Work

Stimulus Selection Influences Prediction of Individual Phenotypes in Naturalistic Conditions

Year: 2025

Type: article

Abstract: While the use of naturalistic stimuli such as movie clips for understanding individual differences and brain-behaviour relationships attracts increasing interest, the influence of stimulus selection remains largely unclear. By using machine learning to predict individual traits (phenotypes) from brain activity evoked during various movie clips, we show that different movie stimuli can result in distinct prediction performances. In brain regions related to lower-level processing of the stimulus, prediction to a certain degree benefits from stronger synchronisation of brain activity across subjects. By contrast, better predictions in frontoparietal brain regions are mainly associated with larger inter-subject variability. Furthermore, we demonstrate that while movie clips with rich social content in general achieve better predictions, the importance of specific movie features for prediction highly depends on the phenotype under investigation. Overall, our findings underscore the importance of careful stimulus selection and provide novel insights into stimulus selection for phenotype prediction in naturalistic conditions, opening new avenues for future research.

Source: Human Brain Mapping

DOI: 10.1002/hbm.70164

Authors: Xuan Li, Simon B. Eickhoff, Susanne Weis

Institutions: Forschungszentrum Jülich, Heinrich Heine University Düsseldorf

Language: English

Topic: Functional Brain Connectivity Studies

Subfield: Cognitive Neuroscience

Field: Neuroscience

Domain: Life Sciences

Open Access status: gold

Estimated APC paid: $3,520

Funders: European Commission, Deutsche Forschungsgemeinschaft, National Institutes of Health, National Institute of Mental Health