Literature DB >> 33570148

Machine learning-based outcome prediction and novel hypotheses generation for substance use disorder treatment.

Murtaza Nasir1, Nichalin S Summerfield1, Asil Oztekin1, Margaret Knight2, Leland K Ackerson3, Stephanie Carreiro4.   

Abstract

OBJECTIVE: Substance use disorder is a critical public health issue. Discovering the synergies among factors impacting treatment program success can help governments and treatment facilities develop effective policies. In this work, we propose a novel data analytics approach using machine learning models to discover interaction effects that might be neglected by traditional hypothesis-generating approaches.
MATERIALS AND METHODS: A patient-episode-level substance use treatment discharge dataset and a Federal Bureau of Investigation crime dataset were joined using core-based statistical area codes. Random forests, artificial neural networks, and extreme gradient boosting were applied with a nested cross-validation methodology. Interaction effects were identified based on the machine learning model with the best performance. These interaction effects were analyzed and tested using traditional logistic regression models on unseen data.
RESULTS: In predicting patient completion of a treatment program, extreme gradient boosting performed the best with an area under the curve of 89.31%. Based on our procedure, 73 interaction effects were identified. Among these, 14 were tested using traditional logistic regression models where 12 were statistically significant (P<.05).
CONCLUSIONS: We identified new interaction effects among the length of stay, frequency of substance use, changes in self-help group attendance frequency, and other factors. This work provides insights into the interactions between factors impacting treatment completion. Further traditional statistical analysis can be employed by practitioners and policy makers to test the effects discovered by our novel machine learning approach.
© The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  healthcare analytics; hypothesis generation; machine learning; substance-related disorders; treatment outcome

Mesh:

Year:  2021        PMID: 33570148      PMCID: PMC8661425          DOI: 10.1093/jamia/ocaa350

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  9 in total

1.  Does retention matter? Treatment duration and improvement in drug use.

Authors:  Zhiwei Zhang; Peter D Friedmann; Dean R Gerstein
Journal:  Addiction       Date:  2003-05       Impact factor: 6.526

Review 2.  Drop-out from addiction treatment: a systematic review of risk factors.

Authors:  Hanne H Brorson; Espen Ajo Arnevik; Kim Rand-Hendriksen; Fanny Duckert
Journal:  Clin Psychol Rev       Date:  2013-07-31

Review 3.  A comparison of goodness-of-fit tests for the logistic regression model.

Authors:  D W Hosmer; T Hosmer; S Le Cessie; S Lemeshow
Journal:  Stat Med       Date:  1997-05-15       Impact factor: 2.373

4.  Residential and outpatient treatment completion for substance use disorders in the U.S.: Moderation analysis by demographics and drug of choice.

Authors:  Gerald J Stahler; Jeremy Mennis; Joseph P DuCette
Journal:  Addict Behav       Date:  2016-02-17       Impact factor: 3.913

5.  Online Searching and Social Media to Detect Alcohol Use Risk at Population Scale.

Authors:  Elissa R Weitzman; Kara M Magane; Po-Hua Chen; Hadi Amiri; Timothy S Naimi; Lauren E Wisk
Journal:  Am J Prev Med       Date:  2019-12-02       Impact factor: 5.043

6.  Analysis of substance use and its outcomes by machine learning I. Childhood evaluation of liability to substance use disorder.

Authors:  Yankang Jing; Ziheng Hu; Peihao Fan; Ying Xue; Lirong Wang; Ralph E Tarter; Levent Kirisci; Junmei Wang; Michael Vanyukov; Xiang-Qun Xie
Journal:  Drug Alcohol Depend       Date:  2019-10-22       Impact factor: 4.492

7.  What could the program have done differently? A qualitative examination of reasons for leaving outpatient treatment.

Authors:  Alexandre B Laudet; Virginia Stanick; Brian Sands
Journal:  J Subst Abuse Treat       Date:  2009-03-31

8.  Probing for Sparse and Fast Variable Selection with Model-Based Boosting.

Authors:  Janek Thomas; Tobias Hepp; Andreas Mayr; Bernd Bischl
Journal:  Comput Math Methods Med       Date:  2017-07-31       Impact factor: 2.238

9.  On classifying sepsis heterogeneity in the ICU: insight using machine learning.

Authors:  Zina M Ibrahim; Honghan Wu; Ahmed Hamoud; Lukas Stappen; Richard J B Dobson; Andrea Agarossi
Journal:  J Am Med Inform Assoc       Date:  2020-03-01       Impact factor: 4.497

  9 in total
  1 in total

1.  Use of machine learning to examine disparities in completion of substance use disorder treatment.

Authors:  Aaron Baird; Yichen Cheng; Yusen Xia
Journal:  PLoS One       Date:  2022-09-23       Impact factor: 3.752

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.