Artificial intelligence-enhanced electrocardiography in cardiovascular disease management.
Artificial intelligence-enhanced electrocardiography in cardiovascular disease management.
复制标题
DOI：
10.1038/s41569-020-00503-2
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Friedman PA
中科院分区：
文献类型：
--
作者：
Siontis KC;Noseworthy PA;Attia ZI;Friedman PA
人工智能（AI）应用于心电图（ECG），这是一种无处不在的标准化测试，是人工智能对心血管医学持续变革影响的一个例子。虽然心电图长期以来为心脏和非心脏健康和疾病提供了有价值的见解，但其解释需要相当多的人类专业知识。先进的人工智能方法，如深度学习卷积神经网络，已经实现了对ECG的快速、类似人类的解释，而人类口译员无法识别的信号和模式可以通过多层人工智能网络精确检测，使ECG成为一种强大的、非侵入性的生物标志物。与丰富的临床数据相关联的大量数字心电图已被用于开发人工智能模型，用于检测左心室功能障碍、无症状（以前未记录和无症状）心房颤动和肥厚性心肌病，以及确定一个人的年龄、性别和种族等表型。基于人工智能的心电图表型在临床和人群水平上的影响不断出现，特别是随着移动和可穿戴心电图技术的迅速普及。在这篇综述中，我们总结了人工智能增强心电图在高危人群心血管疾病检测中的现状和未来状态，讨论了其对心血管疾病患者临床决策的影响，并批判性地评估了潜在的局限性和未知因素。在这篇综述中，Friedman及其同事总结了人工智能增强心电图在高危人群心血管疾病检测中的应用，讨论了其对心血管疾病患者临床决策的影响，并批判性地评估了潜在的局限性和未知因素。先进的人工智能方法，特别是深度学习卷积神经网络（cnn）应用于心电图（ECG）的可行性和潜在价值已经得到证明。使用大量与丰富的临床数据集相关联的数字心电图开发的cnn可能能够对心电图进行准确而细致的类似人类的解释。cnn也被用于检测无症状左心室功能障碍、无症状心房颤动、肥厚性心肌病以及仅基于ECG的个人年龄、性别和种族。cnn检测其他心脏疾病，如主动脉瓣狭窄和淀粉样心脏病，正在积极发展中。这些方法可能适用于标准的12导联心电图，也适用于单导联或多导联移动或可穿戴心电图技术获得的数据。关于患者结果的证据，以及人工智能增强心电图在现实世界中实施的挑战和潜在限制，不断出现。
The application of artificial intelligence (AI) to the electrocardiogram (ECG), a ubiquitous and standardized test, is an example of the ongoing transformative effect of AI on cardiovascular medicine. Although the ECG has long offered valuable insights into cardiac and non-cardiac health and disease, its interpretation requires considerable human expertise. Advanced AI methods, such as deep-learning convolutional neural networks, have enabled rapid, human-like interpretation of the ECG, while signals and patterns largely unrecognizable to human interpreters can be detected by multilayer AI networks with precision, making the ECG a powerful, non-invasive biomarker. Large sets of digital ECGs linked to rich clinical data have been used to develop AI models for the detection of left ventricular dysfunction, silent (previously undocumented and asymptomatic) atrial fibrillation and hypertrophic cardiomyopathy, as well as the determination of a person’s age, sex and race, among other phenotypes. The clinical and population-level implications of AI-based ECG phenotyping continue to emerge, particularly with the rapid rise in the availability of mobile and wearable ECG technologies. In this Review, we summarize the current and future state of the AI-enhanced ECG in the detection of cardiovascular disease in at-risk populations, discuss its implications for clinical decision-making in patients with cardiovascular disease and critically appraise potential limitations and unknowns. In this Review, Friedman and colleagues summarize the use of artificial intelligence-enhanced electrocardiography in the detection of cardiovascular disease in at-risk populations, discuss its implications for clinical decision-making in patients with cardiovascular disease and critically appraise potential limitations and unknowns. The feasibility and potential value of the application of advanced artificial intelligence methods, particularly deep-learning convolutional neural networks (CNNs), to the electrocardiogram (ECG) have been demonstrated. CNNs developed with the use of large numbers of digital ECGs linked to rich clinical datasets might be able to perform accurate and nuanced, human-like interpretation of ECGs. CNNs have also been developed to detect asymptomatic left ventricular dysfunction, silent atrial fibrillation, hypertrophic cardiomyopathy and an individual’s age, sex and race on the basis of the ECG alone. CNNs to detect other cardiac conditions, such as aortic valve stenosis and amyloid heart disease, are in active development. These approaches might be applicable to the standard 12-lead ECG or to data obtained from single-lead or multilead mobile or wearable ECG technologies. Evidence on patient outcomes, as well as the challenges and potential limitations from the real-world implementation of the artificial intelligence-enhanced ECG, continues to emerge.
登录
查看更多内容
DOI：
10.1161/circoutcomes.118.005595
发表时间：
2019-10
期刊：
Circulation. Cardiovascular quality and outcomes
影响因子：
--
作者：
Han L;Askari M;Altman RB;Schmitt SK;Fan J;Bentley JP;Narayan SM;Turakhia MP
通讯作者：
Turakhia MP
影响因子：
168.9
作者：
Attia, Zachi, I;Noseworthy, Peter A.;Friedman, Paul A.
通讯作者：
Friedman, Paul A.
影响因子：
8.4
作者：
Adedinsewo, Demilade;Carter, Rickey E.;Noseworthy, Peter A.
通讯作者：
Noseworthy, Peter A.
影响因子：
158.5
作者：
Gladstone, David J.;Spring, Melanie;Mamdani, Muhammad
通讯作者：
Mamdani, Muhammad
DOI：
10.1111/j.2164-0947.1961.tb03119.x
发表时间：
1961-01-01
期刊：
TRANSACTIONS OF THE NEW YORK ACADEMY OF SCIENCES
影响因子：
--
作者：
CACERES, CA;RIKLI, AE
通讯作者：
RIKLI, AE