Predicting postoperative complications after pneumonectomy using machine learning: a 10-year study

Background Reducing postoperative cardiovascular and neurological complications (PCNC) during thoracic surgery is the key to improving postoperative survival.Objective We aimed to investigate independent predictors of PCNC, develop machine learning models, and construct a predictive nomogram for PCN...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaxuan Wang, Shiyang Xie, Jiayun Liu, He Wang, Jiangang Yu, Wenya Li, Aika Guan, Shun Xu, Yong Cui, Wenfei Tan
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Annals of Medicine
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/07853890.2025.2487636
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850153230235860992
author Yaxuan Wang
Shiyang Xie
Jiayun Liu
He Wang
Jiangang Yu
Wenya Li
Aika Guan
Shun Xu
Yong Cui
Wenfei Tan
author_facet Yaxuan Wang
Shiyang Xie
Jiayun Liu
He Wang
Jiangang Yu
Wenya Li
Aika Guan
Shun Xu
Yong Cui
Wenfei Tan
author_sort Yaxuan Wang
collection DOAJ
description Background Reducing postoperative cardiovascular and neurological complications (PCNC) during thoracic surgery is the key to improving postoperative survival.Objective We aimed to investigate independent predictors of PCNC, develop machine learning models, and construct a predictive nomogram for PCNC in patients undergoing thoracic surgery for lung cancer.Methods This study used data from a previous retrospective study of 16,368 patients with lung cancer (training set: 11,458; validation set: 4,910) with American Standards Association physical statuses I–IV who underwent surgery. Postoperative information was collected from electronic medical records to help build models based on cause-and-effect and statistical data, potentially revealing hidden dependencies between factors and diseases in a big data environment. The optimal model was analyzed and filtered using multiple machine-learning models (Logistic regression, eXtreme Gradient Boosting, Random forest, Light Gradient Boosting Machine and Naïve Bayes). A predictive nomogram was built and receiver operating characteristics were used to assess the validity of the model. The discriminative power and clinical validity were assessed using calibration and decision-making curve analyses.Results Multivariate logistic regression analysis revealed that age, surgery duration, intraoperative intercostal nerve block, postoperative patient-controlled analgesia, bronchial blocker use and sufentanil use were independent predictors of PCNC. Random forest was identified as the optimal model with an area under the curve of 0.898 in the training set and 0.752 in the validation set, confirming the excellent prediction accuracy of the nomogram. All the net benefits of the five machine-learning models in the training and validation sets demonstrated excellent clinical applicability, and the calibration curves showed good agreement between the predicted and observed risks.Conclusion The combination of machine-learning models and nomograms may contribute to the early prediction and reduction in the incidence of PCNC.
format Article
id doaj-art-20156f6d721e4da586a0e9e487647d7c
institution OA Journals
issn 0785-3890
1365-2060
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Annals of Medicine
spelling doaj-art-20156f6d721e4da586a0e9e487647d7c2025-08-20T02:25:47ZengTaylor & Francis GroupAnnals of Medicine0785-38901365-20602025-12-0157110.1080/07853890.2025.2487636Predicting postoperative complications after pneumonectomy using machine learning: a 10-year studyYaxuan Wang0Shiyang Xie1Jiayun Liu2He Wang3Jiangang Yu4Wenya Li5Aika Guan6Shun Xu7Yong Cui8Wenfei Tan9Department of Anesthesiology, the First Hospital of China Medical University, ChinaDepartment of Radiation Oncology, the First Hospital of China Medical University, ChinaDepartment of Anesthesiology, the First Hospital of China Medical University, ChinaDepartment of Anesthesiology, the First Hospital of China Medical University, ChinaDepartment of Anesthesiology, the First Hospital of China Medical University, ChinaDepartment of Thoracic Surgery, the First Hospital of China Medical University, ChinaQueen’ University, Kingston, CanadaDepartment of Thoracic Surgery, the First Hospital of China Medical University, ChinaDepartment of Anesthesiology, the First Hospital of China Medical University, ChinaDepartment of Anesthesiology, the First Hospital of China Medical University, ChinaBackground Reducing postoperative cardiovascular and neurological complications (PCNC) during thoracic surgery is the key to improving postoperative survival.Objective We aimed to investigate independent predictors of PCNC, develop machine learning models, and construct a predictive nomogram for PCNC in patients undergoing thoracic surgery for lung cancer.Methods This study used data from a previous retrospective study of 16,368 patients with lung cancer (training set: 11,458; validation set: 4,910) with American Standards Association physical statuses I–IV who underwent surgery. Postoperative information was collected from electronic medical records to help build models based on cause-and-effect and statistical data, potentially revealing hidden dependencies between factors and diseases in a big data environment. The optimal model was analyzed and filtered using multiple machine-learning models (Logistic regression, eXtreme Gradient Boosting, Random forest, Light Gradient Boosting Machine and Naïve Bayes). A predictive nomogram was built and receiver operating characteristics were used to assess the validity of the model. The discriminative power and clinical validity were assessed using calibration and decision-making curve analyses.Results Multivariate logistic regression analysis revealed that age, surgery duration, intraoperative intercostal nerve block, postoperative patient-controlled analgesia, bronchial blocker use and sufentanil use were independent predictors of PCNC. Random forest was identified as the optimal model with an area under the curve of 0.898 in the training set and 0.752 in the validation set, confirming the excellent prediction accuracy of the nomogram. All the net benefits of the five machine-learning models in the training and validation sets demonstrated excellent clinical applicability, and the calibration curves showed good agreement between the predicted and observed risks.Conclusion The combination of machine-learning models and nomograms may contribute to the early prediction and reduction in the incidence of PCNC.https://www.tandfonline.com/doi/10.1080/07853890.2025.2487636Lung cancer, nomogrammachne learningpostoperative cardiovascular and neurological complicationsthoracic surgeryvideo-assisted thoracoscopic surgery
spellingShingle Yaxuan Wang
Shiyang Xie
Jiayun Liu
He Wang
Jiangang Yu
Wenya Li
Aika Guan
Shun Xu
Yong Cui
Wenfei Tan
Predicting postoperative complications after pneumonectomy using machine learning: a 10-year study
Annals of Medicine
Lung cancer, nomogram
machne learning
postoperative cardiovascular and neurological complications
thoracic surgery
video-assisted thoracoscopic surgery
title Predicting postoperative complications after pneumonectomy using machine learning: a 10-year study
title_full Predicting postoperative complications after pneumonectomy using machine learning: a 10-year study
title_fullStr Predicting postoperative complications after pneumonectomy using machine learning: a 10-year study
title_full_unstemmed Predicting postoperative complications after pneumonectomy using machine learning: a 10-year study
title_short Predicting postoperative complications after pneumonectomy using machine learning: a 10-year study
title_sort predicting postoperative complications after pneumonectomy using machine learning a 10 year study
topic Lung cancer, nomogram
machne learning
postoperative cardiovascular and neurological complications
thoracic surgery
video-assisted thoracoscopic surgery
url https://www.tandfonline.com/doi/10.1080/07853890.2025.2487636
work_keys_str_mv AT yaxuanwang predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT shiyangxie predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT jiayunliu predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT hewang predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT jiangangyu predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT wenyali predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT aikaguan predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT shunxu predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT yongcui predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy
AT wenfeitan predictingpostoperativecomplicationsafterpneumonectomyusingmachinelearninga10yearstudy