EUVIMEDEUVIMED entdecken
Crossref

Predicting Indwelling Catheter Duration in Spinal Cord Injury Patients With Neurogenic Bladder Using Machine Learning

Jiqiang Xie iD, Huilin Liu, Yixing Lu, Xinyu Liu iD, Fei Tian, Xia Du, Linna Hui, Dan Niu, Yani Zhang, Ying Liang iD, Xiaolong Sun iD, Hua Yuan iD

Neurourology and Urodynamics · 23.08.2026

DOI: 10.1002/nau.70411 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neurourology and Urodynamics, online erschienen am 23.08.2026. Verfasst von Jiqiang Xie und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Rehabilitation Medicine, Xijing Hospital, Fourth Military Medical University, Xi'an, People's Republic of China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shaanxi Provincial Key Research and Development Program, The team support project for the enhancement of health research and innovation capabilities in Shaanxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop and validate interpretable machine learning (ML) survival models for predicting indwelling catheter time (ICT) in early‐stage spinal cord injury (SCI) patients with neurogenic bladder (NB), identify key early predictors, and derive a practical prognostic stratification tool.

Methods

We retrospectively analyzed 135 consecutive early‐stage SCI‐NB patients admitted between November 2017 and January 2026. The terminal event was defined as indwelling catheter conversion (ICC). Five ML survival models were developed to estimate the probability of ICC within 1 year, enabling stratification of patients into favorable‐, intermediate‐, and unfavorable‐prognosis groups.

Results

The median ICT was 72 days (IQR 33.65–171.00). 102 patients (75.56%) experienced ICC during follow‐up. The final SHAP‐informed five‐variable Random Survival Forest (RSF) model demonstrated strong discriminative performance, with a validation C‐index of 0.8742. Time‐dependent area under the receiver operating characteristic curve (AUC) values for the final RSF model were 0.9352, 0.8834, and 0.8803 at 3, 6, and 12 months, respectively. SHapley Additive exPlanations (SHAP) analysis identified five dominant, early‐obtainable predictors: H‐reflex, Lower extremity motor score (LEMS), Urinary tract infection (UTI), Time from lesion to rehabilitation facility (TLRF), Spinal cord independence measure (SCIM) bladder score. An RSF‐derived prognostic output generated by the final five‐variable RSF model stratified patients into three distinct prognostic groups: favorable, intermediate, and unfavorable prognosis, with significantly different 3‐month cumulative ICC incidences (97.30%, 50.23%, and 2.22%, respectively; log‐rank p < 0.0001).

Conclusions

We developed a novel prognostic stratification model for predicting ICC in NB patients after SCI. The model demonstrates high predictive accuracy and effective patient stratification. By leveraging an interpretable ML approach, it shows potential to assist clinicians in formulating personalized treatment strategies. Trial Registration The study protocol was prospectively registered with the Chinese Clinical Trial Registry (ChiCTR2300073824; registered July 21, 2023).

Schlagwörter

Stichwörter der Autor:innen

indwelling cathetermachine learningneurogenic bladderspinal cord injury

Autor:innen und Institutionen

  • Department of Rehabilitation Medicine, Xijing Hospital, Fourth Military Medical University, Xi'an, People's Republic of China.
  • Department of Rehabilitation Medicine, The 940th Hospital of Joint Logistics Support Force of Chinese People's Liberation Army, Lanzhou, People's Republic of China.
  • Department of Health Statistics, Fourth Military Medical University, Xi'an, People's Republic of China.

ORCID-Profile: Jiqiang Xie, Xinyu Liu, Ying Liang, Xiaolong Sun, Hua Yuan

Förderung

  • National Natural Science Foundation of China
  • Shaanxi Provincial Key Research and Development Program
  • The team support project for the enhancement of health research and innovation capabilities in Shaanxi Province
  • The Medical Staff Training & Boost Project of Xijing Hospital

Zitieren

APA

Xie, J., Liu, H., Lu, Y., Liu, X., Tian, F., Du, X., Hui, L., Niu, D., Zhang, Y., Liang, Y., Sun, X., & Yuan, H. (2026). Predicting Indwelling Catheter Duration in Spinal Cord Injury Patients With Neurogenic Bladder Using Machine Learning. Neurourology and Urodynamics. https://doi.org/10.1002/nau.70411

Vancouver

Xie J, Liu H, Lu Y, Liu X, Tian F, Du X, et al. Predicting Indwelling Catheter Duration in Spinal Cord Injury Patients With Neurogenic Bladder Using Machine Learning. Neurourology and Urodynamics. 2026. doi:10.1002/nau.70411

BibTeX
@article{Xie2026,
  author = {Xie, Jiqiang and Liu, Huilin and Lu, Yixing and Liu, Xinyu and Tian, Fei and Du, Xia and Hui, Linna and Niu, Dan and Zhang, Yani and Liang, Ying and Sun, Xiaolong and Yuan, Hua},
  title = {Predicting Indwelling Catheter Duration in Spinal Cord Injury Patients With Neurogenic Bladder Using Machine Learning},
  journal = {Neurourology and Urodynamics},
  year = {2026},
  doi = {10.1002/nau.70411}
}
Kostenlos starten →