More Web Proxy on the site http://driver.im/

research-article

Federated Learning and Differential Privacy Techniques on Multi-hospital Population-scale Electrocardiogram Data

Authors:

Vikhyat Agrawal,

Sunil Vasu Kalmady,

Venkataseetharam Malipeddi Manoj,

Manisimha Varma Manthena,

MD Saiful Islam,

Russell GreinerAuthors Info & Claims

ICMHI '24: Proceedings of the 2024 8th International Conference on Medical and Health Informatics

Pages 143 - 152

https://doi.org/10.1145/3673971.3673990

Published: 09 September 2024 Publication History

Abstract

This research paper explores ways to apply Federated Learning (FL) and Differential Privacy (DP) techniques to population-scale Electrocardiogram (ECG) data. The study learns a multi-label ECG classification model using FL and DP based on 1,565,849 ECG tracings from 7 hospitals in Alberta, Canada. The FL approach allowed collaborative model training without sharing raw data between hospitals, while building robust ECG classification models for diagnosing various cardiac conditions. These accurate ECG classification models can facilitate the diagnoses while preserving patient confidentiality using FL and DP techniques. Our results show that the performance achieved using our implementation of the FL approach is comparable to that of the pooled approach, where the model is trained over the aggregating data from all hospitals. Furthermore, our findings suggest that hospitals with limited ECGs for training can benefit from adopting the FL model compared to single-site training. In addition, this study showcases the trade-off between model performance and data privacy by employing DP during model training. Our code is available at https://github.com/vikhyatt/Hospital-FL-DP.

References

[1]

Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. 2016. Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (Vienna Austria). ACM, New York, NY, USA.

Digital Library

[2]

Abien Fred Agarap. 2018. Deep Learning using Rectified Linear Units (ReLU). (2018).

[3]

Joseph C Ahn, Zachi I Attia, Puru Rattan, Aidan F Mullan, Seth Buryska, Alina M Allen, Patrick S Kamath, Paul A Friedman, Vijay H Shah, Peter A Noseworthy, and Douglas A Simonetto. 2022. Development of the AI-cirrhosis-ECG score: An electrocardiogram-based deep learning model in cirrhosis. Am. J. Gastroenterol. 117, 3 (March 2022), 424–432.

[4]

American Health Association. 2023. Privacy Policy. Retrieved June 22, 2023 from https://www.aha.org/2022-07-14-privacy-policy

[5]

American Medical Association. 2016. Code of Medical ethics. Retrieved 2016 from https://code-medical-ethics.ama-assn.org/

[6]

Martin Baumgartner, Sai Pavan Kumar Veeranki, Dieter Hayn, and Günter Schreier. 2023. Introduction and comparison of novel decentral learning schemes with multiple data pools for privacy-preserving ECG classification. J. Healthc. Inform. Res. 7, 3 (Sept. 2023), 291–312.

[7]

Andrew P Bradley. 1997. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 30, 7 (July 1997), 1145–1159.

Digital Library

[8]

Susana Brás, Jacqueline H T Ferreira, Sandra C Soares, and Armando J Pinho. 2018. Biometric and emotion identification: An ECG compression based method. Front. Psychol. 9 (April 2018).

[9]

Bakary Dolo, Faiza Loukil, and Khouloud Boukadi. 2022. Early Detection of Diabetes Mellitus Using Differentially Private SGD in Federated Learning. In 2022 IEEE/ACS 19th International Conference on Computer Systems and Applications (AICCSA). 1–8. https://doi.org/10.1109/AICCSA56895.2022.10017908

[10]

Cynthia Dwork. 2006. Differential Privacy. In Automata, Languages and Programming. Springer Berlin Heidelberg, Berlin, Heidelberg, 1–12.

Digital Library

[11]

Centers for Disease Control and Prevention. 1996. Health Insurance Portability and Accountability Act of 1996. Retrieved 1996 from https://www.cdc.gov/phlp/ publications/topic/hipaa.html

[12]

Shinichi Goto, Divyarajsinhji Solanki, Jenine E John, Ryuichiro Yagi, Max Homilius, Genki Ichihara, Yoshinori Katsumata, Hanna K Gaggin, Yuji Itabashi, Calum A MacRae, and Rahul C Deo. 2022. Multinational federated learning approach to train ECG and echocardiogram models for hypertrophic cardiomyopathy detection. Circulation 146, 10 (Sept. 2022), 755–769.

[13]

Mannsoo Hong, Seok-Kyu Kang, and Jee-Hyong Lee. 2022. Weighted averaging federated learning based on example forgetting events in label imbalanced non-IID. Appl. Sci. (Basel) 12, 12 (June 2022), 5806.

[14]

Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating deep network training by reducing internal covariate shift. (2015).

Digital Library

[15]

Zhanglong Ji, Zachary C Lipton, and Charles Elkan. 2014. Differential privacy and machine learning: A survey and review. (2014).

[16]

Madhura Joshi, Ankit Pal, and Malaikannan Sankarasubbu. 2022. Federated learning for healthcare domain - pipeline, applications and challenges. ACM Trans. Comput. Healthc. 3, 4 (Oct. 2022), 1–36.

Digital Library

[17]

Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. (2014).

[18]

Daoqin Lin, Yuchun Guo, Huan Sun, and Yishuai Chen. 2022. FedCluster: A Federated Learning Framework for Cross-Device Private ECG Classification. In IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). 1–6. https://doi.org/10.1109/INFOCOMWKSHPS54753. 2022.9797945

[19]

Xinwen Liu, Huan Wang, Zongjin Li, and Lang Qin. 2021. Deep learning in ECG diagnosis: A review. Knowl. Based Syst. 227, 107187 (Sept. 2021), 107187.

Digital Library

[20]

Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol.54), Aarti Singh and Jerry Zhu (Eds.). PMLR,1273–1282. https://proceedings. mlr.press/v54/mcmahan17a.html

[21]

Pietro Melzi, Ruben Tolosana, and Ruben Vera-Rodriguez. 2023. ECG biometric recognition: Review, system proposal, and benchmark evaluation. IEEE Access 11 (2023), 15555–15566.

[22]

Maytham N Meqdad, Abdullah Hasan Hussein, Saif O Husain, and Alyaa Mohammed Jawad. 2023. Classification of electrocardiogram signals based on federated learning and a gaussian multivariate aggregation module. Indones. J. Electr. Eng. Comput. Sci. 30, 2 (May 2023), 936.

[23]

Ilya Mironov. 2017. Rényi Differential Privacy. In 2017 IEEE 30th Computer Security Foundations Symposium (CSF). 263–275. https://doi.org/10.1109/CSF.2017.11

[24]

G B Moody and R G Mark. 2001. The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 20, 3 (May 2001), 45–50.

[25]

PhysioNet. 2020. George B. Moody PhysioNet Challenge. Retrieved January 26, 2022 from https://moody-challenge.physionet.org/2020/

[26]

Natalia Ponomareva, Hussein Hazimeh, Alex Kurakin, Zheng Xu, Carson Denison, H Brendan McMahan, Sergei Vassilvitskii, Steve Chien, and Abhradeep Guha Thakurta. 2023. How to DP-fy ML: A practical guide to machine Learning with differential privacy. J. Artif. Intell. Res. 77 (July 2023), 1113–1201.

[27]

Nikita Rafie, Anthony H Kashou, and Peter A Noseworthy. 2021. ECG interpretation: Clinical relevance, challenges, and advances. Hearts (Basel) 2, 4 (Nov. 2021), 505–513.

[28]

Ali Raza, Kim Phuc Tran, Ludovic Koehl, and Shujun Li. 2022. Designing ECG monitoring healthcare system with federated transfer learning and explainable AI. Knowl. Based Syst. 236, 107763 (Jan. 2022), 107763.

Digital Library

[29]

Mohamed Adel Serhani, Hadeel T El Kassabi, Heba Ismail, and Alramzana Nujum Navaz. 2020. ECG monitoring systems: Review, architecture, processes, and key challenges. Sensors (Basel) 20, 6 (March 2020), 1796.

[30]

Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2017. Membership Inference Attacks Against Machine Learning Models. In 2017 IEEE Symposium on Security and Privacy (SP).3–18. https://doi.org/10.1109/SP.2017.41

[31]

Weijie Sun, Sunil Vasu Kalmady, Amir Salimi, Nariman Sepehrvand, Eric Ly, Abram Hindle, Russell Greiner, and Padma Kaul. 2022. ECG for high-throughput screening of multiple diseases: Proof-of-concept using multi-diagnosis deep learning from population-based datasets. (2022).

[32]

Weijie Sun, Sunil Vasu Kalmady, Nariman Sepehrvand, Amir Salimi, Yousef Nademi, Kevin Bainey, Justin A Ezekowitz, Russell Greiner, Abram Hindle, Finlay A McAlister, Roopinder K Sandhu, and Padma Kaul. 2023. Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms. NPJ Digit. Med. 6, 1 (Feb. 2023), 21.

[33]

Renjie Tang, Junzhou Luo, Junbo Qian, and Jiahui Jin.2021. Personalized federated learning for ECG classification based on feature alignment. Secur. Commun. Netw. 2021 (Nov. 2021), 1–9.

[34]

Irene Tenison, Sai Aravind Sreeramadas,Vaikkunth Mugunthan, Edouard Oyallon, Irina Rish, and Eugene Belilovsky. 2022. Gradient masked averaging for federated learning. (2022).

[35]

Liesbet van Zoonen. 2016. Privacy concerns in smart cities. Gov. Inf. Q. 33, 3 (July 2016), 472–480.

[36]

Peng Xiao, Samuel Cheng, Vladimir Stankovic,and Dejan Vukobratovic.2020. Averaging is probably not the optimum way of aggregating parameters in federated learning. Entropy (Basel) 22, 3 (March 2020), 314.

[37]

Xuefei Yin, Yanming Zhu, and Jiankun Hu. 2022. A comprehensive survey of privacy-preserving federated learning. ACM Comput. Surv. 54, 6 (July 2022), 1–36.

Digital Library

[38]

Zuobin Ying, Guoyang Zhang, Zijie Pan, Chiawei Chu, and Ximeng Liu. 2023. FedECG: A federated semi-supervised learning framework for electrocardiogram abnormalities prediction. J. King Saud Univ. - Comput. Inf. Sci. 35, 6 (June 2023), 101568.

[39]

Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, Graham Cormode, and Ilya Mironov. 2021. Opacus: User-Friendly Differential Privacy Library in PyTorch. arXiv preprint arXiv:2109.12298 (2021).

Cited By

Di Stefano VD’Angelo MMonaco FVignapiano AMartiadis VBarone EFornaro MSteardo LSolmi MManchia MSteardo L(2024)Decoding Schizophrenia: How AI-Enhanced fMRI Unlocks New Pathways for Precision PsychiatryBrain Sciences10.3390/brainsci1412119614:12(1196)Online publication date: 27-Nov-2024
https://doi.org/10.3390/brainsci14121196
Das AKrishnadas AKrishnan VFarida ASarath G(2024)An Investigation of Federated Learning Strategies for Disease Diagnosis2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)10.1109/ICCCNT61001.2024.10725147(1-8)Online publication date: 24-Jun-2024
https://doi.org/10.1109/ICCCNT61001.2024.10725147

Index Terms

Federated Learning and Differential Privacy Techniques on Multi-hospital Population-scale Electrocardiogram Data

Recommendations

Detection of cardiac abnormalities in ECG signal using time-based signal processing algorithm

Electrocardiograms are bioelectrical signals that provide information regarding the normal and abnormal physiology of the heart. Early detection of cardiac irregularities in cardiac patients prevents strokes and sudden deaths. The effective functioning ...
Automatic diagnosis of arrhythmia with electrocardiogram using multiple instance learning: From rhythm annotation to heartbeat prediction
Abstract
The electrocardiogram (ECG) is a commonly used technique for detecting arrhythmias and many other cardiac diseases. Automatic ECG diagnosis has seen tremendous success in recent years, owing to the rapid development of the deep ...
Highlights
- Develop an arrhythmia classifier for heartbeats using ECG rhythm annotations
- ...
Breathing Disorder Detection Using Wearable Electrocardiogram And Oxygen Saturation
SenSys '18: Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems

Conventional diagnosis using polysomnography (PSG) on breathing disorder is expensive and uncomfortable to patients. In this paper, we present a low-cost portable and wearable multi-sensor system to non-invasively acquire a subject's vital signs, and ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICMHI '24: Proceedings of the 2024 8th International Conference on Medical and Health Informatics

May 2024

349 pages

ISBN:9798400716874

DOI:10.1145/3673971

Copyright © 2024 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 September 2024

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ICMHI 2024

ICMHI 2024: 2024 8th International Conference on Medical and Health Informatics

May 17 - 19, 2024

Yokohama, Japan

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
39
Total Downloads

Downloads (Last 12 months)39
Downloads (Last 6 weeks)14

Reflects downloads up to 18 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Di Stefano VD’Angelo MMonaco FVignapiano AMartiadis VBarone EFornaro MSteardo LSolmi MManchia MSteardo L(2024)Decoding Schizophrenia: How AI-Enhanced fMRI Unlocks New Pathways for Precision PsychiatryBrain Sciences10.3390/brainsci1412119614:12(1196)Online publication date: 27-Nov-2024
https://doi.org/10.3390/brainsci14121196
Das AKrishnadas AKrishnan VFarida ASarath G(2024)An Investigation of Federated Learning Strategies for Disease Diagnosis2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)10.1109/ICCCNT61001.2024.10725147(1-8)Online publication date: 24-Jun-2024
https://doi.org/10.1109/ICCCNT61001.2024.10725147

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents