Federated Learning With Deep Neural Networks: A Privacy-Preserving Approach to Enhanced ECG Classification

被引:3
作者
Weimann, Kuba [1 ]
Conrad, Tim O. F. [1 ]
机构
[1] Zuse Inst Berlin, D-14195 Berlin, Germany
关键词
Federated learning; Electrocardiography; Training; Data models; Servers; Computational modeling; Residual neural networks; Deep learning; electrocardiogram (ECG) classification; federated learning; residual neural networks; transfer learning;
D O I
10.1109/JBHI.2024.3427787
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In response to increasing data privacy regulations, this work examines the use of federated learning for deep residual networks to diagnose cardiac abnormalities from electrocardiogram (ECG) data. This approach allows medical institutions to collaborate without exchanging raw patient data. We utilize the publicly available data from the PhysioNet/Computing in Cardiology Challenge 2021, featuring diverse ECG databases, to compare the classification performance of three federated learning methods against both central training with data sharing and isolated training scenarios. We show that federated learning outperforms ECG classifiers trained in isolation. In particular, our findings demonstrate that a globally trained model fine-tuned to specific local datasets surpasses non-collaborative approaches. This shows that models trained in federation learn general features that can be tailored to specific tasks. Furthermore, federated learning almost matches the performance of central training with data sharing on out-of-distribution data from non-participating institutions. These results highlight the ability of federated learning in developing models that generalize well across diverse patient data, without the need to share data among institutions, thus addressing data privacy concerns.
引用
收藏
页码:6931 / 6943
页数:13
相关论文
共 59 条
[51]   PTB-XL, a large publicly available electrocardiography dataset [J].
Wagner, Patrick ;
Strodthoff, Nils ;
Bousseljot, Ralf-Dieter ;
Kreiseler, Dieter ;
Lunze, Fatima I. ;
Samek, Wojciech ;
Schaeffter, Tobias .
SCIENTIFIC DATA, 2020, 7 (01)
[52]  
Wen Yuxin, 2022, P MACHINE LEARNING R
[53]   Multi-Label Cardiac Abnormality Classification from Electrocardiogram Using Deep Convolutional Neural Networks [J].
Wickramasinghe, Nima L. ;
Athif, Mohamed .
2021 COMPUTING IN CARDIOLOGY (CINC), 2021,
[54]   Group Normalization [J].
Wu, Yuxin ;
He, Kaiming .
COMPUTER VISION - ECCV 2018, PT XIII, 2018, 11217 :3-19
[55]   See through Gradients: Image Batch Recovery via GradInversion [J].
Yin, Hongxu ;
Mallya, Arun ;
Vahdat, Arash ;
Alvarez, Jose M. ;
Kautz, Jan ;
Molchanov, Pavlo .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :16332-16341
[56]  
Zaheer M, 2018, ADV NEUR IN, V31
[57]   Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study [J].
Zech, John R. ;
Badgeley, Marcus A. ;
Liu, Manway ;
Costa, Anthony B. ;
Titano, Joseph J. ;
Oermann, Eric Karl .
PLOS MEDICINE, 2018, 15 (11)
[58]   Scaling Vision Transformers [J].
Zhai, Xiaohua ;
Kolesnikov, Alexander ;
Houlsby, Neil ;
Beyer, Lucas .
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, :12094-12103
[59]   Optimal Multi-Stage Arrhythmia Classification Approach [J].
Zheng, Jianwei ;
Chu, Huimin ;
Struppa, Daniele ;
Zhang, Jianming ;
Yacoub, Sir Magdi ;
El-Askary, Hesham ;
Chang, Anthony ;
Ehwerhemuepha, Louis ;
Abudayyeh, Islam ;
Barrett, Alexander ;
Fu, Guohua ;
Yao, Hai ;
Li, Dongbo ;
Guo, Hangyuan ;
Rakovski, Cyril .
SCIENTIFIC REPORTS, 2020, 10 (01)