EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced machine learning predictive modeling for delirium in elderly ICU patients with COPD and respiratory failure: A retrospective study based on MIMIC-IV

Verbessertes Machine-Learning-Prädiktionsmodell für Delir bei älteren ICU-Patient:innen mit COPD und respiratorischem Versagen: retrospektive Studie auf Basis von MIMIC-IV

Zong-Bi Wu iD, You-Li Jiang iD, Shuai-Shuai Li, Ao Li iD

PLOS ONE · 20.03.2025 · 20 (3) · e0319297

DOI: 10.1371/journal.pone.0319297 ↗

Auf einen Blick

Bei 1.155 älteren ICU-Patient:innen mit COPD und respiratorischem Versagen trat Delir bei 12,9 % auf. Das XGBoost-Modell zeigte die beste Trennschärfe.

Fragestellung

Soll ein Machine-Learning-Modell das Delirrisiko bei älteren ICU-Patient:innen mit COPD und respiratorischem Versagen vorhersagen?

Methode

Retrospektive Studie mit Daten aus MIMIC-IV; 4 Modelle wurden trainiert und per 10-fold cross-validation geprüft.

Ergebnisse

1.155 Patient:innen; Delirinzidenz 12,9 % (149/1.155). XGBoost: AUC 0,932; Accuracy 0,891; Precision 0,839; Recall 0,795; F1 0,810.

Schlussfolgerung der Autor:innen

Das entwickelte Vorhersagemodell sagte Delir bei älteren COPD-Patient:innen mit respiratorischem Versagen auf der ICU wirksam voraus.

Kernaussagen

  • Delirinzidenz: 12,9 % (149/1.155)
  • XGBoost mit bester diskriminierender Leistung (AUC 0,932)
  • Wichtige Merkmale laut SHAP: u. a. GCS, SpO₂ und Aufenthaltsdauer

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 20.03.2025. Verfasst von Zong-Bi Wu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Nursing Department, Shenzhen Traditional Chinese Medicine Hospital (The Fourth Clinical Medical School of Guangzhou University of Chinese Medicine), …. Hauptthemen laut MEDLINE: Delirium, Machine Learning, Pulmonary Disease, Chronic Obstructive, Respiratory Insufficiency. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and objective Elderly patients with Chronic obstructive pulmonary disease (COPD) and respiratory failure admitted to the intensive care unit (ICU) have a poor prognosis, and the occurrence of delirium further worsens outcomes and increases hospitalization costs. This study aimed to develop a predictive model for delirium in this patient population and identify associated risk factors Methods Data for the machine learning model were obtained from the MIMIC-IV database. Feature variable screening was conducted using Lasso regression and the best subset method. Four models—K-nearest neighbor, random forest, logistic regression, and extreme gradient boosting (XGBoost)—were trained and optimized to predict delirium risk. The stability of the model is evaluated using ten-fold cross validation and the effectiveness of the model on the validation set is evaluated using accuracy, F1 score, precision and recall. The SHapley Additive exPlanations (SHAP) method was used to explain the importance of each variable in the model.

Results

A total of 1,155 patients admitted to the intensive care unit between 2008 and 2019 were included in the study, with a delirium incidence of 12.9% (149/1,155). Among the four ML models evaluated, the XGBoost model demonstrated the best discriminative ability. In the validation set, it achieved an AUC of 0.932, indicating superior performance with high accuracy, precision, recall, and F1 scores of 0.891, 0.839, 0.795, and 0.810, respectively. Key features identified through SHAP analysis included the Glasgow Coma Scale (GCS) verbal score, length of hospital stay, mean SpO₂ on the first day of ICU admission, Modification of Diet in Renal Disease (MDRD) equation score, mean diastolic blood pressure, GCS motor score, gender, and duration of noninvasive ventilation. These findings provide valuable insights for individualized risk management.

Conclusions

The developed prediction model effectively predicts the occurrence of delirium in elderly COPD patients with respiratory failure in the ICU. This model can assist clinical decision-making, potentially improving patient outcomes and reducing healthcare costs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DeliriumMachine LearningPulmonary Disease, Chronic ObstructiveRespiratory InsufficiencyHumansAgedMaleFemaleIntensive Care UnitsRetrospective StudiesRisk FactorsAged, 80 and overPrognosis

Autor:innen und Institutionen

  • Nursing Department, Shenzhen Traditional Chinese Medicine Hospital (The Fourth Clinical Medical School of Guangzhou University of Chinese Medicine), Shenzhen, China.
  • Department of Neurology, People's Hospital of Longhua, Shenzhen, China.
  • Clinical Nursing Teaching and Research Section, The Second Xiangya Hospital of Central South University, Changsha, China.

ORCID-Profile: Zong-Bi Wu, You-Li Jiang, Ao Li

Zitieren

APA

Wu, Z. B., Jiang, Y. L., Li, S. S., & Li, A. (2025). Enhanced machine learning predictive modeling for delirium in elderly ICU patients with COPD and respiratory failure: A retrospective study based on MIMIC-IV. PLOS ONE, 20(3), e0319297. https://doi.org/10.1371/journal.pone.0319297

Vancouver

Wu ZB, Jiang YL, Li SS, Li A. Enhanced machine learning predictive modeling for delirium in elderly ICU patients with COPD and respiratory failure: A retrospective study based on MIMIC-IV. PLOS ONE. 2025;20(3):e0319297. doi:10.1371/journal.pone.0319297

BibTeX
@article{Wu2025,
  author = {Wu, Zong-Bi and Jiang, You-Li and Li, Shuai-Shuai and Li, Ao},
  title = {Enhanced machine learning predictive modeling for delirium in elderly ICU patients with COPD and respiratory failure: A retrospective study based on MIMIC-IV},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {3},
  pages = {e0319297},
  doi = {10.1371/journal.pone.0319297}
}
Kostenlos starten →