Csaba Orbán

97% of 184 high-impact biomedical AI studies compare cross-validated models with tests assuming fold independence; in 69% of re-analyzable studies a significant comparison does not survive correction.

This study examines age-related changes in fMRI signatures of autonomic physiology, finding slower respiratory responses and faster cardiac responses with aging, with a notable turning point after age 60.

This study compares brain age models and direct models for predicting Alzheimer's Disease outcomes, finding that direct models perform better despite brain age models having larger training data.

The paper shows longer scans improve prediction accuracy in brain-wide association studies while reducing costs, with 30-minute scans being the most cost-effective.

The paper examines how stable and changing brain network features predict cognitive development in adolescents using rs-fMRI and cognitive data from the ABCD Study.

The paper develops homotopic local-global parcellations of the human cerebral cortex using resting-state and task-fMRI, showing improved homogeneity and lateralization compared to existing parcellations.

The paper develops individual-specific areal-level parcellations using a Bayesian model and shows they improve functional connectivity prediction of behavior compared to group-level parcellations.

This study develops a spatially-heterogeneous circuit model to simulate brain activity dynamics, showing that anatomical and functional gradients are essential for generating realistic static and dynamic functional connectivity patterns.

The paper identifies shared and unique brain network features that predict cognition, personality, and mental health in children using resting and task-state functional connectivity.

This study shows that global signal fluctuation and functional connectivity in resting-state fMRI decrease throughout the day, contrary to expectations based on circadian arousal patterns.

The paper identifies three latent components of psychopathology linked to whole-brain resting-state functional connectivity across healthy and psychiatric populations.

This study finds that global signal regression enhances the association between resting-state functional connectivity and behavioral measures in young healthy adults.

This study introduces a hierarchical Bayesian model to estimate individual-specific cortical networks and shows that their topography can predict human behavior with moderate accuracy.

This study investigates how LSD affects brain activity during music listening, finding increased cortical and subcortical activity linked to timbral complexity and enhanced emotional responses.