Page 111 - AIH-2-1

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
A machine learning approach to unravel client

and program-specific effects in opioid treatment
retention

4
2
3
Yinfei Kong *, Erick Guerrero , Jemima Frimpong , Tenie Khachikian ,
1
5
6
Suojin Wang , Thomas D’Aunno , and Daniel Howard 4
1 Department of Information Systems and Decision Sciences, College of Business and Economics,
California State University, Fullerton, CA, United States of America
2 Research to End Health Disparities Corp, I-Lead Institute, Los Angeles, CA, United States of
America
3 New York University Stern School of Business, New York University Abu Dhabi, Saadiyat Island,
Abu Dhabi, United Arab Emirates
4 Department of Psychological and Brain Sciences, College of Arts and Sciences, Texas A&M
University, College Station, TX, United States of America
5 Department of Statistics, College of Arts and Sciences, Texas A&M University, College Station, TX,
United States of America
6 Health Policy and Management, Robert F. Wagner Graduate School of Public Service, New York
University, New York, NY, United States of America

Abstract
*Corresponding author:
Yinfei Kong This study examines the impact of workforce diversity, particularly the presence
(yikong@fullerton.edu) of Black/African American staff, on client retention in opioid use disorder
Citation: Kong Y, Guerrero E, (OUD) treatment, recognizing the historically low retention rates among Black
Frimpong J, et al. A machine and Hispanic populations in such programs. Using a novel machine learning
learning approach to unravel client
and program-specific effects in technique called “causal forest,” we explored the heterogeneous treatment
opioid treatment retention. effects of staff diversity on client retention, aiming to identify strategies that
Artif Intell Health. 2025;2(1):105-113. enhance client retention and improve treatment outcomes. Analyzing data from
doi: 10.36922/aih.3750
four waves of the National Drug Abuse Treatment System Survey spanning the
Received: May 24, 2024 years 2000, 2005, 2014, and 2017 (n = 627), we focus on the relationship between
Revised: September 10, 2024 workforce diversity and retention. The findings revealed diversity-related
variations in retention across 61 out of 627 OUD treatment programs (<10%),
Accepted: October 25, 2024
with potential beneficial effects attenuated by other program characteristics.
Published Online: November 14, These characteristics include programs that are more likely to be private-for-
2024 profit, have lower percentages of Black and Latino clients, lower staff-to-client
Copyright: © 2024 Author(s). ratios, higher proportions of staff with graduate degrees, and lower percentages
This is an Open-Access article of unemployed clients. Our results suggest that workforce diversity alone is
distributed under the terms of the
Creative Commons Attribution insufficient for improving retention. Programs with characteristics linked to
License, permitting distribution, greater retention are better positioned to leverage a diverse workforce to
and reproduction in any medium, enhance retention, offering important implications for policy and program
provided the original work is
properly cited. design to better support Black clients with OUDs.
Publisher’s Note: AccScience
Publishing remains neutral with Keywords: Workforce diversity; Opioid use disorder; Treatment retention; Causal forest;
regard to jurisdictional claims in
published maps and institutional Heterogeneous treatment effect
affiliations.

Volume 2 Issue 1 (2025) 105 doi: 10.36922/aih.3750