Generative Data by β-Variational Autoencoders Help Build Stronger Classifiers: ECG Use Case

被引:1
作者
Nademi, Yousef [1 ]
Kalmady, Sunil V. [1 ,2 ,3 ]
Sun, Weijie [1 ]
Salimi, Amir [1 ]
Hindle, Abram [1 ]
Kaul, Padma [2 ,3 ]
Greiner, Russell [1 ,4 ]
机构
[1] Univ Alberta, Dept Comp Sci, Edmonton, AB, Canada
[2] Univ Alberta, Dept Med, Canadian VIGOUR Ctr, Edmonton, AB, Canada
[3] Univ Alberta, Dept Med, Edmonton, AB, Canada
[4] Alberta Machine Intelligence Inst, Edmonton, AB, Canada
来源
2023 19TH INTERNATIONAL SYMPOSIUM ON MEDICAL INFORMATION PROCESSING AND ANALYSIS, SIPAIM | 2023年
基金
加拿大自然科学与工程研究理事会;
关键词
Electrocardiogram; Machine Learning; Variational Autoencoder; Data Generation;
D O I
10.1109/SIPAIM56729.2023.10373478
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
We explore the challenge of learning models that use electrocardiogram (ECG) data to diagnose various cardiovascular diseases. Here, we explore whether classifiers trained on a dataset of real labeled ECGs, augmented with synthetic ECGs, can perform better than ones trained on unaugmented datasets. We first used a dataset of ECGs, each labelled with one or more of 15 diagnoses, from 244,077 patients to train an unsupervised beta-VAE model, that could generate time series of 12-lead ECG signals for each of the diagnoses. We then used this generative model to generate ECGs with the ST-segment Elevated (STE) abnormality, which we added to the public dataset of ECG abnormalities (n = 6877, over normal (Sinus Rhythm) and 8 different abnormalities) of China Physiological Signal Challenge 2018, and found a learner trained on this extended dataset performed better than one trained on only the original data on the targeted STE label but also enhanced its performance for the classification of 4 other labels.
引用
收藏
页数:7
相关论文
共 21 条
[1]   A survey on ECG analysis [J].
Berkaya, Selcan Kaplan ;
Uysal, Alper Kursat ;
Gunal, Efnan Sora ;
Ergin, Semih ;
Gunal, Serkan ;
Gulmezoglu, M. Bilginer .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2018, 43 :216-235
[2]  
Dahlof Bjorn, 2010, Am J Cardiol, V105, p3A, DOI 10.1016/j.amjcard.2009.10.007
[3]   InceptionTime: Finding AlexNet for time series classification [J].
Fawaz, Hassan Ismail ;
Lucas, Benjamin ;
Forestier, Germain ;
Pelletier, Charlotte ;
Schmidt, Daniel F. ;
Weber, Jonathan ;
Webb, Geoffrey, I ;
Idoumghar, Lhassane ;
Muller, Pierre-Alain ;
Petitjean, Francois .
DATA MINING AND KNOWLEDGE DISCOVERY, 2020, 34 (06) :1936-1962
[4]  
Higgins I., 2016, ICLR POSTER
[5]   Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review [J].
Hong, Shenda ;
Zhou, Yuxi ;
Shang, Junyuan ;
Xiao, Cao ;
Sun, Jimeng .
COMPUTERS IN BIOLOGY AND MEDICINE, 2020, 122
[6]   Global Updates on Cardiovascular Disease Mortality Trends and Attribution of Traditional Risk Factors [J].
Jagannathan, Ram ;
Patel, Shivani A. ;
Ali, Mohammed K. ;
Narayan, K. M. Venkat .
CURRENT DIABETES REPORTS, 2019, 19 (07)
[7]   Unsupervised feature learning for electrocardiogram data using the convolutional variational autoencoder [J].
Jang, Jong-Hwan ;
Kim, Tae Young ;
Lim, Hong-Seok ;
Yoon, Dukyong .
PLOS ONE, 2021, 16 (12)
[8]   An Open Access Database for Evaluating the Algorithms of Electrocardiogram Rhythm and Morphology Abnormality Detection [J].
Liu, Feifei ;
Liu, Chengyu ;
Zhao, Lina ;
Zhang, Xiangyu ;
Wu, Xiaoling ;
Xu, Xiaoyan ;
Liu, Yulin ;
Ma, Caiyun ;
Wei, Shoushui ;
He, Zhiqiang ;
Li, Jianqing ;
Kwee, Eddie Ng Yin .
JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, 2018, 8 (07) :1368-1373
[9]   Deep learning in ECG diagnosis: A review [J].
Liu, Xinwen ;
Wang, Huan ;
Li, Zongjin ;
Qin, Lang .
KNOWLEDGE-BASED SYSTEMS, 2021, 227
[10]   An effective data enhancement method for classification of ECG arrhythmia [J].
Ma, Shuai ;
Cui, Jianfeng ;
Chen, Chin-Ling ;
Chen, Xuhui ;
Ma, Ying .
MEASUREMENT, 2022, 203