TY  - JOUR
AU  - Wu, Jianxiao
AU  - Li, Jingwei
AU  - Eickhoff, Simon B.
AU  - Scheinost, Dustin
AU  - Genon, Sarah
TI  - The challenges and prospects of brain-based prediction of behaviour
JO  - Nature human behaviour
VL  - 7
IS  - 8
SN  - 2397-3374
CY  - London
PB  - Nature Research
M1  - FZJ-2023-03484
SP  - 1255 - 1264
PY  - 2023
N1  - This work was supported by the Deutsche Forschungsgemeinschaft (GE 2835/2–1, EI 816/ 4–1), the Helmholtz Portfolio Theme ‘Supercomputing and Modelling for the Human Brain’ and the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement no. 720270 (HBP SGA1) and grant agreement no. 785907 (HBP SGA2).
AB  - Relating individual brain patterns to behaviour is fundamental in systemneuroscience. Recently, the predictive modelling approach has becomeincreasingly popular, largely due to the recent availability of large opendatasets and access to computational resources. This means that we can usemachine learning models and interindividual differences at the brain levelrepresented by neuroimaging features to predict interindividual differencesin behavioural measures. By doing so, we could identify biomarkers andneural correlates in a data-driven fashion. Nevertheless, this budding fieldof neuroimaging-based predictive modelling is facing issues that may limitits potential applications. Here we review these existing challenges, as wellas those that we anticipate as the field develops. We focus on the impactsof these challenges on brain-based predictions. We suggest potentialsolutions to address the resolvable challenges, while keeping in mind thatsome general and conceptual limitations may also underlie the predictivemodelling approach.
LB  - PUB:(DE-HGF)16
C6  - 37524932
UR  - <Go to ISI:>//WOS:001040224100003
DO  - DOI:10.1038/s41562-023-01670-1
UR  - https://juser.fz-juelich.de/record/1014929
ER  -