Machine Learning Approaches for Mortality Prediction in ARDS
Studies in Health Technology and Informatics · 29.06.2026
DOI: 10.3233/shti260878 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 29.06.2026. Verfasst von Xingyue Huo und 2 weiteren Autor:innen. Beteiligte Einrichtung: University of Arizona, Tucson, AZ, USA. Hauptthemen laut MEDLINE: Respiratory Distress Syndrome, Hospital Mortality, Machine Learning. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Mortality prediction in acute respiratory distress syndrome (ARDS) is critical for early triage and targeted treatment. In this study, we compared multiple machine learning models to predict 90-day all-cause mortality and 28-day hospital mortality in ARDS patients, with all models achieving good discrimination (AUC: 0.715–0.753 and 0.693–0.721, respectively). Among models, XGBoost achieved the most consistent balance of AUC, recall, and F1 score across both outcomes, making it the most clinically appropriate model where underpredicting high-risk patients brings significant consequences. Random forest models showed the highest AUC for the primary outcome but substantially lower recall.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Arizona, Tucson, AZ, USA.
Zitieren
APA
Huo, X., Bime, C., & Finkelstein, J. (2026). Machine Learning Approaches for Mortality Prediction in ARDS. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260878
Vancouver
Huo X, Bime C, Finkelstein J. Machine Learning Approaches for Mortality Prediction in ARDS. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260878
BibTeX
@article{Huo2026,
author = {Huo, Xingyue and Bime, Christian and Finkelstein, Joseph},
title = {Machine Learning Approaches for Mortality Prediction in ARDS},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti260878}
}
EUVIMED