Privacy preservation in artificial intelligence-enabled healthcare analytics

Li, Shancang, Iqbal, Muddesar, Bashir, Ali Kashif and Xinheng, Wang 2021. Privacy preservation in artificial intelligence-enabled healthcare analytics. Human-Centric Computing and Information Sciences

Preview

PDF - Published Version Available under License Creative Commons Attribution Non-commercial. Download (986kB) | Preview

Abstract

Emerging techniques such as the Internet of Things (IoT), machine learning, and artificial intelligence (AI) have revolutionized healthcare analytics by offering a multitude of significant benefits, including real-time process, enhanced data efficiency and optimization, enabling offline operation, fostering resilience, personalized and context-aware healthcare, etc. However, privacy concerns are indeed significant when it comes to edge computing and machine learning-enabled healthcare analytics. The training and validation of AI algorithms face considerable obstacles due to privacy concerns and stringent legal and ethical requirements associated with datasets. This work has proposed a healthcare data anonymization framework to address privacy concerns and ensure compliance with data regulations by enhancing privacy protection and anonymizing sensitive information in healthcare analytics, which can maintain a high level of privacy while minimizing any adverse effects on the analytics models. The experimental results have unequivocally showcased the effectiveness of the proposed solution.

Item Type:	Article
Status:	In Press
Schools:	Computer Science & Informatics
Publisher:	SpringerOpen / Springer Verlag (Germany)
ISSN:	2192-1962
Date of First Compliant Deposit:	25 June 2024
Last Modified:	25 Jun 2024 11:15
URI:	https://orca.cardiff.ac.uk/id/eprint/167919

Actions (repository staff only)

Edit Item