Machine Learning of Functional Magnetic Resonance Imaging Network Connectivity Predicts Substance Abuse Treatment Completion

Vaughn R. Steele, J. Michael Maurer, Mohammad R. Arbabshirani, Eric D. Claus, Brandi C. Fink, Vikram Rao, Vince Daniel Calhoun, Kent A. Kiehl

Research output: Contribution to journalArticle

Abstract

Background: Successfully treating illicit drug use has become paramount, yet elusive. Devising specialized treatment interventions could increase positive outcomes, but it is necessary to identify risk factors of poor long-term outcomes to develop specialized, efficacious treatments. We investigated whether functional network connectivity (FNC) measures were predictive of substance abuse treatment completion using machine learning pattern classification of functional magnetic resonance imaging data. Methods: Treatment-seeking stimulant- or heroin-dependent incarcerated participants (n = 139; 89 women) volunteered for a 12-week substance abuse treatment program. Participants performed a response inhibition Go/NoGo functional magnetic resonance imaging task prior to onset of the substance abuse treatment. We tested whether FNC related to the anterior cingulate cortex would be predictive of those who would or would not complete a 12-week substance abuse treatment program. Results: Machine learning pattern classification models using FNC between networks incorporating the anterior cingulate cortex, striatum, and insula predicted which individuals would (sensitivity: 81.31%) or would not (specificity: 78.13%) complete substance abuse treatment. FNC analyses predicted treatment completion above and beyond other clinical assessment measures, including age, sex, IQ, years of substance use, psychopathy, anxiety and depressive symptomatology, and motivation for change. Conclusions: Aberrant neural network connections predicted substance abuse treatment outcomes, which could illuminate new targets for developing interventions designed to reduce or eliminate substance use while facilitating long-term outcomes. This work represents the first application of machine-learning models of FNC analyses of functional magnetic resonance imaging data to predict which substance abusers would or would not complete treatment.

Original languageEnglish (US)
JournalBiological Psychiatry: Cognitive Neuroscience and Neuroimaging
DOIs
StateAccepted/In press - 2017
Externally publishedYes

Fingerprint

Substance-Related Disorders
Magnetic Resonance Imaging
Therapeutics
Gyrus Cinguli
Machine Learning
Heroin
Street Drugs
Motivation
Anxiety

Keywords

  • Drug treatment
  • Error processing
  • FMRI
  • ICA
  • Machine learning
  • Prediction

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Clinical Neurology
  • Cognitive Neuroscience
  • Biological Psychiatry

Cite this

Machine Learning of Functional Magnetic Resonance Imaging Network Connectivity Predicts Substance Abuse Treatment Completion. / Steele, Vaughn R.; Maurer, J. Michael; Arbabshirani, Mohammad R.; Claus, Eric D.; Fink, Brandi C.; Rao, Vikram; Calhoun, Vince Daniel; Kiehl, Kent A.

In: Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 2017.

Research output: Contribution to journalArticle

Steele, Vaughn R. ; Maurer, J. Michael ; Arbabshirani, Mohammad R. ; Claus, Eric D. ; Fink, Brandi C. ; Rao, Vikram ; Calhoun, Vince Daniel ; Kiehl, Kent A. / Machine Learning of Functional Magnetic Resonance Imaging Network Connectivity Predicts Substance Abuse Treatment Completion. In: Biological Psychiatry: Cognitive Neuroscience and Neuroimaging. 2017.
@article{5fd9e976fc2a4460a9b71dbe096ee57c,
title = "Machine Learning of Functional Magnetic Resonance Imaging Network Connectivity Predicts Substance Abuse Treatment Completion",
abstract = "Background: Successfully treating illicit drug use has become paramount, yet elusive. Devising specialized treatment interventions could increase positive outcomes, but it is necessary to identify risk factors of poor long-term outcomes to develop specialized, efficacious treatments. We investigated whether functional network connectivity (FNC) measures were predictive of substance abuse treatment completion using machine learning pattern classification of functional magnetic resonance imaging data. Methods: Treatment-seeking stimulant- or heroin-dependent incarcerated participants (n = 139; 89 women) volunteered for a 12-week substance abuse treatment program. Participants performed a response inhibition Go/NoGo functional magnetic resonance imaging task prior to onset of the substance abuse treatment. We tested whether FNC related to the anterior cingulate cortex would be predictive of those who would or would not complete a 12-week substance abuse treatment program. Results: Machine learning pattern classification models using FNC between networks incorporating the anterior cingulate cortex, striatum, and insula predicted which individuals would (sensitivity: 81.31{\%}) or would not (specificity: 78.13{\%}) complete substance abuse treatment. FNC analyses predicted treatment completion above and beyond other clinical assessment measures, including age, sex, IQ, years of substance use, psychopathy, anxiety and depressive symptomatology, and motivation for change. Conclusions: Aberrant neural network connections predicted substance abuse treatment outcomes, which could illuminate new targets for developing interventions designed to reduce or eliminate substance use while facilitating long-term outcomes. This work represents the first application of machine-learning models of FNC analyses of functional magnetic resonance imaging data to predict which substance abusers would or would not complete treatment.",
keywords = "Drug treatment, Error processing, FMRI, ICA, Machine learning, Prediction",
author = "Steele, {Vaughn R.} and Maurer, {J. Michael} and Arbabshirani, {Mohammad R.} and Claus, {Eric D.} and Fink, {Brandi C.} and Vikram Rao and Calhoun, {Vince Daniel} and Kiehl, {Kent A.}",
year = "2017",
doi = "10.1016/j.bpsc.2017.07.003",
language = "English (US)",
journal = "Biological Psychiatry: Cognitive Neuroscience and Neuroimaging",
issn = "2451-9022",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Machine Learning of Functional Magnetic Resonance Imaging Network Connectivity Predicts Substance Abuse Treatment Completion

AU - Steele, Vaughn R.

AU - Maurer, J. Michael

AU - Arbabshirani, Mohammad R.

AU - Claus, Eric D.

AU - Fink, Brandi C.

AU - Rao, Vikram

AU - Calhoun, Vince Daniel

AU - Kiehl, Kent A.

PY - 2017

Y1 - 2017

N2 - Background: Successfully treating illicit drug use has become paramount, yet elusive. Devising specialized treatment interventions could increase positive outcomes, but it is necessary to identify risk factors of poor long-term outcomes to develop specialized, efficacious treatments. We investigated whether functional network connectivity (FNC) measures were predictive of substance abuse treatment completion using machine learning pattern classification of functional magnetic resonance imaging data. Methods: Treatment-seeking stimulant- or heroin-dependent incarcerated participants (n = 139; 89 women) volunteered for a 12-week substance abuse treatment program. Participants performed a response inhibition Go/NoGo functional magnetic resonance imaging task prior to onset of the substance abuse treatment. We tested whether FNC related to the anterior cingulate cortex would be predictive of those who would or would not complete a 12-week substance abuse treatment program. Results: Machine learning pattern classification models using FNC between networks incorporating the anterior cingulate cortex, striatum, and insula predicted which individuals would (sensitivity: 81.31%) or would not (specificity: 78.13%) complete substance abuse treatment. FNC analyses predicted treatment completion above and beyond other clinical assessment measures, including age, sex, IQ, years of substance use, psychopathy, anxiety and depressive symptomatology, and motivation for change. Conclusions: Aberrant neural network connections predicted substance abuse treatment outcomes, which could illuminate new targets for developing interventions designed to reduce or eliminate substance use while facilitating long-term outcomes. This work represents the first application of machine-learning models of FNC analyses of functional magnetic resonance imaging data to predict which substance abusers would or would not complete treatment.

AB - Background: Successfully treating illicit drug use has become paramount, yet elusive. Devising specialized treatment interventions could increase positive outcomes, but it is necessary to identify risk factors of poor long-term outcomes to develop specialized, efficacious treatments. We investigated whether functional network connectivity (FNC) measures were predictive of substance abuse treatment completion using machine learning pattern classification of functional magnetic resonance imaging data. Methods: Treatment-seeking stimulant- or heroin-dependent incarcerated participants (n = 139; 89 women) volunteered for a 12-week substance abuse treatment program. Participants performed a response inhibition Go/NoGo functional magnetic resonance imaging task prior to onset of the substance abuse treatment. We tested whether FNC related to the anterior cingulate cortex would be predictive of those who would or would not complete a 12-week substance abuse treatment program. Results: Machine learning pattern classification models using FNC between networks incorporating the anterior cingulate cortex, striatum, and insula predicted which individuals would (sensitivity: 81.31%) or would not (specificity: 78.13%) complete substance abuse treatment. FNC analyses predicted treatment completion above and beyond other clinical assessment measures, including age, sex, IQ, years of substance use, psychopathy, anxiety and depressive symptomatology, and motivation for change. Conclusions: Aberrant neural network connections predicted substance abuse treatment outcomes, which could illuminate new targets for developing interventions designed to reduce or eliminate substance use while facilitating long-term outcomes. This work represents the first application of machine-learning models of FNC analyses of functional magnetic resonance imaging data to predict which substance abusers would or would not complete treatment.

KW - Drug treatment

KW - Error processing

KW - FMRI

KW - ICA

KW - Machine learning

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=85029232850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029232850&partnerID=8YFLogxK

U2 - 10.1016/j.bpsc.2017.07.003

DO - 10.1016/j.bpsc.2017.07.003

M3 - Article

C2 - 29529409

AN - SCOPUS:85029232850

JO - Biological Psychiatry: Cognitive Neuroscience and Neuroimaging

JF - Biological Psychiatry: Cognitive Neuroscience and Neuroimaging

SN - 2451-9022

ER -