The EPI Framework: A Dynamic Data Sharing Framework for Healthcare Use Cases

Abstract

To support the current trend of personalised medicine, a collaboration between different healthcare providers is increasingly vital. The main element is the ability to share data among all parties while abiding by a data sharing policy. The EPI (Enabling Personalised Intervention) project addresses the problem of personalised diagnosis by developing real-time monitoring services and digital health twins. The EPI services run over adaptive computing infrastructures which provide more flexibility to accommodate the different requests. This paper proposes the EPI framework to support these novel health services over programmable infrastructure. The framework works on aligning the parties' ability to share data with the policy defined beforehand. We explain the approach by introducing the framework's data sharing logic model. We define the formalism of the logic model to deduce feasible data movements between and possibly satisfy a data collaboration request. We reinforce the framework's logic model by introducing the algorithms running on this federated system to simulate its workflow. We provide three healthcare use cases running on a typical EPI infrastructure. We evaluated our model according to three relevant parameters, performance, feasibility, and aggregation power, and we can conclude that our framework supports the required interoperability between the EPI partners.

Dynamic Data Infrastructure Security for Interoperable e-Healthcare Systems: A Semantic Feature-Driven NoSQL Intrusion Attack Detection Model

“…Though different databases or allied data infrastructures employ gate-level access control using certain authentication methods, however, the nature of intrusion attacks often makes them inferior (see Section 2). This is because the hackers often intrude inside databases by mimicking genuine data structures or injecting malicious codes at the place of query variables [12][13][14][15].…”

“…Being an interoperable e-Healthcare system with multiple stakeholders, the data input and allied characteristics can be different that consequently making classical intrusion detection methods inappropriate [13,14]]. The classical term-matching-based intrusion detection methods might fail in detecting the malicious user or query [12][13][14]. Miscalculation towards the wrongly classified queries can force the model to under false-positive performance and hence can impact reliability.…”

“…Noticeably, so far almost all existing intrusion detection systems focused on SLIintrusion attack (SQLIA) detection, and no significant effort has been made toward intrusion detection in NoSQL databases [14]. This, as a result, broadens the gaps for academia industries to develop a robust intrusion detection system for NoSQL dynamic datasets for e-Healthcare systems [12,14]. An intrusion detection system (IDS) is a software application that detects network intrusions using machine learning algorithms.…”

Multi-domain network infrastructure based on P4 programmable devices for Digital Data Marketplaces

“…A science use case concerns personalized medicine: the EPI project will develop a secure and trustworthy platform to share patient data across medical institutions to help diagnosis and decision making for both patients and health providers; the sharing of information will still fully preserve patients' privacy. It also studies policies definitions and how to set up network infrastructure to enforce them [1].…”

“…Data sharing is currently emerging as an essential element in fields like healthcare systems [1], supply chain logistics [2], and IoT devices in smart cities [3]. Digital Data Marketplaces (DDMs) [4] are emerging frameworks that provide secure data sharing mechanisms among participating parties.…”