ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Machine learning to predict outcomes following endovascular abdominal aortic aneurysm repair

Li, Ben; Aljabri, Badr; Verma, Raj; Beaton, Derek; Eisenberg, Naomi; Lee, Douglas S.; Wijeysundera, Duminda N.; Forbes, Thomas L.; Rotstein, Ori D.; de Mestral, Charles; Mamdani, Muhammad; Roche-Nagle, Graham; Al-Omran, Mohammed*河北医科大学
British Journal of Surgery2023-11-9DOI: 10.1093/bjs/znad287
3被引1阅读
引用收藏
分享

摘要

Background Endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA) carries important perioperative risks; however, there are no widely used outcome prediction tools. The aim of this study was to apply machine learning (ML) to develop automated algorithms that predict 1-year mortality following EVAR.Methods The Vascular Quality Initiative database was used to identify patients who underwent elective EVAR for infrarenal AAA between 2003 and 2023. Input features included 47 preoperative demographic/clinical variables. The primary outcome was 1-year all-cause mortality. Data were split into training (70 per cent) and test (30 per cent) sets. Using 10-fold cross-validation, 6 ML models were trained using preoperative features with logistic regression as the baseline comparator. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score.Results Some 63 655 patients were included. One-year mortality occurred in 3122 (4.9 per cent) patients. The best performing prediction model for 1-year mortality was XGBoost, achieving an AUROC (95 per cent c.i.) of 0.96 (0.95-0.97). Comparatively, logistic regression had an AUROC (95 per cent c.i.) of 0.69 (0.68-0.71). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.04. The top 3 predictive features in the algorithm were 1) unfit for open AAA repair, 2) functional status, and 3) preoperative dialysis.Conclusions In this data set, machine learning was able to predict 1-year mortality following EVAR using preoperative data and outperformed standard logistic regression models. Endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm carries important perioperative risks; however, there are no widely used outcome prediction tools. Using the multicentre Vascular Quality Initiative database consisting of 63 655 patients who underwent elective EVAR between 2003 and 2023, we developed robust machine learning models that accurately predict 1-year postoperative mortality with an area under the receiver operating characteristic curve of 0.96. Our automated algorithms can help guide risk mitigation strategies for patients being considered for EVAR to improve outcomes.

学科与关键词

关键词
VASCULAR-SURGERYARTIFICIAL-INTELLIGENCELOGISTIC-REGRESSIONRISK CALCULATORMODELSSOCIETYUTILITYHEALTHCARE
相关
加载中…
  • Predicting Outcomes Following Lower Extremity Endovascular Revascularization Using Machine Learning
    Li, Ben; Aljabri, Badr; Verma, Raj; Beaton, Derek; Hussain, Mohamad A.; Lee, Douglas S.; Wijeysundera, Duminda N.; de Mestral, Charles; Mamdani, Muhammad; Al-Omran, Mohammed*Journal of the American Heart Association, 2024, 13(9): e033194.
  • Predicting outcomes following lower extremity open revascularization using machine learning
    Li, Ben; Verma, Raj; Beaton, Derek; Tamim, Hani; Hussain, Mohamad A.; Hoballah, Jamal J.; Lee, Douglas S.; Wijeysundera, Duminda N.; de Mestral, Charles; Mamdani, Muhammad; Al-Omran, Mohammed*Scientific Reports, 2024, 14(1): 2899.被引 1
  • Machine learning for prediction of all-cause mortality after transcatheter aortic valve implantation
    Kwiecinski, Jacek; Dabrowski, Maciej; Nombela-Franco, Luis; Grodecki, Kajetan; Pieszko, Konrad; Chmielak, Zbigniew; Pylko, Anna; Hennessey, Breda; Kalinczuk, Lukasz; Tirado-Conte, Gabriela; Rymuza, Bartosz; Kochman, Janusz; Opolski, Maksymilian P.; Huczek, Zenon; Dweck, Marc R.; Dey, Damini; Jimenez-Quevedo, Pilar; Slomka, Piotr*; Witkowski, AdamEuropean Heart Journal-Quality of Care and Clinical Outcomes, 2023, 9(8): 768-777.被引 3
查看全部 →

发表信息

论文状态
公开发表
期刊
British Journal of Surgery
发表日期
2023-11-09
卷期
第 110 卷, 第 12 期
页码
1840-1849
DOI
10.1093/bjs/znad287
语言
ENGLISH
成果收录
SCIE
资助标注
Authors B.L. and B.A. contributed equally to this study.

作者

  • L

    Li, Ben (第一作者)

    inst med

  • A

    Aljabri, Badr

查看全部 13 位作者收起作者
  • V

    Verma, Raj

  • B

    Beaton, Derek

  • E

    Eisenberg, Naomi

  • L

    Lee, Douglas S.

  • W

    Wijeysundera, Duminda N.

  • F

    Forbes, Thomas L.

    inst med

  • R

    Rotstein, Ori D.

    inst med

  • d

    de Mestral, Charles

  • M

    Mamdani, Muhammad

    inst med

  • R

    Roche-Nagle, Graham

  • A

    Al-Omran, Mohammed (通讯)

    inst med

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417