Connecting the Dots: My Research Journey
- Liesbet Peeters
- 7 uur geleden
- 7 minuten om te lezen
When people ask me what I do as a professor, I often smile and say: “It’s complicated.”
Over the years, my research journey has taken me from studying bacteriophages as potential antibiotic alternatives, to genetics in horses, to immunology in multiple sclerosis, and eventually into data science, ethics, and systems change.
At first sight, my work may seem like a collection of very different projects.
However, my research has always been guided by one simple purpose: to use my talents to make the world a better place.
I don’t plan my path in a straight line — I follow where the challenges lead me.
When I see a problem, I feel compelled to understand it and to help address it, focusing my time and energy where I believe I can create the greatest impact.
Still, I often notice that people get confused when they try to understand what I actually do.
It can look chaotic or disconnected from the outside.
But for me, every project I’ve worked on — past, present, and future — is part of one coherent story, connected by the interconnected questions, challenges, and values.
With this blog, I want to share that story.
I hope to take you along in how I think and work, to show how the different projects, problems, and solutions are all linked — at least in my mind — into one evolving narrative.
Theme 1 – Tackling the Technical Challenges of Handling Health Data
The origins of my current research interests go back to around 2016.
At that time, I was working as a postdoctoral researcher at the Biomedical Research Institute (BIOMED) at Hasselt University, studying cytotoxic CD4+ T cells in the context of multiple sclerosis.
While my project focused on immunology, I found myself increasingly frustrated by how difficult it was to access, integrate, and analyse the data I needed to answer my research questions.
The challenges were everywhere
— heterogeneous data,
poor data quality,
privacy constraints,
and limited interoperability between data systems.
That frustration became a turning point.
Drawing on my background in data management and coding, I began improving our data handling processes myself — writing scripts, building tools, and collaborating closely with engineers and computer scientists.
This work marked the initiation of my broader research ideas around Biomedical Data Sciences at Hasselt University.
Our technical focus was clear: developing technical solutions to make complex, high-dimensional, real-world health data usable, reliable, and secure.
At that time, my main research question became: How can we ensure that complex, high-dimensional, real-world health data can lead to maximal impact by making the data FAIR — and by using AI to predict the progression of complex diseases such as multiple sclerosis?
These questions continue to guide much of my work today.
Together with my team, we still focus on the technical frontiers of data wrangling, federated analysis, and trustworthy prediction modeling, while also exploring how these innovations can scale responsibly across healthcare systems.
Highlighted publications related to this theme:
As the use case leader of the use case real-world-evidence of the Flanders AI Research Program, we have the privilege to work with several technical experts across Flanders working on different technical challenges related to real-world-evidence generation. Looking ahead, we are preparing a collaboration with BCTRIMS to apply our methods to the BRANDO dataset. This will be the first AI-driven exploration of BRANDO, offering a valuable opportunity to validate and extend our technical solutions in a new, diverse population. |
Theme 2 – Addressing the Sociotechnical Challenges that Arise when generating Real-World-Evidence
As our technical solutions matured, I began to realize that technology alone was not enough.
The biggest barriers to progress were no longer purely computational — they were human, ethical, and organizational.
Projects could stall for months (or even years) because of unclear governance structures, misaligned expectations, or the absence of shared ethical and legal frameworks.It became clear to me that if we truly wanted to scale real-world evidence generation in healthcare, we needed to build trust, collaboration, and awareness just as deliberately as we built algorithms and models.
This realization shifted my focus toward the sociotechnical dimension of health data science — working on the ethical, legal, and organizational infrastructures that allow innovation to flourish responsibly.
Over time, my group became known for combining both worlds: the technical and the sociological, bridging expertise between all relevant stakeholders and expertise to make real-world evidence work in practice.
Highlighted initiatives related to this theme:
A project I am particularly looking forward to moving forward is MS-Observe, a multi-centric study in Belgium designed to generate real-world evidence on the effectiveness of ofatumumab. |
Theme 3 – Stop Reinventing the Wheel
Then came another realization.
Even when individual use cases worked well, each new project
— including our own
— seemed to start from scratch.
We were constantly reinventing the wheel.
That observation led to a new line of thinking:
What if we could capture and share the knowledge, methods,
and tools needed to set up health data sharing initiatives
— so that others could build faster, smarter, and more collaboratively?
These question became the starting point for what I now call my research line focusing on “foundational elements”
— reusable building blocks and documented roadmaps that enable scale.
The key question became:
How can we move from one successful project to a scalable ecosystem of learning and reuse?
To study this challenge,
we deliberately activate multiple use cases in parallel,
each addressing a different health domain
— for example, multiple sclerosis, cardiovascular disorders, population health management, and remote monitoring.
Although these use cases may appear very different at first sight,
they share a common goal:
to identify the lessons,
patterns,
and tools that can be leveraged and re-used across projects.
The reusable methods and tools we develop are systematically documented, shared, and taught through workshops, symposia, and collaborative training sessions.
Where possible, we make these solutions available in open-source environments,
ensuring that others can adapt and build upon them to accelerate their own initiatives.
Highlighted initiatives related to this theme:
I am excited to share my knowledge and expertise in different projects related to this theme moving forward. With the upcoming implementation of the European Health Data Space, there is a lot of demand for these reflection at different political levels. |
Theme 4 – Networks, Wicked Problems, and Agents of Change
Today, my attention is increasingly drawn to networks
— the living, dynamic systems of people who collaborate to solve wicked problems in healthcare.
Through initiatives like Health Campus Limburg,
I see how interconnected projects
— from digital pathology to remote monitoring
— can reinforce each other when data becomes an enabler rather than an obstacle.
These collaborations have also sparked new questions for me:
How do such networks emerge?
How do they learn, adapt, and create change?
And what makes certain individuals
— the agents of change
— able to inspire and mobilize others toward collective goals?
These questions are now shaping my newest explorations.
I’ve started my podcast,
“The World of Liesbet – How to Become an Agent of Change,”
to learn from these people,
and to understand what drives transformation in complex systems.
I also find inspiration in working with sociologists,
philosophers,
and even artists,
exploring how creativity and reflection can help networks communicate, collaborate, and evolve.
Looking Ahead – Connecting People, Ideas, and Purpose
Looking back,
my research journey has shifted from data to people,
from technology to networks,
from analysis to action.
But the connecting thread has always been the same:
curiosity about how we can use knowledge
— across disciplines, sectors, and perspectives
— to make healthcare systems more resilient, humane, and effective.
Interdisciplinarity can be a lonely path.
Sometimes it takes years before the world catches up with an idea.
But I’ve learned that persistence,
reflection,
and collaboration eventually make the dots connect.
So, if you’re someone who works at the intersection of technology,
health,
policy,
or change
— or if you see yourself as an agent of change
— I’d love to connect.
Because in the end,
data doesn’t change the world.
People do.
Opmerkingen