Researcher in federated machine learning for oncology and medical imaging at Justus-Liebig-Universität Gießen
2
papers here
2
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet scored: the catalog holds only two 2026 arXiv papers and no complete publication record is available. This axis would measure overall research output volume, such as total peer-reviewed publications and cumulative productivity across venues.
Impact—
Not yet scored: no citation counts, h-index or citation-window data were provided. This axis would measure scholarly influence, including uptake of the federated learning methods and citations across the clinical AI community.
Focus0/100
Scored 0/100: the bibliometric field distribution splits evenly, 0.5 to medical informatics (federated machine learning in oncology) and 0.5 to medical image analysis / federated learning. Concentration is minimal by this measure, but the two halves are methodologically contiguous — both apply federated learning to clinical data — so the spread reads as parallel application tracks (pancreatic-cancer frameworks versus chest radiograph methods) rather than unrelated topic drift.
Collaboration55/100
Scored 55/100, from 15 distinct co-authors across the two catalogued 2026 papers — a moderately sized, team-based footprint rather than solo output. Anne-Christin Hauschild is the most frequently repeated name in the record, with Amirreza Aleyasin, Tim Beissbarth and Elisabeth Hessmann also in the frequent co-author list. FedDRAW is first-authored while the FAIrPaCT update lists her mid-author, consistent with hands-on methods contribution inside established multi-institutional consortia.
Activity—
Not yet scored: the record covers only 2026 publications, so a recent output rate cannot be computed. This axis would measure ongoing productivity, such as papers per year and continuity of preprint releases over time.
Reproducibility38/100
Mean readiness score of 38 across the 2 scored papers. FedDRAW rates medium — its aggregation scheme is benchmarked over 12 scenarios, though the reported advantage over FedAvg is not pairwise-significant; the FAIrPaCT strategy update rates low, reporting operational lessons without federated model performance results. Overall, methodological detail exists, but complete replication materials are not yet evidenced in the reviewed record.
Research summary
Maryam Moradpour is a researcher at Justus-Liebig-Universität Gießen working on federated machine learning for clinical data, with a record that splits evenly (0.5/0.5) between medical informatics — federated ML in oncology — and medical image analysis. The Evolve catalog holds two 2026 arXiv papers. The first-authored FedDRAW proposes dual-reputation annealing for federated aggregation weighting, transitioning weights from a size prior through similarity to uniform; it achieves the best average rank across 12 heterogeneous scenarios for multi-institutional chest radiograph classification, though its edge over FedAvg is not pairwise-significant — a carefully benchmarked, honestly reported contribution to the non-IID problem. The FAIrPaCT strategy update, a middle-author contribution, documents operational lessons and oBDS-based data harmonization for a federated framework optimizing pancreatic cancer treatment, with federated model performance results still pending. Working with 15 distinct co-authors — most frequently Anne-Christin Hauschild, alongside Tim Beissbarth, Elisabeth Hessmann and others — she operates in consortium-style medical AI research, scoring 55/100 on collaboration. Reproducibility readiness averages 38 across the two scored papers (FedDRAW medium, FAIrPaCT low). With output, impact and activity axes not yet scored, this is an early-stage but coherent profile: a methods-oriented contributor pushing privacy-preserving learning from hospital data infrastructures toward deployable imaging models.
Collaboration pattern
Collaboration is consortium-style: 15 distinct co-authors across just two 2026 papers, giving a moderate collaboration score of 55. Anne-Christin Hauschild is the most frequent partner, appearing twice in the recurring co-author list; Amirreza Aleyasin, Nils H. Beyer, Lisa Fricke, Jonas Hügel, Anh-Tien Nguyen, Youngjun Park, Sophia Rheinländer, Tim Beissbarth, Elisabeth Hessmann and Martin Middeke round out the network. First authorship on FedDRAW alongside mid-author placement on FAIrPaCT suggests hands-on methodological roles within multi-institutional teams.
Research keywords
Highlights
FedDRAW: annealed dual-reputation weighting leads 12 heterogeneous FL scenarios
FAIrPaCT strategy update: operational lessons for federated pancreatic-cancer AI
Timeline
- 2026First-authored FedDRAW, introducing annealed dual-reputation aggregation weighting for multi-institutional chest radiograph classification (arXiv).
- 2026Co-authored the FAIrPaCT strategy update, reporting operational lessons from the federated artificial intelligence framework for optimizing pancreatic cancer treatment (arXiv).
- 2026Both catalogued outputs appear in the same year, splitting evenly between oncology informatics and medical image analysis within federated learning.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Radar scores and co-author counts come from an automated bibliometric snapshot; no citation counts, h-index or total publication record was provided.
- Evidence base is two 2026 arXiv preprints reviewed by Evolve; peer-review status and journal placement are not reflected in the data.
- Output, impact and activity axes are unscored pending sufficient bibliometric data.
- Profile is name-resolved from public bibliographic data via ORCID 0009-0001-0906-5842; biographical details are not verified.