Predicting inferior vena cava filter complications using machine learning.

Inferior vena cava (IVC) filter placement is associated with important long-term complications. Predictive models for filter-related complications may help guide clinical decision-making but remain limited. We developed machine learning (ML) algorithms that predict 1-year IVC filter complications using pre-operative data. The Vascular Quality Initiative (VQI) database was used to identify patients who underwent IVC filter placement between 2013-2024. We identified 77 pre-operative demographic/clinical features from the index hospitalization when the filter was placed. The primary outcome was 1-year filter-related complications (composite of filter thrombosis, migration, angulation, fracture, and embolization or fragmentation, vein perforation, new caval or iliac vein thrombosis, new pulmonary embolism, access site thrombosis, or failed retrieval). The data were divided into training (70%) and test (30%) sets. Six ML models were trained using pre-operative features with 10-fold cross-validation (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was assessed using calibration plot and Brier score. Performance was evaluated across subgroups based on age, sex, race, ethnicity, rurality, median Area Deprivation Index, planned duration of filter, landing site of filter, and presence of prior IVC filter placement. Overall, 14,476 patients underwent IVC filter placement and 584 (4.0%) experienced 1-year filter-related complications. Patients with a primary outcome were younger (59.3 [SD 16.7] vs. 63.8 [SD 16.0] years, p < 0.001) and more likely to have thrombotic risk factors including thrombophilia, prior venous thromboembolism (VTE), and family history of VTE. The best prediction model was XGBoost, achieving an AUROC (95% CI) of 0.93 (0.92-0.94). In comparison, logistic regression had an AUROC (95% CI) of 0.63 (0.61-0.65). Calibration plot showed good agreement between predicted/observed event probabilities with a Brier score of 0.07. The top 10 predictors of 1-year filter-related complications were 1) thrombophilia, 2) prior VTE, 3) antiphospholipid antibodies, 4) Factor V Leiden mutation, 5) family history of VTE, 6) planned duration of IVC filter (temporary), 7) unable to maintain therapeutic anticoagulation, 8) malignancy, 9) recent/active bleeding, and 10) age. Model performance remained robust across all subgroups. We developed ML models that can accurately predict 1-year IVC filter complications, performing better than logistic regression. These algorithms have potential for important utility in guiding patient selection for filter placement, counselling, peri-operative management, and follow-up to mitigate filter-related complications and improve outcomes.

Informations de copyright

Copyright © 2024. Published by Elsevier Inc.