Explainable machine-learning model for postoperative lower-extremity deep vein thrombosis after gynecologic cancer surgery
- 1Department of Interventional Therapy I, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences , , ,
- 2Depression Disorder Diagnosis and Treatment Center, Shandong Mental Health Center , , ,
- 3Ward 1, Lung Surgery, Shandong Cancer Hospital and Institute , , ,
Abstract
Background: Postoperative lower-extremity deep vein thrombosis (DVT) is a common and potentially fatal complication after radical surgery for gynecologic malignancies, yet population-specific risk tools remain limited.
Methods: We retrospectively analyzed 500 consecutive patients who underwent radical surgery for cervical, endometrial, or ovarian cancer (January 2022-January 2025). The cohort was randomly divided into a training set (n=351, 70%) and a validation set (n=149, 30%) at a 7:3 ratio. Independent predictors were identified using logistic regression, and 10 machine-learning algorithms were trained and compared. Model discrimination, calibration, and clinical utility were evaluated, and the optimal model was interpreted using SHAP.
Results: DVT occurred in 116 patients (23.2%). Five variables were independently associated with DVT: age, Caprini score, lymphocyte count, preoperative D-dimer, and neutrophil-to-lymphocyte ratio (NLR).Across candidate models, CatBoost achieved the optimal overall performance on the validation set, yielding an AUC of 0.816 (95% CI: 0.738–0.881), with sensitivity of 0.824 (95% CI: 0.700–1.000) and specificity of 0.730 (95% CI: 0.515–0.876), and SHAP analysis ranked the predictors by mean absolute SHAP value in the following order: lymphocyte count, Caprini score, age, preoperative D-dimer, and neutrophil-to-lymphocyte ratio (NLR).
Conclusion: An interpretable CatBoost-based model enables individualized postoperative DVT risk stratification after gynecologic cancer surgery and may support targeted, evidence-based thromboprophylaxis and perioperative nursing management.
Related
- Annual variation and clinical characteristics of postoperative lower extremity venous thrombosis after urological surgery: a single-center real-world study
- Development and internal validation of a nomogram for estimating concurrent superficial vein thrombosis at presentation in patients with lower extremity varicose veins
- Lower-extremity Deep Vein Thrombosis after Plastic Surgery: Clinical Characteristics and Outcomes in a Retrospective Case Series
- May Thurner Syndrome (MTS), A Rare Cause of Recurrent Lower Extremity Deep Venous Thrombosis (DVT)
- Explainable machine learning–based prediction of postoperative pulmonary infection after aneurysmal subarachnoid hemorrhage clipping and exploratory analysis of enteral nutrition timing: a dual-cohort retrospective study
BibTeX
@article{zhang2026explainable,
title = {{Explainable machine-learning model for postoperative lower-extremity deep vein thrombosis after gynecologic cancer surgery}},
author = {Yanhong Zhang and Congcong Shi and Deyan Yang and Xiaona Ji and Yingli Chu},
journal = {Frontiers in oncology},
year = {2026},
month = sep,
doi = {10.3389/fonc.2026.1813354},
url = {https://europepmc.org/article/PMC/PMC13661352},
note = {CC BY},
}
RIS
TY - JOUR
TI - Explainable machine-learning model for postoperative lower-extremity deep vein thrombosis after gynecologic cancer surgery
AU - Yanhong Zhang
AU - Congcong Shi
AU - Deyan Yang
AU - Xiaona Ji
AU - Yingli Chu
PY - 2026
DA - 2026/09/30
JO - Frontiers in oncology
DO - 10.3389/fonc.2026.1813354
UR - https://europepmc.org/article/PMC/PMC13661352
AB - Background: Postoperative lower-extremity deep vein thrombosis (DVT) is a common and potentially fatal complication after radical surgery for gynecologic malignancies, yet population-specific risk tools remain limited. Methods: We retrospectively analyzed 500 consecutive patients who underwent radical surgery for cervical, endometrial, or ovarian cancer (January 2022-January 2025). The cohort was randomly divided into a training set (n=351, 70%) and a validation set (n=149, 30%) at a 7:3 ratio. Independent predictors were identified using logistic regression, and 10 machine-learning algorithms were trained and compared. Model discrimination, calibration, and clinical utility were evaluated, and the optimal model was interpreted using SHAP. Results: DVT occurred in 116 patients (23.2%). Five variables were independently associated with DVT: age, Caprini score, lymphocyte count, preoperative D-dimer, and neutrophil-to-lymphocyte ratio (NLR).Across candidate models, CatBoost achieved the optimal overall performance on the validation set, yielding an AUC of 0.816 (95% CI: 0.738–0.881), with sensitivity of 0.824 (95% CI: 0.700–1.000) and specificity of 0.730 (95% CI: 0.515–0.876), and SHAP analysis ranked the predictors by mean absolute SHAP value in the following order: lymphocyte count, Caprini score, age, preoperative D-dimer, and neutrophil-to-lymphocyte ratio (NLR). Conclusion: An interpretable CatBoost-based model enables individualized postoperative DVT risk stratification after gynecologic cancer surgery and may support targeted, evidence-based thromboprophylaxis and perioperative nursing management.
SN - 2234-943X
ER -