EUVIMEDOpdag EUVIMED
Multizentrische StudieValidierungsstudieKohortenstudieOpen access · CC BY-NC 4.0

Development and Validation of a Machine Learning Algorithm to Predict the Risk of Blood Transfusion after Total Hip Replacement in Patients with Femoral Neck Fractures: A Multicenter Retrospective Cohort Study

Jieyang Zhu iD, Chenxi Xu, Yi Jiang, Jinyu Zhu iD, Mengyun Tu, Xiaobing Yan, Zeren Shen, Zhenqi Lou

Orthopaedic Surgery · 2024

DOI: 10.1111/os.14160 ↗

At a glance

Multizentrische Studie in Orthopaedic Surgery, 2024. Written by Jieyang Zhu and 7 co-authors. Institution: Department of Orthopedics, Affiliated Hospital of Jiaxing University, Jiaxing, China. Major MEDLINE topics: Arthroplasty, Replacement, Hip, Femoral Neck Fractures, Blood Transfusion, Machine Learning. Cited 9 times so far (Crossref); 61 references. The full text is freely available (open access, CC BY-NC 4.0). Funded by: Jiaxing Science and Technology Plan Project.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Objective

Total hip arthroplasty (THA) remains the primary treatment option for femoral neck fractures in elderly patients. This study aims to explore the risk factors associated with allogeneic blood transfusion after surgery and to develop a dynamic prediction model to predict post‐operative blood transfusion requirements. This will provide more accurate guidance for perioperative humoral management and rational allocation of medical resources.

Methods

We retrospectively analyzed data from 829 patients who underwent total hip arthroplasty for femoral neck fractures at three third‐class hospitals between January 2017 and August 2023. Patient data from one hospital were used for model development, whereas data from the other two hospitals were used for external validation. Logistic regression analysis was used to screen the characteristic subsets related to blood transfusion. Various machine learning algorithms, including logistic regression, SVA (support vector machine), K‐NN (k‐nearest neighbors), MLP (multilayer perceptron), naive Bayes, decision tree, random forest, and gradient boosting, were used to process the data and construct prediction models. A 10‐fold cross‐validation algorithm facilitated the comparison of the predictive performance of the models, resulting in the selection of the best‐performing model for the development of an open‐source computing program.

Results

BMI (body mass index), surgical duration, IBL (intraoperative blood loss), anticoagulant history, utilization rate of tranexamic acid, Pre‐Hb, and Pre‐ALB were included in the model as well as independent risk factors. The average area under curve (AUC) values for each model were as follows: logistic regression (0.98); SVA (0.91); k‐NN (0.87) MLP, (0.96); naive Bayes (0.97); decision tree (0.87); random forest (0.96); and gradient boosting (0.97). A web calculator based on the best model is available at: ( https://nomo99.shinyapps.io/dynnomapp/ ).

Conclusion

Utilizing a computer algorithm, a prediction model with a high discrimination accuracy (AUC > 0.5) was developed. The logistic regression model demonstrated superior differentiation and reliability, thereby successfully passing external validation. The model's strong generalizability and applicability have significant implications for clinicians, aiding in the identification of patients at high risk for postoperative blood transfusion.

Subjects

MeSH terms (MEDLINE)

Arthroplasty, Replacement, HipFemoral Neck FracturesBlood TransfusionMachine LearningAlgorithmsHumansRetrospective StudiesFemaleMaleAgedRisk FactorsAged, 80 and overMiddle AgedRisk AssessmentCohort Studies

Author keywords

Allogeneic transfusionFemoral neck fractureMachine learningPrediction modelTotal hip arthroplasty

Authors and institutions

  • Department of Orthopedics, Affiliated Hospital of Jiaxing University, Jiaxing, China.
  • General Practice Department, Tongxiang Wutong Street Community Health Service Center, Jiaxing, China.
  • Department of Clinical Laboratory, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, China.
  • Department of Spine Surgery, The Second Affiliated Hospital of Dalian Medical University, Dalian, China.
  • Department of Mechanical & Industrial Engineering, University of Toronto, Toronto, Canada.

ORCID profiles: Jieyang Zhu, Jinyu Zhu

Funding

  • Jiaxing Science and Technology Plan Project

Cite

APA

Zhu, J., Xu, C., Jiang, Y., Zhu, J., Tu, M., Yan, X., Shen, Z., & Lou, Z. (2024). Development and Validation of a Machine Learning Algorithm to Predict the Risk of Blood Transfusion after Total Hip Replacement in Patients with Femoral Neck Fractures: A Multicenter Retrospective Cohort Study. Orthopaedic Surgery. https://doi.org/10.1111/os.14160

Vancouver

Zhu J, Xu C, Jiang Y, Zhu J, Tu M, Yan X, et al. Development and Validation of a Machine Learning Algorithm to Predict the Risk of Blood Transfusion after Total Hip Replacement in Patients with Femoral Neck Fractures: A Multicenter Retrospective Cohort Study. Orthopaedic Surgery. 2024. doi:10.1111/os.14160

BibTeX
@article{Zhu2024,
  author = {Zhu, Jieyang and Xu, Chenxi and Jiang, Yi and Zhu, Jinyu and Tu, Mengyun and Yan, Xiaobing and Shen, Zeren and Lou, Zhenqi},
  title = {Development and Validation of a Machine Learning Algorithm to Predict the Risk of Blood Transfusion after Total Hip Replacement in Patients with Femoral Neck Fractures: A Multicenter Retrospective Cohort Study},
  journal = {Orthopaedic Surgery},
  year = {2024},
  doi = {10.1111/os.14160}
}
Start for free →