative nosocomial pulmonary infection in patients with spinal cord injury[J]. Eur Spine J, 2023, 32(11): 3825-3835.
[22]	LU C, XING Z X, XIA X G, et al. Development and validation of a postoperative pulmonary infection prediction model for patients with primary hepatic carcinoma[J]. World J Gastrointest Oncol, 2023, 15(7): 1241-1252.
[23]	LUO Y, TANG Z, HU X, et al. Machine learning for the prediction of severe pneumonia during posttransplant hospitalization in recipients of a deceased-donor kidney transplant[J]. Ann Transl Med, 2020, 8(4): 82.
[24]	ROSE S. Machine learning for prediction in electronic health data[J]. JAMA Netw Open, 2018, 1(4): e181404.
[25]	WANG R, ZHANG J, SHAN B, et al. XGBoost machine learning algorithm for prediction of outcome in aneurysmal subarachnoid hemorrhage[J]. Neuropsychiatr Dis Treat, 2022, 18: 659-667.
[26]	SHIN H. XGBoost regression of the most significant photoplethysmogram features for assessing vascular aging[J]. IEEE J Biomed Health Inform, 2022, 26(7): 3354-3361.
[27]	CHEKROUD A M, BONDAR J, DELGADILLO J, et al. The promise of machine learning in predicting treatment outcomes in psychiatry[J]. World Psychiatry, 2021, 20(2): 154-170.
[28]	HU X Y, LIU H, ZHAO X, et al. Automated machine learning-based model predicts postoperative delirium using readily extractable perioperative collected electronic data[J]. CNS Neurosci Ther, 2022, 28(4): 608-618.
[29]	MAO D, FU L, ZHANG W. Construction and validation of an early prediction model of delirium in children after congenital heart surgery[J]. Transl Pediatr, 2022, 11(6): 954-964.
[30]	SHI Y, WANG H, ZHANG L, et al. Nomogram models for predicting delirium of patients in emergency intensive care unit: a retrospective cohort study[J]. Int J Gen Med, 2022, 15: 4259-4272.

[1]	CHEN Siyu, BAI Lan, ZHOU Yu. The expression of irregular fractalkine in patients with preeclampsia and its relationships with inflammatory factors and pregnancy outcomes[J]. Journal of Clinical Medicine in Practice, 2023, 27(16): 84-88. DOI: 10.7619/jcmp.20230192
[2]	BAI Jingshu, BAI He, XU Wei. Effects of Compound Jingjie Fumigation Lotion on wound growth factors and inflammatory response in patients after anal fissure surgery[J]. Journal of Clinical Medicine in Practice, 2021, 25(9): 70-73. DOI: 10.7619/jcmp.20201974
[3]	PEI Shuang, WEN Changming. Effect of alprostadil combined with nimodipine on inflammatory factors in patients with cerebral vasospasm after aneurysmal subarachnoid hemorrhage[J]. Journal of Clinical Medicine in Practice, 2020, 24(17): 83-85. DOI: 10.7619/jcmp.202017022
[4]	REN Xiao, YUAN Qiuzhen, GAN Xuefeng, LI Bo, SHI Minjuan. Therapeutic effect of Bailing Capsule in treating early diabetic nephropathy and its influence on hemorheological and inflammatory factors[J]. Journal of Clinical Medicine in Practice, 2020, 24(10): 64-67. DOI: 10.7619/jcmp.202010016
[5]	LI Yunxia, ZHENG Lina. Effect of compound Shenqi Granules on inflammatory factors and immune function of children with recurrent respiratory tract infection[J]. Journal of Clinical Medicine in Practice, 2019, 23(20): 22-24. DOI: 10.7619/jcmp.201920006
[6]	XU Hong, HUA Ye, FENG Zhigang, WU Shuangshuang, MA Tao, LIU Yumin, LU Yunnan. Effect of oxiracetam combined with edaravone on clinical efficacy and serum inflammatory factors in patients with acute cerebral infarction[J]. Journal of Clinical Medicine in Practice, 2017, (19): 31-33. DOI: 10.7619/jcmp.201719009
[7]	YUAN Lei. Influence of atorvastatin on serum inflammatory factors and adiponectin levels in patients with acute myocardial infarction[J]. Journal of Clinical Medicine in Practice, 2016, (5): 4-6,10. DOI: 10.7619/jcmp.201605002
[8]	XIONG Bin, XU Youfan. Influence of atorvastatin on effect and inflammatory factors after percutaneous transluminal coronary intervention in patients with acute coronary syndrome[J]. Journal of Clinical Medicine in Practice, 2015, (5): 8-10. DOI: 10.7619/jcmp.201505003
[9]	LI Wei. Factors of ACS atorvastatin on blood lipid levels, serum inflammatory[J]. Journal of Clinical Medicine in Practice, 2013, (15): 56-58. DOI: 10.7619/jcmp.201315020
[10]	LIANG Yefei, ZHOU Youwang. Effects of an oxygen free radical scavenger on serum inflammatory factors of patients with acute cerebral hemorrhage[J]. Journal of Clinical Medicine in Practice, 2013, (14): 53-55. DOI: 10.7619/jcmp.201314018

Cited By

Cited by

Periodical cited type(14)

1.	曹瑜，林盪. PDCA循环联合PBL教学法对呼吸内科住院医师规范化培训的应用效果. 中国医药指南. 2023(20): 186-189 .
2.	高长燕，程吉英. 医护治一体化品管圈活动降低康复病房呼叫器使用次数的应用研究. 现代医药卫生. 2022(05): 895-897+900 .
3.	丁如梅，郭娜，黄佳宇，金艳，张雯昕，胡浪静，王燕. 多学科团队诊疗模式下PDCA循环管理对胰腺癌患者围术期营养状态的影响. 国际护理学杂志. 2022(12): 2210-2214 .
4.	李楠. PDCA循环管理结合外科康复护理对青光眼患者视力与自我管理能力的影响. 现代中西医结合杂志. 2022(18): 2599-2602 .
5.	吴全峰，周莉萍，郭巧莉，杨二女. 戴明循环管理法的品管圈活动对精神分裂症保护性约束患者压力性损伤的影响. 慢性病学杂志. 2021(03): 417-419 .
6.	刘振新. 老年白内障并发青光眼患者在术后恢复期应用品管圈结合循证护理干预提升其生活质量和术后治疗安全性的效果. 国际护理学杂志. 2021(09): 1670-1673 .
7.	年婧，贺维涛，高行军，周瑾，张少茹，刘洁琼，孙静. 品管圈在优化工作流程、降低门诊药房调剂内差中的应用. 临床医学研究与实践. 2021(19): 190-192 .
8.	张晓艳，周敏娜，陈洁. 心理护理联合疼痛管理在胰腺癌手术患者护理中的应用效果. 心理月刊. 2021(19): 92-93 .
9.	沈婷. 探究胰腺癌伴心衰患者围手术期应用品管圈活动联合PDCA循环的护理效果. 中西医结合心血管病电子杂志. 2021(23): 121-123+116 .
10.	何媛，高华. 戴明循环管理法的QCC活动对提高护理质量和降低创伤骨折患者术后切口感染率的影响. 抗感染药学. 2020(04): 555-557 .
11.	胡新玲. 基于PDCA模式的QCC活动对浅静脉留置针患者的应用效果. 河南医学研究. 2020(15): 2874-2876 .
12.	刘玮丽. 胰腺癌术后患者应用优质护理对生活质量及自我护理能力的影响. 当代护士(上旬刊). 2020(10): 88-90 .
13.	龙艳，李兰. 肝胆外科患者围术期护理中品管圈活动效果. 实用临床医药杂志. 2019(18): 129-132 . 本站查看
14.	刘晓静. 舒适护理干预对胰腺癌围术期并发症及患者满意度的影响. 中国医药指南. 2019(34): 245-246 .

Other cited types(0)

Get Citation

PDF

XML

Article views (23) PDF downloads (5) Cited by(14)

Turn off MathJax

Article Contents

Abstract

References

Risk prediction model construction of postoperative pulmonary infection in lung cancer patients undergoing four-level thoracoscopic surgery based on machine learning algorithms