M.Sc. Elaine Zaunseder

Phone: +49 6221 54 14508
Room: 1/214
elaine.zaunseder <_at_> uni-heidelberg.de

Predoc

Office address/Post address

Engineering Mathematics and Computing Lab (EMCL)
Interdisciplinary Center for Scientific Computing (IWR)
Im Neuenheimer Feld 205
69120 Heidelberg (Germany)

Short Biography

  • From 2013 - 2017 I did my Bachelor of Science in Business Mathematics at the University of Trier.
  • From 2017 - 2020 I did my Master of Science in Business Mathematics at the Technical Unversity Berlin and worked as research student in the Machine Learning group at Fraunhofer HHI as well as at PwC DigiSpace in Berlin.
  • In September 2020, I joined the Engineering Mathematics and Commputing Lab (EMCL) at IWR, University of Heidelberg. 
  • Since December 2020, I am an associated researcher at HIDSS4Health.
     

Research Interests

  • Mathematical Modeling in metabolic networks
  • Data Mining in Disease Diagnosis 
  • Machine Learning and Deep Learning
  • Explainable AI
  • Newborn screening
     

Research activities

  • Conference presentation on "A digital-tier strategy based on machine learning methods improves specificity in newborn screening for isovaleric aciduria" at the SSIEM 2023 in Jerusalem, August 2023. 
  • Invited talk on "Artificial Intelligence in Medicine" at SDW Workshop "KI - Kann man das Essen?!" in Paris, March 2023. 
  • Conference presentation on "Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria" at the APS 2023 in Kassel, March 2023. 
  • Research stay in the Molecular systems physiology group at University of Galway, Ireland, headed by Prof. Dr. Ines Thiele from September - December 2022. 
  • JIMD Podcast on "Machine learning in newborn screening", June 2022. 
     

Publications

2023
  • E. Zaunseder, U. Mütze, S.F. Garbade, S. Haupt, P. Feyh, G.F. Hoffmann, V. Heuveline, S. Kölker, Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria. Metabolites 2023, 13, 304. https://doi.org/10.3390/metabo13020304.
2022
  • Q. Tran, K. Shpileuskaya, E. Zaunseder, L. Putzar, S. Blankenburg: Comparing the Robustness of Classical and Deep Learning Techniques for Text Classification. 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 2022, pp. 1-10, doi: 10.1109/IJCNN55064.2022.9892242.
  • E. Zaunseder, S. Haupt, U. Mütze, SF. Garbade, S. Kölker, V, Heuveline: Opportunities and Challenges in Machine Learning-based Newborn Screening - A systematic literature review. JIMD Reports, 2022. doi:10.1002/jmd2.12285.
2020
2018