An artificial-intelligence interpretable tool to predict risk of deep vein thrombosis after endovenous thermal ablation

Yu Ma, Azadeh Tabari, Jesus Alfonso Juarez Palazuelos, Anthony Gebran, Haytham Kaafarani, Dimitris Bertsimas, Dania Daye
{"title":"An artificial-intelligence interpretable tool to predict risk of deep vein thrombosis after endovenous thermal ablation","authors":"Yu Ma, Azadeh Tabari, Jesus Alfonso Juarez Palazuelos, Anthony Gebran, Haytham Kaafarani, Dimitris Bertsimas, Dania Daye","doi":"10.1101/2024.06.19.24309166","DOIUrl":null,"url":null,"abstract":"Introduction: Endovenous thermal ablation (EVTA) stands as one of the primary treatments for superficial venous insufficiency. Concern exists about the potential for thromboembolic complications following this procedure. Although rare, those complications can be severe, necessitating early identification of patients prone to increased thrombotic risks. This study aims to leverage AI-based algorithms to forecast patients' likelihood of developing deep vein thrombosis (DVT) within 30 days following EVTA.\nMaterials and Methods: From 2007 to 2017, all patients who underwent EVTA were identified using the American College of Surgeons National Surgical Quality Improvement Program database. We developed and validated 4 machine learning models using demographics, comorbidities, and laboratory values to predict the risk of postoperative deep vein thrombosis: Classification and Regression Trees (CART), Optimal Classification Trees (OCT), Random Forests, and Extreme Gradient Boosting (XGBoost). The models were trained using all the available variables. SHAP analysis was adopted to interpret model outcomes and offer medical insights into feature importance and interactions.\nResults: A total of 21,549 patients were included (mean age of 54 +- SD years, 67% female). In this cohort, 1.59% developed DVT. The XGBoost model had good discriminative power for predicting DVT risk with AUC of 0.711 in the hold-out test set for all-variable model. Stratification of the test set by age, BMI, preoperative white blood cell and platelet count shows that the model performs equally well across these groups. Conclusion: We developed and validated an interpretable model that enables physicians to predict which patients with superficial venous insufficiency has higher risk of developing deep vein thrombosis within 30 days following endovenous thermal ablation.","PeriodicalId":501249,"journal":{"name":"medRxiv - Intensive Care and Critical Care Medicine","volume":"16 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"medRxiv - Intensive Care and Critical Care Medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1101/2024.06.19.24309166","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction: Endovenous thermal ablation (EVTA) stands as one of the primary treatments for superficial venous insufficiency. Concern exists about the potential for thromboembolic complications following this procedure. Although rare, those complications can be severe, necessitating early identification of patients prone to increased thrombotic risks. This study aims to leverage AI-based algorithms to forecast patients' likelihood of developing deep vein thrombosis (DVT) within 30 days following EVTA. Materials and Methods: From 2007 to 2017, all patients who underwent EVTA were identified using the American College of Surgeons National Surgical Quality Improvement Program database. We developed and validated 4 machine learning models using demographics, comorbidities, and laboratory values to predict the risk of postoperative deep vein thrombosis: Classification and Regression Trees (CART), Optimal Classification Trees (OCT), Random Forests, and Extreme Gradient Boosting (XGBoost). The models were trained using all the available variables. SHAP analysis was adopted to interpret model outcomes and offer medical insights into feature importance and interactions. Results: A total of 21,549 patients were included (mean age of 54 +- SD years, 67% female). In this cohort, 1.59% developed DVT. The XGBoost model had good discriminative power for predicting DVT risk with AUC of 0.711 in the hold-out test set for all-variable model. Stratification of the test set by age, BMI, preoperative white blood cell and platelet count shows that the model performs equally well across these groups. Conclusion: We developed and validated an interpretable model that enables physicians to predict which patients with superficial venous insufficiency has higher risk of developing deep vein thrombosis within 30 days following endovenous thermal ablation.
预测静脉腔内热消融术后深静脉血栓风险的人工智能可解释工具
简介静脉腔内热消融术(EVTA)是治疗浅静脉功能不全的主要方法之一。人们担心这种手术可能会引起血栓栓塞并发症。这些并发症虽然罕见,但可能很严重,因此有必要及早识别容易增加血栓风险的患者。本研究旨在利用基于人工智能的算法预测患者在 EVTA 术后 30 天内发生深静脉血栓(DVT)的可能性:从2007年到2017年,所有接受EVTA手术的患者都是通过美国外科医生学会国家外科质量改进计划数据库确定的。我们利用人口统计学、合并症和实验室值开发并验证了 4 个机器学习模型,用于预测术后深静脉血栓形成的风险:分类和回归树 (CART)、最优分类树 (OCT)、随机森林和极端梯度提升 (XGBoost)。这些模型使用所有可用变量进行训练。采用SHAP分析来解释模型结果,并就特征的重要性和相互作用提供医学见解:共纳入 21,549 名患者(平均年龄为 54 +- SD 岁,67% 为女性)。其中 1.59% 的患者出现深静脉血栓。XGBoost 模型在预测深静脉血栓风险方面具有良好的判别能力,在所有变量模型的保留测试集中,AUC 为 0.711。按年龄、体重指数、术前白细胞和血小板计数对测试集进行分层显示,该模型在这些组别中的表现同样出色。结论:我们开发并验证了一个可解释的模型,使医生能够预测哪些浅静脉功能不全患者在静脉腔内热消融术后 30 天内发生深静脉血栓的风险较高。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信