An Interpretable and Predictive Connectivity-Based Neural Signature for Chronic Cannabis Use

• Type of Material: Article
• Authors: Kaustubh R Kulkarni, Icahn School of Medicine at Mount Sinai; Matthew Schafer, Icahn School of Medicine at Mount Sinai; Laura A Berner, Icahn School of Medicine at Mount Sinai; Vincenzo G Fiore, Icahn School of Medicine at Mount Sinai; Matt Heflin, Icahn School of Medicine at Mount Sinai; Kent Hutchison, University of Colorado Boulder; Vince Calhoun, Emory University; Francesca Filbey, The University of Texas at Dallas; Gaurav Pandey, Icahn School of Medicine at Mount Sinai; Daneila Schiller, Icahn School of Medicine at Mount Sinai; Xiaosi Gu, Icahn School of Medicine at Mount Sinai
• Language: English
• Date: 2023-03-01
• Publisher: Elsevier Inc
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2022 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.
• License: Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1016/j.bpsc.2022.04.009
• Title of Journal or Parent Work: Biological Psychiatry: Cognitive Neuroscience and Neuroimaging
• Volume: 8
• Issue: 3
• Start Page: 320
• End Page: 330
• Keywords: Brain; Craving; Marijuana Abuse; Biomarker; Cannabis; Substance use; Humans; Interpretability; Machine learning; Neuroimaging

Abstract

Background: Cannabis is one of the most widely used substances in the world, with usage trending upward in recent years. However, although the psychiatric burden associated with maladaptive cannabis use has been well established, reliable and interpretable biomarkers associated with chronic use remain elusive. In this study, we combine large-scale functional magnetic resonance imaging with machine learning and network analysis and develop an interpretable decoding model that offers both accurate prediction and novel insights into chronic cannabis use. Methods: Chronic cannabis users (n = 166) and nonusing healthy control subjects (n = 124) completed a cue-elicited craving task during functional magnetic resonance imaging. Linear machine learning methods were used to classify individuals into chronic users and nonusers based on whole-brain functional connectivity. Network analysis was used to identify the most predictive regions and communities. Results: We obtained high (∼80% out-of-sample) accuracy across 4 different classification models, demonstrating that task-evoked connectivity can successfully differentiate chronic cannabis users from nonusers. We also identified key predictive regions implicating motor, sensory, attention, and craving-related areas, as well as a core set of brain networks that contributed to successful classification. The most predictive networks also strongly correlated with cannabis craving within the chronic user group. Conclusions: This novel approach produced a neural signature of chronic cannabis use that is both accurate in terms of out-of-sample prediction and interpretable in terms of predictive networks and their relation to cannabis craving.