Multi-input deep learning to predict ventilator-associated pneumonia in patients treated for major trauma
Journal of Acute Care Surgery · 31.03.2026 · 16 (1) · 20-30
DOI: 10.17479/jacs.2025.0042 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Acute Care Surgery, erschienen am 31.03.2026. Verfasst von Jae Young Yang und 8 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0).
Themen: Pneumonieprophylaxe
Abstract (Originalsprache)
Purpose
Ventilator-associated pneumonia (VAP) is a frequent complication among critically ill patients with major trauma. We aimed to develop and evaluate a multi-input deep learning model that integrates early clinical data and chest radiographs to predict VAP in mechanically ventilated trauma patients.
Methods
We retrospectively analyzed patients aged ≥16 years with an Injury Severity Score ≥16 who were admitted to a level I trauma center intensive care unit and required mechanical ventilation for more than 2 days. VAP was defined as the presence of new or progressive pulmonary infiltrates within the first week after admission together with compatible microbiological findings. Selected clinical variables and early chest radiographs were processed using a ResNet50-based convolutional neural network with long short-term memory layers. Clinical and imaging features were integrated into a multi-input neural network and evaluated using a held-out test dataset.
Results
Among 491 patients, 147 (29.9%) developed VAP. In the test dataset, the integrated model achieved a sensitivity of 0.92, a negative predictive value of 0.97, and an area under the receiver operating characteristic curve of 0.84.
Conclusion
A multi-input deep learning model that combined early clinical variables with chest radiographs demonstrated high sensitivity and negative predictive value for predicting VAP in patients with major trauma.
Zitieren
APA
Yang, J. Y., Lee, J. Y., Sul, Y., Lee, J. S., Yoon, S., Han, J., Seok, J., Choi, J. H., & Kim, H. R. (2026). Multi-input deep learning to predict ventilator-associated pneumonia in patients treated for major trauma. Journal of Acute Care Surgery, 16(1), 20-30. https://doi.org/10.17479/jacs.2025.0042
Vancouver
Yang JY, Lee JY, Sul Y, Lee JS, Yoon S, Han J, et al. Multi-input deep learning to predict ventilator-associated pneumonia in patients treated for major trauma. Journal of Acute Care Surgery. 2026;16(1):20-30. doi:10.17479/jacs.2025.0042
BibTeX
@article{Yang2026,
author = {Yang, Jae Young and Lee, Jin Young and Sul, Younghoon and Lee, Jin Suk and Yoon, Suyoung and Han, Jonghee and Seok, Junepill and Choi, Jung Hee and Kim, Hong Rye},
title = {Multi-input deep learning to predict ventilator-associated pneumonia in patients treated for major trauma},
journal = {Journal of Acute Care Surgery},
year = {2026},
volume = {16},
number = {1},
pages = {20--30},
doi = {10.17479/jacs.2025.0042}
}
EUVIMED