Health Data Sharing towards Knowledge Creation

Abstract

Data sharing and service reuse in the health sector pose significant privacy and security challenges. The European Commission recognizes health data as a unique and cost-effective resource for research, while the OECD emphasizes the need for privacy-protecting data governance systems. In this paper, we propose a novel approach to health data access in a hospital environment, leveraging homomorphic encryption to ensure privacy and secure sharing of medical data among healthcare entities. Our framework establishes a secure environment that enforces GDPR adoption. We present an Information Sharing Infrastructure (ISI) framework that seamlessly integrates artificial intelligence (AI) capabilities for data analysis. Through our implementation, we demonstrate the ease of applying AI algorithms to treated health data within the ISI environment. Evaluating machine learning models, we achieve high accuracies of 96.88% with logistic regression and 97.62% with random forest. To address privacy concerns, our framework incorporates Data Sharing Agreements (DSAs). Data producers and consumers (prosumers) have the flexibility to express their prefearences for sharing and analytics operations. Data-centric policy enforcement mechanisms ensure compliance and privacy preservation. In summary, our comprehensive framework combines homomorphic encryption, secure data sharing, and AI-driven analytics. By fostering collaboration and knowledge creation in a secure environment, our approach contributes to the advancement of medical research and improves healthcare outcomes. A real case application was implemented between Portuguese hospitals and universities for this data sharing.

AI-Driven Decision Support for Early Detection of Cardiac Events: Unveiling Patterns and Predicting Myocardial Ischemia

“…The use of AI in healthcare necessitates a robust consideration of ethical implications. We acknowledge our access to the clinical data of patients admitted to the Intensive Care Units of Hospital de Santa Maria, in the framework of FCT project DSAIPA/AI/0122/2020 AIMHealth, and the work [ 10 ], where DSAs were signed and homomorphic encryption was implemented. These ethical safeguards protected patient privacy and confidentiality while enabling critical research.…”

“…Our exploration of myocardial ischemia prediction, while promising, remains a singular facet of AI applications in cardiovascular healthcare. We advocate for a broader exploration of AI’s potential in addressing various cardiovascular diseases, and on behalf of the study that was conducted [ 10 ], we will focus on further enhancing the robustness and generalizability of our predictive models by integrating data from multiple hospitals and medical institutions. This collaborative approach aims to encompass a broader patient population and provide a more comprehensive understanding of cardiovascular diseases.…”

“…Building upon a doctoral research initiative, Data Sharing Agreements were meticulously crafted and signed. The implementation of homomorphic encryption, initially explored in a previously published paper [ 10 ], imparted an additional layer of academic rigor and depth to our methodology.…”

“…Importantly, these data were homomorphically encrypted to uphold privacy and confidentiality standards. The application of Data Sharing Agreements (DSAs) ensures responsible and compliant data sharing practices, safeguarding patient information [ 10 ].…”

Towards Municipal Data Utilities: Experiences Regarding the Development of a Municipal Data Utility for Intra- and Intermunicipal Actors within the German City of Mainz

“…Elvas et al propose a novel approach to health data access in a hospital environment hereby using homomorphic encryption to ensure privacy and secure data sharing. Their proposed Information Sharing Infrastructure (ISI) framework enforces GDPR adoption and integrates artificial intelligence (AI) capabilities for data analysis as well as data-sharing agreements [4]. Šestak and Copot outline key challenges to data sharing in agri-food chains that hinder the establishment of an Agricultural Data Ecosystem (ADE).…”