The digital transformation of health processes has resulted in the collection of vast amounts of health-related data that presents significant potential to support medical research projects and improve the healthcare system. Many of these possibilities arise as a consequence of integrating data from different sources to create an accurate and unified representation of the underlying data and enable detailed data analysis that is not possible through any individual source. Achieving this vision requires the collection and processing of sensitive health-related data about individuals, thus privacy and confidentiality implications have to be considered. In this paper, I describe my doctoral research topic: the design and development of a novel Privacy-Preserving Data Integration (PPDI) framework which aims to effectively address the challenges and opportunities of integrating Big Health Data (BHD) while ensuring compliance with the General Data Protection Regulation (GDPR). The paper describes the planned methodology for implementing the PPDI process through the usage of data pseudonymization techniques and Privacy-Preserving Record Linkage (PPRL) methods and provides an overview of the new framework, which is based on the re-implementation of MOMIS towards a microservices architecture with added PPDI functionalities.
Privacy-Preserving Data Integration for Health / Trigiante, L.. - 3478:(2023), pp. 750-756. (Intervento presentato al convegno 31st Symposium of Advanced Database Systems, SEBD 2023 tenutosi a ita nel 2023).
Privacy-Preserving Data Integration for Health
Trigiante L.
Project Administration
2023
Abstract
The digital transformation of health processes has resulted in the collection of vast amounts of health-related data that presents significant potential to support medical research projects and improve the healthcare system. Many of these possibilities arise as a consequence of integrating data from different sources to create an accurate and unified representation of the underlying data and enable detailed data analysis that is not possible through any individual source. Achieving this vision requires the collection and processing of sensitive health-related data about individuals, thus privacy and confidentiality implications have to be considered. In this paper, I describe my doctoral research topic: the design and development of a novel Privacy-Preserving Data Integration (PPDI) framework which aims to effectively address the challenges and opportunities of integrating Big Health Data (BHD) while ensuring compliance with the General Data Protection Regulation (GDPR). The paper describes the planned methodology for implementing the PPDI process through the usage of data pseudonymization techniques and Privacy-Preserving Record Linkage (PPRL) methods and provides an overview of the new framework, which is based on the re-implementation of MOMIS towards a microservices architecture with added PPDI functionalities.File | Dimensione | Formato | |
---|---|---|---|
TrigianteL_SEBD2023_PPDI.pdf
Open access
Tipologia:
Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
874.39 kB
Formato
Adobe PDF
|
874.39 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris