Curriculum Vitae
Ashkan Pirmani. Postdoctoral Researcher at KU Leuven and Hasselt University, Belgium. Federated learning and real world data in health research.
01Education
Where I trained
Two PhDs
Electrical engineering, KU Leuven. Biomedical sciences, Hasselt University. Belgium. Defended November 2024.
- Thesis: From Centralized to Federated. The Journey of Data in Healthcare.
- Supervisors: Yves Moreau (KU Leuven), Liesbet M. Peeters (Hasselt University), Niels Hellings (co-supervisor).
MSc, Industrial Engineering
Socio-economic systems. Kharazmi University, Tehran.
MBA, Quality Engineering
Tose'e Institute, Tehran.
02Experience
What I have done
Postdoctoral Researcher
KU Leuven and Hasselt University, Belgium.
- Lead of FLkit, the federated learning toolkit for health and life sciences.
- Developing FLoRank, adaptive structured personalisation for federated models predicting disability progression in multiple sclerosis.
- Continuing work on personalised federated learning for health applications.
- Collaboration on federated frameworks and real world data analysis across multiple international consortia.
Doctoral Researcher
KU Leuven and Hasselt University, Belgium.
- Architect of the three layer federated pipeline for the worldwide multiple sclerosis and COVID-19 data sharing effort, which assembled the largest group of its kind.
- Author of FL4E, introducing the degree of federation.
- First systematic evaluation of personalised federated learning for two year disability progression in multiple sclerosis.
Research Assistant, Decision Support Systems Lab
IranDoc, Iranian Research Institute for Information Science and Technology, Tehran.
- Built a hybrid agent based and system dynamics model for Iran Post, cutting transport costs by 15 per cent.
- Genetic algorithms for hub location, and a simulation backed dashboard for scenario analysis.
03Awards
Recognition
Innovation Mandate, Flanders Innovation and Entrepreneurship
A government grant that funds a researcher to carry their own work into a company. Awarded with Johnson & Johnson Innovative Medicine.
ECTRIMS personal grant for scientific quality
Awarded for FLoRank, presented at ECTRIMS 2025, Barcelona.
Fully funded PhD scholarship
Both doctorates were funded in full, KU Leuven and Hasselt University, through to the defence in 2024.
04Software
What I maintain
Lead developer. Federated learning toolkit for health and life sciences. Community project with more than 29 contributors.
FL4E and FL4E-Analysis
Author. Framework bridging centralised and decentralised analysis for real world health data, with the reference implementations and benchmarks.
05Teaching
Teaching and supervision
Data Science in Healthcare
Teaching member, Healthcare Engineering programme, Hasselt University. Academic years 2022 to 2023 and 2023 to 2024.
Master's thesis supervision
Seven Master's theses in Artificial Intelligence, KU Leuven.
- Predicting hospitalised patients. Federated, pooled and local data compared.
- How data partitioning changes training accuracy.
- Federated boosting in semi-supervised learning.
- Contrastive learning for federated models.
- Personalised models. Architectures and parameter exchange.
- Fine-tuning a global federated model for local performance.
- Early disease detection from shallow whole genome sequencing of cell-free DNA.
06Areas
Areas I work in
Talks and news have their own page: where this work has been presented.
Methods
- Federated learning and federated analysis
- Personalisation under non-identical data across sites
- Privacy-preserving machine learning
- Survival analysis and classification on clinical data
Data
- Real world and observational data
- Registry harmonisation across countries
- FAIR data practice and standardisation
- Low prevalence and rare disease research