Azadeh Kushki

This study identifies unique functional connectivity patterns in autism associated with five sensory processing phenotypes using machine learning.

This study uses deep learning to predict internalizing problems from brain structure in youth, finding good performance in neurodevelopmental conditions but sub-optimal in the general population.

The paper examines multisensory integration network (MSN) functional connectivity in neurodevelopmental disorders and finds that sensory characteristics, not diagnoses, drive the observed neural patterns.

The paper examines age-related changes in brain structure and function across two neurodiverse datasets, finding differences linked to demographic and clinical factors.

This study identifies 135 ASD-associated protein-coding genes using whole-genome sequencing data from 11,312 individuals and exome sequencing from over 18,000 trios, with a false discovery rate of 80%.