{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:22:26Z","timestamp":1791393746959,"version":"4.3.3"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T00:00:00Z","timestamp":1663891200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>The objective of this work is to examine disparities in the completion of substance use disorder treatment in the U.S. Our data is from the Treatment Episode Dataset Discharge (TEDS-D) datasets from the U.S. Substance Abuse and Mental Health Services Administration (SAMHSA) for 2017\u20132019. We apply a two-stage virtual twins model (random forest + decision tree) where, in the first stage (random forest), we determine differences in treatment completion probability associated with race\/ethnicity, income source, no co-occurrence of mental health disorders, gender (biological), no health insurance, veteran status, age, and primary substance (alcohol or opioid). In the second stage (decision tree), we identify subgroups associated with probability differences, where such subgroups are more or less likely to complete treatment. We find the subgroups most likely to complete substance use disorder treatment, when the subgroup represents more than 1% of the sample, are those with no mental health condition co-occurrence (4.8% more likely when discharged from an ambulatory outpatient treatment program, representing 62% of the sample; and 10% more likely for one of the more specifically defined subgroups representing 10% of the sample), an income source of job-related wages\/salary (4.3% more likely when not having used in the 30 days primary to discharge and when primary substance is not alcohol only, representing 28% of the sample), and white non-Hispanics (2.7% more likely when discharged from residential long-term treatment, representing 9% of the sample). Important implications are that: 1) those without a co-occurring mental health condition are the most likely to complete treatment, 2) those with job related wages or income are more likely to complete treatment, and 3) racial\/ethnicity disparities persist in favor of white non-Hispanic individuals seeking to complete treatment. Thus, additional resources may be needed to combat such disparities.<\/jats:p>","DOI":"10.1371\/journal.pone.0275054","type":"journal-article","created":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T18:16:27Z","timestamp":1663956987000},"page":"e0275054","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":24,"title":["Use of machine learning to examine disparities in completion of substance use disorder treatment"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5620-2926","authenticated-orcid":true,"given":"Aaron","family":"Baird","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusen","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,9,23]]},"reference":[{"key":"pone.0275054.ref001","article-title":"Key Substance Use and Mental Health Indicators in the United States: Results from the 2020 National Survey on Drug Use and Health.","author":"D Richesson","year":"2021","journal-title":"Substance Abuse and Mental Health Services Administration (SAMHSA)"},{"issue":"10","key":"pone.0275054.ref002","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1001\/jama.1982.03320350027022","article-title":"Is treatment for substance abuse effective?","volume":"247","author":"AT McLellan","year":"1982","journal-title":"JAMA"},{"issue":"6","key":"pone.0275054.ref003","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1176\/appi.ps.201300249","article-title":"Substance abuse intensive outpatient programs: assessing the evidence.","volume":"65","author":"D McCarty","year":"2014","journal-title":"Psychiatric Services"},{"key":"pone.0275054.ref004","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1146\/annurev-publhealth-032315-021439","article-title":"Racial and ethnic disparities in the quality of health care.","volume":"37","author":"K Fiscella","year":"2016","journal-title":"Annual review of public health."},{"key":"pone.0275054.ref005","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.jsat.2015.12.007","article-title":"Racial and ethnic disparities in outpatient substance use disorder treatment episode completion for different substances","volume":"63","author":"J Mennis","year":"2016","journal-title":"Journal of Substance Abuse Treatment"},{"key":"pone.0275054.ref006","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.addbeh.2016.02.030","article-title":"Residential and outpatient treatment completion for substance use disorders in the US: Moderation analysis by demographics and drug of choice.","volume":"58","author":"GJ Stahler","year":"2016","journal-title":"Addictive Behaviors."},{"key":"pone.0275054.ref007","doi-asserted-by":"crossref","first-page":"108437","DOI":"10.1016\/j.jsat.2021.108437","article-title":"Substance use among women who are pregnant: Examining treatment completion by race and ethnicity","volume":"131","author":"Z. Suntai","year":"2021","journal-title":"Journal of Substance Abuse Treatment"},{"key":"pone.0275054.ref008","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.addbeh.2015.04.006","article-title":"Evaluating racial disparity in referral source and successful completion of substance abuse treatment.","volume":"48","author":"E Sahker","year":"2015","journal-title":"Addictive behaviors."},{"issue":"4","key":"pone.0275054.ref009","doi-asserted-by":"crossref","first-page":"e0175383","DOI":"10.1371\/journal.pone.0175383","article-title":"Use of a machine learning framework to predict substance use disorder treatment success.","volume":"12","author":"L Acion","year":"2017","journal-title":"PloS ONE."},{"issue":"1","key":"pone.0275054.ref010","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1177\/0044118X20960635","article-title":"Racial and ethnic disparities, referral source and attrition from outpatient substance use disorder treatment among adolescents in the United States.","volume":"54","author":"PL Marotta","year":"2022","journal-title":"Youth & Society."},{"issue":"9","key":"pone.0275054.ref011","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1001\/jamapsychiatry.2019.0876","article-title":"Buprenorphine treatment divide by race\/ethnicity and payment","volume":"76","author":"PA Lagisetty","year":"2019","journal-title":"JAMA psychiatry"},{"key":"pone.0275054.ref012","article-title":"Using Machine Learning to Advance Disparities Research: Subgroup Analyses of Access to Opioid Treatment.","author":"Y Kong","year":"2021","journal-title":"Health Services Research."},{"issue":"5","key":"pone.0275054.ref013","doi-asserted-by":"crossref","first-page":"e205734","DOI":"10.1001\/jamanetworkopen.2020.5734","article-title":"Assessment of racial and ethnic disparities in the use of medication to treat opioid use disorder among pregnant women in Massachusetts","volume":"3","author":"DM Schiff","year":"2020","journal-title":"JAMA Network Open"},{"issue":"4","key":"pone.0275054.ref014","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1111\/1475-6773.12031","article-title":"Disparities in Completion of Substance Abuse Treatment between and within Racial and Ethnic Groups.","volume":"48","author":"EG Guerrero","year":"2013","journal-title":"Health Services Research."},{"issue":"1","key":"pone.0275054.ref015","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1377\/hlthaff.2011.0983","article-title":"Blacks and Hispanics are less likely than whites to complete addiction treatment, largely due to socioeconomic factors.","volume":"32","author":"B Saloner","year":"2013","journal-title":"Health affairs."},{"key":"pone.0275054.ref016","unstructured":"Racial\/ethnic differences in substance use, substance use disorders, and substance use treatment utilization among people aged 12 or older (2015\u20132019) Rockville, MD: Center for Behavioral Health Statistics and Quality, 2021 PEP21-07-01-001)."},{"key":"pone.0275054.ref017","unstructured":"2019 National Healthcare Quality and Disparities Report. Rockville, MD: Agency for Healthcare Research and Quality, 2020."},{"issue":"5","key":"pone.0275054.ref018","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.amepre.2005.12.008","article-title":"Gender and age disparities for smoking-cessation treatment","volume":"30","author":"MB Steinberg","year":"2006","journal-title":"American journal of preventive medicine"},{"issue":"11","key":"pone.0275054.ref019","doi-asserted-by":"crossref","first-page":"1962","DOI":"10.2105\/AJPH.2009.167346","article-title":"Mental health disparities","volume":"99","author":"MA Safran","year":"2009","journal-title":"American Journal of Public Health"},{"issue":"11","key":"pone.0275054.ref020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11920-018-0969-9","article-title":"Social determinants of mental health: where we are and where we need to go.","volume":"20","author":"M Alegr\u00eda","year":"2018","journal-title":"Current psychiatry reports."},{"issue":"13","key":"pone.0275054.ref021","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1001\/jama.2017.18391","article-title":"Big data and machine learning in health care","volume":"319","author":"AL Beam","year":"2018","journal-title":"JAMA"},{"issue":"14","key":"pone.0275054.ref022","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"A Rajkomar","year":"2019","journal-title":"New England Journal of Medicine"},{"issue":"4","key":"pone.0275054.ref023","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1097\/YCO.0000000000000611","article-title":"Machine-learning approaches to substance-abuse research: emerging trends and their implications.","volume":"33","author":"E Barenholtz","year":"2020","journal-title":"Current Opinion in Psychiatry"},{"issue":"6","key":"pone.0275054.ref024","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1093\/jamia\/ocaa350","article-title":"Machine learning\u2013based outcome prediction and novel hypotheses generation for substance use disorder treatment","volume":"28","author":"M Nasir","year":"2021","journal-title":"Journal of the American Medical Informatics Association"},{"issue":"3","key":"pone.0275054.ref025","doi-asserted-by":"crossref","first-page":"e190968","DOI":"10.1001\/jamanetworkopen.2019.0968","article-title":"Evaluation of machine-learning algorithms for predicting opioid overdose risk among medicare beneficiaries with opioid prescriptions","volume":"2","author":"W-H Lo-Ciganic","year":"2019","journal-title":"JAMA Network Open"},{"key":"pone.0275054.ref026","doi-asserted-by":"crossref","first-page":"100836","DOI":"10.1016\/j.ssmph.2021.100836","article-title":"A scoping review on the use of machine learning in research on social determinants of health: Trends and research prospects.","volume":"15","author":"S Kino","year":"2021","journal-title":"SSM-population health."},{"key":"pone.0275054.ref027","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1146\/annurev.soc.012809.102529","article-title":"Socioeconomic disparities in health behaviors","volume":"36","author":"FC Pampel","year":"2010","journal-title":"Annual Review of Sociology"},{"issue":"12","key":"pone.0275054.ref028","doi-asserted-by":"crossref","first-page":"e0145455","DOI":"10.1371\/journal.pone.0145455","article-title":"The relationship between health literacy and health disparities: a systematic review.","volume":"10","author":"S Mantwill","year":"2015","journal-title":"PLoS One"},{"issue":"11","key":"pone.0275054.ref029","doi-asserted-by":"crossref","first-page":"5171","DOI":"10.1287\/mnsc.2020.3698","article-title":"The role of decision support systems in attenuating racial biases in healthcare delivery.","volume":"66","author":"KK Ganju","year":"2020","journal-title":"Management Science."},{"key":"pone.0275054.ref030","doi-asserted-by":"crossref","first-page":"S1","DOI":"10.1097\/MLR.0000000000000220","article-title":"Promoting a new research agenda: Health disparities research at the intersection of disability, race, and ethnicity.","volume":"52","author":"W Horner-Johnson","year":"2014","journal-title":"Medical Care."},{"issue":"523","key":"pone.0275054.ref031","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume":"113","author":"S Wager","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"pone.0275054.ref032","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.ssmph.2017.11.008","article-title":"Machine learning approaches to the social determinants of health in the health and retirement study.","volume":"4","author":"B Seligman","year":"2018","journal-title":"SSM-population health."},{"issue":"1","key":"pone.0275054.ref033","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1177\/0081175012452652","article-title":"Estimating heterogeneous treatment effects with observational data.","volume":"42","author":"Y Xie","year":"2012","journal-title":"Sociological methodology."},{"issue":"24","key":"pone.0275054.ref034","doi-asserted-by":"crossref","first-page":"2867","DOI":"10.1002\/sim.4322","article-title":"Subgroup identification from randomized clinical trial data.","volume":"30","author":"JC Foster","year":"2011","journal-title":"Statistics in Medicine"},{"issue":"1","key":"pone.0275054.ref035","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1080\/10618600.2017.1356325","article-title":"Estimating individual treatment effect in observational data using random forest methods.","volume":"27","author":"M Lu","year":"2018","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"6","key":"pone.0275054.ref036","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1377\/hlthaff.2016.0098","article-title":"Access to mental health care increased but not for substance use, while disparities remain.","volume":"35","author":"TB Creedon","year":"2016","journal-title":"Health Affairs."},{"issue":"8","key":"pone.0275054.ref037","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1176\/appi.ps.56.8.954","article-title":"Use of mental health care and substance abuse treatment among adults with co-occurring disorders.","volume":"56","author":"KM Harris","year":"2005","journal-title":"Psychiatric Services."},{"key":"pone.0275054.ref038","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.jsat.2015.09.006","article-title":"Treatment access barriers and disparities among individuals with co-occurring mental health and substance use disorders: an integrative literature review","volume":"61","author":"MA Priester","year":"2016","journal-title":"Journal of substance abuse treatment"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0275054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T18:17:16Z","timestamp":1663957036000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0275054"}},"subtitle":[],"editor":[{"given":"Dylan A.","family":"Mordaunt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,9,23]]},"references-count":38,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,9,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0275054","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,23]]}}}