作者：黄艳，邓琪，曹丽萍，范咏梅，肖春霞

单位：

1.410005湖南省长沙市，湖南师范大学附属第一医院 湖南省人民医院心内科 2.410005湖南省长沙市，湖南省人民医院 湖南师范大学附属第一医院功能科 3.410005湖南省长沙市，湖南省人民医院 湖南师范大学附属第一医院心电图室 通信作者：肖春霞，E-mail：Xiaochunxia-2006@163.com

Units：

1.Department of Cardiology, the First Affiliated Hospital of Hunan Normal University/Hunan Provincial People's Hospital, Changsha 410005, China 2.Functional Department, Hunan Provincial People's Hospital/the First Affiliated Hospital of Hunan Normal University, Changsha 410005, China 3.Department of Electrocardiogram, Hunan Provincial People's Hospital/the First Affiliated Hospital of Hunan Normal University, Changsha 410005, China Corresponding author: XIAO Chunxia, E-mail: Xiaochunxia-2006@163.com

关键词：

心房颤动; 人工智能; 机器学习; 筛查; 疾病管理;

Keywords：

Atrial fibrillation; Artificial intelligence; Machine learning; Screenin; Disease management

CLC：

DOI：

10.12114/j.issn.1008-5971.2022.00.269

Funds：

湖南省研究生科研创新项目（CX20210498）；湖南 省卫生健康委项目（02203103241）；长沙市自然科学基金资助项目 （kq2014190）

摘要：

心房颤动是一种常见的心律失常类型，随着年龄增长其发病率不断升高，且其不规则的心脏节律会引起急性脑卒中等严重并发症。但心房颤动发作时多无明显症状，患者常在发生栓塞事件后才会被首次确诊。近年来随着人工智能技术不断发展，机器学习可以帮助临床医生识别心房颤动高危人群。本文主要综述了机器学习在心房颤动筛查和管理中的应用进展，旨在提高临床医生对机器学习的认识。

Abstract：

【Abstract】 Atrial fibrillation is a common type of arrhythmia. Its incidence increases with age, and its irregular heart rhythm can cause serious complications such as acute stroke. However, there are no obvious symptoms when atrial fibrillation attacks, and patients are often diagnosed for the first time after embolization events. In recent years, with the development of artificial intelligence technology, machine learning can help clinicians identify people with high risk of atrial fibrillation. This article reviews the application progress of machine learning in screening and management of atrial fibrillation, in order to improve clinicians' understanding of machine learning.

ReferenceList：