% 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{Kuhles:1047524,
      author       = {Kuhles, Gianna and Hamdan, Sami and Heim, Stefan and
                      Eickhoff, Simon B. and Patil, Kaustubh R. and Camilleri,
                      Julia A. and Weis, Susanne},
      title        = {{P}itfalls in using {ML} to predict cognitive function
                      performance},
      journal      = {Scientific reports},
      volume       = {15},
      number       = {1},
      issn         = {2045-2322},
      address      = {[London]},
      publisher    = {Springer Nature},
      reportid     = {FZJ-2025-04364},
      pages        = {37747},
      year         = {2025},
      note         = {This study was supported by the Deutsche
                      Forschungsgemeinschaft (DFG, GE 2835/2–1, EI
                      816/16 − 1 and EI 816/21 − 1), the National
                      Institute of Mental Health (R01-MH074457), the Helmholtz
                      Portfolio Theme “Supercomputing and Modeling for the Human
                      Brain”, the Virtual Brain Cloud (EU H2020, no. 826421)
                      $\&$ the National Institute on Aging (R01AG067103).},
      abstract     = {Machine learning analyses are widely used for predicting
                      cognitive abilities, yet there are pitfalls that need to be
                      considered during their implementation and interpretation of
                      the results. Hence, the present study aimed at drawing
                      attention to the risks of erroneous conclusions incurred by
                      confounding variables illustrated by a case example
                      predicting executive function (EF) performance by prosodic
                      features. Healthy participants (n = 231) performed
                      speech tasks and EF tests. From 264 prosodic features, we
                      predicted EF performance using 66 variables, controlling for
                      confounding effects of age, sex, and education. A reasonable
                      prediction performance was apparently achieved for EF
                      variables of the Trail Making Test. However, in-depth
                      analyses revealed indications of confound leakage, leading
                      to inflated prediction accuracies, due to a strong
                      relationship between confounds and targets. These findings
                      highlight the need to control confounding variables in ML
                      pipelines and caution against potential pitfalls in ML
                      predictions.},
      cin          = {INM-7 / INM-1},
      ddc          = {600},
      cid          = {I:(DE-Juel1)INM-7-20090406 / I:(DE-Juel1)INM-1-20090406},
      pnm          = {5251 - Multilevel Brain Organization and Variability
                      (POF4-525) / 5252 - Brain Dysfunction and Plasticity
                      (POF4-525)},
      pid          = {G:(DE-HGF)POF4-5251 / G:(DE-HGF)POF4-5252},
      typ          = {PUB:(DE-HGF)16},
      doi          = {10.1038/s41598-025-24325-9},
      url          = {https://juser.fz-juelich.de/record/1047524},
}