Yu Zhang

This study benchmarks foundation models for resting-state fMRI time series in cognitive aging, finding mixed results on their utility for cognitive assessment and prediction.

This study identifies early functional connectivity changes in MDD patients treated with antidepressants or placebo, revealing common and distinct treatment effects.

This study uses machine learning and transcriptomic integration to identify brain network and molecular signatures associated with amyloid-beta and tau in Alzheimer's disease.

This study maps TMS-induced discomfort across the whole brain using TMS-fMRI and shows it accounts for 12-25% of TMS-evoked responses.

This paper evaluates rsfMRI foundation models for identifying robust neural patterns predicting cognitive intervention outcomes in aging, showing improved performance over conventional methods.

The paper uses deep learning to identify brain-behavior dimensions and biotypes in youth with ADHD and anxiety disorders, revealing distinct symptom profiles and brain development patterns.

The paper develops and validates a Facial Signature Score (FSS) from facial dynamics during cognitive interventions to predict executive function response in older adults.

This study identifies a functional connectivity signature, ARC, that distinguishes superagers from AD patients and predicts cognitive decline and amyloid-beta accumulation.

This paper identifies two neurophysiology-informed symptom dimensions in MDD using contrastive functional connectivity analysis of fMRI data.

CRISPR-GEM predicts optimal CRISPR target genes by modeling gene regulatory networks using MLPs trained on differential gene expression data.

This study identifies two transdiagnostic subtypes in ADHD and ASD using contrastive graph machine learning on brain connectivity patterns from resting-state fMRI.

The paper identifies dementia subtypes based on neuropsychiatric symptom-linked brain connectivity patterns using neuroimaging data.

The paper identifies two EEG connectivity dimensions linked to ASD symptoms using contrastive learning and sparse canonical correlation analysis in 392 ASD samples.