利用应用于心电图和胸部 X 射线的深度学习模型对缺血性心脏病患者进行多模态风险评估

IF 1.2 4区 医学 Q3 CARDIAC & CARDIOVASCULAR SYSTEMS
Shinnosuke Sawano, Satoshi Kodera, Masataka Sato, Hiroki Shinohara, Atsushi Kobayashi, Hiroshi Takiguchi, Kazutoshi Hirose, Tatsuya Kamon, Akihito Saito, Hiroyuki Kiriyama, Mizuki Miura, Shun Minatsuki, Hironobu Kikuchi, Norifumi Takeda, Hiroyuki Morita, Issei Komuro
{"title":"利用应用于心电图和胸部 X 射线的深度学习模型对缺血性心脏病患者进行多模态风险评估","authors":"Shinnosuke Sawano, Satoshi Kodera, Masataka Sato, Hiroki Shinohara, Atsushi Kobayashi, Hiroshi Takiguchi, Kazutoshi Hirose, Tatsuya Kamon, Akihito Saito, Hiroyuki Kiriyama, Mizuki Miura, Shun Minatsuki, Hironobu Kikuchi, Norifumi Takeda, Hiroyuki Morita, Issei Komuro","doi":"10.1536/ihj.23-402","DOIUrl":null,"url":null,"abstract":"</p><p>Comprehensive management approaches for patients with ischemic heart disease (IHD) are important aids for prognostication and treatment planning. While single-modality deep neural networks (DNNs) have shown promising performance for detecting cardiac abnormalities, the potential benefits of using DNNs for multimodality risk assessment in patients with IHD have not been reported. The purpose of this study was to investigate the effectiveness of multimodality risk assessment in patients with IHD using a DNN that utilizes 12-lead electrocardiograms (ECGs) and chest X-rays (CXRs), with the prediction of major adverse cardiovascular events (MACEs) being of particular concern.</p><p>DNN models were applied to detection of left ventricular systolic dysfunction (LVSD) on ECGs and identification of cardiomegaly findings on CXRs. A total of 2107 patients who underwent elective percutaneous coronary intervention were categorized into 4 groups according to the models' outputs: Dual-modality high-risk (<i>n</i> = 105), ECG high-risk (<i>n</i> = 181), CXR high-risk (<i>n</i> = 392), and No-risk (<i>n</i> = 1,429).</p><p>A total of 342 MACEs were observed. The incidence of a MACE was the highest in the Dual-modality high-risk group (<i>P</i> &lt; 0.001). Multivariate Cox hazards analysis for predicting MACE revealed that the Dual-modality high-risk group had a significantly higher risk of MACE than the No-risk group (hazard ratio (HR): 2.370, <i>P</i> &lt; 0.001), the ECG high-risk group (HR: 1.906, <i>P</i> = 0.010), and the CXR high-risk group (HR: 1.624, <i>P</i> = 0.018), after controlling for confounding factors.</p><p>The results suggest the usefulness of multimodality risk assessment using DNN models applied to 12-lead ECG and CXR data from patients with IHD.</p>\n<p></p>","PeriodicalId":13711,"journal":{"name":"International heart journal","volume":"7 1","pages":""},"PeriodicalIF":1.2000,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multimodality Risk Assessment of Patients with Ischemic Heart Disease Using Deep Learning Models Applied to Electrocardiograms and Chest X-rays\",\"authors\":\"Shinnosuke Sawano, Satoshi Kodera, Masataka Sato, Hiroki Shinohara, Atsushi Kobayashi, Hiroshi Takiguchi, Kazutoshi Hirose, Tatsuya Kamon, Akihito Saito, Hiroyuki Kiriyama, Mizuki Miura, Shun Minatsuki, Hironobu Kikuchi, Norifumi Takeda, Hiroyuki Morita, Issei Komuro\",\"doi\":\"10.1536/ihj.23-402\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"</p><p>Comprehensive management approaches for patients with ischemic heart disease (IHD) are important aids for prognostication and treatment planning. While single-modality deep neural networks (DNNs) have shown promising performance for detecting cardiac abnormalities, the potential benefits of using DNNs for multimodality risk assessment in patients with IHD have not been reported. The purpose of this study was to investigate the effectiveness of multimodality risk assessment in patients with IHD using a DNN that utilizes 12-lead electrocardiograms (ECGs) and chest X-rays (CXRs), with the prediction of major adverse cardiovascular events (MACEs) being of particular concern.</p><p>DNN models were applied to detection of left ventricular systolic dysfunction (LVSD) on ECGs and identification of cardiomegaly findings on CXRs. A total of 2107 patients who underwent elective percutaneous coronary intervention were categorized into 4 groups according to the models' outputs: Dual-modality high-risk (<i>n</i> = 105), ECG high-risk (<i>n</i> = 181), CXR high-risk (<i>n</i> = 392), and No-risk (<i>n</i> = 1,429).</p><p>A total of 342 MACEs were observed. The incidence of a MACE was the highest in the Dual-modality high-risk group (<i>P</i> &lt; 0.001). Multivariate Cox hazards analysis for predicting MACE revealed that the Dual-modality high-risk group had a significantly higher risk of MACE than the No-risk group (hazard ratio (HR): 2.370, <i>P</i> &lt; 0.001), the ECG high-risk group (HR: 1.906, <i>P</i> = 0.010), and the CXR high-risk group (HR: 1.624, <i>P</i> = 0.018), after controlling for confounding factors.</p><p>The results suggest the usefulness of multimodality risk assessment using DNN models applied to 12-lead ECG and CXR data from patients with IHD.</p>\\n<p></p>\",\"PeriodicalId\":13711,\"journal\":{\"name\":\"International heart journal\",\"volume\":\"7 1\",\"pages\":\"\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2024-01-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International heart journal\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1536/ihj.23-402\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International heart journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1536/ihj.23-402","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

缺血性心脏病(IHD)患者的综合管理方法是预后和治疗计划的重要辅助工具。虽然单模态深度神经网络(DNN)在检测心脏异常方面表现出良好的性能,但使用 DNN 对缺血性心脏病患者进行多模态风险评估的潜在益处尚未见报道。本研究的目的是调查使用 DNN 对 IHD 患者进行多模态风险评估的有效性,该 DNN 利用 12 导联心电图 (ECG) 和胸部 X 光片 (CXR),其中对主要不良心血管事件 (MACE) 的预测尤为重要。DNN 模型适用于检测 ECG 上的左心室收缩功能障碍 (LVSD),以及识别 CXR 上的心脏肥大发现。根据模型的输出结果,共有 2107 名接受择期经皮冠状动脉介入治疗的患者被分为 4 组:共观察到 342 例 MACE。双方式高风险组的 MACE 发生率最高(P < 0.001)。预测 MACE 的多变量 Cox 危险分析显示,双模式高风险组的 MACE 风险显著高于无风险组(危险比 (HR):2.370,P < 0.001)、ECG 高风险组(HR:1.906,P = 0.结果表明,使用 DNN 模型对 IHD 患者的 12 导联 ECG 和 CXR 数据进行多模态风险评估非常有用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Multimodality Risk Assessment of Patients with Ischemic Heart Disease Using Deep Learning Models Applied to Electrocardiograms and Chest X-rays

Comprehensive management approaches for patients with ischemic heart disease (IHD) are important aids for prognostication and treatment planning. While single-modality deep neural networks (DNNs) have shown promising performance for detecting cardiac abnormalities, the potential benefits of using DNNs for multimodality risk assessment in patients with IHD have not been reported. The purpose of this study was to investigate the effectiveness of multimodality risk assessment in patients with IHD using a DNN that utilizes 12-lead electrocardiograms (ECGs) and chest X-rays (CXRs), with the prediction of major adverse cardiovascular events (MACEs) being of particular concern.

DNN models were applied to detection of left ventricular systolic dysfunction (LVSD) on ECGs and identification of cardiomegaly findings on CXRs. A total of 2107 patients who underwent elective percutaneous coronary intervention were categorized into 4 groups according to the models' outputs: Dual-modality high-risk (n = 105), ECG high-risk (n = 181), CXR high-risk (n = 392), and No-risk (n = 1,429).

A total of 342 MACEs were observed. The incidence of a MACE was the highest in the Dual-modality high-risk group (P < 0.001). Multivariate Cox hazards analysis for predicting MACE revealed that the Dual-modality high-risk group had a significantly higher risk of MACE than the No-risk group (hazard ratio (HR): 2.370, P < 0.001), the ECG high-risk group (HR: 1.906, P = 0.010), and the CXR high-risk group (HR: 1.624, P = 0.018), after controlling for confounding factors.

The results suggest the usefulness of multimodality risk assessment using DNN models applied to 12-lead ECG and CXR data from patients with IHD.

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
International heart journal
International heart journal 医学-心血管系统
CiteScore
2.50
自引率
6.70%
发文量
148
审稿时长
6-12 weeks
期刊介绍: Authors of research articles should disclose at the time of submission any financial arrangement they may have with a company whose product figures prominently in the submitted manuscript or with a company making a competing product. Such information will be held in confidence while the paper is under review and will not influence the editorial decision, but if the article is accepted for publication, the editors will usually discuss with the authors the manner in which such information is to be communicated to the reader.
×
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