Development of a Disease Model for Predicting Postoperative Delirium Using Combined Blood Biomarkers
Entwicklung eines Krankheitsmodells zur Vorhersage von postoperativem Delir mithilfe kombinierter Blutbiomarker
Annals of Clinical and Translational Neurology · 2025-05 · 12 (5) · 976-985
DOI: 10.1002/acn3.70029 ↗Auf einen Blick
Bei 555 Patient:innen nach radikaler Kolorektalkarzinom-Operation sagte ein Machine-Learning-Modell postoperatives Delir anhand von Demografie- und Blutmarkern vorher. Das beste Modell war ein Random Forest mit AUC 0,795.
Fragestellung
Kann ein multidimensionales Risikovorhersagemodell mit demografischen Parametern und Blutbiomarkern postoperatives Delir nach Operation vorhersagen?
Methode
555 Patient:innen nach radikaler Operation wegen Kolorektalkarzinom; präoperative Demografie und Lipide, perioperative Anästhesie- und Operationsdaten, Blutbiomarker vor und nach der Operation; Delir mit 3D-CAM innerhalb von 3 Tagen; Vergleich von 10 Machine-Learning-Modellen.
Ergebnisse
100 Patient:innen mit postoperativem Delir und 455 ohne Delir. Der Random Forest erzielte in der Validierung die beste Leistung: AUC 0,795 (95 %-KI 0,704–0,885). Wichtige Prädiktoren waren Gesamtcholesterin, Triglyzeride und Trimethylamin-N-oxid.
Schlussfolgerung der Autor:innen
Blutbiomarker sind wichtig für die Vorhersage von postoperativem Delir und unterstützen Anästhesist:innen bei der rechtzeitigen Risikoerkennung. Das Modell soll eine personalisierte perioperative Behandlung ermöglichen.
Kernaussagen
- Random Forest: AUC 0,795 (95 %-KI 0,704–0,885)
- Wichtige Prädiktoren: Gesamtcholesterin, Triglyzeride, Trimethylamin-N-oxid
- 3D-CAM erfasste Delir innerhalb von 3 Tagen nach der Operation
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 Annals of Clinical and Translational Neurology, online erschienen am 17.03.2025. Verfasst von Hengjun Wan und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology, The Affiliated Hospital, Southwest Medical University, Luzhou, Sichuan, China. Hauptthemen laut MEDLINE: Biomarkers, Machine Learning, Postoperative Complications, Delirium. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medical Research Project of Luzhou, The Affiliated Hospital of Southwest Medical University medical Research Project.
Themen: Delir
Abstract (Originalsprache)
Objective
Postoperative delirium, a common neurocognitive complication after surgery and anesthesia, requires early detection for potential intervention. Herein, we constructed a multidimensional postoperative delirium risk‐prediction model incorporating multiple demographic parameters and blood biomarkers to enhance prediction accuracy.
Methods
We included 555 patients undergoing radical surgery for colorectal cancer. Demographic characteristics and lipid profiles were collected preoperatively, and perioperative anesthesia and surgical conditions were recorded; blood biomarkers were measured before and after surgery. The 3D‐CAM scale was used to assess postoperative delirium occurrence within 3 days after surgery. Patients were divided into the postoperative delirium ( N = 100) and non‐postoperative delirium ( N = 455) groups. Based on machine learning, linear and nine non‐linear models were developed and compared to select the optimal model. Shapley value‐interpretation methods and mediation analysis were used to assess feature importance and interaction.
Results
The median age of the participants was 65 years (interquartile range: 56–71 years; 57.8% male). Among the 10 machine‐learning models, the random forest model performed the best (validation cohort, area under the receiver operating characteristic curve of 0.795 [0.704–0.885]). Lipid profile (total cholesterol, triglycerides, and trimethylamine‐N‐oxide) levels were identified as key postoperative delirium predictors. Mediation analysis further confirmed mediating effects among total cholesterol, trimethylamine‐N‐oxide, and postoperative delirium; a nomogram model was developed as a web‐based tool for external validation and use by other clinicians.
Interpretation
Blood biomarkers are crucial in predicting postoperative delirium and aid anesthesiologists in identifying its risks in a timely manner. This model facilitates personalized perioperative management and reduces the occurrence of postoperative delirium. Trial Registration ChiCTR2300075723
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Anesthesiology, The Affiliated Hospital, Southwest Medical University, Luzhou, Sichuan, China.
- Anesthesiology and Critical Care Medicine Key Laboratory of Luzhou, Southwest Medical University, Luzhou, Sichuan, China.
- Operating Room, The Affiliated Hospital, Southwest Medical University, Luzhou, Sichuan, China.
- Department of Anesthesiology, Hejiang People's Hospital, Luzhou, Sichuan, China.
ORCID-Profile: Daiying Zhang, Xiaoxia Duan
Förderung
- Medical Research Project of Luzhou
- The Affiliated Hospital of Southwest Medical University medical Research Project
Zitieren
APA
Wan, H., Tian, H., Wu, C., Zhao, Y., Zhang, D., Zheng, Y., Li, Y., & Duan, X. (2025). Development of a Disease Model for Predicting Postoperative Delirium Using Combined Blood Biomarkers. Annals of Clinical and Translational Neurology, 12(5), 976-985. https://doi.org/10.1002/acn3.70029
Vancouver
Wan H, Tian H, Wu C, Zhao Y, Zhang D, Zheng Y, et al. Development of a Disease Model for Predicting Postoperative Delirium Using Combined Blood Biomarkers. Annals of Clinical and Translational Neurology. 2025;12(5):976-985. doi:10.1002/acn3.70029
BibTeX
@article{Wan2025,
author = {Wan, Hengjun and Tian, Huaju and Wu, Cheng and Zhao, Yue and Zhang, Daiying and Zheng, Yujie and Li, Yuan and Duan, Xiaoxia},
title = {Development of a Disease Model for Predicting Postoperative Delirium Using Combined Blood Biomarkers},
journal = {Annals of Clinical and Translational Neurology},
year = {2025},
volume = {12},
number = {5},
pages = {976--985},
doi = {10.1002/acn3.70029}
}
EUVIMED