Multi-center atrial fibrillation electrocardiogram (ECG) classification using Fourier space convolutional neural networks (FD-CNN) and transfer learning.

Autor: Vasconcelos L; Department of Radiology, Mayo Clinic, Rochester, MN, USA. Electronic address: vasconcelos.luiz@mayo.edu., Martinez BP; Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA., Kent M; Division of Cardiology, Henry Ford Hospital, Detroit, MI, USA., Ansari S; Department of Emergency Medicine, University of Michigan, Ann Arbor, MI, USA., Ghanbari H; Cardiovascular Disease, Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA., Nenadic I; Department of Radiology, Mayo Clinic, Rochester, MN, USA; Duke Cardiology, Duke University Medical Center, Durham, NC, USA.
Jazyk: angličtina
Zdroj: Journal of electrocardiology [J Electrocardiol] 2023 Nov-Dec; Vol. 81, pp. 201-206. Date of Electronic Publication: 2023 Sep 25.
DOI: 10.1016/j.jelectrocard.2023.09.010
Abstrakt: There has been a proliferation of machine learning (ML) electrocardiogram (ECG) classification algorithms reaching >85% accuracy for various cardiac pathologies. Despite the high accuracy at individual institutions, challenges remain when it comes to multi-center deployment. Transfer learning (TL) is a technique in which a model trained for a specific task is repurposed for another related task, in this case ECG ML model trained at one institution is fine-tuned to be utilized to classify ECGs at another institution. Models trained at one institution, however, might not be generalizable for accurate classification when deployed broadly due to differences in type, time, and sampling rate of traditional ECG acquisition. In this study, we evaluate the performance of time domain (TD) and frequency domain (FD) convolutional neural network (CNN) classification models in an inter-institutional scenario leveraging three different publicly available datasets. The larger PTB-XL ECG dataset was used to initially train TD and FD CNN models for atrial fibrillation (AFIB) classification. The models were then tested on two different data sets, Lobachevsky University Electrocardiography Database (LUDB) and Korea University Medical Center database (KURIAS). The FD model was able to retain most of its performance (>0.81 F1-score), whereas TD was highly affected (<0.53 F1-score) by the dataset variations, even with TL applied. The FD CNN showed superior robustness to cross-institutional variability and has potential for widespread application with no compromise to ECG classification performance.
(Copyright © 2023 Elsevier Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: