• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

开发和验证一种机器学习模型,以从患者心电图预测心肌血流和临床结局。

Development and validation of a machine learning model to predict myocardial blood flow and clinical outcomes from patients' electrocardiograms.

机构信息

Houston Methodist DeBakey Heart & Vascular Center, Houston, TX, USA; Departments of Biomedical Informatics, Biostatistics, Epidemiology, and Cardiology, University of Missouri, Columbia, MO.

Department of Imaging Physics, Division of Diagnostic Imaging, MD Anderson Cancer Center, Houston, TX, USA.

出版信息

Cell Rep Med. 2024 Oct 15;5(10):101746. doi: 10.1016/j.xcrm.2024.101746. Epub 2024 Sep 25.

DOI:10.1016/j.xcrm.2024.101746
PMID:39326409
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11513811/
Abstract

We develop a machine learning (ML) model using electrocardiography (ECG) to predict myocardial blood flow reserve (MFR) and assess its prognostic value for major adverse cardiovascular events (MACEs). Using 3,639 ECG-positron emission tomography (PET) and 17,649 ECG-single-photon emission computed tomography (SPECT) data pairs, the ML model is trained with a swarm intelligence approach and support vector regression (SVR). The model achieves a receiver-operator curve (ROC) area under the curve (AUC) of 0.83, with a sensitivity and specificity of 0.75. An ECG-MFR value below 2 is significantly associated with MACE, with hazard ratios (HRs) of 3.85 and 3.70 in the discovery and validation phases, respectively. The model's C-statistic is 0.76, with a net reclassification improvement (NRI) of 0.35. Validated in an independent cohort, the ML model using ECG data offers superior MACE prediction compared to baseline clinical models, highlighting its potential for risk stratification in patients with coronary artery disease (CAD) using the accessible 12-lead ECG.

摘要

我们开发了一种使用心电图(ECG)预测心肌血流储备(MFR)的机器学习(ML)模型,并评估其对主要不良心血管事件(MACE)的预后价值。使用 3639 对心电图正电子发射断层扫描(PET)和 17649 对心电图单光子发射计算机断层扫描(SPECT)数据对,该 ML 模型采用群体智能方法和支持向量回归(SVR)进行训练。该模型的接收者操作曲线(ROC)下面积(AUC)为 0.83,灵敏度和特异性分别为 0.75。ECG-MFR 值低于 2 与 MACE 显著相关,在发现和验证阶段的危险比(HR)分别为 3.85 和 3.70。该模型的 C 统计量为 0.76,净重新分类改善(NRI)为 0.35。在独立队列中进行验证后,使用 ECG 数据的 ML 模型在预测 MACE 方面优于基线临床模型,突出了其在使用可获得的 12 导联 ECG 对冠心病(CAD)患者进行风险分层的潜力。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/440076a29d6c/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/9fd55c9cc0e1/fx1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/5f5b4c155368/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/def32c5ba92c/gr3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/8f6ead8aaea6/gr4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/440076a29d6c/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/9fd55c9cc0e1/fx1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/5f5b4c155368/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/def32c5ba92c/gr3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/8f6ead8aaea6/gr4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c029/11513811/440076a29d6c/gr1.jpg

相似文献

1
Development and validation of a machine learning model to predict myocardial blood flow and clinical outcomes from patients' electrocardiograms.开发和验证一种机器学习模型,以从患者心电图预测心肌血流和临床结局。
Cell Rep Med. 2024 Oct 15;5(10):101746. doi: 10.1016/j.xcrm.2024.101746. Epub 2024 Sep 25.
2
Added prognostic value of myocardial blood flow quantitation in rubidium-82 positron emission tomography imaging.锶-82 正电子发射断层成像心肌血流定量增加预后价值。
Eur Heart J Cardiovasc Imaging. 2013 Dec;14(12):1203-10. doi: 10.1093/ehjci/jet068. Epub 2013 May 9.
3
Prediction of cardiovascular events using myocardial strain ratio derived from N-ammonia positron emission tomography.使用 N-氨质子发射断层扫描得出的心肌应变比预测心血管事件。
Eur Radiol. 2023 Jun;33(6):3889-3896. doi: 10.1007/s00330-022-09359-1. Epub 2022 Dec 23.
4
Prognostic value of myocardial flow reserve vs corrected myocardial flow reserve in patients without obstructive coronary artery disease.无阻塞性冠状动脉疾病患者中心肌血流储备与校正心肌血流储备的预后价值。
J Nucl Cardiol. 2024 Jul;37:101854. doi: 10.1016/j.nuclcard.2024.101854. Epub 2024 Apr 7.
5
SPECT myocardial blood flow quantitation toward clinical use: a comparative study with N-Ammonia PET myocardial blood flow quantitation.SPECT心肌血流定量分析在临床中的应用:与N-氨PET心肌血流定量分析的比较研究
Eur J Nucl Med Mol Imaging. 2017 Jan;44(1):117-128. doi: 10.1007/s00259-016-3491-5. Epub 2016 Sep 1.
6
Comparison between NNH-PET and Tc-Tetrofosmin-CZT SPECT in the evaluation of absolute myocardial blood flow and flow reserve.NNH-PET与锝-替曲膦-碲锌镉单光子发射计算机断层扫描在评估绝对心肌血流量和血流储备方面的比较。
J Nucl Cardiol. 2021 Oct;28(5):1906-1918. doi: 10.1007/s12350-019-01939-x. Epub 2019 Nov 14.
7
Does quantification of myocardial flow reserve using rubidium-82 positron emission tomography facilitate detection of multivessel coronary artery disease?使用铷-82 正电子发射断层扫描技术对心肌血流储备进行定量分析是否有助于检测多支冠状动脉疾病?
J Nucl Cardiol. 2012 Aug;19(4):670-80. doi: 10.1007/s12350-011-9506-5. Epub 2012 Mar 14.
8
Optimization of SPECT Measurement of Myocardial Blood Flow with Corrections for Attenuation, Motion, and Blood Binding Compared with PET.与PET相比,通过衰减、运动和血液结合校正优化心肌血流的SPECT测量
J Nucl Med. 2017 Dec;58(12):2013-2019. doi: 10.2967/jnumed.117.191049. Epub 2017 Jun 13.
9
Accuracy and Reproducibility of Myocardial Blood Flow Quantification by Single Photon Emission Computed Tomography Imaging in Patients With Known or Suspected Coronary Artery Disease.单光子发射计算机断层扫描成像在已知或疑似冠状动脉疾病患者中心肌血流定量的准确性和可重复性。
Circ Cardiovasc Imaging. 2022 Jun;15(6):e013987. doi: 10.1161/CIRCIMAGING.122.013987. Epub 2022 Jun 8.
10
Integration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging.机器学习整合 CT 衰减扫描的冠状动脉钙评分可改善 SPECT/CT 心肌灌注成像患者不良心血管事件的预测。
J Nucl Cardiol. 2023 Apr;30(2):590-603. doi: 10.1007/s12350-022-03099-x. Epub 2022 Oct 4.

引用本文的文献

1
Association between the COVID-19 pandemic and cardiopulmonary function in acute coronary syndrome patients without SARS-CoV-2 infection.2019冠状病毒病大流行与未感染严重急性呼吸综合征冠状病毒2的急性冠状动脉综合征患者心肺功能之间的关联
Sci Rep. 2025 Aug 22;15(1):30906. doi: 10.1038/s41598-025-17016-y.
2
Identification of atrial fibrillation using heart rate variability: a meta-analysis.利用心率变异性识别心房颤动:一项荟萃分析。
Front Cardiovasc Med. 2025 Jun 19;12:1581683. doi: 10.3389/fcvm.2025.1581683. eCollection 2025.

本文引用的文献

1
Deep learning-derived cardiovascular age shares a genetic basis with other cardiac phenotypes.深度学习衍生的心血管年龄与其他心脏表型具有共同的遗传基础。
Sci Rep. 2022 Dec 31;12(1):22625. doi: 10.1038/s41598-022-27254-z.
2
Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective.用机器学习推动心血管医学的发展:进展、潜力和展望。
Cell Rep Med. 2022 Dec 20;3(12):100869. doi: 10.1016/j.xcrm.2022.100869.
3
An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythm.
一种基于人工智能的心电图算法,用于在窦性节律期间识别室性期前收缩。
Eur J Med Res. 2022 Dec 14;27(1):289. doi: 10.1186/s40001-022-00929-z.
4
The Global Burden of Cardiovascular Diseases and Risk: A Compass for Future Health.心血管疾病及其风险的全球负担:未来健康指南。
J Am Coll Cardiol. 2022 Dec 20;80(25):2361-2371. doi: 10.1016/j.jacc.2022.11.005. Epub 2022 Nov 9.
5
Artificial Intelligence-Enabled Electrocardiogram Improves the Diagnosis and Prediction of Mortality in Patients With Pulmonary Hypertension.人工智能辅助心电图可改善肺动脉高压患者的死亡率诊断和预测。
JACC Asia. 2022 May 17;2(3):258-270. doi: 10.1016/j.jacasi.2022.02.008. eCollection 2022 Jun.
6
Implementation of an All-Day Artificial Intelligence-Based Triage System to Accelerate Door-to-Balloon Times.实施全天人工智能分诊系统以加速门球时间。
Mayo Clin Proc. 2022 Dec;97(12):2291-2303. doi: 10.1016/j.mayocp.2022.05.014. Epub 2022 Nov 3.
7
Artificial intelligence-guided screening for atrial fibrillation using electrocardiogram during sinus rhythm: a prospective non-randomised interventional trial.人工智能引导窦性心律心电图心房颤动筛查:一项前瞻性非随机干预性试验。
Lancet. 2022 Oct 8;400(10359):1206-1212. doi: 10.1016/S0140-6736(22)01637-3. Epub 2022 Sep 27.
8
Investigation of Applying Machine Learning and Hyperparameter Tuned Deep Learning Approaches for Arrhythmia Detection in ECG Images.应用机器学习和超参数调整深度学习方法在 ECG 图像中的心律失常检测研究。
Comput Math Methods Med. 2022 Sep 12;2022:8571970. doi: 10.1155/2022/8571970. eCollection 2022.
9
The Role of Artificial Intelligence in Predicting Outcomes by Cardiovascular Magnetic Resonance: A Comprehensive Systematic Review.人工智能在心血管磁共振预测结果中的作用:全面的系统评价。
Medicina (Kaunas). 2022 Aug 12;58(8):1087. doi: 10.3390/medicina58081087.
10
Artificial Intelligence-Enabled Model for Early Detection of Left Ventricular Hypertrophy and Mortality Prediction in Young to Middle-Aged Adults.人工智能辅助模型对年轻至中年成年人左心室肥厚和死亡率的早期检测。
Circ Cardiovasc Qual Outcomes. 2022 Aug;15(8):e008360. doi: 10.1161/CIRCOUTCOMES.121.008360. Epub 2022 Aug 12.