EUVIMEDEUVIMED entdecken
ValidierungsstudieKohortenstudie

Development and Validation of a Machine Learning‐Based Risk Prediction Model for Delirium in Older Inpatients: A Prospective Cohort Study

Entwicklung und Validierung eines machine-learning-basierten Risikovorhersagemodells für Delir bei älteren stationären Patient:innen: prospektive Kohortenstudie

Xu-Hua Zhou iD, Di-Fei Duan, Meng Zhang, Shuang Liu, Jing Lv, Yi Wang iD, Lin Chen, Ying-Jun Zhang, Bo Gu iD, Qian Chen

Journal of Advanced Nursing · 2026-05 · 82 (5) · 4968-4982

DOI: 10.1111/jan.70154 ↗

Auf einen Blick

Ein Machine-Learning-Modell sagte Delir bei älteren stationären Patient:innen mit guter Leistung voraus. Das beste Modell war Random Forest mit AUC 0,908.

Fragestellung

Lässt sich mit Machine Learning das Delirrisiko bei älteren stationären Patient:innen vorhersagen?

Methode

Prospektive Kohortenstudie; 18 klinische Merkmale aus elektronischen Krankenakten während des Aufenthalts; 4 Machine-Learning-Algorithmen; Bewertung mit AUC, Accuracy, Sensitivität und Brier-Score.

Ergebnisse

973 ältere stationäre Patient:innen. Vier Modelle: AUC 0,869 bis 0,992, Accuracy 0,931 bis 0,962, Sensitivität 0,564 bis 0,997. Random Forest: AUC 0,908 (95 %-KI 0,848–0,968), Accuracy 0,935, Sensitivität 0,992, Brier-Score 0,053.

Schlussfolgerung der Autor:innen

Das entwickelte und validierte Machine-Learning-Modell zeigte eine ausgezeichnete Vorhersageleistung. Es könnte die frühe Diagnose und klinische Entscheidungsfindung unterstützen.

Kernaussagen

  • 973 ältere stationäre Patient:innen wurden für Entwicklung und Validierung genutzt
  • Random Forest erzielte die beste Gesamtleistung
  • AUC 0,908 (95 %-KI 0,848–0,968), Sensitivität 0,992

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

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of Advanced Nursing, online erschienen am 01.09.2025. Verfasst von Xu-Hua Zhou und 9 weiteren Autor:innen. Beteiligte Einrichtung: Hemodialysis Center, Department of Nephrology, West China Hospital, Sichuan University/West China School of Nursing, Sichuan University, Chengdu, Sic…. Hauptthemen laut MEDLINE: Delirium, Machine Learning, Inpatients. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Sichuan Provincial Popular Science Training Programme.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

To develop and validate a machine learning‐based risk prediction model for delirium in older inpatients.

Design

A prospective cohort study.

Methods

A prospective cohort study was conducted. Eighteen clinical features were prospectively collected from electronic medical records during hospitalisation to inform the model. Four machine learning algorithms were employed to develop and validate risk prediction models. The performance of all models in the training and test sets was evaluated using a combination of the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, Brier score, and other metrics before selecting the best model for SHAP interpretation.

Results

A total of 973 older inpatient data were utilised for model construction and validation. The AUC of four machine learning models in the training and test sets ranged from 0.869 to 0.992; the accuracy ranged from 0.931 to 0.962; and the sensitivity ranged from 0.564 to 0.997. Compared to other models, the Random Forest model exhibited the best overall performance with an AUC of 0.908 (95% CI, 0.848, 0.968), an accuracy of 0.935, a sensitivity of 0.992, and a Brier score of 0.053.

Conclusion

The machine learning model we developed and validated for predicting delirium in older inpatients demonstrated excellent predictive performance. This model has the potential to assist healthcare professionals in early diagnosis and support informed clinical decision‐making. Impact By identifying patients at risk of delirium early, healthcare professionals can implement preventive measures and timely interventions, potentially reducing the incidence and severity of delirium. The model's ability to support informed clinical decision‐making can lead to more personalised and effective care strategies, ultimately benefiting both patients and healthcare providers. Reporting Method This study was reported in accordance with the TRIPOD statement. Patient or Public Contribution No patient or public contribution.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DeliriumMachine LearningInpatientsHumansAgedProspective StudiesFemaleMaleAged, 80 and overRisk AssessmentRisk Factors

Stichwörter der Autor:innen

deliriummachine learningolder inpatientsrisk predictive model

Autor:innen und Institutionen

  • Hemodialysis Center, Department of Nephrology, West China Hospital, Sichuan University/West China School of Nursing, Sichuan University, Chengdu, Sichuan, People's Republic of China.
  • Department of Nephrology, Kidney Research Institute, West China Hospital of Sichuan University/West China School of Nursing, Sichuan University, Sichuan, People's Republic of China.
  • Center of Gerontology and Geriatrics, West China Hospital, Sichuan University/West China School of Nursing, Sichuan University, Chengdu, Sichuan, People's Republic of China.
  • Department of Urology, Institute of Urology, West China Hospital of Sichuan University/West China School of Nursing, Sichuan University, Sichuan, People's Republic of China.
  • Endocrinology and Metabolism Department, West China Hospital, Sichuan University/West China School of Nursing, Sichuan University, Chengdu, Sichuan, People's Republic of China.
  • Nephrology and Urology Ward, West China Hospital, Sichuan University/West China School of Nursing, Sichuan University, Chengdu, Sichuan, People's Republic of China.

ORCID-Profile: Xu-Hua Zhou, Yi Wang, Bo Gu

Förderung

  • National Key Research and Development Program of China
  • Sichuan Provincial Popular Science Training Programme

Zitieren

APA

Zhou, X. H., Duan, D. F., Zhang, M., Liu, S., Lv, J., Wang, Y., Chen, L., Zhang, Y. J., Gu, B., & Chen, Q. (2026). Development and Validation of a Machine Learning‐Based Risk Prediction Model for Delirium in Older Inpatients: A Prospective Cohort Study. Journal of Advanced Nursing, 82(5), 4968-4982. https://doi.org/10.1111/jan.70154

Vancouver

Zhou XH, Duan DF, Zhang M, Liu S, Lv J, Wang Y, et al. Development and Validation of a Machine Learning‐Based Risk Prediction Model for Delirium in Older Inpatients: A Prospective Cohort Study. Journal of Advanced Nursing. 2026;82(5):4968-4982. doi:10.1111/jan.70154

BibTeX
@article{Zhou2026,
  author = {Zhou, Xu-Hua and Duan, Di-Fei and Zhang, Meng and Liu, Shuang and Lv, Jing and Wang, Yi and Chen, Lin and Zhang, Ying-Jun and Gu, Bo and Chen, Qian},
  title = {Development and Validation of a Machine Learning‐Based Risk Prediction Model for Delirium in Older Inpatients: A Prospective Cohort Study},
  journal = {Journal of Advanced Nursing},
  year = {2026},
  volume = {82},
  number = {5},
  pages = {4968--4982},
  doi = {10.1111/jan.70154}
}
Kostenlos starten →