Predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine-learning models

IntroductionThe aim of this study is to construct and validate new machine learning models to predict pneumonia events in intensive care unit (ICU) patients with acute brain injury.MethodsAcute brain injury patients in ICU of hospitals from January 1, 2020, to December 31, 2021 were retrospective re...

Full description

Saved in:
Bibliographic Details
Main Authors: Junchen Pan, Zhen Yue, Jing Ji, Yongping You, Liqing Bi, Yun Liu, Xinglin Xiong, Genying Gu, Ming Chen, Shen Zhang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1501025/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850211274362716160
author Junchen Pan
Zhen Yue
Jing Ji
Yongping You
Liqing Bi
Yun Liu
Xinglin Xiong
Genying Gu
Ming Chen
Shen Zhang
author_facet Junchen Pan
Zhen Yue
Jing Ji
Yongping You
Liqing Bi
Yun Liu
Xinglin Xiong
Genying Gu
Ming Chen
Shen Zhang
author_sort Junchen Pan
collection DOAJ
description IntroductionThe aim of this study is to construct and validate new machine learning models to predict pneumonia events in intensive care unit (ICU) patients with acute brain injury.MethodsAcute brain injury patients in ICU of hospitals from January 1, 2020, to December 31, 2021 were retrospective reviewed. Patients were divided into training, and validation sets. The primary outcome was nosocomial pneumonia infection during ICU stay. Machine learning models including XGBoost, DecisionTree, Random Forest, Light GBM, Adaptive Boost, BP, and TabNet were used for model derivation. The predictive value of each model was evaluated using accuracy, precision, recall, F1-score, and area under the curve (AUC), and internal and external validation was performed.ResultsA total of 280 ICU patients with acute brain injury were included. Five independent variables for nosocomial pneumonia infection were identified and selected for machine learning model derivations and validations, including tracheotomy time, antibiotic use days, blood glucose, ventilator-assisted ventilation time, and C-reactive protein. The training set revealed the superior and robust performance of the XGBoost with the highest AUC value (0.956), while the Random Forest and Adaptive Boost had the highest AUC value (0.883) in validation set.ConclusionMachine learning models can effectively predict the risk of nosocomial pneumonia infection in patients with acute brain injury in the ICU. Despite differences in populations and algorithms, the models we constructed demonstrated reliable predictive performance.
format Article
id doaj-art-5ed2862aaf144f9282c0ebb40a0104d4
institution OA Journals
issn 2296-858X
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-5ed2862aaf144f9282c0ebb40a0104d42025-08-20T02:09:35ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-04-011210.3389/fmed.2025.15010251501025Predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine-learning modelsJunchen Pan0Zhen Yue1Jing Ji2Yongping You3Liqing Bi4Yun Liu5Xinglin Xiong6Genying Gu7Ming Chen8Shen Zhang9Department of Neurosurgery, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaDepartment of Neurosurgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaDepartment of Neurosurgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaDepartment of Neurosurgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaDepartment of Neurosurgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaDepartment of Information, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaDepartment of Nursing, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaDepartment of Neurosurgery, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaDepartment of Rehabilitation, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, Jiangsu, ChinaEngineering Research Center of Health Service System Based on Ubiquitous Wireless Networks, Ministry of Education, Nanjing, ChinaIntroductionThe aim of this study is to construct and validate new machine learning models to predict pneumonia events in intensive care unit (ICU) patients with acute brain injury.MethodsAcute brain injury patients in ICU of hospitals from January 1, 2020, to December 31, 2021 were retrospective reviewed. Patients were divided into training, and validation sets. The primary outcome was nosocomial pneumonia infection during ICU stay. Machine learning models including XGBoost, DecisionTree, Random Forest, Light GBM, Adaptive Boost, BP, and TabNet were used for model derivation. The predictive value of each model was evaluated using accuracy, precision, recall, F1-score, and area under the curve (AUC), and internal and external validation was performed.ResultsA total of 280 ICU patients with acute brain injury were included. Five independent variables for nosocomial pneumonia infection were identified and selected for machine learning model derivations and validations, including tracheotomy time, antibiotic use days, blood glucose, ventilator-assisted ventilation time, and C-reactive protein. The training set revealed the superior and robust performance of the XGBoost with the highest AUC value (0.956), while the Random Forest and Adaptive Boost had the highest AUC value (0.883) in validation set.ConclusionMachine learning models can effectively predict the risk of nosocomial pneumonia infection in patients with acute brain injury in the ICU. Despite differences in populations and algorithms, the models we constructed demonstrated reliable predictive performance.https://www.frontiersin.org/articles/10.3389/fmed.2025.1501025/fullintensive care unitarea under the curveacute brain injurynosocomial pneumoniamachine-learning models
spellingShingle Junchen Pan
Zhen Yue
Jing Ji
Yongping You
Liqing Bi
Yun Liu
Xinglin Xiong
Genying Gu
Ming Chen
Shen Zhang
Predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine-learning models
Frontiers in Medicine
intensive care unit
area under the curve
acute brain injury
nosocomial pneumonia
machine-learning models
title Predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine-learning models
title_full Predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine-learning models
title_fullStr Predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine-learning models
title_full_unstemmed Predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine-learning models
title_short Predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine-learning models
title_sort predicting nosocomial pneumonia of patients with acute brain injury in intensive care unit using machine learning models
topic intensive care unit
area under the curve
acute brain injury
nosocomial pneumonia
machine-learning models
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1501025/full
work_keys_str_mv AT junchenpan predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT zhenyue predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT jingji predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT yongpingyou predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT liqingbi predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT yunliu predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT xinglinxiong predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT genyinggu predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT mingchen predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels
AT shenzhang predictingnosocomialpneumoniaofpatientswithacutebraininjuryinintensivecareunitusingmachinelearningmodels