TY - JOUR
T1 - Enhancing ECG-based heart age
T2 - impact of acquisition parameters and generalization strategies for varying signal morphologies and corruptions
AU - Ansari, Mohammed Yusuf
AU - Qaraqe, Marwa
AU - Righetti, Raffaella
AU - Serpedin, Erchin
AU - Qaraqe, Khalid
N1 - © 2024 Ansari, Qaraqe, Righetti, Serpedin and Qaraqe.
PY - 2024
Y1 - 2024
N2 - Electrocardiogram (ECG) is a non-invasive approach to capture the overall electrical activity produced by the contraction and relaxation of the cardiac muscles. It has been established in the literature that the difference between ECG-derived age and chronological age represents a general measure of cardiovascular health. Elevated ECG-derived age strongly correlates with cardiovascular conditions (e.g., atherosclerotic cardiovascular disease). However, the neural networks for ECG age estimation are yet to be thoroughly evaluated from the perspective of ECG acquisition parameters. Additionally, deep learning systems for ECG analysis encounter challenges in generalizing across diverse ECG morphologies in various ethnic groups and are susceptible to errors with signals that exhibit random or systematic distortions To address these challenges, we perform a comprehensive empirical study to determine the threshold for the sampling rate and duration of ECG signals while considering their impact on the computational cost of the neural networks. To tackle the concern of ECG waveform variability in different populations, we evaluate the feasibility of utilizing pre-trained and fine-tuned networks to estimate ECG age in different ethnic groups. Additionally, we empirically demonstrate that finetuning is an environmentally sustainable way to train neural networks, and it significantly decreases the ECG instances required (by more than
100
×
) for attaining performance similar to the networks trained from random weight initialization on a complete dataset. Finally, we systematically evaluate augmentation schemes for ECG signals in the context of age estimation and introduce a random cropping scheme that provides best-in-class performance while using shorter-duration ECG signals. The results also show that random cropping enables the networks to perform well with systematic and random ECG signal corruptions.
AB - Electrocardiogram (ECG) is a non-invasive approach to capture the overall electrical activity produced by the contraction and relaxation of the cardiac muscles. It has been established in the literature that the difference between ECG-derived age and chronological age represents a general measure of cardiovascular health. Elevated ECG-derived age strongly correlates with cardiovascular conditions (e.g., atherosclerotic cardiovascular disease). However, the neural networks for ECG age estimation are yet to be thoroughly evaluated from the perspective of ECG acquisition parameters. Additionally, deep learning systems for ECG analysis encounter challenges in generalizing across diverse ECG morphologies in various ethnic groups and are susceptible to errors with signals that exhibit random or systematic distortions To address these challenges, we perform a comprehensive empirical study to determine the threshold for the sampling rate and duration of ECG signals while considering their impact on the computational cost of the neural networks. To tackle the concern of ECG waveform variability in different populations, we evaluate the feasibility of utilizing pre-trained and fine-tuned networks to estimate ECG age in different ethnic groups. Additionally, we empirically demonstrate that finetuning is an environmentally sustainable way to train neural networks, and it significantly decreases the ECG instances required (by more than
100
×
) for attaining performance similar to the networks trained from random weight initialization on a complete dataset. Finally, we systematically evaluate augmentation schemes for ECG signals in the context of age estimation and introduce a random cropping scheme that provides best-in-class performance while using shorter-duration ECG signals. The results also show that random cropping enables the networks to perform well with systematic and random ECG signal corruptions.
KW - ECG acquisition
KW - ECG age estimation
KW - ECG distortion
KW - ECG sampling duration
KW - ECG sampling rate
KW - ECG waveform variability
KW - deep learning
KW - neural network
UR - http://www.scopus.com/inward/record.url?scp=85198707630&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85198707630&partnerID=8YFLogxK
U2 - 10.3389/fcvm.2024.1424585
DO - 10.3389/fcvm.2024.1424585
M3 - Article
C2 - 39027006
AN - SCOPUS:85198707630
SN - 2297-055X
VL - 11
SP - 1424585
JO - Frontiers in cardiovascular medicine
JF - Frontiers in cardiovascular medicine
M1 - 1424585
ER -