YSPH Biostatistics Seminar-"A Statistical AI Method for Learning Directed Connectomes and Uncovering Subpopulation Differences in Brain Organization"

Note: BIS 526 students are required to attend in person. Others are invited to attend in person but may also attend via zoom.

Speaker- Ying Guo, Ph.D.

Title- "A Statistical AI Method for Learning Directed Connectomes and Uncovering Subpopulation

Differences in Brain Organization"

Abstract

In recent years, connectome-based research has become a central focus in neuroscience, offering essential insights into brain organization and advancing predictive modeling of cognitive, behavioral, and mental health outcomes. While most existing approaches focus on undirected brain connectivity, they overlook the directionality and causal influences between brain regions. To address this limitation, we propose a statistical AI method for learning directed brain connectomes from neuroimaging data. Our approach integrates principled statistical modeling with deep learning to infer sparse, interpretable directed connectivity graphs that characterize latent causal interactions across the brain. At the same time, the method learns low-dimensional graph embeddings optimized for downstream prediction tasks, including demographic attributes and clinical phenotypes. The proposed method uncovers whole-brain directed connectivity patterns and reveals novel subpopulation-specific connectomic differences, highlighting its potential to advance both mechanistic understanding and predictive modeling in neuroscience