Machine learning prediction of deep vein thrombosis before staged surgery in lower-leg and ankle fractures treated with temporary external fixation
- 1Department of Orthopaedic Surgery, Zhangzhou Affiliated Hospital of Fujian Medical University , , ,
Abstract
Background: Deep vein thrombosis (DVT) detected between temporary external fixation and staged definitive surgery can complicate perioperative management of lower-leg and ankle fractures. We developed machine-learning models to estimate DVT probability during this interval.
Methods: This retrospective cohort included adults admitted during 2015−2025 who underwent staged fixation and bilateral lower-extremity venous ultrasonography. A stratified 70:30 split defined development and validation sets. Development-set imputation, Boruta feature selection, and five-fold cross-validation were used to develop 12 classifiers. Algorithms were compared in the validation set. The selected Naive Bayes pipeline underwent 500 development-cohort bootstrap replications for optimism correction. Discrimination, precision-recall performance, calibration, and decision curves were evaluated. SHapley additive explanations (SHAP) and a bilingual research prototype web application supported interpretation.
Results: Among 356 patients, 55 (15.4%) had DVT, including 40 with calf muscular vein thrombosis. The development and validation sets comprised 250 patients (39 events) and 106 patients (16 events). Boruta retained nine predictors. Naive Bayes had the highest validation receiver operating characteristic area under the curve (AUC), 0.807 (95% confidence interval, 0.705−0.909). Precision-recall AUC was 0.343, sensitivity was 0.875, and specificity was 0.589. Beta calibration reduced the Brier score from 0.135 to 0.116 without changing discrimination. The apparent AUC was 0.858, mean bootstrap optimism was 0.084, and optimism-corrected AUC was 0.773. Injury-to-admission time, calcium, age, platelet count, fibrinogen, and hemoglobin had the largest mean absolute SHAP values.
Conclusion: The model may support risk stratification for an ultrasound-detected composite DVT endpoint in this staged-treatment population. Its proposed use is to inform surveillance timing and intensity while retaining routine bilateral ultrasonography. Prospective validation is required before clinical implementation.
Related
- Analysis of risk factors and construction of a prediction model for postoperative deep vein thrombosis in patients with periarticular knee fractures.
- Temporary percutaneous trans-tibiofibular K-wire stabilization of selected unstable ankle fractures.
- Discharge Mobility After Osteoporotic Thoracolumbar Fractures Using a 2-Stage Machine Learning Prediction Model: Prospective Cohort Study.
- Development and external validation of machine learning models for early prediction of delirium risk in patients with severe pneumonia
- Ligamentotaxis-Based Dynamic External Fixation for Comminuted Intra-articular Fractures of the Proximal Phalanx Base of the Thumb: A Report of Two Cases.
BibTeX
@article{lin2026machine,
title = {{Machine learning prediction of deep vein thrombosis before staged surgery in lower-leg and ankle fractures treated with temporary external fixation}},
author = {Ximing Lin and Hongpeng Gao and Weizhang Lin and Shijie Wang and Zepeng Lin and Yue Yang and Peiyi Zhuang and Chenxing Cai and Rongyuan Yang},
journal = {Frontiers in cardiovascular medicine},
year = {2026},
month = sep,
doi = {10.3389/fcvm.2026.1963261},
url = {https://europepmc.org/article/PMC/PMC13662060},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine learning prediction of deep vein thrombosis before staged surgery in lower-leg and ankle fractures treated with temporary external fixation
AU - Ximing Lin
AU - Hongpeng Gao
AU - Weizhang Lin
AU - Shijie Wang
AU - Zepeng Lin
AU - Yue Yang
AU - Peiyi Zhuang
AU - Chenxing Cai
AU - Rongyuan Yang
PY - 2026
DA - 2026/09/30
JO - Frontiers in cardiovascular medicine
DO - 10.3389/fcvm.2026.1963261
UR - https://europepmc.org/article/PMC/PMC13662060
AB - Background: Deep vein thrombosis (DVT) detected between temporary external fixation and staged definitive surgery can complicate perioperative management of lower-leg and ankle fractures. We developed machine-learning models to estimate DVT probability during this interval. Methods: This retrospective cohort included adults admitted during 2015−2025 who underwent staged fixation and bilateral lower-extremity venous ultrasonography. A stratified 70:30 split defined development and validation sets. Development-set imputation, Boruta feature selection, and five-fold cross-validation were used to develop 12 classifiers. Algorithms were compared in the validation set. The selected Naive Bayes pipeline underwent 500 development-cohort bootstrap replications for optimism correction. Discrimination, precision-recall performance, calibration, and decision curves were evaluated. SHapley additive explanations (SHAP) and a bilingual research prototype web application supported interpretation. Results: Among 356 patients, 55 (15.4%) had DVT, including 40 with calf muscular vein thrombosis. The development and validation sets comprised 250 patients (39 events) and 106 patients (16 events). Boruta retained nine predictors. Naive Bayes had the highest validation receiver operating characteristic area under the curve (AUC), 0.807 (95% confidence interval, 0.705−0.909). Precision-recall AUC was 0.343, sensitivity was 0.875, and specificity was 0.589. Beta calibration reduced the Brier score from 0.135 to 0.116 without changing discrimination. The apparent AUC was 0.858, mean bootstrap optimism was 0.084, and optimism-corrected AUC was 0.773. Injury-to-admission time, calcium, age, platelet count, fibrinogen, and hemoglobin had the largest mean absolute SHAP values. Conclusion: The model may support risk stratification for an ultrasound-detected composite DVT endpoint in this staged-treatment population. Its proposed use is to inform surveillance timing and intensity while retaining routine bilateral ultrasonography. Prospective validation is required before clinical implementation.
SN - 2297-055X
ER -