Individual risk assessment for rupture of abdominal aortic aneurysm using artificial intelligence.

IF 3.9 2区医学 Q1 PERIPHERAL VASCULAR DISEASE Journal of Vascular Surgery Pub Date : 2024-11-20 DOI:10.1016/j.jvs.2024.11.017

Joachim Sejr Skovbo, Nicklas Sindlev Andersen, Lasse Møllegaard Obel, Malene Skaarup Laursen, Andreas Stoklund Riis, Kim Christian Houlind, Axel Cosmus Pyndt Diederichsen, Jes Sanddal Lindholt

{"title":"Individual risk assessment for rupture of abdominal aortic aneurysm using artificial intelligence.","authors":"Joachim Sejr Skovbo, Nicklas Sindlev Andersen, Lasse Møllegaard Obel, Malene Skaarup Laursen, Andreas Stoklund Riis, Kim Christian Houlind, Axel Cosmus Pyndt Diederichsen, Jes Sanddal Lindholt","doi":"10.1016/j.jvs.2024.11.017","DOIUrl":null,"url":null,"abstract":"Objective: This study aimed to develop a prediction tool to identify abdominal aortic aneurysms (AAA) at increased risk of rupture incorporating demographic, clinical, imaging, and medication data using artificial intelligence (AI).Design: A development and validation study for individual prognosis using AI in a case-control design.Methods: From two Danish hospitals, all available ruptured AAA cases between January 2009 and December 2016 were included in a ratio of 1:2 with elective surgery controls. Cases with previous AAA surgery or missing pre-operative scans were excluded. Features from computed tomography angiography scans and hospital records were manually retrieved. The sample was divided randomly and evenly into developmental and internal validation groups. A SHapley Additive exPlanations Feature Importance Rank Ensembling (SHAPFire) AI tool was developed using a gradient boosting decision tree framework. The final SHAPFire AI model was compared with models using 1) solely infrarenal anterior-posterior-diameter, and 2) all available features.Results: The study included 637 individuals (84.8% men, mean age 73±7 years, 213 ruptured AAAs). The SHAPFire AI incorporated 20 of 68 available features, and aneurysm size, blood pressure, and relationships between height and weight were given highest rankings. The receiver operating characteristic curve for the SHAPFire AI model displayed a significant increase in accuracy identifying ruptured AAA cases compared to the conventional model based solely on diameter with areas under the curves of 0.86±0.04 and 0.74±0.03 (P=0.008), respectively. SHAPFire AI was comparable in performance with the model using all features.Conclusion: This study successfully developed a SHAPFire AI tool to identify AAAs at increased risk of rupture with significant higher accuracy than diameter alone. External validation of the model is warranted before clinical implementation.","PeriodicalId":17475,"journal":{"name":"Journal of Vascular Surgery","volume":" ","pages":""},"PeriodicalIF":3.9000,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Vascular Surgery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.jvs.2024.11.017","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PERIPHERAL VASCULAR DISEASE","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: This study aimed to develop a prediction tool to identify abdominal aortic aneurysms (AAA) at increased risk of rupture incorporating demographic, clinical, imaging, and medication data using artificial intelligence (AI).

Design: A development and validation study for individual prognosis using AI in a case-control design.

Methods: From two Danish hospitals, all available ruptured AAA cases between January 2009 and December 2016 were included in a ratio of 1:2 with elective surgery controls. Cases with previous AAA surgery or missing pre-operative scans were excluded. Features from computed tomography angiography scans and hospital records were manually retrieved. The sample was divided randomly and evenly into developmental and internal validation groups. A SHapley Additive exPlanations Feature Importance Rank Ensembling (SHAPFire) AI tool was developed using a gradient boosting decision tree framework. The final SHAPFire AI model was compared with models using 1) solely infrarenal anterior-posterior-diameter, and 2) all available features.

Results: The study included 637 individuals (84.8% men, mean age 73±7 years, 213 ruptured AAAs). The SHAPFire AI incorporated 20 of 68 available features, and aneurysm size, blood pressure, and relationships between height and weight were given highest rankings. The receiver operating characteristic curve for the SHAPFire AI model displayed a significant increase in accuracy identifying ruptured AAA cases compared to the conventional model based solely on diameter with areas under the curves of 0.86±0.04 and 0.74±0.03 (P=0.008), respectively. SHAPFire AI was comparable in performance with the model using all features.

Conclusion: This study successfully developed a SHAPFire AI tool to identify AAAs at increased risk of rupture with significant higher accuracy than diameter alone. External validation of the model is warranted before clinical implementation.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

利用人工智能对腹主动脉瘤破裂进行个体风险评估。

研究目的本研究旨在开发一种预测工具，利用人工智能（AI）结合人口统计学、临床、影像学和药物治疗数据，识别破裂风险增加的腹主动脉瘤（AAA）：设计：在病例对照设计中使用人工智能进行个体预后的开发和验证研究：丹麦两家医院2009年1月至2016年12月期间的所有AAA破裂病例与择期手术对照病例的比例为1:2。既往接受过 AAA 手术或术前扫描缺失的病例被排除在外。人工检索计算机断层扫描血管造影扫描和医院记录的特征。样本被随机平均分为开发组和内部验证组。使用梯度提升决策树框架开发了 SHapley Additive exPlanations Feature Importance Rank Ensembling（SHAPFire）人工智能工具。最终的 SHAPFire AI 模型与 1）仅使用脐下前后径的模型和 2）使用所有可用特征的模型进行了比较：研究共纳入 637 人（84.8% 为男性，平均年龄为 73±7 岁，213 例 AAA 破裂）。SHAPFire AI纳入了68个可用特征中的20个，其中动脉瘤大小、血压以及身高和体重之间的关系排名最高。SHAPFire AI 模型的接收器操作特征曲线显示，与仅基于直径的传统模型相比，SHAPFire AI 模型识别破裂 AAA 病例的准确性显著提高，曲线下面积分别为 0.86±0.04 和 0.74±0.03 (P=0.008)。SHAPFire AI与使用所有特征的模型性能相当：本研究成功开发了一种 SHAPFire AI 工具，用于识别破裂风险增加的 AAA，其准确性明显高于单纯的直径识别。在临床应用之前，有必要对该模型进行外部验证。

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分钟内获得全文去求助

来源期刊

Journal of Vascular Surgery 医学-外科

CiteScore

7.70

自引率

18.60%

发文量

1469

审稿时长

54 days

期刊介绍： Journal of Vascular Surgery ® aims to be the premier international journal of medical, endovascular and surgical care of vascular diseases. It is dedicated to the science and art of vascular surgery and aims to improve the management of patients with vascular diseases by publishing relevant papers that report important medical advances, test new hypotheses, and address current controversies. To acheive this goal, the Journal will publish original clinical and laboratory studies, and reports and papers that comment on the social, economic, ethical, legal, and political factors, which relate to these aims. As the official publication of The Society for Vascular Surgery, the Journal will publish, after peer review, selected papers presented at the annual meeting of this organization and affiliated vascular societies, as well as original articles from members and non-members.