Orbital learning: a novel, actively orchestrated decentralised learning for healthcare

Chakshu, Neeraj Kavan; Nithiarasu, Perumal

doi:10.1038/s41598-024-60915-9

Journal article 55 views 11 downloads

Orbital learning: a novel, actively orchestrated decentralised learning for healthcare

Neeraj Kavan Chakshu, Perumal Nithiarasu

Scientific Reports, Volume: 14, Issue: 1

Swansea University Authors: Neeraj Kavan Chakshu, Perumal Nithiarasu

PDF | Version of Record

© The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License.
Download (1.58MB)

Check full text

DOI (Published version): 10.1038/s41598-024-60915-9

Abstract

A novel collaborative and continual learning across a network of decentralised healthcare units, avoiding identifiable data-sharing capacity, is proposed. Currently available methodologies, such as federated learning and swarm learning, have demonstrated decentralised learning. However, the majority...

Full description

Published in:	Scientific Reports
ISSN:	2045-2322
Published:	Springer Science and Business Media LLC 2024
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa66208
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2024-04-29T09:06:17Z
last_indexed	2024-04-29T09:06:17Z
id	cronfa66208
recordtype	SURis
fullrecord	<?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>66208</id><entry>2024-04-29</entry><title>Orbital learning: a novel, actively orchestrated decentralised learning for healthcare</title><swanseaauthors><author><sid>e21c85ee9062e9be0fff8ab9d77b14d7</sid><firstname>Neeraj Kavan</firstname><surname>Chakshu</surname><name>Neeraj Kavan Chakshu</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>3b28bf59358fc2b9bd9a46897dbfc92d</sid><ORCID>0000-0002-4901-2980</ORCID><firstname>Perumal</firstname><surname>Nithiarasu</surname><name>Perumal Nithiarasu</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-04-29</date><deptcode>ACEM</deptcode><abstract>A novel collaborative and continual learning across a network of decentralised healthcare units, avoiding identifiable data-sharing capacity, is proposed. Currently available methodologies, such as federated learning and swarm learning, have demonstrated decentralised learning. However, the majority of them face shortcomings that affect their performance and accuracy. These shortcomings include a non-uniform rate of data accumulation, non-uniform patient demographics, biased human labelling, and erroneous or malicious training data. A novel method to reduce such shortcomings is proposed in the present work through selective grouping and displacing of actors in a network of many entities for intra-group sharing of learning with inter-group accessibility. The proposed system, known as Orbital Learning, incorporates various features from split learning and ensemble learning for a robust and secure performance of supervised models. A digital embodiment of the information quality and flow within a decentralised network, this platform also acts as a digital twin of healthcare network. An example of ECG classification for arrhythmia with 6 clients is used to analyse its performance and is compared against federated learning. In this example, four separate experiments are conducted with varied configurations, such as varied age demographics and clients with data tampering. The results obtained show an average area under receiver operating characteristic curve (AUROC) of 0.819 (95% CI 0.784–0.853) for orbital learning whereas 0.714 (95% CI 0.692–0.736) for federated learning. This result shows an increase in overall performance and establishes that the proposed system can address the majority of the issues faced by existing decentralised learning methodologies. Further, a scalability demo conducted establishes the versatility and scalability of this platform in handling state-of-the-art large language models.</abstract><type>Journal Article</type><journal>Scientific Reports</journal><volume>14</volume><journalNumber>1</journalNumber><paginationStart/><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2045-2322</issnElectronic><keywords>Decentralised learning; Digital health; Data security; Data privacy</keywords><publishedDay>7</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-05-07</publishedDate><doi>10.1038/s41598-024-60915-9</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm>External research funder(s) paid the OA fee (includes OA grants disbursed by the Library)</apcterm><funders>The first author would like to thank IMPACT at Swansea University for funding and supporting this project during their fellowship. Authors would also like to acknowledge Faculty of Science and Engineering, Swansea University for their support. This work was partially supported through Impact Acceleration Account grant number: EP/X525637/1.</funders><projectreference/><lastEdited>2024-05-13T16:10:51.6302934</lastEdited><Created>2024-04-29T10:03:26.9886759</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Biomedical Engineering</level></path><authors><author><firstname>Neeraj Kavan</firstname><surname>Chakshu</surname><order>1</order></author><author><firstname>Perumal</firstname><surname>Nithiarasu</surname><orcid>0000-0002-4901-2980</orcid><order>2</order></author></authors><documents><document><filename>66208__30310__ab1df840286944b682a69c15a22e9e5a.pdf</filename><originalFilename>66208.VoR.pdf</originalFilename><uploaded>2024-05-08T11:22:07.8693057</uploaded><type>Output</type><contentLength>1656766</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	v2 66208 2024-04-29 Orbital learning: a novel, actively orchestrated decentralised learning for healthcare e21c85ee9062e9be0fff8ab9d77b14d7 Neeraj Kavan Chakshu Neeraj Kavan Chakshu true false 3b28bf59358fc2b9bd9a46897dbfc92d 0000-0002-4901-2980 Perumal Nithiarasu Perumal Nithiarasu true false 2024-04-29 ACEM A novel collaborative and continual learning across a network of decentralised healthcare units, avoiding identifiable data-sharing capacity, is proposed. Currently available methodologies, such as federated learning and swarm learning, have demonstrated decentralised learning. However, the majority of them face shortcomings that affect their performance and accuracy. These shortcomings include a non-uniform rate of data accumulation, non-uniform patient demographics, biased human labelling, and erroneous or malicious training data. A novel method to reduce such shortcomings is proposed in the present work through selective grouping and displacing of actors in a network of many entities for intra-group sharing of learning with inter-group accessibility. The proposed system, known as Orbital Learning, incorporates various features from split learning and ensemble learning for a robust and secure performance of supervised models. A digital embodiment of the information quality and flow within a decentralised network, this platform also acts as a digital twin of healthcare network. An example of ECG classification for arrhythmia with 6 clients is used to analyse its performance and is compared against federated learning. In this example, four separate experiments are conducted with varied configurations, such as varied age demographics and clients with data tampering. The results obtained show an average area under receiver operating characteristic curve (AUROC) of 0.819 (95% CI 0.784–0.853) for orbital learning whereas 0.714 (95% CI 0.692–0.736) for federated learning. This result shows an increase in overall performance and establishes that the proposed system can address the majority of the issues faced by existing decentralised learning methodologies. Further, a scalability demo conducted establishes the versatility and scalability of this platform in handling state-of-the-art large language models. Journal Article Scientific Reports 14 1 Springer Science and Business Media LLC 2045-2322 Decentralised learning; Digital health; Data security; Data privacy 7 5 2024 2024-05-07 10.1038/s41598-024-60915-9 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University External research funder(s) paid the OA fee (includes OA grants disbursed by the Library) The first author would like to thank IMPACT at Swansea University for funding and supporting this project during their fellowship. Authors would also like to acknowledge Faculty of Science and Engineering, Swansea University for their support. This work was partially supported through Impact Acceleration Account grant number: EP/X525637/1. 2024-05-13T16:10:51.6302934 2024-04-29T10:03:26.9886759 Faculty of Science and Engineering School of Engineering and Applied Sciences - Biomedical Engineering Neeraj Kavan Chakshu 1 Perumal Nithiarasu 0000-0002-4901-2980 2 66208__30310__ab1df840286944b682a69c15a22e9e5a.pdf 66208.VoR.pdf 2024-05-08T11:22:07.8693057 Output 1656766 application/pdf Version of Record true © The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License. true eng http://creativecommons.org/licenses/by/4.0/
title	Orbital learning: a novel, actively orchestrated decentralised learning for healthcare
spellingShingle	Orbital learning: a novel, actively orchestrated decentralised learning for healthcare Neeraj Kavan Chakshu Perumal Nithiarasu
title_short	Orbital learning: a novel, actively orchestrated decentralised learning for healthcare
title_full	Orbital learning: a novel, actively orchestrated decentralised learning for healthcare
title_fullStr	Orbital learning: a novel, actively orchestrated decentralised learning for healthcare
title_full_unstemmed	Orbital learning: a novel, actively orchestrated decentralised learning for healthcare
title_sort	Orbital learning: a novel, actively orchestrated decentralised learning for healthcare
author_id_str_mv	e21c85ee9062e9be0fff8ab9d77b14d7 3b28bf59358fc2b9bd9a46897dbfc92d
author_id_fullname_str_mv	e21c85ee9062e9be0fff8ab9d77b14d7_*_Neeraj Kavan Chakshu 3b28bf59358fc2b9bd9a46897dbfc92d_*_Perumal Nithiarasu
author	Neeraj Kavan Chakshu Perumal Nithiarasu
author2	Neeraj Kavan Chakshu Perumal Nithiarasu
format	Journal article
container_title	Scientific Reports
container_volume	14
container_issue	1
publishDate	2024
institution	Swansea University
issn	2045-2322
doi_str_mv	10.1038/s41598-024-60915-9
publisher	Springer Science and Business Media LLC
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Engineering and Applied Sciences - Biomedical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Biomedical Engineering
document_store_str	1
active_str	0
description	A novel collaborative and continual learning across a network of decentralised healthcare units, avoiding identifiable data-sharing capacity, is proposed. Currently available methodologies, such as federated learning and swarm learning, have demonstrated decentralised learning. However, the majority of them face shortcomings that affect their performance and accuracy. These shortcomings include a non-uniform rate of data accumulation, non-uniform patient demographics, biased human labelling, and erroneous or malicious training data. A novel method to reduce such shortcomings is proposed in the present work through selective grouping and displacing of actors in a network of many entities for intra-group sharing of learning with inter-group accessibility. The proposed system, known as Orbital Learning, incorporates various features from split learning and ensemble learning for a robust and secure performance of supervised models. A digital embodiment of the information quality and flow within a decentralised network, this platform also acts as a digital twin of healthcare network. An example of ECG classification for arrhythmia with 6 clients is used to analyse its performance and is compared against federated learning. In this example, four separate experiments are conducted with varied configurations, such as varied age demographics and clients with data tampering. The results obtained show an average area under receiver operating characteristic curve (AUROC) of 0.819 (95% CI 0.784–0.853) for orbital learning whereas 0.714 (95% CI 0.692–0.736) for federated learning. This result shows an increase in overall performance and establishes that the proposed system can address the majority of the issues faced by existing decentralised learning methodologies. Further, a scalability demo conducted establishes the versatility and scalability of this platform in handling state-of-the-art large language models.
published_date	2024-05-07T16:10:50Z
_version_	1798950669805158400
score	11.012678

Orbital learning: a novel, actively orchestrated decentralised learning for healthcare

Similar Items