EUVIMEDEUVIMED entdecken
Validierungsstudie

Construction and temporal external validation of interpretable machine-learning models for predicting tigecycline-associated hypofibrinogenemia

An Fu, Daihong Guo, Man Zhu, Le Cai, Ao Gao, Liqiang Cui

European Journal of Clinical Pharmacology · 2026

DOI: 10.1007/s00228-025-03941-4 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift European Journal of Clinical Pharmacology, 2026. Verfasst von An Fu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacy, Medical Supplies Center of the Chinese PLA General Hospital, Beijing, 100853, China. Hauptthemen laut MEDLINE: Machine Learning, Tigecycline, Anti-Bacterial Agents, Afibrinogenemia. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: the Project of Monitoring and Evaluation of the Use of Key Clinical Drugs commissioned by the Chinese Association of Research Hospitals, Capital's Funds for Health Improvement and Research, Capital’s Funds for Health Improvement and Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND PURPOSE: There is a paucity of available clinical tools with which to accurately predict the risk of tigecycline-associated hypofibrinogenemia, an adverse reaction with a high incidence and serious consequences. This study aimed to developed an optimal machine-learning model for predicting tigecycline-associated hypofibrinogenemia and to facilitate its clinical application. METHODS: A total of 896 inpatients who received tigecycline treatment in a large tertiary teaching hospital between 2016 and 2022 were included in the model development cohort. Subsequent temporal external validation of the models was performed on 313 patients admitted in 2023. Three robust machine-learning algorithms, including LASSO, Boruta, and VSURF were integrated to identify predictors. These features were then utilized to construct nine machine-learning models. The optimal one was identified through model evaluation and validation and was interpreted based on the SHAP method. RESULTS: The three algorithms identified five predictors, including age, treatment duration, pre-dose fibrinogen level, D-dimer level, and activated partial thromboplastin time. The XGboost model was identified as the most suitable due to its stability and excellent discrimination, calibration, and clinical utility. The area under the receiver operating characteristic curve for the model were 0.823 (0.794-0.853), 0.810 (0.746-0.873), and 0.773 (0.721-0.825) in the training, internal validation, and temporal external validation cohorts, respectively. CONCLUSIONS: Machine-learning models are promising in solving the classification prediction problem of tigecycline-associated hypofibrinogenemia. Model interpretation based on SHAP enables clinicians to visualize individualized risk and tailor prophylactic strategies, potentially improving patient safety and treatment outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTigecyclineAnti-Bacterial AgentsAfibrinogenemiaHumansFemaleMaleMiddle AgedAgedAdultAlgorithmsFibrin Fibrinogen Degradation ProductsFibrinogenAged, 80 and overPartial Thromboplastin Time

Stichwörter der Autor:innen

Antibacterial managementFeature selectionHypofibrinogenemiaMachine-learningPrediction modelTigecycline

Substanzen

TigecyclineAnti-Bacterial AgentsFibrin Fibrinogen Degradation ProductsFibrinogenfibrin fragment D

Autor:innen und Institutionen

  • Department of Pharmacy, Medical Supplies Center of the Chinese PLA General Hospital, Beijing, 100853, China.
  • Medical School of the Chinese PLA, Beijing, 100853, China.
  • Department of Pharmacy, Medical Supplies Center of the Chinese PLA General Hospital, Beijing, 100853, China. guodh301@163.com.
  • Department of Pharmacy, Medical Supplies Center of the Chinese PLA General Hospital, Beijing, 100853, China. zhucindy301@189.cn.

Förderung

  • the Project of Monitoring and Evaluation of the Use of Key Clinical Drugs commissioned by the Chinese Association of Research Hospitals
  • Capital's Funds for Health Improvement and Research
  • Capital’s Funds for Health Improvement and Research

Zitieren

APA

Fu, A., Guo, D., Zhu, M., Cai, L., Gao, A., & Cui, L. (2026). Construction and temporal external validation of interpretable machine-learning models for predicting tigecycline-associated hypofibrinogenemia. European Journal of Clinical Pharmacology. https://doi.org/10.1007/s00228-025-03941-4

Vancouver

Fu A, Guo D, Zhu M, Cai L, Gao A, Cui L. Construction and temporal external validation of interpretable machine-learning models for predicting tigecycline-associated hypofibrinogenemia. European Journal of Clinical Pharmacology. 2026. doi:10.1007/s00228-025-03941-4

BibTeX
@article{Fu2026,
  author = {Fu, An and Guo, Daihong and Zhu, Man and Cai, Le and Gao, Ao and Cui, Liqiang},
  title = {Construction and temporal external validation of interpretable machine-learning models for predicting tigecycline-associated hypofibrinogenemia},
  journal = {European Journal of Clinical Pharmacology},
  year = {2026},
  doi = {10.1007/s00228-025-03941-4}
}
Kostenlos starten →