Practical intelligent diagnostic algorithm for wearable 12-lead ECG via self-supervised learning on large-scale dataset

Jiewei Lai, Huixin Tan, Jinliang Wang, Lei Ji, Jun Guo, Baoshi Han, Yajun Shi, Qianjin Feng () and Wei Yang ()
Additional contact information
Jiewei Lai: Southern Medical University
Huixin Tan: Southern Medical University
Jinliang Wang: CardioCloud Medical Technology (Beijing) Co., Ltd.
Lei Ji: Chinese PLA General Hospital
Jun Guo: Chinese PLA General Hospital
Baoshi Han: Chinese PLA General Hospital
Yajun Shi: Chinese PLA General Hospital
Qianjin Feng: Southern Medical University
Wei Yang: Southern Medical University

Nature Communications, 2023, vol. 14, issue 1, 1-13

Abstract: Abstract Cardiovascular disease is a major global public health problem, and intelligent diagnostic approaches play an increasingly important role in the analysis of electrocardiograms (ECGs). Convenient wearable ECG devices enable the detection of transient arrhythmias and improve patient health by making it possible to seek intervention during continuous monitoring. We collected 658,486 wearable 12-lead ECGs, among which 164,538 were annotated, and the remaining 493,948 were without diagnostic. We present four data augmentation operations and a self-supervised learning classification framework that can recognize 60 ECG diagnostic terms. Our model achieves an average area under the receiver-operating characteristic curve (AUROC) and average F1 score on the offline test of 0.975 and 0.575. The average sensitivity, specificity and F1-score during the 2-month online test are 0.736, 0.954 and 0.468, respectively. This approach offers real-time intelligent diagnosis, and detects abnormal segments in long-term ECG monitoring in the clinical setting for further diagnosis by cardiologists.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-023-39472-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-39472-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-39472-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().