TY - GEN
T1 - CONTRASTIVE HEARTBEATS
T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
AU - Wei, Crystal T.
AU - Hsieh, Ming En
AU - Liu, Chien Liang
AU - Tseng, Vincent S.
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - The non-invasive and easily accessible characteristics of electrocardiogram (ECG) attract many studies targeting AI-enabled cardiovascular-related disease screening tools based on ECG. However, the high cost of manual labels makes high-performance deep learning models challenging to obtain. Hence, we propose a new self-supervised representation learning framework, contrastive heartbeats (CT-HB), which learns general and robust electrocardiogram representations for efficient training on various downstream tasks. We employ a novel heartbeat sampling method to define positive and negative pairs of heartbeats for contrastive learning by utilizing the periodic and meaningful patterns of electrocardiogram signals. Using the CT-HB framework, the self-supervised learning model learns personalized heartbeat representations representing the specific cardiology context of a patient. Evaluations on public benchmark datasets and a private large-scale real-world dataset with multiple tasks demonstrate that the learned semantic representations result in better performance on downstream tasks and retain high performance while supervised learning suffers performance degradation with fewer supervised labels in downstream tasks.
AB - The non-invasive and easily accessible characteristics of electrocardiogram (ECG) attract many studies targeting AI-enabled cardiovascular-related disease screening tools based on ECG. However, the high cost of manual labels makes high-performance deep learning models challenging to obtain. Hence, we propose a new self-supervised representation learning framework, contrastive heartbeats (CT-HB), which learns general and robust electrocardiogram representations for efficient training on various downstream tasks. We employ a novel heartbeat sampling method to define positive and negative pairs of heartbeats for contrastive learning by utilizing the periodic and meaningful patterns of electrocardiogram signals. Using the CT-HB framework, the self-supervised learning model learns personalized heartbeat representations representing the specific cardiology context of a patient. Evaluations on public benchmark datasets and a private large-scale real-world dataset with multiple tasks demonstrate that the learned semantic representations result in better performance on downstream tasks and retain high performance while supervised learning suffers performance degradation with fewer supervised labels in downstream tasks.
KW - Contrastive learning
KW - Electrocardiogram
KW - Representation learning
KW - Self-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85131250610&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9746887
DO - 10.1109/ICASSP43922.2022.9746887
M3 - Conference contribution
AN - SCOPUS:85131250610
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1126
EP - 1130
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 23 May 2022 through 27 May 2022
ER -