心电形态与节律特征融合的轻量房颤检测模型及可解释性研究

高宁; 李玉榕; 陈泓; 陈文升; 贾梓豪

doi:10.12263/DZXB.20240998

您当前的位置：

首页 >

文章列表页 >

心电形态与节律特征融合的轻量房颤检测模型及可解释性研究

学术论文 | 更新时间：2025-12-08

- 心电形态与节律特征融合的轻量房颤检测模型及可解释性研究
  增强出版
- Lightweight Atrial Fibrillation Model Based on Feature Fusion of Morphology and Rhythmic and Interpretability Analysis
- 电子学报 2025年53卷第2期页码：503-513
- 作者机构：
  
  1.福州大学电气工程与自动化学院，福建福州 350108
  2.福建省医疗器械和医药技术重点实验室，福建福州 350108
- 作者简介：
  
  [ "高宁男，2000年11月出生，福建人.现为福州大学电气工程与自动化学院硕士研究生.主要研究方向为心电信号的去噪与智能识别技术." ]
  [ "李玉榕女， 1973年2月出生，福建人. 现为福州大学电气工程与自动化学院教授、博士生导师. 主要研究方向为多模态电生理信号建模与智能康复技术研究与应用. E-mail:liyurong@fzu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62373108)
- DOI：10.12263/DZXB.20240998
  中图分类号： TP391;
- 收稿：2024-11-05，
  
  修回：2025-01-03，
  
  纸质出版：2025-02-25
- 稿件说明：
移动端阅览
高宁, 李玉榕, 陈泓, 等. 心电形态与节律特征融合的轻量房颤检测模型及可解释性研究[J]. 电子学报, 2025, 53(02): 503-513.

GAO Ning, LI Yu-rong, CHEN Hong, et al. Lightweight Atrial Fibrillation Model Based on Feature Fusion of Morphology and Rhythmic and Interpretability Analysis[J]. Acta Electronica Sinica, 2025, 53(02): 503-513.
高宁, 李玉榕, 陈泓, 等. 心电形态与节律特征融合的轻量房颤检测模型及可解释性研究[J]. 电子学报, 2025, 53(02): 503-513. DOI：10.12263/DZXB.20240998

GAO Ning, LI Yu-rong, CHEN Hong, et al. Lightweight Atrial Fibrillation Model Based on Feature Fusion of Morphology and Rhythmic and Interpretability Analysis[J]. Acta Electronica Sinica, 2025, 53(02): 503-513. DOI：10.12263/DZXB.20240998

摘要

房颤是一种常见的心律失常，通常与中风、心力衰竭等心血管疾病相关.近年来，虽然有许多研究者使用深度学习方法在房颤检测上取得了重大进展，但所提出的方法大都需要大量的计算资源，并且由于深度学习模型的黑盒效应，模型的检测结果较难以在临床上推广应用.为此，本文提出一种基于特征融合的轻量房颤检测模型并对其开展可解释性研究，模型由ECG（ElectroCardioGram）主干网络和RRI（R-R Interval）支路组成.ECG主干网络使用深度可分离卷积以及少量的标准卷积来提取心电信号的深层形态特征，RRI支路使用多尺度卷积提取RRI的深层节律特征，网络通过融合二者来学习全面鲁棒的特征表示，实现准确的房颤检测.进一步，基于Grad-CAM++来可视化不同特征对于分类结果的贡献实现模型的可解释性分析.本文在长期房颤数据库LTAFDB进行训练与数据集内部测试，准确率达到了97.99%.为了验证模型的泛化性能，利用MIT-BIH心房颤动数据库AFDB与中国生理信号挑战赛数据库CPSC2021开展跨数据集的外部测试，分别取得了95.17%和93.81%的准确率.实验结果表明，本文提出的方法具有轻量级特性，稳定性和准确性良好，同时可解释性深度学习的引入使得本文所提出的方法在房颤的临床诊断中具有更加广阔的应用前景.

Abstract

Atrial fibrillation (AF) is a common arrhythmia often associated with cardiovascular diseases such as stroke and heart failure. Although numerous researchers have made substantial progress in AF detection using deep learning methods in recent years

most of these methods require extensive computational resources. Moreover

the clinical application of these models is challenging due to the black-box nature of deep learning models. Therefore

this paper proposes a lightweight AF detection model based on feature fusion and conducts an interpretability study. The model comprises an ECG (ElectroCardioGram) backbone network and an RRI (R-R Interval) branch. The ECG backbone network uses depthwise separable convolutions along with a few standard convolutions to extract deep morphological features of the ECG signals

while the RRI branch employs multi-scale convolutions to extract deep rhythm features of the RRI. The network learns robust feature representations by fusing morphological features and rhythm features to detect AF accurately. As to interpretability analysis

Grad-CAM++ is utilized to visualize the contribution of different features to the classification results. In this paper

the training and dataset internal tests are conducted in the LTAFDB and achieved an accuracy of 97.99%. In order to validate the generalization performance of the model

external testing experiments are conducted using the AFDB and the CPSC2021

achieving an accuracy of 95.17% and 93.81%

respectively. Experimental results demonstrate that the proposed method is lightweight

stable

and accurate

and the incorporation of interpretable deep-learning techniques suggests that the proposed method holds significant potential for the clinical diagnosis of AF.

关键词

Keywords

references

HAIM M , HOSHEN M , REGES O , et al . Prospective national study of the prevalence, incidence, management and outcome of a large contemporary cohort of patients with incident non-valvular atrial fibrillation [J ] . Journal of the American Heart Association , 2015 , 4 ( 1 ): e001486 .

LLOYD-JONES D M , WANG T J , LEIP E P , et al . Lifetime risk for development of atrial fibrillation: The Framingham Heart Study [J ] . Circulation , 2004 , 110 ( 9 ): 1042 - 1046 .

HINDRICKS G , POTPARA T , DAGRES N , et al . 2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS): The Task Force for the diagnosis and management of atrial fibrillation of the European Society of Cardiology (ESC) Developed with the special contribution of the European Heart Rhythm Association (EHRA) of the ESC [J ] . European Heart Journal , 2021 , 42 ( 5 ): 373 - 498 .

HENDRIKS J M L , HEIDBÜCHEL H . The management of atrial fibrillation: An integrated team approach-insights of the 2016 European society of cardiology guidelines for the management of atrial fibrillation for nurses and allied health professionals [J ] . European Journal of Cardiovascular Nursing , 2019 , 18 ( 2 ): 88 - 95 .

吕杭 , 蒋明峰 , 李杨 , 等 . 基于混合时频域特征的卷积神经网络心律失常分类方法的研究 [J ] . 电子学报 , 2023 , 51 ( 3 ): 701 - 711 .

LU¨ H , JIANG M F , LI Y , et al . Research on arrhythmia classification by using convolutional neural network with mixed time-frequency domain features [J ] . Acta Electronica Sinica , 2023 , 51 ( 3 ): 701 - 711 . (in Chinese)

FREEDMAN B , CAMM J , CALKINS H , et al . Screening for atrial fibrillation: A report of the AF-SCREEN international collaboration [J ] . Circulation , 2017 , 135 ( 19 ): 1851 - 1867 .

QUER G , FREEDMAN B , STEINHUBL S R . Screening for atrial fibrillation: Predicted sensitivity of short, intermittent electrocardiogram recordings in an asymptomatic at-risk population [J ] . Europace , 2020 , 22 ( 12 ): 1781 - 1787 .

汪毅峰 , 李江涛 , 徐峥一 , 等 . 基于电容耦合式电极的非接触式ECG采集方法研究 [J ] . 仪器仪表学报 , 2022 , 43 ( 2 ): 138 - 147 .

WANG Y F , LI J T , XU Z Y , et al . A non-contact ECG measurement method based on capacitance coupling electrodes [J ] . Chinese Journal of Scientific Instrument , 2022 , 43 ( 2 ): 138 - 147 . (in Chinese)

ZHOU X L , DING H X , UNG B , et al . Automatic online detection of atrial fibrillation based on symbolic dynamics and Shannon entropy [J ] . Biomedical Engineering Online , 2014 , 13 ( 1 ): 18 .

ALCARAZ R , ABÁSOLO D , HORNERO R , et al . Optimal parameters study for sample entropy-based atrial fibrillation organization analysis [J ] . Computer Methods and Programs in Biomedicine , 2010 , 99 ( 1 ): 124 - 132 .

PARK J , LEE S , JEON M . Atrial fibrillation detection by heart rate variability in Poincare plot [J ] . Biomedical Engineering Online , 2009 , 8 : 38 .

GARCIA-ISLA G , CORINO V , MAINARDI L . Poincaré plot image and rhythm-specific atlas for atrial bigeminy and atrial fibrillation detection [J ] . IEEE Journal of Biomedical and Health Informatics , 2021 , 25 ( 4 ): 1093 - 1100 .

CZABANSKI R , HOROBA K , WROBEL J , et al . Detection of atrial fibrillation episodes in long-term heart rhythm signals using a support vector machine [J ] . Sensors , 2020 , 20 ( 3 ): 765 .

LADAVICH S , GHORAANI B . Rate-independent detection of atrial fibrillation by statistical modeling of atrial activity [J ] . Biomedical Signal Processing and Control , 2015 , 18 : 274 - 281 .

SBROLLINI A , MARCANTONI I , MORETTINI M , et al . Spectral F-wave index for automatic identification of atrial fibrillation in very short electrocardiograms [J ] . Biomedical Signal Processing and Control , 2022 , 71 : 103210 .

KUMAR M , PACHORI R B , RAJENDRA ACHARYA U . Automated diagnosis of atrial fibrillation ECG signals using entropy features extracted from flexible analytic wavelet transform [J ] . Biocybernetics and Biomedical Engineering , 2018 , 38 ( 3 ): 564 - 573 .

FAUST O , KAREEM M , ALI A L , et al . Automated arrhythmia detection based on RR intervals [J ] . Diagnostics , 2021 , 11 ( 8 ): 1446 .

ANDERSEN R S , PEIMANKAR A , PUTHUSSERYPADY S . A deep learning approach for real-time detection of atrial fibrillation [J ] . Expert Systems with Applications , 2019 , 115 : 465 - 473 .

FANG B , CHEN J X , LIU Y , et al . Dual-channel neural network for atrial fibrillation detection from a single lead ECG wave [J ] . IEEE Journal of Biomedical and Health Informatics , 2023 , 27 ( 5 ): 2296 - 2305 .

BUI T H , HOANG V M , PHAM M T . Automatic varied-length ECG classification using a lightweight DenseNet model [J ] . Biomedical Signal Processing and Control , 2023 , 82 : 104529 .

FAN X M , YAO Q H , CAI Y P , et al . Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings [J ] . IEEE Journal of Biomedical and Health Informatics , 2018 , 22 ( 6 ): 1744 - 1753 .

LI Y J , CHEN M , JIANG X E , et al . An atrial fibrillation detection algorithm based on lightweight design architecture and feature fusion strategy [J ] . Biomedical Signal Processing and Control , 2024 , 91 : 106016 .

CAI W J , CHEN Y D , GUO J , et al . Accurate detection of atrial fibrillation from 12-lead ECG using deep neural network [J ] . Computers in Biology and Medicine , 2020 , 116 : 103378 .

GAO Y B , WANG H , LIU Z H . An end-to-end atrial fibrillation detection by a novel residual-based temporal attention convolutional neural network with exponential nonlinearity loss [J ] . Knowledge-Based Systems , 2021 , 212 : 106589 .

HUANG G , LIU Z , VAN DER MAATEN L , et al . Densely connected convolutional networks [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 4700 - 4708 .

郭一楠 , 邵慧杰 , 巩敦卫 , 等 . 基于希尔伯特黄变换和深度卷积神经网络的房颤检测 [J ] . 电子与信息学报 , 2022 , 44 ( 1 ): 99 - 106 .

GUO Y N , SHAO H J , GONG D W , et al . Atrial fibrillation detection based on Hilbert-Huang transform and deep convolutional neural network [J ] . Journal of Electronics & Information Technology , 2022 , 44 ( 1 ): 99 - 106 . (in Chinese)

中华医学会心血管病学分会 , 中国生物医学工程学会心律分会 . 心房颤动诊断和治疗中国指南 [J ] . 中华心血管病杂志 , 2023 , 51 ( 6 ): 572 - 618 .

CHINESE SOCIETY OF CARDIOLOGY C M A HEART RHYTHM COMMITTEE OF CHINESE SOCIETY OF BIOMEDICAL E . Chinese guidelines on diagnosis and management of atrial fibrillation [J ] . Chinese Journal of Cardiology , 2023 , 51 ( 6 ): 572 - 618 . (in Chinese)

ZOU Y G , YU X Y , LI S Y , et al . A generalizable and robust deep learning method for atrial fibrillation detection from long-term electrocardiogram [J ] . Biomedical Signal Processing and Control , 2024 , 90 : 105797 .

GOLDBERGER A L , AMARAL L A , GLASS L , et al . PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals [J ] . Circulation , 2000 , 101 ( 23 ): 215 - 220 .

MOODY G . A new method for detecting atrial fibrillation using RR intervals [J ] . Proceedings of Computing Cardiology , 1983 , 10 : 227 - 230 .

WANG X , MA C , ZHANG X , et al . Paroxysmal atrial fibrillation events detection from dynamic ecg recordings: The 4th china physiological signal challenge 2021 [J ] . PhysioNet , 2021 , 1 : 1 - 83 .

PETRUTIU S , SAHAKIAN A V , SWIRYN S . Abrupt changes in fibrillatory wave characteristics at the termination of paroxysmal atrial fibrillation in humans [J ] . Europace , 2007 , 9 ( 7 ): 466 - 470 .

KUMAR K S , YAZDANPANAH B , KUMAR P R . Removal of noise from electrocardiogram using digital FIR and IIR filters with various methods [C ] // 2015 International Conference on Communications and Signal Processing (ICCSP) . Piscataway : IEEE , 2015 : 157 - 162 .

HAMILTON P . Open source ECG analysis [C ] // Computers in Cardiology . Piscataway : IEEE , 2002 : 101 - 104 .

ZHANG X Y , LI J Q , CAI Z P , et al . Over-fitting suppression training strategies for deep learning-based atrial fibrillation detection [J ] . Medical & Biological Engineering & Computing , 2021 , 59 ( 1 ): 165 - 173 .

ZHANG X , HE C , LU Y P , et al . Fault diagnosis for small samples based on attention mechanism [J ] . Measurement , 2022 , 187 : 110242 .

LUTHRA A . ECG Made Easy [M ] . New Delhi : Jaypee Brothers Medical Publishers , 2019 : 171 - 178 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于梯度协同与特征融合的加密流量检测

融合大语言模型与跨域图结构的多模态对话情感识别方法

基于镜像数据增强与多尺度特征卷积融合的Transformer调制识别技术

基于空频双域特征融合的高迁移性对抗样本生成方法