EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detection of atrial fibrillation using a nonlinear Lorenz Scattergram and deep learning in primary care

Yi Yao, Yu Jia, Miaomiao Wu, Songzhu Wang, Haiqi Song, Xiang Fang, Xiaoyang Liao, Dongze Li, Qian Zhao

BMC Primary Care · 2024

DOI: 10.1186/s12875-024-02407-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BMC Primary Care, 2024. Verfasst von Yi Yao und 8 weiteren Autor:innen. Beteiligte Einrichtung: General Practice Ward/International Medical Center Ward, General Practice Medical Center, West China Hospital, Sichuan University, Chengdu, China. Hauptthemen laut MEDLINE: Deep Learning, Atrial Fibrillation, Primary Health Care. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Province Science and Technology Support Program, Sichuan Provincial Health Commission, Sichuan University West China Nursing Discipline Development Special Fund Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Atrial fibrillation (AF) is highly correlated with heart failure, stroke and death. Screening increases AF detection and facilitates the early adoption of comprehensive intervention. Long-term wearable devices have become increasingly popular for AF screening in primary care. However, interpreting data obtained by long-term wearable ECG devices is a problem in primary care. To diagnose the disease quickly and accurately, we aimed to build AF episode detection model based on a nonlinear Lorenz scattergram (LS) and deep learning.

Methods

The MIT-BIH Normal Sinus Rhythm Database, MIT-BIH Arrhythmia Database and the Long-Term AF Database were extracted to construct the MIT-BIH Ambulatory Electrocardiograph (MIT-BIH AE) dataset. We converted the long-term ECG into a two-dimensional LSs. The LSs from MIT-BIH AE dataset was randomly divided into training and internal validation sets in a 9:1 ratio, which was used to develop and internally validated model. We built a MOBILE-SCREEN-AF (MS-AF) dataset from a single-lead wearable ECG device in primary care for external validation. Performance was quantified using a confusion matrix and standard classification metrics.

Results

During the evaluation of model performance based on the LS, the sensitivity, specificity and accuracy of the model in diagnosing AF were 0.992, 0.973, and 0.983 in the internal validation set respectively. In the external validation set, these metrics were 0.989, 0.956, and 0.967, respectively. Furthermore, when evaluating the model’s performance based on ECG records in the MS-AF dataset, the sensitivity, specificity and accuracy of model diagnosis paroxysmal AF were 1.000, 0.870 and 0.876 respectively, and 0.927, 1.000 and 0.973 for the persistent AF.

Conclusions

The model based on the nonlinear LS and deep learning has high accuracy, making it promising for AF screening in primary care. It has potential for generalization and practical application.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAtrial FibrillationPrimary Health CareHumansElectrocardiography, AmbulatoryWearable Electronic DevicesElectrocardiographyMaleSensitivity and SpecificityFemale

Stichwörter der Autor:innen

Atrial fibrillationComputer-assisted diagnosis modelConvolutional neural networkLorenz scattergramPrimary care

Autor:innen und Institutionen

  • General Practice Ward/International Medical Center Ward, General Practice Medical Center, West China Hospital, Sichuan University, Chengdu, China.
  • Teaching&Research Section, General Practice Medical Center, West China Hospital, Sichuan University, Chengdu, China.
  • General Practice Medical Center and General Practice Research Institute, West China Hospital, Sichuan University, Chengdu, China.
  • Department of Emergency Medicine and Laboratory of Emergency Medicine, West China Hospital, Sichuan University, Chengdu, China. lidongze@wchscu.cn.
  • General Practice Ward/International Medical Center Ward, General Practice Medical Center, West China Hospital, Sichuan University, Chengdu, China. 27355151@qq.com.
  • Teaching&Research Section, General Practice Medical Center, West China Hospital, Sichuan University, Chengdu, China. 27355151@qq.com.

Förderung

  • Sichuan Province Science and Technology Support Program
  • Sichuan Provincial Health Commission
  • Sichuan University West China Nursing Discipline Development Special Fund Project

Zitieren

APA

Yao, Y., Jia, Y., Wu, M., Wang, S., Song, H., Fang, X., Liao, X., Li, D., & Zhao, Q. (2024). Detection of atrial fibrillation using a nonlinear Lorenz Scattergram and deep learning in primary care. BMC Primary Care. https://doi.org/10.1186/s12875-024-02407-3

Vancouver

Yao Y, Jia Y, Wu M, Wang S, Song H, Fang X, et al. Detection of atrial fibrillation using a nonlinear Lorenz Scattergram and deep learning in primary care. BMC Primary Care. 2024. doi:10.1186/s12875-024-02407-3

BibTeX
@article{Yao2024,
  author = {Yao, Yi and Jia, Yu and Wu, Miaomiao and Wang, Songzhu and Song, Haiqi and Fang, Xiang and Liao, Xiaoyang and Li, Dongze and Zhao, Qian},
  title = {Detection of atrial fibrillation using a nonlinear Lorenz Scattergram and deep learning in primary care},
  journal = {BMC Primary Care},
  year = {2024},
  doi = {10.1186/s12875-024-02407-3}
}
Kostenlos starten →