EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudie

Anticipating femoral shaft nonunion at 1-3 months: a multimodal framework with automated X‑ray segmentation despite metal implants

Puxin Yang, Xiaofeng Du, Zixuan Liu, Hao Liu, Chengkai Li, Huizhao Wu, Yunhao Zhu, Yukai Ji, Ziqi Yang, Zhiyong Hou iD, Wei Xiang, Wei Chen iD

International Orthopaedics · 2026-12 · 50 (12) · 3307-3318

DOI: 10.1007/s00264-026-07010-y ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift International Orthopaedics, online erschienen am 23.09.2026. Verfasst von Puxin Yang und 11 weiteren Autor:innen. Beteiligte Einrichtung: Hebei Medical University Third Affiliated Hospital, Shijiazhuang, China. Hauptthemen laut MEDLINE: Femoral Fractures, Fractures, Ununited, Radiomics, Predictive Learning Models. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Science and Technology Basic Resources Survey Project, Key Projects of the National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Nonunion is a costly and serious complication in trauma surgery. The RUST score can assess tibial healing on radiographs but offers no prediction of nonunion at nine to 12 months. A prediction model integrating demographics, blood tests, and radiomics fills this gap and brings clinical value. METHODS: We collected 1-3 month postoperative X-ray, patient data, and blood tests across three centers including 550 patients and 2,344 X-ray. 13 predictive features were selected via two-stage LASSO with group-wise preselection. A U-Net based segmentation framework standardized bone and implant masks under heterogeneous imaging conditions, enabling robust radiomics extraction. ExtraTrees, LightGBM, SVM, CatBoost, Random forest, Gradient boosting, XGBoost, HistGradientBoosting, MLP, Logistic Regression, ElasticNet, Lasso, AdaBoost, Gaussian NB, and Decision Tree were employed to develop NU model. RESULTS: A total of 492 patients formed the training cohort and 58 patients formed the external validation cohort. An automated segmentation model achieved mean Dice coefficients of 0.947 for bone/callus and 0.921 for implants. LASSO selected 13 predictors: five radiomic features, seven blood tests, and one clinical variable. The ExtraTrees-based NU model yielded an AUC of 0.891±0.021 in the training cohort, with good calibration and net benefit on decision curve analysis. In external validation, AUC was 0.840. The model enables early nonunion risk stratification within three months after surgery. CONCLUSION: The NU model is the first automated multimodal prediction model integrating radiomics, blood tests, and clinical data to predict femoral shaft nonunion within three months after intramedullary nailing, providing a technically scalable solution for early nonunion risk stratification before conventional imaging becomes diagnostic.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Femoral FracturesFractures, UnunitedRadiomicsPredictive Learning ModelsFemaleHumansMaleBoosting Machine Learning AlgorithmsFracture HealingPredictive Value of TestsRadiographyRandom Forest

Stichwörter der Autor:innen

Machine learningNonunionPredictionRadiomicsX‑ray

Autor:innen und Institutionen

  • Hebei Medical University Third Affiliated Hospital, Shijiazhuang, China.
  • Hebei Institute of Orthopedics, Third Hospital of Hebei Medical University, Shijiazhuang, China.
  • Hebei Medical University, Shijiazhuang, China.
  • Engineering Research Center of Orthopaedic Minimally Invasive Intelligent Equipment, Ministry of Education, Hebei Medical University Third Affiliated Hospital, Shijiazhuang, China.
  • Hebei Medical University, Shijiazhuang, China. xiangwvivi@gmail.com.
  • Hebei Medical University Third Affiliated Hospital, Shijiazhuang, China. surgeonchenwei@126.com.

ORCID-Profile: Zhiyong Hou, Wei Chen

Förderung

  • National Science and Technology Basic Resources Survey Project
  • Key Projects of the National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Undergraduate Innovative Experiment Program of Hebei Medical University
  • Natural Science Foundation of Hebei Province for Yanzhao Young Scientists Project
  • Major Science and Technology Support Program of Hebei Province – Health Innovation Special Project

Zitieren

APA

Yang, P., Du, X., Liu, Z., Liu, H., Li, C., Wu, H., Zhu, Y., Ji, Y., Yang, Z., Hou, Z., Xiang, W., & Chen, W. (2026). Anticipating femoral shaft nonunion at 1-3 months: a multimodal framework with automated X‑ray segmentation despite metal implants. International Orthopaedics, 50(12), 3307-3318. https://doi.org/10.1007/s00264-026-07010-y

Vancouver

Yang P, Du X, Liu Z, Liu H, Li C, Wu H, et al. Anticipating femoral shaft nonunion at 1-3 months: a multimodal framework with automated X‑ray segmentation despite metal implants. International Orthopaedics. 2026;50(12):3307-3318. doi:10.1007/s00264-026-07010-y

BibTeX
@article{Yang2026,
  author = {Yang, Puxin and Du, Xiaofeng and Liu, Zixuan and Liu, Hao and Li, Chengkai and Wu, Huizhao and Zhu, Yunhao and Ji, Yukai and Yang, Ziqi and Hou, Zhiyong and Xiang, Wei and Chen, Wei},
  title = {Anticipating femoral shaft nonunion at 1-3 months: a multimodal framework with automated X‑ray segmentation despite metal implants},
  journal = {International Orthopaedics},
  year = {2026},
  volume = {50},
  number = {12},
  pages = {3307--3318},
  doi = {10.1007/s00264-026-07010-y}
}
Kostenlos starten →