基于无心肌缺血证据的心电图的冠状动脉疾病规则输入和排除的深度学习算法的开发和验证

IF 2.5 Q2 CARDIAC & CARDIOVASCULAR SYSTEMS

IJC Heart and Vasculature Pub Date : 2025-08-15 DOI:10.1016/j.ijcha.2025.101772

Runchen Sun , Xiangqian Zhu , Shen Lin , Mengnan Shi , Xuexin Yu , Chang Liu , Yaoguan Yue , Juntong Zeng , Yan Zhao , Xiaoqi Wang , Xiaocong Lian , Xin Jin , Zhe Zheng , Xiangyang Ji

{"title":"基于无心肌缺血证据的心电图的冠状动脉疾病规则输入和排除的深度学习算法的开发和验证","authors":"Runchen Sun , Xiangqian Zhu , Shen Lin , Mengnan Shi , Xuexin Yu , Chang Liu , Yaoguan Yue , Juntong Zeng , Yan Zhao , Xiaoqi Wang , Xiaocong Lian , Xin Jin , Zhe Zheng , Xiangyang Ji","doi":"10.1016/j.ijcha.2025.101772","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Current coronary artery disease (CAD) guidelines recommend to rule-out or rule-in patients for further examination by assessing a pretest probability (PTP) ≤ 5 % or ≥ 15 %. We developed and validated a deep-learning algorithm for rule-in or rule-out based on electrocardiogram (ECG) without myocardial ischemia evidence.</div></div><div><h3>Methods</h3><div>Between October 2019 and June 2022, data from two centers (Fuwai Hospital [Beijing] and Yunnan Fuwai Hospital) of CAD-suspected patients undergoing either coronary angiography or coronary computed tomography were used. Data from the Fuwai Hospital (Beijing) were used to train (randomly 90 %) and internally validate (randomly 10 %) a deep-learning algorithm to detect CAD (≥ 70 % stenosis) based on 12-lead ECGs. An algorithm-based decision-making protocol was established for rule-out or rule-in based on a predefined threshold allowing for a 95 % negative predictive value (NPV). Data from the Yunnan Fuwai Hospital were used to externally validate the performance of the decision-making protocol. The CAD prevalence was calculated in patients who were recommended to rule-in or rule-out.</div></div><div><h3>Results</h3><div>In internal validation set, area under the receiver operating characteristic curve (AUC) was 0.81 and the CAD prevalence of patients who were recommended rule-out and rule-in were 5 % (40/790) and 23 % (527/2253), respectively. In external validation set, the CAD prevalence of patients who were recommended rule-out and rule-in were 0 % (0/661) and 15 % (255/1699), respectively.</div></div><div><h3>Conclusions</h3><div>Our algorithm based on ECG without myocardial ischemia evidence performed good in CAD detection. An algorithm-based decision-making protocol could achieve the guideline-recommended performance in guiding rule-out or rule-in for further examination.</div></div>","PeriodicalId":38026,"journal":{"name":"IJC Heart and Vasculature","volume":"60 ","pages":"Article 101772"},"PeriodicalIF":2.5000,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Development and validation of a deep-learning algorithm for rule-in and rule-out coronary artery disease based on electrocardiogram without evidence of myocardial ischemia\",\"authors\":\"Runchen Sun , Xiangqian Zhu , Shen Lin , Mengnan Shi , Xuexin Yu , Chang Liu , Yaoguan Yue , Juntong Zeng , Yan Zhao , Xiaoqi Wang , Xiaocong Lian , Xin Jin , Zhe Zheng , Xiangyang Ji\",\"doi\":\"10.1016/j.ijcha.2025.101772\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Current coronary artery disease (CAD) guidelines recommend to rule-out or rule-in patients for further examination by assessing a pretest probability (PTP) ≤ 5 % or ≥ 15 %. We developed and validated a deep-learning algorithm for rule-in or rule-out based on electrocardiogram (ECG) without myocardial ischemia evidence.</div></div><div><h3>Methods</h3><div>Between October 2019 and June 2022, data from two centers (Fuwai Hospital [Beijing] and Yunnan Fuwai Hospital) of CAD-suspected patients undergoing either coronary angiography or coronary computed tomography were used. Data from the Fuwai Hospital (Beijing) were used to train (randomly 90 %) and internally validate (randomly 10 %) a deep-learning algorithm to detect CAD (≥ 70 % stenosis) based on 12-lead ECGs. An algorithm-based decision-making protocol was established for rule-out or rule-in based on a predefined threshold allowing for a 95 % negative predictive value (NPV). Data from the Yunnan Fuwai Hospital were used to externally validate the performance of the decision-making protocol. The CAD prevalence was calculated in patients who were recommended to rule-in or rule-out.</div></div><div><h3>Results</h3><div>In internal validation set, area under the receiver operating characteristic curve (AUC) was 0.81 and the CAD prevalence of patients who were recommended rule-out and rule-in were 5 % (40/790) and 23 % (527/2253), respectively. In external validation set, the CAD prevalence of patients who were recommended rule-out and rule-in were 0 % (0/661) and 15 % (255/1699), respectively.</div></div><div><h3>Conclusions</h3><div>Our algorithm based on ECG without myocardial ischemia evidence performed good in CAD detection. An algorithm-based decision-making protocol could achieve the guideline-recommended performance in guiding rule-out or rule-in for further examination.</div></div>\",\"PeriodicalId\":38026,\"journal\":{\"name\":\"IJC Heart and Vasculature\",\"volume\":\"60 \",\"pages\":\"Article 101772\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2025-08-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IJC Heart and Vasculature\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2352906725001757\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IJC Heart and Vasculature","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352906725001757","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

摘要

当前的冠状动脉疾病（CAD）指南建议通过评估预测概率(PTP)≤5%或≥15%来排除或纳入患者进行进一步检查。我们开发并验证了一种基于无心肌缺血证据的心电图（ECG）的规则输入或排除的深度学习算法。方法2019年10月至2022年6月，使用来自两个中心（阜外医院[北京]和云南阜外医院）进行冠状动脉造影或冠状动脉计算机断层扫描的疑似cad患者的数据。来自北京阜外医院的数据用于训练（随机90%）和内部验证（随机10%）基于12导联心电图检测CAD（≥70%狭窄）的深度学习算法。基于预定义的阈值（允许95%的负预测值（NPV）），建立了基于算法的排除或规则加入决策协议。采用云南省阜外医院的数据对决策方案的绩效进行外部验证。计算推荐纳入或排除的患者的CAD患病率。结果在内验证集中，受试者工作特征曲线下面积（AUC）为0.81，推荐排除和纳入患者的CAD患病率分别为5%（40/790）和23%（527/2253）。在外部验证集中，推荐排除和纳入的患者的CAD患病率分别为0%（0/661）和15%（255/1699）。结论基于心电图无心肌缺血证据的sour算法在CAD检测中具有较好的效果。基于算法的决策协议可以达到指南推荐的指导排除或规则进入进一步检查的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Development and validation of a deep-learning algorithm for rule-in and rule-out coronary artery disease based on electrocardiogram without evidence of myocardial ischemia

查看原文本刊更多论文

Development and validation of a deep-learning algorithm for rule-in and rule-out coronary artery disease based on electrocardiogram without evidence of myocardial ischemia

Background

Current coronary artery disease (CAD) guidelines recommend to rule-out or rule-in patients for further examination by assessing a pretest probability (PTP) ≤ 5 % or ≥ 15 %. We developed and validated a deep-learning algorithm for rule-in or rule-out based on electrocardiogram (ECG) without myocardial ischemia evidence.

Methods

Between October 2019 and June 2022, data from two centers (Fuwai Hospital [Beijing] and Yunnan Fuwai Hospital) of CAD-suspected patients undergoing either coronary angiography or coronary computed tomography were used. Data from the Fuwai Hospital (Beijing) were used to train (randomly 90 %) and internally validate (randomly 10 %) a deep-learning algorithm to detect CAD (≥ 70 % stenosis) based on 12-lead ECGs. An algorithm-based decision-making protocol was established for rule-out or rule-in based on a predefined threshold allowing for a 95 % negative predictive value (NPV). Data from the Yunnan Fuwai Hospital were used to externally validate the performance of the decision-making protocol. The CAD prevalence was calculated in patients who were recommended to rule-in or rule-out.

Results

In internal validation set, area under the receiver operating characteristic curve (AUC) was 0.81 and the CAD prevalence of patients who were recommended rule-out and rule-in were 5 % (40/790) and 23 % (527/2253), respectively. In external validation set, the CAD prevalence of patients who were recommended rule-out and rule-in were 0 % (0/661) and 15 % (255/1699), respectively.

Conclusions

Our algorithm based on ECG without myocardial ischemia evidence performed good in CAD detection. An algorithm-based decision-making protocol could achieve the guideline-recommended performance in guiding rule-out or rule-in for further examination.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

IJC Heart and Vasculature Medicine-Cardiology and Cardiovascular Medicine

CiteScore

4.90

自引率

10.30%

发文量

216

审稿时长

56 days

期刊介绍： IJC Heart & Vasculature is an online-only, open-access journal dedicated to publishing original articles and reviews (also Editorials and Letters to the Editor) which report on structural and functional cardiovascular pathology, with an emphasis on imaging and disease pathophysiology. Articles must be authentic, educational, clinically relevant, and original in their content and scientific approach. IJC Heart & Vasculature requires the highest standards of scientific integrity in order to promote reliable, reproducible and verifiable research findings. All authors are advised to consult the Principles of Ethical Publishing in the International Journal of Cardiology before submitting a manuscript. Submission of a manuscript to this journal gives the publisher the right to publish that paper if it is accepted. Manuscripts may be edited to improve clarity and expression.