通过使用卷积神经网络的表面电心图来识别 supraventricular 高心率机制
Satoshi Higuchi1, Roland Li2, Edward P Gerstenfeld1
1Section of Cardiac Electrophysiology, Division of Cardiology, University of California, San Francisco, San Francisco, California.
机器学习,特别是卷积神经网络 (CNN),可以准确地从12导电心电图中区分 supraventricular tachycardia (SVT) 机制,匹配专家电生理学家的性能.
科学领域:
- 心脏病学 心脏病学
- 人工智能的人工智能
- 医学诊断 医学诊断 医学诊断
背景情况:
- 仅使用12导电心电图 (ECG) 区分 supraventricular tachycardia (SVT) 机制是具有挑战性的.
- 机器学习 (ML) 提供了检测微妙的ECG变化的潜力,以改进SVT机制的识别.
研究的目的:
- 开发一个卷积神经网络 (CNN) 用于识别 SVT 机制.
- 为了比较CNN的诊断性能与特定SVT类型的经验丰富的电生理学家.
主要方法:
- 一个CNN在1287个心电图上接受了培训,并在218个心电图上进行了测试,这些患者具有已知的SVT机制 (AVNRT,AVRT,AT) 和鼻节律.
- 在同一测试数据集上,CNN的表现与独立专家电生理学家的判断进行了比较.
主要成果:
- 美国有线电视新闻网在曲线下的高面积 (0.909为AVNRT,0.867为AVRT,0.817为AT).
- 在同等的特异性下,CNN在识别所有SVT类中表现出比电生理学家更高的灵敏度.
结论:
- 一个CNN可以有效地区分SVT机制使用表面12导电心电图.
- 在固定的特点下,CNN实现了高性能,与经验丰富的电生理学家相美.
更多相关视频
06:57Ablation of Ischemic Ventricular Tachycardia Using a Multipolar Catheter and 3-dimensional Mapping System for High-density Electro-anatomical Reconstruction
Published on: January 31, 2019
10:17Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
Published on: April 11, 2025
相关概念视频
Dysrhythmias III: Characteristics of Dysrhythmias
ECG Interpretation of Arrhythmias II: Atrial, Junctional and Ventricular Arrhythmias
Electrocardiogram Fundamentals
An electrocardiogram (ECG) is a diagnostic tool for identifying cardiac conditions such as arrhythmias, conduction abnormalities, and myocardial ischemia.
Definition
An electrocardiogram (ECG) visualizes the heart's electrical activity by tracing the electrical movement associated with each heartbeat on a graph or monitor. As the heart beats, an electrical wave passes through it, correlating with the cardiac cycle events.
Parts of an ECG
An ECG utilizes electrodes on the skin...
Dysrhythmias II: Classification of Tachyarrhythmias
Electrophysiology of Normal Cardiac Rhythm
Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
