AI-enhanced diagnosis of atrial arrhythmia using 3D-printed origami ECG sensors
Biosensors and Bioelectronics · 2026
DOI: 10.1016/j.bios.2025.118069 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors and Bioelectronics, 2026. Verfasst von Yiting Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronic Systems Engineering, Simon Fraser University, Surrey, V3T 0A3, Canada. Hauptthemen laut MEDLINE: Electrocardiography, Biosensing Techniques, Arrhythmias, Cardiac. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Traditional Electrocardiogram (ECG) sensors using silver/silver chloride (Ag/AgCl) electrodes suffer from skin irritation, short shelf life, single-use limitation, and environmental waste. Here, we introduce a sustainable 3D-printed origami-structured ECG sensor featuring dry attachment, accurate measurement, reusability, and AI-powered diagnosis. The origami design combines mechanical stretchability, robustness, and self-adhesive, while the patterned carbon-based conductive ink provides high electrical conductivity (5681 ± 122.5 S/m), flexibility (bending to 2.5 mm radius), and biocompatibility, altogether offering a sustainable alternative to Ag/AgCl electrodes. The resulting sensor delivers accurate ECG signals comparable to commercial Ag/AgCl electrodes, in addition to an AI-enabled swift classification system that combines continuous wavelet transform (CWT) and a customized convolutional neural network (CNN) for real-time pre-diagnosis of one sinus rhythm and ten arrhythmias types from ECG scalogram images. This system monitors continuously for up to 34 h, promoting early detection of transient cardiac conditions and personalized health monitoring. This advancement establishes a new standard for AI-enhanced, eco-friendly ECG sensors, with significant potential for applications in remote healthcare, emergency diagnostics, and real-time cardiac monitoring.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Mechatronic Systems Engineering, Simon Fraser University, Surrey, V3T 0A3, Canada.
- School of Mechatronic Systems Engineering, Simon Fraser University, Surrey, V3T 0A3, Canada. Electronic address: woosook@sfu.ca.
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Chen, Y., Non, J., Vozovik, Z., & Kim, W. S. (2026). AI-enhanced diagnosis of atrial arrhythmia using 3D-printed origami ECG sensors. Biosensors and Bioelectronics. https://doi.org/10.1016/j.bios.2025.118069
Vancouver
Chen Y, Non J, Vozovik Z, Kim WS. AI-enhanced diagnosis of atrial arrhythmia using 3D-printed origami ECG sensors. Biosensors and Bioelectronics. 2026. doi:10.1016/j.bios.2025.118069
BibTeX
@article{Chen2026,
author = {Chen, Yiting and Non, Jake and Vozovik, Zakhar and Kim, Woo Soo},
title = {AI-enhanced diagnosis of atrial arrhythmia using 3D-printed origami ECG sensors},
journal = {Biosensors and Bioelectronics},
year = {2026},
doi = {10.1016/j.bios.2025.118069}
}
EUVIMED