No Cover Image

Journal article 14 views

Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data

Solmaz Eradat Oskoui, Matthew Retford, Eoghan Forde, Rodrigo Barnes, Karen J Hunter, Anne Wozencraft, Simon Ellwood-Thompson, Chris Orton Orcid Logo, David Ford Orcid Logo, Sharon Heys, Julie Kennedy, Cynthia McNerney, Jeffrey Peng, Hamed Ghanbarialadolat, Sarah Rees Orcid Logo, Rachel H Mulholland, Aziz Sheikh, David Burgner, Meredith Brockway, Meghan B Azad, Natalie Rodriguez, Helga Zoega, Sarah J Stock, Clara Calvert, Jessica E Miller, Nicole Fiorentino, Amy Racine, Jonas Haggstrom, Neil Postlethwaite

International Journal of Medical Informatics, Volume: 195, Start page: 105708

Swansea University Authors: Simon Ellwood-Thompson, Chris Orton Orcid Logo, David Ford Orcid Logo, Sharon Heys, Julie Kennedy, Cynthia McNerney, Jeffrey Peng, Hamed Ghanbarialadolat, Sarah Rees Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1016/j.ijmedinf.2024.105708

Abstract

The use of federated networks can reduce the risk of disclosure for sensitive datasets by removing the requirement to physically transfer data. Federated networks support federated analytics, a type of privacy-enhancing technology, enabling trustworthy data analysis without the movement of source da...

Full description

Published in: International Journal of Medical Informatics
ISSN: 1386-5056 1872-8243
Published: Elsevier BV 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa68610
first_indexed 2025-01-09T20:33:57Z
last_indexed 2025-01-09T20:33:57Z
id cronfa68610
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2024-12-20T10:37:07.1750621</datestamp><bib-version>v2</bib-version><id>68610</id><entry>2024-12-20</entry><title>Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data</title><swanseaauthors><author><sid>6498256ca5bc432bd9626503f1019113</sid><firstname>Simon</firstname><surname>Ellwood-Thompson</surname><name>Simon Ellwood-Thompson</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>555c622e1f7bd9d2e0341f2ebbfd3e7f</sid><ORCID>0000-0002-9561-2493</ORCID><firstname>Chris</firstname><surname>Orton</surname><name>Chris Orton</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>52fc0c473b0da1b7218d87f9fc68a3e6</sid><ORCID>0000-0001-6551-721X</ORCID><firstname>David</firstname><surname>Ford</surname><name>David Ford</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>61f095d8f6942db1b4fd65e2053091f5</sid><firstname>Sharon</firstname><surname>Heys</surname><name>Sharon Heys</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>39d52ad5eb7a5ee132ee326841bb8a0c</sid><ORCID/><firstname>Julie</firstname><surname>Kennedy</surname><name>Julie Kennedy</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>72a863680d277585888649ae8e0bbeae</sid><ORCID/><firstname>Cynthia</firstname><surname>McNerney</surname><name>Cynthia McNerney</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>4b794150a07cb814843f803bac7a3c4c</sid><ORCID/><firstname>Jeffrey</firstname><surname>Peng</surname><name>Jeffrey Peng</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>223819dbb6e81719ec4be146a8acb117</sid><firstname>Hamed</firstname><surname>Ghanbarialadolat</surname><name>Hamed Ghanbarialadolat</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>86073be88970f36d7ffa0a1f0768be2b</sid><ORCID>0000-0002-1939-0120</ORCID><firstname>Sarah</firstname><surname>Rees</surname><name>Sarah Rees</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-12-20</date><deptcode>MEDS</deptcode><abstract>The use of federated networks can reduce the risk of disclosure for sensitive datasets by removing the requirement to physically transfer data. Federated networks support federated analytics, a type of privacy-enhancing technology, enabling trustworthy data analysis without the movement of source data. To set out the methodology used by the International COVID-19 Data Alliance (ICODA) and its partners, the Secure Anonymised Information Linkage (SAIL) Databank and Aridhia Informatics in piloting a federated network infrastructure and consequently testing federated analytics using test data provided from an ICODA project, the International Perinatal Outcome in the Pandemic (iPOP) Study. To share the challenges and benefits of using a federated network infrastructure to enable trustworthy analysis of health-related data from multiple countries and sources. This project successfully developed a federated network between the SAIL Databank and the ICODA Workbench and piloted the use of federated analysis using aggregate-level model outputs as test data from the iPOP Study, a one-year, multi-country COVID-19 research project. This integration is a first step in implementing the necessary technical, governance and user experiences for future research studies to build upon, including those using individual-level datasets from multiple data nodes. Creating federated networks requires extensive investment from a data governance, technology, training, resources, timing and funding perspective. For future initiatives, the establishment of a federated network should be built into medium to long term plans to provide researchers with a secure and robust data analysis platform to perform joint multi-site collaboration. Federated networks can unlock the enormous potential of national and international health datasets through enabling collaborative research that addresses critical public health challenges, whilst maintaining privacy and trustworthiness by preventing direct access to the source data.</abstract><type>Journal Article</type><journal>International Journal of Medical Informatics</journal><volume>195</volume><journalNumber/><paginationStart>105708</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1386-5056</issnPrint><issnElectronic>1872-8243</issnElectronic><keywords>Federated Networks; Federated Analytics; COVID-19; Health Data Research; Privacy-Preserving; Secondary Data; Data Re-use</keywords><publishedDay>1</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-03-01</publishedDate><doi>10.1016/j.ijmedinf.2024.105708</doi><url/><notes/><college>COLLEGE NANME</college><department>Medical School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MEDS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>This work was supported by International COVID-19 Data Alliance (ICODA), an initiative funded by the COVID-19 Therapeutics Accelerator and convened by Health Data Research UK (HDR UK). We acknowledge funding via the COVID-19 Therapeutics Accelerator from the Bill &amp; Melinda Gates Foundation (INV-017293), and the Minderoo Foundation (INV-017293) and support from Microsoft&#x2019;s AI for Good Research Lab. Aridhia Informatics Ltd was funded by the Bill &amp; Melinda Gates Foundation (INV-021793). Cloud hosting support was provided by Microsoft AI for Health. SAIL Databank and the Secure eResearch Platform (SeRP) UK, based at Swansea University, were funded by an award from Health Data Research UK (2020.112), supported by funds from the ICODA initiative, to develop the underlying infrastructure and providing expertise in establishing the federated analytics platform and governance models. This study makes use of anonymised data held in the Secure Anonymised Information Linkage (SAIL) Databank. We would like to acknowledge the iPOP data providers who made their anonymised data available for research [15]. This work used data collected on behalf of patients as part of their care and support. This project was approved by the SAIL Information Governance Review Panel, under project numbers 1292 and 1299. Helga Zoega was supported by a UNSW Scientia Program Award during the conduct of this study. Sarah J Stock was funded by a Wellcome Trust Clinical Career Development Fellowship (209560/Z/17/Z). Meghan B. Azad is supported by a Canada Research Chair in the Developmental Origins of Chronic Disease. All authors approved the version of the manuscript to be published. This publication is based on research funded in part by the Bill &amp; Melinda Gates Foundation. The findings and conclusions contained within are those of the authors and do not necessarily reflect positions or policies of the Bill &amp; Melinda Gates Foundation.</funders><projectreference/><lastEdited>2024-12-20T10:37:07.1750621</lastEdited><Created>2024-12-20T10:30:05.9779979</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">Swansea University Medical School - Health Data Science</level></path><authors><author><firstname>Solmaz Eradat</firstname><surname>Oskoui</surname><order>1</order></author><author><firstname>Matthew</firstname><surname>Retford</surname><order>2</order></author><author><firstname>Eoghan</firstname><surname>Forde</surname><order>3</order></author><author><firstname>Rodrigo</firstname><surname>Barnes</surname><order>4</order></author><author><firstname>Karen J</firstname><surname>Hunter</surname><order>5</order></author><author><firstname>Anne</firstname><surname>Wozencraft</surname><order>6</order></author><author><firstname>Simon</firstname><surname>Ellwood-Thompson</surname><order>7</order></author><author><firstname>Chris</firstname><surname>Orton</surname><orcid>0000-0002-9561-2493</orcid><order>8</order></author><author><firstname>David</firstname><surname>Ford</surname><orcid>0000-0001-6551-721X</orcid><order>9</order></author><author><firstname>Sharon</firstname><surname>Heys</surname><order>10</order></author><author><firstname>Julie</firstname><surname>Kennedy</surname><orcid/><order>11</order></author><author><firstname>Cynthia</firstname><surname>McNerney</surname><orcid/><order>12</order></author><author><firstname>Jeffrey</firstname><surname>Peng</surname><orcid/><order>13</order></author><author><firstname>Hamed</firstname><surname>Ghanbarialadolat</surname><order>14</order></author><author><firstname>Sarah</firstname><surname>Rees</surname><orcid>0000-0002-1939-0120</orcid><order>15</order></author><author><firstname>Rachel H</firstname><surname>Mulholland</surname><order>16</order></author><author><firstname>Aziz</firstname><surname>Sheikh</surname><order>17</order></author><author><firstname>David</firstname><surname>Burgner</surname><order>18</order></author><author><firstname>Meredith</firstname><surname>Brockway</surname><order>19</order></author><author><firstname>Meghan B</firstname><surname>Azad</surname><order>20</order></author><author><firstname>Natalie</firstname><surname>Rodriguez</surname><order>21</order></author><author><firstname>Helga</firstname><surname>Zoega</surname><order>22</order></author><author><firstname>Sarah J</firstname><surname>Stock</surname><order>23</order></author><author><firstname>Clara</firstname><surname>Calvert</surname><order>24</order></author><author><firstname>Jessica E</firstname><surname>Miller</surname><order>25</order></author><author><firstname>Nicole</firstname><surname>Fiorentino</surname><order>26</order></author><author><firstname>Amy</firstname><surname>Racine</surname><order>27</order></author><author><firstname>Jonas</firstname><surname>Haggstrom</surname><order>28</order></author><author><firstname>Neil</firstname><surname>Postlethwaite</surname><order>29</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2024-12-20T10:37:07.1750621 v2 68610 2024-12-20 Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data 6498256ca5bc432bd9626503f1019113 Simon Ellwood-Thompson Simon Ellwood-Thompson true false 555c622e1f7bd9d2e0341f2ebbfd3e7f 0000-0002-9561-2493 Chris Orton Chris Orton true false 52fc0c473b0da1b7218d87f9fc68a3e6 0000-0001-6551-721X David Ford David Ford true false 61f095d8f6942db1b4fd65e2053091f5 Sharon Heys Sharon Heys true false 39d52ad5eb7a5ee132ee326841bb8a0c Julie Kennedy Julie Kennedy true false 72a863680d277585888649ae8e0bbeae Cynthia McNerney Cynthia McNerney true false 4b794150a07cb814843f803bac7a3c4c Jeffrey Peng Jeffrey Peng true false 223819dbb6e81719ec4be146a8acb117 Hamed Ghanbarialadolat Hamed Ghanbarialadolat true false 86073be88970f36d7ffa0a1f0768be2b 0000-0002-1939-0120 Sarah Rees Sarah Rees true false 2024-12-20 MEDS The use of federated networks can reduce the risk of disclosure for sensitive datasets by removing the requirement to physically transfer data. Federated networks support federated analytics, a type of privacy-enhancing technology, enabling trustworthy data analysis without the movement of source data. To set out the methodology used by the International COVID-19 Data Alliance (ICODA) and its partners, the Secure Anonymised Information Linkage (SAIL) Databank and Aridhia Informatics in piloting a federated network infrastructure and consequently testing federated analytics using test data provided from an ICODA project, the International Perinatal Outcome in the Pandemic (iPOP) Study. To share the challenges and benefits of using a federated network infrastructure to enable trustworthy analysis of health-related data from multiple countries and sources. This project successfully developed a federated network between the SAIL Databank and the ICODA Workbench and piloted the use of federated analysis using aggregate-level model outputs as test data from the iPOP Study, a one-year, multi-country COVID-19 research project. This integration is a first step in implementing the necessary technical, governance and user experiences for future research studies to build upon, including those using individual-level datasets from multiple data nodes. Creating federated networks requires extensive investment from a data governance, technology, training, resources, timing and funding perspective. For future initiatives, the establishment of a federated network should be built into medium to long term plans to provide researchers with a secure and robust data analysis platform to perform joint multi-site collaboration. Federated networks can unlock the enormous potential of national and international health datasets through enabling collaborative research that addresses critical public health challenges, whilst maintaining privacy and trustworthiness by preventing direct access to the source data. Journal Article International Journal of Medical Informatics 195 105708 Elsevier BV 1386-5056 1872-8243 Federated Networks; Federated Analytics; COVID-19; Health Data Research; Privacy-Preserving; Secondary Data; Data Re-use 1 3 2025 2025-03-01 10.1016/j.ijmedinf.2024.105708 COLLEGE NANME Medical School COLLEGE CODE MEDS Swansea University Another institution paid the OA fee This work was supported by International COVID-19 Data Alliance (ICODA), an initiative funded by the COVID-19 Therapeutics Accelerator and convened by Health Data Research UK (HDR UK). We acknowledge funding via the COVID-19 Therapeutics Accelerator from the Bill & Melinda Gates Foundation (INV-017293), and the Minderoo Foundation (INV-017293) and support from Microsoft’s AI for Good Research Lab. Aridhia Informatics Ltd was funded by the Bill & Melinda Gates Foundation (INV-021793). Cloud hosting support was provided by Microsoft AI for Health. SAIL Databank and the Secure eResearch Platform (SeRP) UK, based at Swansea University, were funded by an award from Health Data Research UK (2020.112), supported by funds from the ICODA initiative, to develop the underlying infrastructure and providing expertise in establishing the federated analytics platform and governance models. This study makes use of anonymised data held in the Secure Anonymised Information Linkage (SAIL) Databank. We would like to acknowledge the iPOP data providers who made their anonymised data available for research [15]. This work used data collected on behalf of patients as part of their care and support. This project was approved by the SAIL Information Governance Review Panel, under project numbers 1292 and 1299. Helga Zoega was supported by a UNSW Scientia Program Award during the conduct of this study. Sarah J Stock was funded by a Wellcome Trust Clinical Career Development Fellowship (209560/Z/17/Z). Meghan B. Azad is supported by a Canada Research Chair in the Developmental Origins of Chronic Disease. All authors approved the version of the manuscript to be published. This publication is based on research funded in part by the Bill & Melinda Gates Foundation. The findings and conclusions contained within are those of the authors and do not necessarily reflect positions or policies of the Bill & Melinda Gates Foundation. 2024-12-20T10:37:07.1750621 2024-12-20T10:30:05.9779979 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Health Data Science Solmaz Eradat Oskoui 1 Matthew Retford 2 Eoghan Forde 3 Rodrigo Barnes 4 Karen J Hunter 5 Anne Wozencraft 6 Simon Ellwood-Thompson 7 Chris Orton 0000-0002-9561-2493 8 David Ford 0000-0001-6551-721X 9 Sharon Heys 10 Julie Kennedy 11 Cynthia McNerney 12 Jeffrey Peng 13 Hamed Ghanbarialadolat 14 Sarah Rees 0000-0002-1939-0120 15 Rachel H Mulholland 16 Aziz Sheikh 17 David Burgner 18 Meredith Brockway 19 Meghan B Azad 20 Natalie Rodriguez 21 Helga Zoega 22 Sarah J Stock 23 Clara Calvert 24 Jessica E Miller 25 Nicole Fiorentino 26 Amy Racine 27 Jonas Haggstrom 28 Neil Postlethwaite 29
title Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data
spellingShingle Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data
Simon Ellwood-Thompson
Chris Orton
David Ford
Sharon Heys
Julie Kennedy
Cynthia McNerney
Jeffrey Peng
Hamed Ghanbarialadolat
Sarah Rees
title_short Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data
title_full Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data
title_fullStr Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data
title_full_unstemmed Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data
title_sort Developing a prototype for federated analysis to enhance privacy and enable trustworthy access to COVID-19 research data
author_id_str_mv 6498256ca5bc432bd9626503f1019113
555c622e1f7bd9d2e0341f2ebbfd3e7f
52fc0c473b0da1b7218d87f9fc68a3e6
61f095d8f6942db1b4fd65e2053091f5
39d52ad5eb7a5ee132ee326841bb8a0c
72a863680d277585888649ae8e0bbeae
4b794150a07cb814843f803bac7a3c4c
223819dbb6e81719ec4be146a8acb117
86073be88970f36d7ffa0a1f0768be2b
author_id_fullname_str_mv 6498256ca5bc432bd9626503f1019113_***_Simon Ellwood-Thompson
555c622e1f7bd9d2e0341f2ebbfd3e7f_***_Chris Orton
52fc0c473b0da1b7218d87f9fc68a3e6_***_David Ford
61f095d8f6942db1b4fd65e2053091f5_***_Sharon Heys
39d52ad5eb7a5ee132ee326841bb8a0c_***_Julie Kennedy
72a863680d277585888649ae8e0bbeae_***_Cynthia McNerney
4b794150a07cb814843f803bac7a3c4c_***_Jeffrey Peng
223819dbb6e81719ec4be146a8acb117_***_Hamed Ghanbarialadolat
86073be88970f36d7ffa0a1f0768be2b_***_Sarah Rees
author Simon Ellwood-Thompson
Chris Orton
David Ford
Sharon Heys
Julie Kennedy
Cynthia McNerney
Jeffrey Peng
Hamed Ghanbarialadolat
Sarah Rees
author2 Solmaz Eradat Oskoui
Matthew Retford
Eoghan Forde
Rodrigo Barnes
Karen J Hunter
Anne Wozencraft
Simon Ellwood-Thompson
Chris Orton
David Ford
Sharon Heys
Julie Kennedy
Cynthia McNerney
Jeffrey Peng
Hamed Ghanbarialadolat
Sarah Rees
Rachel H Mulholland
Aziz Sheikh
David Burgner
Meredith Brockway
Meghan B Azad
Natalie Rodriguez
Helga Zoega
Sarah J Stock
Clara Calvert
Jessica E Miller
Nicole Fiorentino
Amy Racine
Jonas Haggstrom
Neil Postlethwaite
format Journal article
container_title International Journal of Medical Informatics
container_volume 195
container_start_page 105708
publishDate 2025
institution Swansea University
issn 1386-5056
1872-8243
doi_str_mv 10.1016/j.ijmedinf.2024.105708
publisher Elsevier BV
college_str Faculty of Medicine, Health and Life Sciences
hierarchytype
hierarchy_top_id facultyofmedicinehealthandlifesciences
hierarchy_top_title Faculty of Medicine, Health and Life Sciences
hierarchy_parent_id facultyofmedicinehealthandlifesciences
hierarchy_parent_title Faculty of Medicine, Health and Life Sciences
department_str Swansea University Medical School - Health Data Science{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}Swansea University Medical School - Health Data Science
document_store_str 0
active_str 0
description The use of federated networks can reduce the risk of disclosure for sensitive datasets by removing the requirement to physically transfer data. Federated networks support federated analytics, a type of privacy-enhancing technology, enabling trustworthy data analysis without the movement of source data. To set out the methodology used by the International COVID-19 Data Alliance (ICODA) and its partners, the Secure Anonymised Information Linkage (SAIL) Databank and Aridhia Informatics in piloting a federated network infrastructure and consequently testing federated analytics using test data provided from an ICODA project, the International Perinatal Outcome in the Pandemic (iPOP) Study. To share the challenges and benefits of using a federated network infrastructure to enable trustworthy analysis of health-related data from multiple countries and sources. This project successfully developed a federated network between the SAIL Databank and the ICODA Workbench and piloted the use of federated analysis using aggregate-level model outputs as test data from the iPOP Study, a one-year, multi-country COVID-19 research project. This integration is a first step in implementing the necessary technical, governance and user experiences for future research studies to build upon, including those using individual-level datasets from multiple data nodes. Creating federated networks requires extensive investment from a data governance, technology, training, resources, timing and funding perspective. For future initiatives, the establishment of a federated network should be built into medium to long term plans to provide researchers with a secure and robust data analysis platform to perform joint multi-site collaboration. Federated networks can unlock the enormous potential of national and international health datasets through enabling collaborative research that addresses critical public health challenges, whilst maintaining privacy and trustworthiness by preventing direct access to the source data.
published_date 2025-03-01T20:36:59Z
_version_ 1821348640790151168
score 11.04748

Similar Items