Department of Surgery, University of Toronto, Toronto, Canada; Division of Vascular Surgery, St. Michael's Hospital, Unity Health Toronto, Toronto, Canada; Institute of Medical Science, University of Toronto, Toronto, Canada; Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM), University of Toronto, Toronto, Canada.
Division of Vascular Surgery, Peter Munk Cardiac Centre, University Health Network, Toronto, Canada.
J Vasc Surg Venous Lymphat Disord. 2024 Nov;12(6):101943. doi: 10.1016/j.jvsv.2024.101943. Epub 2024 Jul 29.
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 preoperative data.
The Vascular Quality Initiative database was used to identify patients who underwent IVC filter placement between 2013 and 2024. We identified 77 preoperative demographic and 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 preoperative features with 10-fold cross-validation (Extreme Gradient Boosting, 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 ± 16.7 years vs 63.8 ± 16.0 years; P < .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 Extreme Gradient Boosting, achieving an AUROC of 0.93 (95% confidence interval, 0.92-0.94). In comparison, logistic regression had an AUROC of 0.63 (95% confidence interval, 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 or 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 to guide patient selection for filter placement, counselling, perioperative management, and follow-up to mitigate filter-related complications and improve outcomes.
下腔静脉（IVC）滤器置入与重要的长期并发症相关。预测滤器相关并发症的模型可能有助于指导临床决策，但仍存在局限性。我们开发了机器学习（ML）算法，使用术前数据预测 1 年 IVC 滤器并发症。
使用血管质量倡议（Vascular Quality Initiative）数据库确定 2013 年至 2024 年间接受 IVC 滤器置入的患者。我们从放置滤器的索引住院期间确定了 77 个术前人口统计学和临床特征。主要结局是 1 年滤器相关并发症（复合血栓形成、迁移、成角、骨折和栓塞或碎裂、静脉穿孔、新腔静脉或髂静脉血栓形成、新的肺栓塞、入路血栓形成或取回失败）。数据分为训练（70%）和测试（30%）集。使用 10 倍交叉验证（极端梯度增强、随机森林、朴素贝叶斯分类器、支持向量机、人工神经网络和逻辑回归）使用术前特征训练了 6 个 ML 模型。主要模型评估指标是接收器操作特征曲线下的面积（AUROC）。使用校准图和 Brier 分数评估模型稳健性。根据年龄、性别、种族、民族、农村程度、中位区域剥夺指数、滤器计划持续时间、滤器着陆点和既往 IVC 滤器置入情况，根据亚组评估性能。
总体而言，14476 名患者接受了 IVC 滤器置入，584 名（4.0%）发生了 1 年滤器相关并发症。主要结局患者更年轻（59.3±16.7 岁 vs 63.8±16.0 岁；P<.001），且更可能存在血栓形成危险因素，包括血栓形成倾向、既往静脉血栓栓塞（VTE）和 VTE 家族史。最佳预测模型是极端梯度增强，AUROC 为 0.93（95%置信区间，0.92-0.94）。相比之下，逻辑回归的 AUROC 为 0.63（95%置信区间，0.61-0.65）。校准图显示预测/观察到的事件概率之间具有良好的一致性，Brier 得分为 0.07。1 年滤器相关并发症的前 10 个预测因素是（1）血栓形成倾向，（2）既往 VTE，（3）抗磷脂抗体，（4）因子 V Leiden 突变，（5）VTE 家族史，（6）IVC 滤器计划持续时间（临时），（7）无法维持治疗性抗凝，（8）恶性肿瘤，（9）近期或活动性出血，（10）年龄。模型性能在所有亚组中均保持稳健。
我们开发了能够准确预测 1 年 IVC 滤器并发症的 ML 模型，其性能优于逻辑回归。这些算法有可能指导滤器放置、咨询、围手术期管理和随访，以减轻滤器相关并发症并改善结果。
