% 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{Omidvarnia:1029132,
      author       = {Omidvarnia, Amir and Sasse, Leonard and Larabi, Daouia I.
                      and Raimondo, Federico and Hoffstaedter, Felix and Kasper,
                      Jan and Dukart, Jürgen and Petersen, Marvin and Cheng,
                      Bastian and Thomalla, Götz and Eickhoff, Simon B. and
                      Patil, Kaustubh R.},
      title        = {{I}ndividual characteristics outperform resting-state
                      f{MRI} for the prediction of behavioral phenotypes},
      journal      = {Communications biology},
      volume       = {7},
      number       = {1},
      issn         = {2399-3642},
      address      = {London},
      publisher    = {Springer Nature},
      reportid     = {FZJ-2024-04988},
      pages        = {771},
      year         = {2024},
      abstract     = {In this study, we aimed to compare imaging-based features
                      of brain function, measured by resting-state fMRI (rsfMRI),
                      with individual characteristics such as age, gender, and
                      total intracranial volume to predict behavioral measures. We
                      developed a machine learning framework based on rsfMRI
                      features in a dataset of 20,000 healthy individuals from the
                      UK Biobank, focusing on temporal complexity and functional
                      connectivity measures. Our analysis across four behavioral
                      phenotypes revealed that both temporal complexity and
                      functional connectivity measures provide comparable
                      predictive performance. However, individual characteristics
                      consistently outperformed rsfMRI features in predictive
                      accuracy, particularly in analyses involving smaller sample
                      sizes. Integrating rsfMRI features with demographic data
                      sometimes enhanced predictive outcomes. The efficacy of
                      different predictive modeling techniques and the choice of
                      brain parcellation atlas were also examined, showing no
                      significant influence on the results. To summarize, while
                      individual characteristics are superior to rsfMRI in
                      predicting behavioral phenotypes, rsfMRI still conveys
                      additional predictive value in the context of machine
                      learning, such as investigating the role of specific brain
                      regions in behavioral phenotypes.},
      cin          = {INM-7},
      ddc          = {570},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {5251 - Multilevel Brain Organization and Variability
                      (POF4-525)},
      pid          = {G:(DE-HGF)POF4-5251},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {38926486},
      UT           = {WOS:001255406300001},
      doi          = {10.1038/s42003-024-06438-5},
      url          = {https://juser.fz-juelich.de/record/1029132},
}