Prediction of Postoperative Venous Thromboembolism in Patients With Traumatic Brain Injury: Model Development and Validation Study
Vorhersage postoperativer venöser Thromboembolien bei Patient:innen mit traumatischer Hirnverletzung: Entwicklung und Validierung eines Modells
JMIR Medical Informatics · 17.11.2025 · 13 · e78655
DOI: 10.2196/78655 ↗Auf einen Blick
Bei 1.806 Patient:innen mit TBI und Operation sagte ein logistisches Regressionsmodell postoperative VTE am besten voraus (AUC 0,83).
Fragestellung
Lassen sich postoperative VTE bei Patient:innen mit TBI nach Operation mit ML-basierten Modellen vorhersagen?
Methode
Datensatz aus einem Krankenhaus von Oktober 2016 bis Dezember 2024; 7:3-Teilung in Trainings- und internen Testdatensatz; sechs ML-Modelle trainiert und validiert.
Ergebnisse
1.806 Teilnehmende; 257 (14,2 %) mit VTE. AUC der ML-Modelle 0,79 bis 0,83; LR: AUC 0,83, Accuracy 0,80, Spezifität 0,83.
Einschränkungen
Externe Validierung über verschiedene Populationen hinweg wurde als notwendig genannt.
Schlussfolgerung der Autor:innen
Die Studie entwickelte und validierte mehrere ML-Modelle zur Vorhersage postoperativer VTE bei TBI; das LR-basierte Nomogramm könnte klinisch nutzbar sein.
Kernaussagen
- 257 von 1.806 Patient:innen hatten VTE
- LR-Modell mit AUC 0,83
- Externe Validierung wurde als erforderlich bezeichnet
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 JMIR Medical Informatics, online erschienen am 17.11.2025. Verfasst von Jiang Zheng und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Ch…. Hauptthemen laut MEDLINE: Venous Thromboembolism, Brain Injuries, Traumatic, Postoperative Complications. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Thromboseprophylaxe
Abstract (Originalsprache)
Background
Venous thromboembolism (VTE) remains a critical cause of mortality among patients who are hospitalized. Patients with traumatic brain injury (TBI) are particularly susceptible to VTE due to coagulation abnormalities and immobilization. Despite this elevated risk, no validated predictive model currently exists for postoperative VTE in populations with TBI.
Objective
This study aims to develop machine learning (ML)–based predictive models for VTE in patients with TBI undergoing surgical procedures, with a focus on clinical translatability.
Methods
Data were collected from patients with TBI who underwent surgical treatment at Chongqing University Central Hospital (from October 2016 to December 2024). The dataset was randomly partitioned into a training set and an internal test set in a 7:3 ratio. The recursive feature elimination algorithm was applied for feature selection, followed by the synthetic minority oversampling technique to address class imbalance. Six ML models, including logistic regression (LR), random forest, gradient boosting decision tree, extreme gradient boosting, support vector machine, and categorical boosting, were trained and validated. Model performance was evaluated using receiver operating characteristic analysis, calibration curves (assessing probability-observation alignment), and decision curve analysis to quantify clinical net benefit. For the LR model, clinical utility was enhanced through nomogram construction, with Shapley additive explanation values providing interpretability.
Results
A total of 1806 participants were enrolled in this study, and 257 (14.2%) experienced VTE events. All ML models demonstrated strong predictive performance, with area under the receiver operating characteristic curve values ranging from 0.79 to 0.83. The LR model exhibited the highest discriminatory power (area under the receiver operating characteristic curve 0.83; accuracy 0.80; specificity 0.83). Calibration curves confirmed that the LR model provided well-calibrated probability estimates. Shapley additive explanations analysis identified key contributors to VTE risk and transformed model outputs into individualized risk predictions. A user-friendly postoperative VTE risk prediction nomogram was developed for patients with TBI.
Conclusions
This study successfully developed and validated multiple ML models for postoperative VTE prediction in patients with TBI. The LR-based nomogram, supported by calibration and decision curve validation, offers a clinically actionable tool to guide thromboprophylaxis strategies. Future external validation across diverse populations is warranted to confirm generalizability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Anesthesiology, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, China, Chongqing, China.
- The First People's Hospital of Chongqing High-Tech Zone, Chongqing, China.
ORCID-Profile: Jiang Zheng, Qiling Jiang, Yusheng Zhan, Yanming Tang, Xiaohui Du, Guangrong Xiang, Yufang Ouyang, Hong Fu
Zitieren
APA
Zheng, J., Jiang, Q., Zhan, Y., Tang, Y., Du, X., Xiang, G., Ouyang, Y., & Fu, H. (2025). Prediction of Postoperative Venous Thromboembolism in Patients With Traumatic Brain Injury: Model Development and Validation Study. JMIR Medical Informatics, 13, e78655. https://doi.org/10.2196/78655
Vancouver
Zheng J, Jiang Q, Zhan Y, Tang Y, Du X, Xiang G, et al. Prediction of Postoperative Venous Thromboembolism in Patients With Traumatic Brain Injury: Model Development and Validation Study. JMIR Medical Informatics. 2025;13:e78655. doi:10.2196/78655
BibTeX
@article{Zheng2025,
author = {Zheng, Jiang and Jiang, Qiling and Zhan, Yusheng and Tang, Yanming and Du, Xiaohui and Xiang, Guangrong and Ouyang, Yufang and Fu, Hong},
title = {Prediction of Postoperative Venous Thromboembolism in Patients With Traumatic Brain Injury: Model Development and Validation Study},
journal = {JMIR Medical Informatics},
year = {2025},
volume = {13},
pages = {e78655},
doi = {10.2196/78655}
}
EUVIMED