Mathilde Antoniades

The paper identifies two neuroanatomical subtypes of callous-unemotional traits using machine learning in a community sample of youth, showing distinct clinical and environmental profiles.

The paper identifies cellular and neurochemical signatures associated with cerebral blood flow alterations in schizophrenia and clinical high-risk states using combined neuroimaging and transcriptomic data.

The paper examines sex differences in brain-age-gap estimates using neuroimaging data from the Human Connectome Project, finding sex-specific patterns in regional brain ageing and predictors of global brainAGE.

This study compares machine learning algorithms for predicting brain age in schizophrenia, finding that most linear methods perform similarly but OLS regression is less accurate, leading to variability in brainPAD estimates.