Machine learning-based risk prediction for invasive pulmonary aspergillosis in non-neutropenic intensive care unit patients, with an exploratory analysis of pathogen-related risk factors.
4 affiliations
- 1Department of Critical Care Medicine, General Hospital of Ningxia Medical University, Yinchuan, China.
- 2The Third People's Hospital of Ningxia, Yinchuan, Ningxia, China.
- 3The Fourth People's Hospital of Ningxia Hui Autonomous Region, Yinchuan, Ningxia, China.
- 4The First School of Clinical Medicine, Ningxia Medical University, Yinchuan, Ningxia, China.
Abstract
Invasive pulmonary aspergillosis (IPA) is increasingly recognized in non-neutropenic patients, but validated bedside risk stratification tools remain scarce. We developed a machine learning model to predict IPA and tested whether corticosteroid effect depends on bacterial co-pathogen. This multicenter retrospective cohort study enrolled 837 non-neutropenic adults hospitalized with pulmonary infections across three tertiary hospitals in China between December 2020 and December 2025. The discovery cohort was split into training and internal validation sets. Four classifiers were compared, with Random Forest selected for optimal performance. The final model was externally validated in an independent cohort. Feature importance was assessed using SHAP (SHapley Additive exPlanations) analysis. Corticosteroid-bacteria interactions were examined using subgroup analyses and propensity score matching, with the synergy index S calculated to quantify biological interaction. A simplified bedside score was derived from the top-ranking predictors. The Random Forest model achieved external validation AUC of 0.865. Six predictors consistently dominated across all assessments: Pseudomonas aeruginosa isolation, hypoxemia (PaO2/FiO2 <200 mmHg), diabetes mellitus, organ failure (Sequential Organ Failure Assessment, SOFA >5), lymphopenia (lymphocyte count <0.8×109/L), and ICU (intensive care unit) admission. Corticosteroid exposure did not rank among the top six predictors. However, its association with IPA diverged sharply by bacterial context: OR below 1 with P. aeruginosa (OR 0.52, 95% CI 0.214-1.283) but OR above 1 with other Gram-negative bacilli (OR 2.17, 95% CI 0.722-6.535); P for interaction = 0.131; a directional pattern that persisted after propensity matching. The six-variable score derived from these predictors showed AUCs of 0.869 (training), 0.774 (internal validation), and 0.719 (external validation). IPA risk in non-neutropenic ICU patients is shaped more by bacterial co-pathogen context than by corticosteroid exposure alone. The divergent corticosteroid effects across bacterial species challenge the conventional assumption of a uniform steroid-associated risk. The externally validated six-variable score offers a practical, software-free tool to support pathogen-informed, individualized risk stratification and clinical decision-making in the ICU.
Related
- Unclassifiable Invasive Pulmonary Aspergillosis in the Intensive Care Unit: Insights From a Multicenter, Retrospective Cohort Study in France (2022–2024)
- Comments on "Chronic Pulmonary Aspergillosis Complicated by a Lung Abscess Within a Pulmonary Cavity Successfully Treated With Percutaneous Drainage: A Case Report"
- Identification of soluble immune markers for the diagnosis of aspergillosis and pneumocystosis: an exploratory study
- "Chronic Pulmonary Aspergillosis Complicated by a Lung Abscess Within a Pulmonary Cavity Successfully Treated With Percutaneous Drainage: A Case Report"
- COVID-19-associated pulmonary aspergillosis: clinical characteristics, species distribution, environmental fungal contamination, and antifungal susceptibility
BibTeX
@article{bai2026machine,
title = {{Machine learning-based risk prediction for invasive pulmonary aspergillosis in non-neutropenic intensive care unit patients, with an exploratory analysis of pathogen-related risk factors.}},
author = {Jijia Bai and Tao Feng and Bofei Liu and Jinyan Wang and Zhifeng Wang and Furui Liu and Jinyuan Zhu},
journal = {Frontiers in cellular and infection microbiology},
year = {2026},
month = oct,
doi = {10.3389/fcimb.2026.1967577},
url = {https://europepmc.org/article/MED/42952730},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine learning-based risk prediction for invasive pulmonary aspergillosis in non-neutropenic intensive care unit patients, with an exploratory analysis of pathogen-related risk factors.
AU - Jijia Bai
AU - Tao Feng
AU - Bofei Liu
AU - Jinyan Wang
AU - Zhifeng Wang
AU - Furui Liu
AU - Jinyuan Zhu
PY - 2026
DA - 2026/10/14
JO - Frontiers in cellular and infection microbiology
DO - 10.3389/fcimb.2026.1967577
UR - https://europepmc.org/article/MED/42952730
AB - Invasive pulmonary aspergillosis (IPA) is increasingly recognized in non-neutropenic patients, but validated bedside risk stratification tools remain scarce. We developed a machine learning model to predict IPA and tested whether corticosteroid effect depends on bacterial co-pathogen. This multicenter retrospective cohort study enrolled 837 non-neutropenic adults hospitalized with pulmonary infections across three tertiary hospitals in China between December 2020 and December 2025. The discovery cohort was split into training and internal validation sets. Four classifiers were compared, with Random Forest selected for optimal performance. The final model was externally validated in an independent cohort. Feature importance was assessed using SHAP (SHapley Additive exPlanations) analysis. Corticosteroid-bacteria interactions were examined using subgroup analyses and propensity score matching, with the synergy index S calculated to quantify biological interaction. A simplified bedside score was derived from the top-ranking predictors. The Random Forest model achieved external validation AUC of 0.865. Six predictors consistently dominated across all assessments: Pseudomonas aeruginosa isolation, hypoxemia (PaO2/FiO2 <200 mmHg), diabetes mellitus, organ failure (Sequential Organ Failure Assessment, SOFA >5), lymphopenia (lymphocyte count <0.8×109/L), and ICU (intensive care unit) admission. Corticosteroid exposure did not rank among the top six predictors. However, its association with IPA diverged sharply by bacterial context: OR below 1 with P. aeruginosa (OR 0.52, 95% CI 0.214-1.283) but OR above 1 with other Gram-negative bacilli (OR 2.17, 95% CI 0.722-6.535); P for interaction = 0.131; a directional pattern that persisted after propensity matching. The six-variable score derived from these predictors showed AUCs of 0.869 (training), 0.774 (internal validation), and 0.719 (external validation). IPA risk in non-neutropenic ICU patients is shaped more by bacterial co-pathogen context than by corticosteroid exposure alone. The divergent corticosteroid effects across bacterial species challenge the conventional assumption of a uniform steroid-associated risk. The externally validated six-variable score offers a practical, software-free tool to support pathogen-informed, individualized risk stratification and clinical decision-making in the ICU.
SN - 2235-2988
ER -