Machine learning vs addiction therapists: A pilot study predicting alcohol dependence treatment outcome from patient data in behavior therapy with adjunctive medication.

Journal: Journal of substance abuse treatment
PMID:

Abstract

BACKGROUND AND OBJECTIVES: Clinical staff providing addiction treatment predict patient outcome poorly. Prognoses based on linear statistics are rarely replicated. Addiction is a complex non-linear behavior. Incorporating non-linear models, Machine Learning (ML) has successfully predicted treatment outcome when applied in other areas of medicine. Using identical assessment data across the two groups, this study compares the accuracy of ML models versus clinical staff to predict alcohol dependence treatment outcome in behavior therapy using patient data only.

Authors

  • Martyn Symons
    Telethon Kids Institute, University of Western Australia, Perth.
  • Gerald F X Feeney
    Alcohol and Drug Assessment Unit, Princess Alexandra Hospital, Wooloongabba, Brisbane, Queensland 4102, Australia; Centre for Youth Substance Abuse Research, The University of Queensland, Upland Road, St Lucia, Brisbane, Queensland 4072, Australia.
  • Marcus R Gallagher
    School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, Queensland 4072, Australia.
  • Ross McD Young
    Alcohol and Drug Assessment Unit, Princess Alexandra Hospital, Wooloongabba, Brisbane, Queensland 4102, Australia; Faculty of Health, Queensland University of Technology, Kelvin Grove, Brisbane, Queensland 4059, Australia.
  • Jason P Connor
    Alcohol and Drug Assessment Unit, Princess Alexandra Hospital, Wooloongabba, Brisbane, Queensland 4102, Australia; Discipline of Psychiatry, The University of Queensland, K Floor, Mental Health Centre, Royal Brisbane and Women's Hospital, Herston, Brisbane, Queensland 4029, Australia; Centre for Youth Substance Abuse Research, The University of Queensland, Upland Road, St Lucia, Brisbane, Queensland 4072, Australia. Electronic address: Jason.Connor@uq.edu.au.