Curriculum vitae
Ashkan Pirmani
Applied machine learning · Real world evidence · Health data held in many places
- Now
- Postdoctoral researcher, KU Leuven and Hasselt University. Innovation Mandate, a Flemish government grant, with Johnson & Johnson Innovative Medicine as industry partner.
- PhD
- Dual PhD, 2024. Electrical engineering at KU Leuven, biomedical sciences at Hasselt University.
- Evidence
- 45.5% more patient records in a worldwide COVID-19 study, through the route I built
- 26,246 patients in my study of models that adapt to each country
- 30+ countries whose registries and consortia I have worked with
On this page
ashkan-pirmani.github.io · github.com/ashkan-pirmani · linkedin.com/in/ashkan-p-3b8a8896
Experience
Postdoctoral researcher
KU Leuven, Department of Electrical Engineering, and Hasselt University, Data Science Institute. Belgium.
- Lead FLkit, an open guide for starting studies across centers that keep their own data. It went from an internal need to a public resource, designed to help teams get started on their own.
- Wrote the Innovation Mandate proposal and defended it. Awarded in 2026, with Johnson & Johnson Innovative Medicine as industry partner.
- Took the disability progression study to publication as first author, in npj Digital Medicine (2025).
- Designed FLoRank, a way for each site to keep a small private part of a shared model. Prototype. Awarded an ECTRIMS personal grant in 2025.
- Retired FL4E and wrote up why it was not reused, for Medical Informatics Europe 2026.
- Organizing team of OHDSI Europe 2025. Invited talks at Roche, the Flower community and the North American Society of Artificial Intelligence in Multiple Sclerosis.
- Coordinate with data holders, clinicians and legal teams in more than thirty countries. Supervise master's students.
Doctoral researcher
KU Leuven and Hasselt University.
- Built the federated route into the worldwide multiple sclerosis and COVID-19 data collection, so registries that could not send data could still take part. It added 3,527 records. First author, JMIR Medical Informatics (2023).
- Built FL4E, a framework for federated studies, and the degree of federation. First author, JMIR Formative Research (2024).
- Ran the first systematic comparison of personalized federated learning for two year disability progression in multiple sclerosis, on 26,246 patients.
- Taught in the Data Science in Healthcare course at Hasselt University, and began supervising master's theses in 2021.
- Presented at ECTRIMS and Medical Informatics Europe in 2024.
Research assistant, Decision Support Systems Lab
IranDoc, Iranian Research Institute for Information Science and Technology, Tehran.
- Agent based and system dynamics simulation of the national parcel network, searched with a genetic algorithm for a better set of hubs. Best scenario: 15% lower projected transport cost, in simulation.
- Delivered as a decision support dashboard and a policy analysis for senior executives.
Education
Dual PhD
Electrical engineering, KU Leuven. Biomedical sciences, Hasselt University. Defended November 2024.
- Thesis: From Centralized to Federated. The Journey of Data in Healthcare.
- Supervisors: Yves Moreau (KU Leuven), Liesbet M. Peeters (Hasselt University). Co-supervisor: Niels Hellings.
MSc, Industrial Engineering
Socio-economic systems. Kharazmi University, Tehran.
MBA, Quality Engineering
Tose'e Institute, Tehran.
Recognition
Innovation Mandate
Flanders Innovation and Entrepreneurship, with Johnson & Johnson Innovative Medicine as the industry partner. Drug safety research on health records and insurance claims.
ECTRIMS personal grant for scientific quality
For FLoRank, at ECTRIMS 2025, Barcelona.
Fully funded PhD scholarship
KU Leuven and Hasselt University, through to the defense in 2024.
Selected contributions
45.5% more records
Designed and built the federated route into a worldwide COVID-19 and multiple sclerosis study. The four registries counted in the paper added 3,527 records to the 7,757 already collected, and a fifth joined later. Analyses of the combined data set informed worldwide COVID-19 advice for people with multiple sclerosis.
Personalized to each country
Personalizing a federated model to each country improved AUC-PR by 31% over the same method without personalization, and ROC-AUC by 3.8% over one model trained on all records pooled together. The best model uses AdaptiveDualBranchNet, an architecture I designed. Simulated federation on records from 26,246 patients and 146 centers. First author, in a collaboration of 73.
The degree of federation
Each center chooses whether its records leave. On a public benchmark, letting half the centers send their records kept 97.5% of the fully federated score.
A public resource, maintained
FLkit: 39 pages, eleven ways in by role, seven worked project stories, 29 contributors. Supported by ELIXIR Belgium. Its use has not been evaluated yet.
Teaching and supervision
Data Science in Healthcare
Teaching member, Healthcare Engineering program, Hasselt University. Two academic years.
Master's thesis supervision
Seven master's theses in artificial intelligence, KU Leuven.
- Predicting admission to care. Federated, pooled and local data compared.
- How splitting the data changes what the model learns.
- Federated boosting in semi-supervised learning.
- Contrastive learning for federated models.
- Personalized 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.
Methods and systems
Methods
- Federated learning and federated analysis
- Personalization when sites hold different patients
- Privacy-preserving machine learning
- Survival analysis and classification on clinical data
Data
- Real world and observational data
- Cohort building and phenotype definition across registries
- Registry harmonization and data quality
- Data feasibility: whether a question can be answered at all
- OMOP common data model, through OHDSI
- FAIR data practice
Tools
- Python, PyTorch, Flower, scikit-learn, pandas
- R and SQL
- Docker, Kubernetes, continuous integration
Networks
- OHDSI Belgium, and the organizing team of OHDSI Europe 2025
- ELIXIR Belgium
- The MSBase registry and the MS Data Alliance
Selected publications
All 22 entries are on the publications page. Talks, including Roche, Flower, ECTRIMS and Medical Informatics Europe, are on the talks page.
Let's talk.
If your question depends on health data that can't simply be put in one place, I probably want to hear about it.