A Machine Learning Approach to Identify Socio-Economic Factors Responsible for Patients Dropping out of Substance Abuse Treatment

Prateek Gautam¹ and Pradeep Singh^2,

¹Marquette High School, Chesterfield, MO, USA

²Department of Mathematics, Southeast Missouri State University, Cape Girardeau, MO, USA

Cite this paper

Prateek Gautam and Pradeep Singh. A Machine Learning Approach to Identify Socio-Economic Factors Responsible for Patients Dropping out of Substance Abuse Treatment. American Journal of Public Health Research. 2020; 8(5):140-146. doi: 10.12691/AJPHR-8-5-2

Abstract

In recent years, the subject of substance abuse has drawn considerable attention from researchers and policymakers alike. Researchers have been utilizing the wealth of patient level data available from various agencies to develop prediction models for the relationship between socio-economic factors and substance abuse issues. According to the Substance Abuse and Mental Health Services Administration (SAMHSA), in 2017, 26% of patients admitted to treatment facilities drop out prematurely, which is significant when considering that roughly 1.5 million people are admitted to these treatment facilities every year, thereby revealing the need for an analysis to identify variables associated with such a large number of people not completing treatment. This study applies Multiple Logistic Regression (MLRM) as well as Random Forest Classification (RF) model to determine significant socio-economic factors responsible for patients prematurely dropping out of substance abuse treatment for opioid misuse. A MLRM has its limitations when the dataset has a large number of categorical variables; machine learning methods such as RF have proven more effective and accurate when dealing with such data. Patient level data from the Treatment Episode Dataset - Discharge (TEDS-D 2017) was analyzed and the models were compared using the Area Under the Curve (AUC) operating characteristic. The MLRM was found to have an AUC of .68 while the RF model had an AUC of .89, thereby demonstrating the advantage of machine learning methods. The factors deemed significant from the RF model can provide healthcare professionals as well as administrative officials with the necessary information to help address the issue of patients prematurely dropping out of opioid misuse treatment.

Keywords

opioid abuse, random forest, machine learning, TEDS-D, treatment dropout

Copyright

This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

References

[1]	“Key Substance Use and Mental Health Indicators in the United States: Results from the 2018 National Survey on Drug Use and Health.” Substance Abuse and Mental Health Services Administration, SAMHSA, 2018, www.samhsa.gov/data/sites/default/files/cbhsq- reports/NSDUHNationalFindingsReport2018/NSDUHNationalFin dingsReport2018.pdf.
[2]	Patrick, Stephen W., et al. “Implementation of Prescription Drug Monitoring Programs Associated With Reductions In Opioid-Related Death Rates.” Health Affairs, vol. 35, no. 7, July 2016, pp. 1324-1332.
[3]	“SAMHSA Strategic Plan – FY2019-FY2023.” Substance Abuse and Mental Health Services Administration, SAMHSA, 2018, www.samhsa.gov/sites/default/files/samhsa_strategic_plan_fy19-fy23_final-508.pdf.
[4]	Wright ER, Kooreman HE, Greene MS, Chambers RA, Banerjee A, Wilson J. The iatrogenic epidemic of prescription drug abuse: county-level determinants of opioid availability and abuse. Drug Alcohol Depend. 2014; 138: 209-215.
[5]	Alex Hollingsworth & Christopher J. Ruhm & Kosali Simon, 2017. "Macroeconomic conditions and opioid abuse," Journal of Health Economics.
[6]	Brown E, Wehby GL. Economic Conditions and Drug and Opioid Overdose Deaths. Med Care Res Rev. 2019; 76(4): 462-477.
[7]	Acion, Laura & Kelmansky, Diana & Laan, Mark & Sahker, Ethan & Jones, Deshauna & Arndt, Stephan. (2017). Use of a machine learning framework to predict substance use disorder treatment success. PLOS ONE. 12. e0175383.
[8]	Stahler, Gerald J., and Jeremy Mennis. “Treatment Outcome Disparities for Opioid Users: Are There Racial and Ethnic Differences in Treatment Completion across Large US Metropolitan Areas?” Drug and Alcohol Dependence, vol. 190, Sept. 2018, pp. 170-178.
[9]	Godinet, Meripa & McGlinn, Lindsey & Nelson, Dawna & Vakalahi, Halaevalu. (2019). Factors Contributing to Substance Misuse Treatment Completion among Native Hawaiians, Other Pacific Islanders, and Asian Americans. Substance Use & Misuse. 55. 1-14.
[10]	Sharma D. Improving the art, craft and science of economic credit risk scorecards using random forests: Why credit scorers and economists should use random forests. Academy of Banking Studies Journal, 11(1): 93-116, 2012.