Close

Advanced School for Computing and Imaging (ASCI)

ASCI office
Delft University of Technology
Building 28, room E.3080
Van Mourik Broekmanweg 6
2628 XE – DELFT, The Netherlands

E: asci-office@tudelft.nl

Directions

The ASCI office is located at the Delft University of Technology campus.  It is easily accessible by bicycle, public transport and car. The numbers of buildings can help you find your way around the campus. Make sure you remember the name and building number of your destination.

Contact us at +31 15 278 8032 or send us an email at asci-office@tudelft.nl

Programmable Infrastructures for Secure Healthcare

Programmable Infrastructures for Secure Healthcare

Author : Jamila Alsayed Kassem
Promotor(s) : Prof.dr.ir. C.T.A.M. de Laat
University : UVA
Year of publication : 2025
Link to repository : Link to thesis

Abstract

With the exponential growth of health-related data, there is a pressing need for secure
data-sharing mechanisms to unlock its full potential in advancing personalized medicine and the
development of Digital Health Twins (DHT). The accumulation of diverse patient data, including
electronic health records, genomics, medical imaging, wearable devices, and lifestyle information,
has paved the way for data-centric health applications. However, harnessing the power of this vast
and varied data requires secure and efficient mechanisms for data sharing among healthcare
providers, researchers, and other stakeholders. Additionally, secure data sharing allows
researchers and developers to train advanced machine learning algorithms and artificial
intelligence models, enabling predictive analytics, precision medicine, and the creation of DHT.

Despite the transformative potential of data-driven healthcare, challenges surrounding data
security, privacy, and interoperability have raised concerns about the widespread adoption of
secure data-sharing practices. Protecting sensitive medical information from unauthorized access,
ensur- ing data integrity, and maintaining patient privacy are crucial for establishing trust among
patients, healthcare providers, and data custodians. Robust security frameworks, encrypted
communication channels, and advanced access controls are essential components in building a secure
data-sharing ecosystem that fosters collaboration while safeguarding patient interests. In the EPI
project¹, we develop a framework to combine data analytics, and health decision support algorithms
to create personalised insights for prevention, management, and intervention to providers and
patients. We start by investigating the current state of art addressing similar challenges and
aiming to support DHT applications and data sharing challenges. First and foremost, we answer the
question RQ1: ”What are the state-of-art technologies and framework approaches for building dynamic
infras- tructures for DHT use cases, and what are the open challenges?” [1]

We design the framework to dynamically provision workflow requests of different health- care use
cases according to set data policy, and network and security requirements. The framework proposed
provides the means to build and run distributed frameworks across healthcare institutions within
the consortium while reasoning about policies and enforcing network rules. The set of pol- icy and
security rules are use case dependant, and hence the question we ask ourselves here: RQ2: ”How do
we automate data sharing reasoning by aggregating and enforcing high-level policies (intent, data
type, users, etc.) and low-level policies (network security, access control, etc) in a DHT use case
environment?” The EPI services run over adaptive computing infrastructures, which provide more
flexibility to accommodate different requests. This thesis proposes the EPI framework to support
these novel health services over programmable infrastructure. The frame- work 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 for- malism 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
1https://enablingpersonalizedinterventions.nl/

running on a typical EPI infrastructure. We evaluated our model according to three relevant param-
eters, performance, feasibility, and aggregation power, and we can conclude that our framework
supports the required data-sharing use cases between the EPI partners. [2]

(More information can be found on the UvA repository website – see link above).