Cargando…
In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare
Artificial Intelligence and its subdomain, Machine Learning (ML), have shown the potential to make an unprecedented impact in healthcare. Federated Learning (FL) has been introduced to alleviate some of the limitations of ML, particularly the capability to train on larger datasets for improved perfo...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8528445/ https://www.ncbi.nlm.nih.gov/pubmed/34693280 http://dx.doi.org/10.3389/frai.2021.746497 |
_version_ | 1784586251627659264 |
---|---|
author | Topaloglu, Mustafa Y. Morrell, Elisabeth M. Rajendran, Suraj Topaloglu, Umit |
author_facet | Topaloglu, Mustafa Y. Morrell, Elisabeth M. Rajendran, Suraj Topaloglu, Umit |
author_sort | Topaloglu, Mustafa Y. |
collection | PubMed |
description | Artificial Intelligence and its subdomain, Machine Learning (ML), have shown the potential to make an unprecedented impact in healthcare. Federated Learning (FL) has been introduced to alleviate some of the limitations of ML, particularly the capability to train on larger datasets for improved performance, which is usually cumbersome for an inter-institutional collaboration due to existing patient protection laws and regulations. Moreover, FL may also play a crucial role in circumventing ML’s exigent bias problem by accessing underrepresented groups’ data spanning geographically distributed locations. In this paper, we have discussed three FL challenges, namely: privacy of the model exchange, ethical perspectives, and legal considerations. Lastly, we have proposed a model that could aide in assessing data contributions of a FL implementation. In light of the expediency and adaptability of using the Sørensen–Dice Coefficient over the more limited (e.g., horizontal FL) and computationally expensive Shapley Values, we sought to demonstrate a new paradigm that we hope, will become invaluable for sharing any profit and responsibilities that may accompany a FL endeavor. |
format | Online Article Text |
id | pubmed-8528445 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-85284452021-10-21 In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare Topaloglu, Mustafa Y. Morrell, Elisabeth M. Rajendran, Suraj Topaloglu, Umit Front Artif Intell Artificial Intelligence Artificial Intelligence and its subdomain, Machine Learning (ML), have shown the potential to make an unprecedented impact in healthcare. Federated Learning (FL) has been introduced to alleviate some of the limitations of ML, particularly the capability to train on larger datasets for improved performance, which is usually cumbersome for an inter-institutional collaboration due to existing patient protection laws and regulations. Moreover, FL may also play a crucial role in circumventing ML’s exigent bias problem by accessing underrepresented groups’ data spanning geographically distributed locations. In this paper, we have discussed three FL challenges, namely: privacy of the model exchange, ethical perspectives, and legal considerations. Lastly, we have proposed a model that could aide in assessing data contributions of a FL implementation. In light of the expediency and adaptability of using the Sørensen–Dice Coefficient over the more limited (e.g., horizontal FL) and computationally expensive Shapley Values, we sought to demonstrate a new paradigm that we hope, will become invaluable for sharing any profit and responsibilities that may accompany a FL endeavor. Frontiers Media S.A. 2021-10-06 /pmc/articles/PMC8528445/ /pubmed/34693280 http://dx.doi.org/10.3389/frai.2021.746497 Text en Copyright © 2021 Topaloglu, Morrell, Rajendran and Topaloglu. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Artificial Intelligence Topaloglu, Mustafa Y. Morrell, Elisabeth M. Rajendran, Suraj Topaloglu, Umit In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare |
title | In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare |
title_full | In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare |
title_fullStr | In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare |
title_full_unstemmed | In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare |
title_short | In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare |
title_sort | in the pursuit of privacy: the promises and predicaments of federated learning in healthcare |
topic | Artificial Intelligence |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8528445/ https://www.ncbi.nlm.nih.gov/pubmed/34693280 http://dx.doi.org/10.3389/frai.2021.746497 |
work_keys_str_mv | AT topaloglumustafay inthepursuitofprivacythepromisesandpredicamentsoffederatedlearninginhealthcare AT morrellelisabethm inthepursuitofprivacythepromisesandpredicamentsoffederatedlearninginhealthcare AT rajendransuraj inthepursuitofprivacythepromisesandpredicamentsoffederatedlearninginhealthcare AT topalogluumit inthepursuitofprivacythepromisesandpredicamentsoffederatedlearninginhealthcare |