EUVIMEDEUVIMED entdecken
Crossref

Machine Learning–Based Prediction of Subsyndromal Delirium in Intensive Care Patients

Machine-Learning-basierte Vorhersage von Subsyndromalem Delir bei Intensivpatient:innen

Weiguang Wen, Xue Bai, Huimiao Jing, Ni Yang, Jie Zhai, Yingli Gao

American Journal of Critical Care · 01.01.2026 · 35 (1) · 20-31

DOI: 10.4037/ajcc2026815 ↗

Auf einen Blick

Bei 447 ICU-Patient:innen trat subsyndromales Delir in 20,1 % auf. Das Random-Forest-Modell zeigte unter 4 Machine-Learning-Modellen die beste Gesamtleistung.

Fragestellung

Ein Machine-Learning-Modell zur Vorhersage des Risikos für subsyndromales Delir bei Intensivpatient:innen entwickeln.

Methode

Prospektive Kohortenstudie mit 447 ICU-Patient:innen zwischen September 2023 und August 2024; 4 Machine-Learning-Modelle und eine logistische Regression.

Ergebnisse

Subsyndromales Delir trat bei 90 von 447 Patient:innen (20,1 %) auf. Das Random-Forest-Modell hatte die beste Leistung (AUC 0,885; F1-Score 0,629).

Schlussfolgerung der Autor:innen

Vier Machine-Learning-basierte Risikomodelle und 1 logistisches Regressionsmodell wurden entwickelt. Die Auswahl eines geeigneten Modells für das frühe Screening könnte individualisierte Frühinterventionen ermöglichen.

Kernaussagen

  • Subsyndromales Delir: 20,1 % bei 447 ICU-Patient:innen
  • Random-Forest-Modell mit bester Gesamtleistung
  • 8 unabhängige Prädiktoren wurden identifiziert

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 American Journal of Critical Care, erschienen am 01.01.2026. Verfasst von Weiguang Wen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Weiguang Wen is a master's degree candidate, School of Nursing, Shandong First Medical University and Shandong Academy of Medical Sciences, Taian, Sh…. Hauptthemen laut MEDLINE: Machine Learning, Delirium, Intensive Care Units, Critical Care. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Subsyndromal delirium is common in intensive care unit (ICU) patients and can prolong hospital stay, increase costs, and worsen prognosis. Advance intervention to prevent subsyndromal delirium would be valuable.

Objective

To construct a machine learning–based model to predict the risk of subsyndromal delirium in ICU patients.

Methods

This prospective cohort study included data from 447 patients hospitalized in the ICU between September 2023 and August 2024. Eight independent predictors of subsyndromal delirium were identified by least absolute shrinkage and selection operator and multivariate logistic regression analyses. Four machine learning models and a logistic regression model were constructed and validated to obtain the optimal algorithmic model.

Results

Subsyndromal delirium occurred in 90 ICU patients (20.1%). Richards-Campbell Sleep Questionnaire score, sedative use, restraint tape use, receipt of continuous renal replacement therapy or extracorporeal membrane oxygenation, intra-abdominal pressure, prealbumin level, history of alcohol consumption, and stroke were independent predictors of subsyndromal delirium. Of the 4 machine learning models constructed, the random forest model had the best comprehensive performance (area under the receiver operating characteristic curve, 0.885; F1 score, 0.629).

Conclusions

Four machine learning–based risk prediction models and 1 traditional logistic regression model were developed to predict risk of subsyndromal delirium in ICU patients. Choosing a suitable model for early screening of ICU patients at high risk of subsyndromal delirium would allow medical staff to formulate individualized early intervention plans, which could improve patients’ prognosis and save medical costs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningDeliriumIntensive Care UnitsCritical CareHumansMaleFemaleProspective StudiesMiddle AgedAgedLogistic ModelsRisk Factors

Autor:innen und Institutionen

  • Weiguang Wen is a master's degree candidate, School of Nursing, Shandong First Medical University and Shandong Academy of Medical Sciences, Taian, Shandong, China.
  • Xue Bai is a nurse, Second Ward of Department of Critical Care Medicine, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, China.
  • Huimiao Jing is a master's degree candidate, School of Nursing, Shandong First Medical University and Shandong Academy of Medical Sciences, Taian, Shandong, China.
  • Ni Yang is a master's degree candidate, School of Nursing, Shandong First Medical University and Shandong Academy of Medical Sciences, Taian, Shandong, China.
  • Jie Zhai is a master's degree candidate, School of Nursing, Shandong First Medical University and Shandong Academy of Medical Sciences, Taian, Shandong, China.
  • Yingli Gao is a professor, School of Nursing, Shandong First Medical University and Shandong Academy of Medical Sciences, Taian, Shandong, China.

Zitieren

APA

Wen, W., Bai, X., Jing, H., Yang, N., Zhai, J., & Gao, Y. (2026). Machine Learning–Based Prediction of Subsyndromal Delirium in Intensive Care Patients. American Journal of Critical Care, 35(1), 20-31. https://doi.org/10.4037/ajcc2026815

Vancouver

Wen W, Bai X, Jing H, Yang N, Zhai J, Gao Y. Machine Learning–Based Prediction of Subsyndromal Delirium in Intensive Care Patients. American Journal of Critical Care. 2026;35(1):20-31. doi:10.4037/ajcc2026815

BibTeX
@article{Wen2026,
  author = {Wen, Weiguang and Bai, Xue and Jing, Huimiao and Yang, Ni and Zhai, Jie and Gao, Yingli},
  title = {Machine Learning–Based Prediction of Subsyndromal Delirium in Intensive Care Patients},
  journal = {American Journal of Critical Care},
  year = {2026},
  volume = {35},
  number = {1},
  pages = {20--31},
  doi = {10.4037/ajcc2026815}
}
Kostenlos starten →