Vaughn R Steele1, J Michael Maurer2, Mohammad R Arbabshirani3, Eric D Claus4, Brandi C Fink5, Vikram Rao4, Vince D Calhoun6, Kent A Kiehl7. 1. Intramural Research Program, Neuroimaging Research Branch, National Institute of Drug Abuse, National Institutes of Health, Baltimore, Maryland. Electronic address: vaughn.r.steele@gmail.com. 2. Mind Research Network & Lovelace Biomedical and Environmental Research Institute, Albuquerque, New Mexico; Department of Psychology, University of New Mexico, Albuquerque, New Mexico. 3. Mind Research Network & Lovelace Biomedical and Environmental Research Institute, Albuquerque, New Mexico; Institute for Advanced Application, Geisinger Health System, Danville, Pennsylvania. 4. Mind Research Network & Lovelace Biomedical and Environmental Research Institute, Albuquerque, New Mexico. 5. Department of Psychiatry and Behavioral Sciences, University of New Mexico, Albuquerque, New Mexico. 6. Mind Research Network & Lovelace Biomedical and Environmental Research Institute, Albuquerque, New Mexico; Department of Psychiatry and Behavioral Sciences, University of New Mexico, Albuquerque, New Mexico; Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, New Mexico; Department of Neurosciences, University of New Mexico, Albuquerque, New Mexico. 7. Mind Research Network & Lovelace Biomedical and Environmental Research Institute, Albuquerque, New Mexico; Department of Psychology, University of New Mexico, Albuquerque, New Mexico; Department of Neurosciences, University of New Mexico, Albuquerque, New Mexico.
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.
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.
Authors: F Gerard Moeller; Joel L Steinberg; Joy M Schmitz; Liangsuo Ma; Shijing Liu; Kimberly L Kjome; Nuvan Rathnayaka; Larry A Kramer; Ponnada A Narayana Journal: Psychiatry Res Date: 2010-02-12 Impact factor: 3.222
Authors: Matthew T Sutherland; Allison J Carroll; Betty Jo Salmeron; Thomas J Ross; L Elliot Hong; Elliot A Stein Journal: Biol Psychiatry Date: 2013-03-15 Impact factor: 13.382
Authors: Hamed Ekhtiari; Hosna Tavakoli; Giovanni Addolorato; Chris Baeken; Antonello Bonci; Salvatore Campanella; Luis Castelo-Branco; Gaëlle Challet-Bouju; Vincent P Clark; Eric Claus; Pinhas N Dannon; Alessandra Del Felice; Tess den Uyl; Marco Diana; Massimo di Giannantonio; John R Fedota; Paul Fitzgerald; Luigi Gallimberti; Marie Grall-Bronnec; Sarah C Herremans; Martin J Herrmann; Asif Jamil; Eman Khedr; Christos Kouimtsidis; Karolina Kozak; Evgeny Krupitsky; Claus Lamm; William V Lechner; Graziella Madeo; Nastaran Malmir; Giovanni Martinotti; William M McDonald; Chiara Montemitro; Ester M Nakamura-Palacios; Mohammad Nasehi; Xavier Noël; Masoud Nosratabadi; Martin Paulus; Mauro Pettorruso; Basant Pradhan; Samir K Praharaj; Haley Rafferty; Gregory Sahlem; Betty Jo Salmeron; Anne Sauvaget; Renée S Schluter; Carmen Sergiou; Alireza Shahbabaie; Christine Sheffer; Primavera A Spagnolo; Vaughn R Steele; Ti-Fei Yuan; Josanne D M van Dongen; Vincent Van Waes; Ganesan Venkatasubramanian; Antonio Verdejo-García; Ilse Verveer; Justine W Welsh; Michael J Wesley; Katie Witkiewitz; Fatemeh Yavari; Mohammad-Reza Zarrindast; Laurie Zawertailo; Xiaochu Zhang; Yoon-Hee Cha; Tony P George; Flavio Frohlich; Anna E Goudriaan; Shirley Fecteau; Stacey B Daughters; Elliot A Stein; Felipe Fregni; Michael A Nitsche; Abraham Zangen; Marom Bikson; Colleen A Hanlon Journal: Neurosci Biobehav Rev Date: 2019-07-02 Impact factor: 8.989
Authors: Scott A Langenecker; Leah R Kling; Natania A Crane; Stephanie M Gorka; Robin Nusslock; Katherine S F Damme; Jessica Weafer; Harriet de Wit; K Luan Phan Journal: Drug Alcohol Depend Date: 2019-11-07 Impact factor: 4.492
Authors: Ashley N Nielsen; Deanna M Barch; Steven E Petersen; Bradley L Schlaggar; Deanna J Greene Journal: Biol Psychiatry Cogn Neurosci Neuroimaging Date: 2019-11-27
Authors: Claire E Wilcox; Christopher C Abbott; Vince D Calhoun Journal: Prog Neuropsychopharmacol Biol Psychiatry Date: 2018-06-25 Impact factor: 5.067