EUVIMEDScopri EUVIMED
Crossref

Deep learning‐based regional ECG diagnosis platform

Fang Li, Ping Wang, Xiao Wang Li iD

Pacing and Clinical Electrophysiology · 2024

DOI: 10.1111/pace.14891 ↗

At a glance

Journal article in Pacing and Clinical Electrophysiology, 2024. Written by Fang Li and 2 co-authors. Institution: Department of Cardiology, The First Affiliated Hospital of Huzhou University, Huzhou, Zhejiang Province, China. Major MEDLINE topics: Deep Learning, Ventricular Premature Complexes, Physicians. Cited 3 times so far (Crossref); 32 references. Funded by: the Medical and Health Science and Technology Project of Zhejiang Province, the Public Welfare Technology Application Research Project of Huzhou Science and Technology Bureau.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Objective

To enable the intelligent diagnosis of a variety of common Electrocardiogram (ECG), we investigate the deep learning‐based ECG diagnosis system.

Methods

From January 2015 to December 2019, four consecutive years of 100,120 conventional 12‐lead ECG data were collected in our hospital. Utilizing this dataset, we constructed a deep learning model designed to intelligently diagnose prevalent ECG anomalies by employing a multi‐task learning framework. The system performance was evaluated using various metrics, including sensitivity, specificity, negative predictive value, positive predictive value, and so forth. Additionally, we employed an ECG intelligent diagnostic platform for clinical application to undertake real‐time online analysis of 2500 conventional 12‐lead ECG samples in June 2020, aiming to validate our model. At this stage, we compared the performance of our model against the traditional manual identification method.

Results

The efficacy of the ECG intelligent diagnostic model was notably high for common and straightforward ECG patterns, such as sinus rhythm (F1 = 98.01%), sinus tachycardia (F1 = 96.26%), sinus bradycardia (F1 = 94.88%), and a normal electrocardiogram (F1 = 91.71%), as well as for Premature Ventricular Contractions (F1 = 91.62%). Nevertheless, when diagnosing rarer and more intricate ECG anomalies, the system requires an increased number of samples to refine the deep learning models. During the validation stage, our model exhibited better efficiency in terms of accuracy, labor time and labor cost when compared to the manual identification approach.

Conclusions

Our deep learning‐driven intelligent ECG diagnostic model clearly demonstrates significant clinical utility. The integrated artificial intelligence diagnosis system not only has the potential to augment physicians in their diagnostic processes but also offers a viable avenue to reduce associated labor costs.

Subjects

MeSH terms (MEDLINE)

Deep LearningVentricular Premature ComplexesPhysiciansHumansArtificial IntelligenceElectrocardiography

Author keywords

ECG diagnosisdeep learningdiagnostic systemelectrocardiogramthe neural network

Authors and institutions

  • Department of Cardiology, The First Affiliated Hospital of Huzhou University, Huzhou, Zhejiang Province, China.

ORCID profiles: Xiao Wang Li

Funding

  • the Medical and Health Science and Technology Project of Zhejiang Province
  • the Public Welfare Technology Application Research Project of Huzhou Science and Technology Bureau

Cite

APA

Li, F., Wang, P., & Wang Li, X. (2024). Deep learning‐based regional ECG diagnosis platform. Pacing and Clinical Electrophysiology. https://doi.org/10.1111/pace.14891

Vancouver

Li F, Wang P, Wang Li X. Deep learning‐based regional ECG diagnosis platform. Pacing and Clinical Electrophysiology. 2024. doi:10.1111/pace.14891

BibTeX
@article{Li2024,
  author = {Li, Fang and Wang, Ping and Wang Li, Xiao},
  title = {Deep learning‐based regional ECG diagnosis platform},
  journal = {Pacing and Clinical Electrophysiology},
  year = {2024},
  doi = {10.1111/pace.14891}
}
Start for free →