Clear Search sequence regions


  • adult (1)
  • behavior (1)
  • brain (5)
  • female (1)
  • fmri (7)
  • humans (1)
  • phenotypes (4)
  • Sizes of these terms reflect their relevance to your search.

    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. © 2024. The Author(s).

    Citation

    Amir Omidvarnia, Leonard Sasse, Daouia I Larabi, Federico Raimondo, Felix Hoffstaedter, Jan Kasper, Jürgen Dukart, Marvin Petersen, Bastian Cheng, Götz Thomalla, Simon B Eickhoff, Kaustubh R Patil. Individual characteristics outperform resting-state fMRI for the prediction of behavioral phenotypes. Communications biology. 2024 Jun 26;7(1):771

    Expand section icon Mesh Tags


    PMID: 38926486

    View Full Text