Mary Louise Phillips

This study analyzes structural brain network changes in bipolar disorder, finding widespread connectivity disruptions linked to illness severity and medication use.

This study examines longitudinal stability of mood-related resting-state networks in youth with bipolar-I/II disorder, finding reduced within-person stability in BD compared to healthy controls.

This paper develops a deep autoencoder for detecting brain morphology anomalies in bipolar disorder using the StratiBip dataset, finding greater and more heterogeneous deviations in BD patients.

The paper examines hippocampal and amygdala subfield volumes in OCD patients and healthy controls, finding differences based on medication status.

This paper uses deep learning on pre-treatment reward processing fMRI and clinical data to predict antidepressant outcomes, achieving up to 37% variance explained and remission prediction with NNT 2-4.

ComBat, an empirical Bayes location-and-scale model from genomics, removes additive and multiplicative scanner effects from regional cortical thickness across 11 scanners while preserving age associations.