Application of Machine Learning Algorithms to Predict New-Onset Postoperative Atrial Fibrillation and Identify Risk Factors Following Isolated Valve Surgery.

IF 0.7 4区 医学 Q4 CARDIAC & CARDIOVASCULAR SYSTEMS Heart Surgery Forum Pub Date : 2023-06-14 DOI:10.1532/hsf.5341
Siming Zhu, Hebin Che, Yunlong Fan, Shengli Jiang
{"title":"Application of Machine Learning Algorithms to Predict New-Onset Postoperative Atrial Fibrillation and Identify Risk Factors Following Isolated Valve Surgery.","authors":"Siming Zhu,&nbsp;Hebin Che,&nbsp;Yunlong Fan,&nbsp;Shengli Jiang","doi":"10.1532/hsf.5341","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>New-onset postoperative atrial fibrillation (POAF) is the most common complication after valvular surgery, but its etiology and risk factors are incompletely understood. This study investigates the benefits of machine learning methods in risk prediction and in identifying relative perioperative variables for POAF after valve surgery.</p><p><strong>Methods: </strong>This retrospective study involved 847 patients, who underwent isolated valve surgery from January 2018 to September 2021 in our institution. We used machine learning algorithms to predict new-onset postoperative atrial fibrillation and to select relatively important variables from a set of 123 preoperative characteristics and intraoperative information.</p><p><strong>Results: </strong>The support vector machine (SVM) model demonstrated the best area under the receiver operating characteristic (AUC) value of 0.786, followed by logistic regression (AUC = 0.745) and the Complement Naive Bayes (CNB) model (AUC = 0.672). Left atrium diameter, age, estimated glomerular filtration rate (eGFR), duration of cardiopulmonary bypass, New York Heart Association (NYHA) class III-IV, and preoperative hemoglobin were high-ranked variables.</p><p><strong>Conclusions: </strong>Risk models based on machine learning algorithms may be superior to traditional models, which were primarily based on logistic algorithms to predict the occurrence of POAF after valve surgery. Further prospective multicenter studies are needed to confirm the performance of SVM in predicting POAF.</p>","PeriodicalId":51056,"journal":{"name":"Heart Surgery Forum","volume":"26 3","pages":"E255-E263"},"PeriodicalIF":0.7000,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Heart Surgery Forum","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1532/hsf.5341","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 1

Abstract

Background: New-onset postoperative atrial fibrillation (POAF) is the most common complication after valvular surgery, but its etiology and risk factors are incompletely understood. This study investigates the benefits of machine learning methods in risk prediction and in identifying relative perioperative variables for POAF after valve surgery.

Methods: This retrospective study involved 847 patients, who underwent isolated valve surgery from January 2018 to September 2021 in our institution. We used machine learning algorithms to predict new-onset postoperative atrial fibrillation and to select relatively important variables from a set of 123 preoperative characteristics and intraoperative information.

Results: The support vector machine (SVM) model demonstrated the best area under the receiver operating characteristic (AUC) value of 0.786, followed by logistic regression (AUC = 0.745) and the Complement Naive Bayes (CNB) model (AUC = 0.672). Left atrium diameter, age, estimated glomerular filtration rate (eGFR), duration of cardiopulmonary bypass, New York Heart Association (NYHA) class III-IV, and preoperative hemoglobin were high-ranked variables.

Conclusions: Risk models based on machine learning algorithms may be superior to traditional models, which were primarily based on logistic algorithms to predict the occurrence of POAF after valve surgery. Further prospective multicenter studies are needed to confirm the performance of SVM in predicting POAF.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
应用机器学习算法预测孤立瓣膜手术后新发心房颤动和识别危险因素。
背景:术后新发心房颤动(POAF)是瓣膜手术后最常见的并发症,但其病因和危险因素尚不完全清楚。本研究探讨了机器学习方法在瓣膜手术后POAF风险预测和识别相关围手术期变量方面的益处。方法:本回顾性研究纳入了2018年1月至2021年9月在我院接受孤立瓣膜手术的847例患者。我们使用机器学习算法来预测术后新发心房颤动,并从123个术前特征和术中信息中选择相对重要的变量。结果:支持向量机(SVM)模型在接收者工作特征(AUC)值为0.786下的面积最佳,其次是逻辑回归(AUC = 0.745)和互补朴素贝叶斯(CNB)模型(AUC = 0.672)。左心房直径、年龄、估计肾小球滤过率(eGFR)、体外循环时间、纽约心脏协会(NYHA) III-IV级和术前血红蛋白是重要的变量。结论:基于机器学习算法的风险模型可能优于传统模型,传统模型主要基于logistic算法预测瓣膜术后POAF的发生。支持向量机预测POAF的性能有待进一步的多中心前瞻性研究来证实。
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
Heart Surgery Forum
Heart Surgery Forum 医学-外科
CiteScore
1.20
自引率
16.70%
发文量
130
审稿时长
6-12 weeks
期刊介绍: The Heart Surgery Forum® is an international peer-reviewed, open access journal seeking original investigative and clinical work on any subject germane to the science or practice of modern cardiac care. The HSF publishes original scientific reports, collective reviews, case reports, editorials, and letters to the editor. New manuscripts are reviewed by reviewers for originality, content, relevancy and adherence to scientific principles in a double-blind process. The HSF features a streamlined submission and peer review process with an anticipated completion time of 30 to 60 days from the date of receipt of the original manuscript. Authors are encouraged to submit full color images and video that will be included in the web version of the journal at no charge.
期刊最新文献
You Either Pull Freight or You are Freight-Admonition #1 for Third Year Medical Students on a Surgery Service. Left Atrial Low Voltage Areas Predicts Recurrence of Atrial Fibrillation after Catheter Ablation: A Meta-Analysis. A Meta-Analysis for Postoperative Alternations of Aortic Coarctation. Effects of Phase Ⅰ Cardiac Rehabilitation Combined with Cognitive Behavioural Therapy on Cardiac Function, Exercise Capacity and Mental Health in Patients after Aortic Valve Replacement: A Retrospective Study. Effects of Concomitant CABG on Outcomes in Veterans Who Require Surgery for Endocarditis.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1