% 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{Wiersch:1019408,
      author       = {Wiersch, Lisa and Friedrich, Patrick and Hamdan, Sami and
                      Komeyer, Vera and Hoffstaedter, Felix and Patil, Kaustubh
                      and Eickhoff, Simon and Weis, Susanne},
      title        = {{S}ex classification from functional brain connectivity:
                      {G}eneralization to multiple datasets},
      reportid     = {FZJ-2023-05368},
      year         = {2023},
      abstract     = {Machine learning (ML) approaches are increasingly being
                      applied to neuroimaging data. Studies in neuroscience
                      typically have to rely on a limited set of training data
                      which may impair the generalizability of ML models. However,
                      it is still unclear which kind of training sample is best
                      suited to optimize generalization performance. In the
                      present study, we systematically investigated the
                      generalization performance of sex classification models
                      trained on the parcelwise connectivity profile of either
                      single samples or a compound sample containing data from
                      four different datasets. Generalization performance was
                      quantified in terms of mean across-sample classification
                      accuracy and spatial consistency of accurately classifying
                      parcels. Our results indicate that generalization
                      performance of pwCs trained on single dataset samples is
                      dependent on the specific test samples. Certain datasets
                      seem to “match” in the sense that classifiers trained on
                      a sample from one dataset achieved a high accuracy when
                      tested on the respected other one and vice versa. The pwC
                      trained on the compound sample demonstrated overall highest
                      generalization performance for all test samples, including
                      one derived from a dataset not included in building the
                      training samples. Thus, our results indicate that a big and
                      heterogenous training sample comprising data of multiple
                      datasets is best suited to achieve generalizable results.},
      cin          = {INM-7},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {5251 - Multilevel Brain Organization and Variability
                      (POF4-525) / DFG project 491111487 -
                      Open-Access-Publikationskosten / 2022 - 2024 /
                      Forschungszentrum Jülich (OAPKFZJ) (491111487)},
      pid          = {G:(DE-HGF)POF4-5251 / G:(GEPRIS)491111487},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.1101/2023.08.30.555495},
      url          = {https://juser.fz-juelich.de/record/1019408},
}