Explainable Machine Learning Models for Classifying Preoperative Anxiety in Patients With Femoral Neck Fractures: A Retrospective Cohort Study
Erklärbare Machine-Learning-Modelle zur Klassifikation präoperativer Angst bei Patient:innen mit Schenkelhalsfrakturen: retrospektive Kohortenstudie
Nursing Open · 2026-10 · 13 (10)
DOI: 10.1002/nop2.70919 ↗Auf einen Blick
Bei 271 chirurgischen Aufnahmen wurden erklärbare Machine-Learning-Modelle zur gleichzeitigen Klassifikation präoperativer Angst entwickelt und intern validiert. Die drei Modelle zeigten ähnliche interne Diskrimination.
Fragestellung
Entwickeln und intern validieren von Machine-Learning-Modellen zur gleichzeitigen Klassifikation präoperativer Angst bei Patient:innen mit Schenkelhalsfrakturen.
Methode
Monozentrische retrospektive Beobachtungs-Kohortenstudie; klinische, perioperative und psychosoziale Daten aus 271 Aufnahmen; fünfmalige patientengruppierte nested Cross-Validation mit Präprozessierung, Feature-Selection, Resampling, Tuning und Kalibrierung.
Ergebnisse
Präoperative Angst war in 79 Aufnahmen nach HADS-A > 8 vorhanden. Die drei Algorithmen zeigten ähnliche interne Diskrimination; keine Paarvergleiche stützten die Überlegenheit eines Modells.
Einschränkungen
Externe und prospektive Validierung vor klinischer Anwendung erforderlich.
Schlussfolgerung der Autor:innen
Die Modelle identifizierten ein stabiles psychosoziales Merkmalsprofil für die gleichzeitige Klassifikation, benötigen aber externe und prospektive Validierung vor klinischer Nutzung.
Kernaussagen
- Präoperative Angst in 79 von 271 Aufnahmen nach HADS-A > 8
- Kein Modell war intern klar überlegen
- Psychische Resilienz, soziale Unterstützung und Operationsangst waren stabil ausgewählt
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Beobachtungsstudie in der Zeitschrift Nursing Open, online erschienen am 16.10.2026. Verfasst von Xue Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Post-Anesthesia Care Unit, The Second Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China. Hauptthemen laut MEDLINE: Machine Learning, Anxiety, Femoral Neck Fractures. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wenzhou Municipal Science and Technology Bureau.
Themen: Angst bei Patientinnen und Patienten, Künstliche Intelligenz in der Pflege
Abstract (Originalsprache)
Aim
To develop and internally validate explainable machine learning models for concurrent classification of preoperative anxiety in patients with femoral neck fractures.
Design
Single‐centre retrospective observational cohort study.
Methods
Clinical, perioperative and psychosocial data from 271 surgical admissions (270 patients) during 2024 were analysed. Preoperative anxiety was classified during the preoperative bedside assessment phase using a prespecified score greater than 8 on the anxiety subscale of the Hospital Anxiety and Depression Scale. Three tree‐based ensemble models were compared using fivefold, patient‐grouped nested cross‐validation with fold‐specific preprocessing, feature selection, resampling, tuning and separate probability calibration.
Results
Preoperative anxiety according to this prespecified definition was identified in 79 admissions. The anxiety group was older, had lower psychological resilience and perceived social support, and had greater surgical fear and frailty. The three algorithms showed similar internal discrimination, and paired comparisons did not support superiority of one model. Psychological resilience, perceived social support and surgical fear were selected in every validation fold for all models. Frailty index was selected in three of five folds for each model.
Conclusion
The models identified a stable psychosocial feature profile for concurrent classification but require external and prospective validation before clinical use.
Implications for Nursing
Practice These findings may inform future research on structured nursing assessment of preoperative anxiety. The models should not replace validated screening or clinical judgement and require prospective evaluation before routine use. Impact Psychological resilience, perceived social support and surgical fear were the most stable selected features. Reporting Method The Strengthening the Reporting of Observational Studies in Epidemiology and TRIPOD+AI reporting guidelines were followed. No Patient or Public Contribution None, because this study retrospectively analysed existing de‐identified records.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Post-Anesthesia Care Unit, The Second Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China.
- Department of Operating Room, The Second Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China.
- Department of Intensive Care Unit, The Second Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China.
- Department of General Intensive Care Unit, The Second Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China.
ORCID-Profile: Shuzhi Zheng, Fang He
Förderung
- Wenzhou Municipal Science and Technology Bureau
Zitieren
APA
Zhang, X., Zheng, S., Zhang, Z., Yang, P., Wei, Q., Jin, M., & He, F. (2026). Explainable Machine Learning Models for Classifying Preoperative Anxiety in Patients With Femoral Neck Fractures: A Retrospective Cohort Study. Nursing Open, 13(10). https://doi.org/10.1002/nop2.70919
Vancouver
Zhang X, Zheng S, Zhang Z, Yang P, Wei Q, Jin M, et al. Explainable Machine Learning Models for Classifying Preoperative Anxiety in Patients With Femoral Neck Fractures: A Retrospective Cohort Study. Nursing Open. 2026;13(10). doi:10.1002/nop2.70919
BibTeX
@article{Zhang2026,
author = {Zhang, Xue and Zheng, Shuzhi and Zhang, Zanhua and Yang, Peiyi and Wei, Qiao and Jin, Mimi and He, Fang},
title = {Explainable Machine Learning Models for Classifying Preoperative Anxiety in Patients With Femoral Neck Fractures: A Retrospective Cohort Study},
journal = {Nursing Open},
year = {2026},
volume = {13},
number = {10},
doi = {10.1002/nop2.70919}
}
EUVIMED