Wu Zhaoyu, Li Yixuan, Lei Jiahao, Qiu Peng, Liu Haichun, Yang Xinrui, Chen Tao, Lu Xinwu
Department of Vascular Surgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Big Data Research Lab, University of Waterloo, Waterloo, Ontario, Canada; Department of Economics, University of Waterloo, Waterloo, Ontario, Canada; Data Research Lab, Stoppingtime (Shanghai) BigData & Technology Co Ltd, Shanghai, China.
J Vasc Surg Venous Lymphat Disord. 2023 May;11(3):555-564.e5. doi: 10.1016/j.jvsv.2022.12.006. Epub 2022 Dec 26.
Post-thrombotic syndrome (PTS) is the most common chronic complication of deep venous thrombosis (DVT). Risk measurement and stratification of PTS are crucial for patients with DVT. This study aimed to develop predictive models of PTS using machine learning for patients with proximal DVT.
Herein, hospital inpatients from a DVT registry electronic health record database were randomly divided into a derivation and a validation set, and four predictive models were constructed using logistic regression, simple decision tree, eXtreme Gradient Boosting (XGBoost), and random forest (RF) algorithms. The presence of PTS was defined according to the Villalta scale. The areas under the receiver operating characteristic curves, decision-curve analysis, and calibration curves were applied to evaluate the performance of these models. The Shapley Additive exPlanations analysis was performed to explain the predictive models.
Among the 300 patients, 126 developed a PTS at 6 months after DVT. The RF model exhibited the best performance among the four models, with an area under the receiver operating characteristic curves of 0.891. The RF model demonstrated that Villalta score at admission, age, body mass index, and pain on calf compression were significant predictors for PTS, with accurate prediction at the individual level. The Shapley Additive exPlanations analysis suggested a nonlinear correlation between age and PTS, with two peak ages of onset at 50 and 70 years.
The current predictive model identified significant predictors and accurately predicted PTS for patients with proximal DVT. Moreover, the model demonstrated a nonlinear correlation between age and PTS, which might be valuable in risk measurement and stratification of PTS in patients with proximal DVT.
血栓形成后综合征（PTS）是深静脉血栓形成（DVT）最常见的慢性并发症。PTS的风险评估和分层对DVT患者至关重要。本研究旨在使用机器学习为近端DVT患者开发PTS预测模型。
在此，将来自DVT登记电子健康记录数据库的住院患者随机分为推导集和验证集，并使用逻辑回归、简单决策树、极端梯度提升（XGBoost）和随机森林（RF）算法构建四个预测模型。PTS的存在根据Villalta量表定义。应用受试者工作特征曲线下面积、决策曲线分析和校准曲线来评估这些模型的性能。进行Shapley加性解释分析以解释预测模型。
在300例患者中，126例在DVT后6个月出现PTS。RF模型在四个模型中表现最佳，受试者工作特征曲线下面积为0.891。RF模型表明，入院时的Villalta评分、年龄、体重指数和小腿按压疼痛是PTS的重要预测因素，在个体水平上具有准确的预测能力。Shapley加性解释分析表明年龄与PTS之间存在非线性相关性，发病高峰年龄为50岁和70岁。
当前的预测模型识别出了重要的预测因素，并准确预测了近端DVT患者的PTS。此外，该模型表明年龄与PTS之间存在非线性相关性，这可能对近端DVT患者PTS的风险评估和分层具有重要价值。
