Individualized relapse prediction: Personality measures and striatal and insular activity during reward-processing robustly predict relapse

Highlights • We did fMRI on abstinent methamphetamine-dependent individuals and determined who relapsed. • We used a robust classification technique called random forest to generate individual-level predictions. • The random forest model was consistent with a standard linear model. • Our models perf...

Full description

Saved in:
Bibliographic Details
Published in:Drug and alcohol dependence 2015-07, Vol.152, p.93-101
Main Authors: Gowin, Joshua L, Ball, Tali M, Wittmann, Marc, Tapert, Susan F, Paulus, Martin P
Format: Article
Language:English
Subjects:
Adult
Amphetamine-Related Disorders - physiopathology
Amphetamine-Related Disorders - psychology
Amphetamine-Related Disorders - rehabilitation
Cerebral Cortex - physiopathology
Female
Functional Laterality
Humans
Likelihood Functions
Magnetic Resonance Imaging
Male
Methamphetamine
Methamphetamine dependence
Models, Neurological
Neostriatum - physiopathology
Neuroimaging
Neuropsychological Tests
Personality
Personality Tests
Predictive Value of Tests
Psychiatry
Recurrence
Relapse
Reward
Risk prediction
Striatum
Substance-Related Disorders - physiopathology
Substance-Related Disorders - psychology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • We did fMRI on abstinent methamphetamine-dependent individuals and determined who relapsed. • We used a robust classification technique called random forest to generate individual-level predictions. • The random forest model was consistent with a standard linear model. • Our models performed well, with specificity, sensitivity and ROC AUC around 0.7. • Our results suggest that neuroimaging can be developed to predict individual clinical outcomes.
ISSN:0376-8716
1879-0046
DOI:10.1016/j.drugalcdep.2015.04.018