EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A machine learning-based prediction of hospital mortality in mechanically ventilated ICU patients

Hexin Li, Negin Ashrafi iD, Chris Kang, Guanlan Zhao, Yubing Chen, Maryam Pishgar iD

PLOS ONE · 04.09.2024 · 19 (9) · e0309383

DOI: 10.1371/journal.pone.0309383 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 04.09.2024. Verfasst von Hexin Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Industrial and Systems Engineering, University of Southern California (USC), Los Angeles, CA, United States of America. Hauptthemen laut MEDLINE: Respiration, Artificial, Hospital Mortality, Intensive Care Units, Machine Learning. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Mechanical ventilation (MV) is vital for critically ill ICU patients but carries significant mortality risks. This study aims to develop a predictive model to estimate hospital mortality among MV patients, utilizing comprehensive health data to assist ICU physicians with early-stage alerts.

Methods

We developed a Machine Learning (ML) framework to predict hospital mortality in ICU patients receiving MV. Using the MIMIC-III database, we identified 25,202 eligible patients through ICD-9 codes. We employed backward elimination and the Lasso method, selecting 32 features based on clinical insights and literature. Data preprocessing included eliminating columns with over 90% missing data and using mean imputation for the remaining missing values. To address class imbalance, we used the Synthetic Minority Over-sampling Technique (SMOTE). We evaluated several ML models, including CatBoost, XGBoost, Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Logistic Regression, using a 70/30 train-test split. The CatBoost model was chosen for its superior performance in terms of accuracy, precision, recall, F1-score, AUROC metrics, and calibration plots.

Results

The study involved a cohort of 25,202 patients on MV. The CatBoost model attained an AUROC of 0.862, an increase from an initial AUROC of 0.821, which was the best reported in the literature. It also demonstrated an accuracy of 0.789, an F1-score of 0.747, and better calibration, outperforming other models. These improvements are due to systematic feature selection and the robust gradient boosting architecture of CatBoost.

Conclusion

The preprocessing methodology significantly reduced the number of relevant features, simplifying computational processes, and identified critical features previously overlooked. Integrating these features and tuning the parameters, our model demonstrated strong generalization to unseen data. This highlights the potential of ML as a crucial tool in ICUs, enhancing resource allocation and providing more personalized interventions for MV patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Respiration, ArtificialHospital MortalityIntensive Care UnitsMachine LearningHumansMaleFemaleMiddle AgedAgedSupport Vector MachineCritical IllnessDatabases, Factual

Autor:innen und Institutionen

  • Department of Industrial and Systems Engineering, University of Southern California (USC), Los Angeles, CA, United States of America.

ORCID-Profile: Negin Ashrafi, Maryam Pishgar

Zitieren

APA

Li, H., Ashrafi, N., Kang, C., Zhao, G., Chen, Y., & Pishgar, M. (2024). A machine learning-based prediction of hospital mortality in mechanically ventilated ICU patients. PLOS ONE, 19(9), e0309383. https://doi.org/10.1371/journal.pone.0309383

Vancouver

Li H, Ashrafi N, Kang C, Zhao G, Chen Y, Pishgar M. A machine learning-based prediction of hospital mortality in mechanically ventilated ICU patients. PLOS ONE. 2024;19(9):e0309383. doi:10.1371/journal.pone.0309383

BibTeX
@article{Li2024,
  author = {Li, Hexin and Ashrafi, Negin and Kang, Chris and Zhao, Guanlan and Chen, Yubing and Pishgar, Maryam},
  title = {A machine learning-based prediction of hospital mortality in mechanically ventilated ICU patients},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {9},
  pages = {e0309383},
  doi = {10.1371/journal.pone.0309383}
}
Kostenlos starten →