Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 11:12:1501025.
doi: 10.3389/fmed.2025.1501025. eCollection 2025.

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

Junchen Pan  1 , Zhen Yue  2 , Jing Ji  2 , Yongping You  2 , Liqing Bi  2 , Yun Liu  3 , Xinglin Xiong  4 , Genying Gu  1 , Ming Chen  5 , Shen Zhang  6
Affiliations

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

Junchen Pan et al. Front Med (Lausanne). .

Abstract

Introduction: The 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.

Methods: Acute 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.

Results: A 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.

Conclusion: Machine 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.

Keywords: acute brain injury; area under the curve; intensive care unit; machine-learning models; nosocomial pneumonia.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Pearson correlation heatmap between variable.
Figure 2
Figure 2
Variable importance of features included in the machine learning algorithm for prediction of nosocomial pneumonia in ABI patients.
Figure 3
Figure 3
Accuracy chart of out-of-pocket data.
Figure 4
Figure 4
Receiver operating characteristic (ROC) curve and AUC among the 7 algorithm models.
Figure 5
Figure 5
Receiver operating characteristic curve and AUC among the external validation set.
Figure 6
Figure 6
The diagnosis model of XGBoost is used to predict the infection risk.
See this image and copyright information in PMC

References

    1. Krishnamoorthy V, Hough CL, Vavilala MS, Komisarow J, Chaikittisilpa N, Lele AV, et al. Tracheostomy after severe acute brain injury: trends and variability in the USA. Neurocrit Care. (2019) 30:546–54. doi: 10.1007/s12028-019-00697-5, PMID: - DOI - PMC - PubMed
    1. Gao L, Chang Y, Lu S, Liu X, Yao X, Zhang W, et al. A nomogram for predicting the necessity of tracheostomy after severe acute brain injury in patients within the neurosurgery intensive care unit: a retrospective cohort study. Heliyon. (2024) 10:e27416. doi: 10.1016/j.heliyon.2024.e27416, PMID: - DOI - PMC - PubMed
    1. Meisel C, Schwab JM, Prass K, Meisel A, Dirnagl U. Central nervous system injury-induced immune deficiency syndrome. Nat Rev Neurosci. (2005) 6:775–86. doi: 10.1038/nrn1765, PMID: - DOI - PubMed
    1. Sharma R, Shultz SR, Robinson MJ, Belli A, Hibbs ML, O'Brien TJ, et al. Infections after a traumatic brain injury: the complex interplay between the immune and neurological systems. Brain Behav Immun. (2019) 79:63–74. doi: 10.1016/j.bbi.2019.04.034, PMID: - DOI - PubMed
    1. Kourbeti IS, Vakis AF, Papadakis JA, Karabetsos DA, Bertsias G, Filippou M, et al. Infections in traumatic brain injury patients. Clin Microbiol Infect. (2012) 18:359–64. doi: 10.1111/j.1469-0691.2011.03625.x, PMID: - DOI - PubMed

LinkOut - more resources