Timezone: »

Advanced Methods for Connectome-Based Predictive Modeling of Human Intelligence: A Novel Approach Based on Individual Differences in Cortical Topography
Evan Anderson · Anuj Nayak · Pablo Robles-Granda · Lav Varshney · Been Kim · Aron K Barbey
Event URL: https://openreview.net/forum?id=VJ1KoBzl3ja »

Individual differences in human intelligence can be modeled and predicted from in vivo neurobiological connectivity. Many established modeling frameworks for predicting intelligence, however, discard higher-order information about individual differences in brain network topology, and show only moderate performance when generalized to make predictions in out-of-sample subjects. In this paper, we propose that connectome-based predictive modeling, a common predictive modeling framework for neuroscience data, can be productively modified to incorporate information about brain network topology and individual differences via the incorporation of bagged decision trees and the network based statistic. These modifications produce a novel predictive modeling framework that leverages individual differences in cortical tractography to generate accurate regression predictions of intelligence. Network topology-based feature selection provides for natively interpretable networks as input features, increasing the model's explainability. Investigating the proposed modeling framework's efficacy, we find that advanced connectome-based predictive modeling generates neuroscience predictions that account for a significantly greater proportion of variance in intelligence than previously established methods, advancing our scientific understanding of the network architecture that underlies human intelligence.

Author Information

Evan Anderson (University of Illinois, Urbana Champaign)
Anuj Nayak (University of Illinois, Urbana-Champaign)
Pablo Robles-Granda (University of Illinois at Urbana-Champaign)
Lav Varshney (Salesforce Research)
Been Kim (Google Brain)
Aron K Barbey (University of Illinois at Urbana-Champaign)

Aron K. Barbey is Professor of Psychology, Neuroscience, and Bioengineering at the University of Illinois at Urbana-Champaign. He is chair of the Intelligence Systems Research Theme, leader of the Intelligence, Learning, and Plasticity Initiative, and director of the Decision Neuroscience Laboratory at the Beckman Institute for Advanced Science and Technology. He received a Ph.D. in Psychology from Emory University in 2007 and completed a research fellowship in Cognitive Neuroscience at the National Institutes of Health in 2011. Professor Barbey’s research investigates the neural mechanisms of human intelligence and decision making, with particular emphasis on enhancing these functions through cognitive neuroscience, physical fitness, and nutritional intervention. He has won more than $25 million in federal and private research grants since joining the University of Illinois in 2011, receiving support from the National Institutes of Health (NIH), the NIH BRAIN Initiative, the research division of the United States Director of National Intelligence (IARPA), the Department of Defense (DARPA), the National Science Foundation (NSF), and private industry. He has received multiple academic achievement awards, is co-editor of The Cambridge Handbook of Intelligence and Cognitive Neuroscience, and serves on the editorial board of Intelligence, Thinking & Reasoning, and NeuroImage.

More from the Same Authors