Bayesian network model for identification of factors associated with ventilator-associated pneumonia in…

Cohort studyBMC pulmonary medicine· Jul 2026

Bayesian network model for identification of factors associated with ventilator-associated pneumonia in mechanically ventilated patients in the ICU: retrospective cohort study.

Liyu Zhang, Cailing Wang, Jing He … Yinghui Zhang

Pulmonology & Critical CareCohort studyPrognosisQ2IF 3.1

Bayesian network model showed good performance for identifying ventilator-associated pneumonia risk.

Bayesian network model for identification of factors associated with ventilator-associated pneumonia in mechanically ventilated patients in the ICU: retrospective cohort study.

Liyu Zhang … Yinghui Zhang

BMC pulmonary medicine · Jul 2026

Background

Ventilator-associated pneumonia (ventilator-associated pneumonia) represents a complication occurring in patients undergoing mechanical ventilation.

Purpose

This study aimed to develop a Bayesian network model to identify factors associated with the occurrence of ventilator-associated pneumonia.

Methods

A retrospective cohort analysis was conducted using data from patients aged ≥ 60 years who underwent mechanical ventilation in the Department of Intensive care unit at the Second Hospital of Shanxi Medical University between June 2018 and June 2022.

n = 502 patients

0.84

Results

0.84

the model performed well in identifying patients at higher risk for ventilator-associated pneumonia

n = 502 patients

More results

The prevalence of ventilator-associated pneumonia was 9.6% (48/502 patients).

The constructed Bayesian network included 10 nodes and 17 directed edges.

More results

Direct associations with ventilator-associated pneumonia were identified for antibiotic use exceeding three agents, reintubation, mechanical ventilation methods, and an Acute Physiology and Chronic Health Evaluation II (APACHE II) score ≥ 15.

“

Conclusion · 1 of 2

The Bayesian network model elucidates the interrelationships among multiple factors associated with ventilator-associated pneumonia.

Conclusion · 2 of 2

The model may provide ancillary information to help clinicians identify patient profiles associated with higher ventilator-associated pneumonia risk and facilitate the implementation of early during mechanical ventilation.

Bayesian network model for identification of factors associated with ventilator-associated pneumonia in mechanically ventilated patients in the ICU: retrospective cohort study.

Bayesian network model for identification of factors associated with ventilator-associated pneumonia in mechanically ventilated patients in the ICU: retrospective cohort study.

Related papers