Ashkan Pirmani
Hi there! šš¼
I love turning data into stories that matter
, especially in fields where sensitive information demands thoughtful
handling and innovative
solutions. Iām driven by the challenge of making data
useful while navigating the ethical, legal, and practical complexities of working with it.
Most recently, I completed a double PhD
in Belgium š§šŖ at KU Leuven
and Hasselt University
, where I worked on making real-world data (RWD) more accessible
and actionable
to derive meaningful insights from it.
But let me tell you, working with data isnāt as straightforward as it sounds. It often feels like trying to solve a jigsaw puzzle
, but this isnāt your typical puzzle. Imagine the pieces are scattered
across different locations, some of them locked away
in drawers labeled āprivateā, and others so rare they might as well be one-of-a-kind. Now, add a rule: youāre not allowed
to move any pieces from their original location
. Thatās what working with data in fields like rare diseases or low-prevalence conditions feels like. Every single piece matters
, but putting them together is far from simple.
Youād think the solution would be straightforward: gather all the data into one place and get to work.
But in reality
, centralizing data is often out of the question. Privacy concerns, ethical dilemmas, data ownership rules, and layers of administrative hurdles stand in the way. Itās like trying to build the puzzle while someone keeps reminding you, āYou canāt touch the piecesā.
So, how do we solve
this? Thatās where Federated Learning (FL) comes in.
Think of FL as a way to build the puzzle
together
, but with a twist:everyone
works on their piecesseparately
, sharing justenough hints
to complete the bigger picture. With FL, machine learning (ML) models can be trained ondecentralized
data without ever moving the data itself.Collaborating
while keeping whatās personalsafe
andsecure
. This approach doesnāt just safeguard privacy; it opens doors. Organizations canwork together
without worrying about sensitive information leaving their walls, unlocking insights that were once impossible to achieve. My research focused on designing and implementing FL techniques to tackle exactly these kinds of challenges, bringing together innovation and practicality to make this futuristic idea a reality.
Why I Do What I Do šØš»āš»
The world is full of complex problems, and I believe the best solutions come from collaboration. But collaboration isnāt always easy, especially when sensitive data is involved. Thatās why I love combining technical innovation with practical problem-solving to create tools that make working together possibleāeven when the odds are stacked against us. Whether itās improving global data-sharing pipelines or designing tools for personalized predictions, I focus on creating solutions that are inclusive, accessible, and meaningful.
Here are some highlights of my work (check out more details on the projects page):
- Built a federated, research-agnostic data analysis pipeline for the Global Data Sharing Initiative on COVID-19 and MS, contributing to one of the most comprehensive datasets for these conditions. šš
- Developed a new federated learning approach that enabled ML models to adapt to local datasets, significantly improving predictions like disability progression in MS. š
- Introduced the concept of a ādegree of federationā, offering organizations a flexible way to balance privacy, practicality, and collaboration. šÆ
- Created FL4E (Federated Learning For Everyone), a framework bridging centralized and decentralized data analysis for real-world applications. šš
- Pioneered a study that predicted disability progression in MS for over 26,000 patients, using one of the largest routine clinical datasets availableāall while keeping data secure. š§ āØ
Letās Connect! š
Iām always excited to collaborate with people who share my passion for turning data into insights that make a difference. If youāre working on something where real-world data and AI/ML could play a roleāwhether itās in healthcare, finance, or beyondāIād love to chat and explore ways we can team up to create meaningful impact. š
news
Nov 29, 2024 | š DrĀ² (Doctor Squared) ā Yes, you heard it right! Click on me for more detailed info! š” |
---|---|
Sep 18, 2024 | š§ ECTRIMS 2024
|
Aug 20, 2024 | š” MIE 2024
|