% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Nieto:1038496,
      author       = {Nieto, Nicolas and Eickhoff, Simon and Jung, Christian and
                      Reuter, Martin and Diers, Kersten and Kelm, Malte and
                      Lichtenberg, Artur and Raimondo, Federico and Patil,
                      Kaustubh},
      title        = {{I}mpact of {L}eakage on {D}ata {H}armonization in
                      {M}achine {L}earning {P}ipelines in {C}lass {I}mbalance
                      {A}cross {S}ites},
      journal      = {Arxiv},
      reportid     = {FZJ-2025-01491},
      year         = {2024},
      abstract     = {Machine learning (ML) models benefit from large datasets.
                      Collecting data in biomedical domains is costly and
                      challenging, hence, combining datasets has become a common
                      practice. However, datasets obtained under different
                      conditions could present undesired site-specific
                      variability. Data harmonization methods aim to remove
                      site-specific variance while retaining biologically relevant
                      information. This study evaluates the effectiveness of
                      popularly used ComBat-based methods for harmonizing data in
                      scenarios where the class balance is not equal across sites.
                      We find that these methods struggle with data leakage
                      issues. To overcome this problem, we propose a novel
                      approach PrettYharmonize, designed to harmonize data by
                      pretending the target labels. We validate our approach using
                      controlled datasets designed to benchmark the utility of
                      harmonization. Finally, using real-world MRI and clinical
                      data, we compare leakage-prone methods with PrettYharmonize
                      and show that it achieves comparable performance while
                      avoiding data leakage, particularly in
                      site-target-dependence scenarios.},
      cin          = {INM-7},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {5254 - Neuroscientific Data Analytics and AI (POF4-525)},
      pid          = {G:(DE-HGF)POF4-5254},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.34734/FZJ-2025-01491},
      url          = {https://juser.fz-juelich.de/record/1038496},
}