Efficient Edge-AI Models for Robust ECG Abnormality Detection on Resource-Constrained Hardware
Journal of Cardiovascular Translational Research · 2024-08 · 17 (4) · 879-892
DOI: 10.1007/s12265-024-10504-y ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Journal of Cardiovascular Translational Research, online erschienen am 12.03.2024. Verfasst von Zhaojing Huang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, The University of Sydney, NSW 2008, Sydney, Australia. zhaojing.huang@sydney.edu.au. Hauptthemen laut MEDLINE: Electrocardiography, Predictive Value of Tests, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Sydney.
Abstract (Originalsprache)
This study introduces two models, ConvLSTM2D-liquid time-constant network (CLTC) and ConvLSTM2D-closed-form continuous-time neural network (CCfC), designed for abnormality identification using electrocardiogram (ECG) data. Trained on the Telehealth Network of Minas Gerais (TNMG) subset dataset, both models were evaluated for their performance, generalizability capacity, and resilience. They demonstrated comparable results in terms of F1 scores and AUROC values. The CCfC model achieved slightly higher accuracy, while the CLTC model showed better handling of empty channels. Remarkably, the models were successfully deployed on a resource-constrained microcontroller, proving their suitability for edge device applications. Generalization capabilities were confirmed through the evaluation on the China Physiological Signal Challenge 2018 (CPSC) dataset. The models’ efficient resource utilization, occupying 70.6% of memory and 9.4% of flash memory, makes them promising candidates for real-world healthcare applications. Overall, this research advances abnormality identification in ECG data, contributing to the progress of AI in healthcare. Graphical Abstract
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Biomedical Engineering, The University of Sydney, NSW 2008, Sydney, Australia. zhaojing.huang@sydney.edu.au.
- School of Biomedical Engineering, The University of Sydney, NSW 2008, Sydney, Australia.
- Department of Neurology, Royal Prince Alfred Hospital, and Central Clinical School, The University of Sydney, NSW 2006, Sydney, Australia.
ORCID-Profile: Zhaojing Huang
Förderung
- University of Sydney
Zitieren
APA
Huang, Z., Herbozo Contreras, L. F., Leung, W. H., Yu, L., Truong, N. D., Nikpour, A., & Kavehei, O. (2024). Efficient Edge-AI Models for Robust ECG Abnormality Detection on Resource-Constrained Hardware. Journal of Cardiovascular Translational Research, 17(4), 879-892. https://doi.org/10.1007/s12265-024-10504-y
Vancouver
Huang Z, Herbozo Contreras LF, Leung WH, Yu L, Truong ND, Nikpour A, et al. Efficient Edge-AI Models for Robust ECG Abnormality Detection on Resource-Constrained Hardware. Journal of Cardiovascular Translational Research. 2024;17(4):879-892. doi:10.1007/s12265-024-10504-y
BibTeX
@article{Huang2024,
author = {Huang, Zhaojing and Herbozo Contreras, Luis Fernando and Leung, Wing Hang and Yu, Leping and Truong, Nhan Duy and Nikpour, Armin and Kavehei, Omid},
title = {Efficient Edge-AI Models for Robust ECG Abnormality Detection on Resource-Constrained Hardware},
journal = {Journal of Cardiovascular Translational Research},
year = {2024},
volume = {17},
number = {4},
pages = {879--892},
doi = {10.1007/s12265-024-10504-y}
}
EUVIMED