An Interpretable Machine Learning Model for Predicting In-hospital Mortality in ICU Patients with Ventilator-associated Pneumonia

Overview

Journal PLoS One

Specialties General Medicine
Science

Date 2025 Jan 8

PMID 39774553

Authors

Junying Wei

Heshan Cao

Mingling Peng

Yinzhou Zhang

Sibei Li

Wuhua Ma

Yuhui Li

Affiliations

Soon will be listed here.

Abstract

Background: Ventilator-associated pneumonia (VAP) is a common nosocomial infection in ICU, significantly associated with poor outcomes. However, there is currently a lack of reliable and interpretable tools for assessing the risk of in-hospital mortality in VAP patients. This study aims to develop an interpretable machine learning (ML) prediction model to enhance the assessment of in-hospital mortality risk in VAP patients.

Methods: This study extracted VAP patient data from versions 2.2 and 3.1 of the MIMIC-IV database, using version 2.2 for model training and validation, and version 3.1 for external testing. Feature selection was conducted using the Boruta algorithm, and 14 ML models were constructed. The optimal model was identified based on the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, and specificity across both validation and test cohorts. SHapley Additive exPlanations (SHAP) analysis was applied for global and local interpretability.

Results: A total of 1,894 VAP patients were included, with 12 features ultimately selected for model construction: 24-hour urine output, blood urea nitrogen, age, diastolic blood pressure, platelet count, anion gap, body temperature, bicarbonate level, sodium level, body mass index, and whether combined with congestive heart failure and cerebrovascular disease. The random forest (RF) model showed the best performance, achieving an AUC of 0.780 in internal validation and 0.724 in external testing, outperforming other ML models and common clinical scoring systems.

Conclusion: The RF model demonstrated robust and reliable performance in predicting in-hospital mortality risk for VAP patients. The developed online tool can assist clinicians in efficiently assessing VAP in-hospital mortality risk, supporting clinical decision-making.

References

Chao H, Wu C, Singh A, Shedd A, Wolfshohl J, Chou E . Using Machine Learning to Develop and Validate an In-Hospital Mortality Prediction Model for Patients with Suspected Sepsis. Biomedicines. 2022; 10(4). PMC: 9030924. DOI: 10.3390/biomedicines10040802. View

Frondelius T, Atkova I, Miettunen J, Rello J, Vesty G, Chew H . Early prediction of ventilator-associated pneumonia with machine learning models: A systematic review and meta-analysis of prediction model performance. Eur J Intern Med. 2023; 121:76-87. DOI: 10.1016/j.ejim.2023.11.009. View

Liu B, Beck E, Fisher M . The Brief Case: Ventilator-Associated Corynebacterium accolens Pneumonia in a Patient with Respiratory Failure Due to COVID-19. J Clin Microbiol. 2021; 59(9):e0013721. PMC: 8372998. DOI: 10.1128/JCM.00137-21. View

Li Y, Wang Y, Lee H, Tsao S, Lu M, Yang S . Monocyte Chemoattractant Protein-1, a Possible Biomarker of Multiorgan Failure and Mortality in Ventilator-Associated Pneumonia. Int J Mol Sci. 2019; 20(9). PMC: 6539645. DOI: 10.3390/ijms20092218. View

Wen C, Zhang X, Li Y, Xiao W, Hu Q, Lei X . An interpretable machine learning model for predicting 28-day mortality in patients with sepsis-associated liver injury. PLoS One. 2024; 19(5):e0303469. PMC: 11104601. DOI: 10.1371/journal.pone.0303469. View

Xu D, Lu Y, Wang Y, Li F . The obesity paradox and 90 day mortality in chronic critically ill patients: a cohort study using a large clinical database. Eur J Med Res. 2024; 29(1):392. PMC: 11285416. DOI: 10.1186/s40001-024-01962-w. View

Du Y, Lv Y, Zha W, Zhou N, Hong X . Association of body mass index (BMI) with critical COVID-19 and in-hospital mortality: A dose-response meta-analysis. Metabolism. 2020; 117:154373. PMC: 7493748. DOI: 10.1016/j.metabol.2020.154373. View

Liu B, Hill H . Role of Host Immune and Inflammatory Responses in COVID-19 Cases with Underlying Primary Immunodeficiency: A Review. J Interferon Cytokine Res. 2020; 40(12):549-554. PMC: 7757688. DOI: 10.1089/jir.2020.0210. View

Zhou S, Lu Z, Liu Y, Wang M, Zhou W, Cui X . Interpretable machine learning model for early prediction of 28-day mortality in ICU patients with sepsis-induced coagulopathy: development and validation. Eur J Med Res. 2024; 29(1):14. PMC: 10763177. DOI: 10.1186/s40001-023-01593-7. View

10.

Perez A, Viana M, DallOrto Thomazini L, Loss S, de Machado F, do Nascimento A . BMI and mortality in critically ill patients with COVID-19: another brick in the wall of the obesity paradox. Obesity (Silver Spring). 2024; 32(8):1474-1482. DOI: 10.1002/oby.24069. View

11.

Delle Rose D, Pezzotti P, Fortunato E, Sordillo P, Gini S, Boros S . Clinical predictors and microbiology of ventilator-associated pneumonia in the intensive care unit: a retrospective analysis in six Italian hospitals. Eur J Clin Microbiol Infect Dis. 2016; 35(9):1531-9. DOI: 10.1007/s10096-016-2694-9. View

12.

Topol E . High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019; 25(1):44-56. DOI: 10.1038/s41591-018-0300-7. View

13.

Heffernan A, Judge S, Petrie S, Godahewa R, Bergmeir C, Pilcher D . Association Between Urine Output and Mortality in Critically Ill Patients: A Machine Learning Approach. Crit Care Med. 2021; 50(3):e263-e271. DOI: 10.1097/CCM.0000000000005310. View

14.

Lundberg S, Erion G, Chen H, DeGrave A, Prutkin J, Nair B . From Local Explanations to Global Understanding with Explainable AI for Trees. Nat Mach Intell. 2020; 2(1):56-67. PMC: 7326367. DOI: 10.1038/s42256-019-0138-9. View

15.

Ortiz-Barrios M, Arias-Fonseca S, Ishizaka A, Barbati M, Avendano-Collante B, Navarro-Jimenez E . Artificial intelligence and discrete-event simulation for capacity management of intensive care units during the Covid-19 pandemic: A case study. J Bus Res. 2023; 160:113806. PMC: 9981538. DOI: 10.1016/j.jbusres.2023.113806. View

16.

Dana R, Bannay A, Bourst P, Ziegler C, Losser M, Gibot S . Obesity and mortality in critically ill COVID-19 patients with respiratory failure. Int J Obes (Lond). 2021; 45(9):2028-2037. PMC: 8190754. DOI: 10.1038/s41366-021-00872-9. View

17.

Hu C, Li L, Huang W, Wu T, Xu Q, Liu J . Interpretable Machine Learning for Early Prediction of Prognosis in Sepsis: A Discovery and Validation Study. Infect Dis Ther. 2022; 11(3):1117-1132. PMC: 9124279. DOI: 10.1007/s40121-022-00628-6. View

18.

Pirracchio R, Cohen M, Malenica I, Cohen J, Chambaz A, Cannesson M . Big data and targeted machine learning in action to assist medical decision in the ICU. Anaesth Crit Care Pain Med. 2018; 38(4):377-384. DOI: 10.1016/j.accpm.2018.09.008. View

19.

Liu B, Martins T, Peterson L, Hill H . Clinical significance of measuring serum cytokine levels as inflammatory biomarkers in adult and pediatric COVID-19 cases: A review. Cytokine. 2021; 142:155478. PMC: 7901304. DOI: 10.1016/j.cyto.2021.155478. View

20.

Johnson A, Bulgarelli L, Shen L, Gayles A, Shammout A, Horng S . MIMIC-IV, a freely accessible electronic health record dataset. Sci Data. 2023; 10(1):1. PMC: 9810617. DOI: 10.1038/s41597-022-01899-x. View