|
Affiliation
|
The Department of Psychiatry (Yip, Potenza, Carroll), the Child Study Center (Yip, Scheinost, Potenza), the Department of Radiology and Biomedical Imaging (Scheinost), and the Department of Neuroscience (Potenza), Yale School of Medicine, New Haven, Conn.; and the Connecticut Mental Health Center, New Haven, Conn. (Potenza). |
|
Abstract
|
OBJECTIVE:: The authors sought to identify a brain-based predictor of cocaine abstinence by using connectome-based predictive modeling (CPM), a recently developed machine learning approach. CPM is a predictive tool and a method of identifying networks that underlie specific behaviors ("neural fingerprints").
METHODS:: Fifty-three individuals participated in neuroimaging protocols at the start of treatment for cocaine use disorder, and again at the end of 12 weeks of treatment. CPM with leave-one-out cross-validation was conducted to identify pretreatment networks that predicted abstinence (percent cocaine-negative urine samples during treatment). Networks were applied to posttreatment functional MRI data to assess changes over time and ability to predict abstinence during follow-up. The predictive ability of identified networks was then tested in a separate, heterogeneous sample of individuals who underwent scanning before treatment for cocaine use disorder (N=45).
RESULTS:: CPM predicted abstinence during treatment, as indicated by a significant correspondence between predicted and actual abstinence values (r=0.42, df=52). Identified networks included connections within and between canonical networks implicated in cognitive/executive control (frontoparietal, medial frontal) and in reward responsiveness (subcortical, salience, motor/sensory). Connectivity strength did not change with treatment, and strength at posttreatment assessment also significantly predicted abstinence during follow-up (r=0.34, df=39). Network strength in the independent sample predicted treatment response with 64% accuracy by itself and 71% accuracy when combined with baseline cocaine use.
CONCLUSIONS:: These data demonstrate that individual differences in large-scale neural networks contribute to variability in treatment outcomes for cocaine use disorder, and they identify specific abstinence networks that may be targeted in novel interventions.
Language: en |