{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T15:51:36Z","timestamp":1767973896937,"version":"3.49.0"},"reference-count":18,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2021,2,11]],"date-time":"2021-02-11T00:00:00Z","timestamp":1613001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"InterDisciplinary Exchange and Advancement Leadership Fund from the University of Massachusetts Lowell"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>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.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>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.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>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&amp;lt;.05).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>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.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocaa350","type":"journal-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T15:36:55Z","timestamp":1609861015000},"page":"1216-1224","source":"Crossref","is-referenced-by-count":23,"title":["Machine learning\u2013based outcome prediction and novel hypotheses generation for substance use disorder treatment"],"prefix":"10.1093","volume":"28","author":[{"given":"Murtaza","family":"Nasir","sequence":"first","affiliation":[{"name":"Department of Operations and Information Systems, Manning School of Business, University of Massachusetts Lowell, Lowell, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nichalin S","family":"Summerfield","sequence":"additional","affiliation":[{"name":"Department of Operations and Information Systems, Manning School of Business, University of Massachusetts Lowell, Lowell, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asil","family":"Oztekin","sequence":"additional","affiliation":[{"name":"Department of Operations and Information Systems, Manning School of Business, University of Massachusetts Lowell, Lowell, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Margaret","family":"Knight","sequence":"additional","affiliation":[{"name":"Susan and Alan Solomont School of Nursing, Zuckerberg College of Health Sciences, University of Massachusetts Lowell, Lowell, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leland K","family":"Ackerson","sequence":"additional","affiliation":[{"name":"Department of Public Health, Zuckerberg College of Health Sciences, University of Massachusetts Lowell, Lowell, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephanie","family":"Carreiro","sequence":"additional","affiliation":[{"name":"Division of Medical Toxicology, Department of Emergency Medicine, UMass Memorial Healthcare, University of Massachusetts Medical School, Worcester, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,2,11]]},"reference":[{"key":"2021061318595653000_ocaa350-B1","volume-title":"Opioid Overdose: Understanding the Epidemic","year":"2017"},{"issue":"8","key":"2021061318595653000_ocaa350-B2","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1016\/j.cpr.2013.07.007","article-title":"Drop-out from addiction treatment: A systematic review of risk factors","volume":"33","author":"Brorson","year":"2013","journal-title":"Clin Psychol Rev"},{"key":"2021061318595653000_ocaa350-B3","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":"Stahler","year":"2016","journal-title":"Addict Behav"},{"issue":"5","key":"2021061318595653000_ocaa350-B4","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1046\/j.1360-0443.2003.00354.x","article-title":"Does retention matter? Treatment duration and improvement in drug use","volume":"98","author":"Zhang","year":"2003","journal-title":"Addiction"},{"issue":"2","key":"2021061318595653000_ocaa350-B5","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.jsat.2009.01.001","article-title":"What could the program have done differently? A qualitative examination of reasons for leaving outpatient treatment","volume":"37","author":"Laudet","year":"2009","journal-title":"J Subst Abuse Treat"},{"issue":"3","key":"2021061318595653000_ocaa350-B6","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1093\/jamia\/ocz211","article-title":"On classifying sepsis heterogeneity in the ICU: insight using machine learning","volume":"27","author":"Ibrahim","year":"2020","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2021061318595653000_ocaa350-B7","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1108\/IMDS-12-2017-0579","article-title":"A comparative data analytic approach to construct a risk trade-off for cardiac patients\u2019 re-admissions","volume":"119","author":"Nasir","year":"2019","journal-title":"Ind Mnang Data Syst"},{"issue":"1\u20132","key":"2021061318595653000_ocaa350-B8","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1007\/s10479-017-2489-0","article-title":"Predicting pediatric clinic no-shows: a decision analytic framework using elastic net and Bayesian belief network","volume":"263","author":"Topuz","year":"2018","journal-title":"Ann Oper Res"},{"key":"2021061318595653000_ocaa350-B9","doi-asserted-by":"crossref","first-page":"107605","DOI":"10.1016\/j.drugalcdep.2019.107605","article-title":"Analysis of substance use and its outcomes by machine learning I. Childhood evaluation of liability to substance use disorder","volume":"206","author":"Jing","year":"2020","journal-title":"Drug Alcohol Depend"},{"key":"2021061318595653000_ocaa350-B10","year":"2017"},{"key":"2021061318595653000_ocaa350-B11","year":"2017"},{"key":"2021061318595653000_ocaa350-B12","year":"2019"},{"key":"2021061318595653000_ocaa350-B13","doi-asserted-by":"crossref","first-page":"1421409","DOI":"10.1155\/2017\/1421409","article-title":"Probing for sparse and fast variable selection with model-based boosting","volume":"2017","author":"Thomas","year":"2017","journal-title":"Comput Math Methods Med"},{"key":"2021061318595653000_ocaa350-B14","first-page":"522","author":"Xu","year":"2014"},{"key":"2021061318595653000_ocaa350-B15","first-page":"233","author":"Davis","year":"2006"},{"issue":"1","key":"2021061318595653000_ocaa350-B16","first-page":"15","article-title":"Data analytic methods for generalized linear models","volume":"29","author":"Pregibon","year":"1980","journal-title":"J R Stat Soc Ser C Appl Stat"},{"issue":"9","key":"2021061318595653000_ocaa350-B17","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1002\/(SICI)1097-0258(19970515)16:9<965::AID-SIM509>3.0.CO;2-O","article-title":"A comparison of goodness-of-fit tests for the logistic regression model","volume":"16","author":"Hosmer","year":"1997","journal-title":"Stat Med"},{"issue":"1","key":"2021061318595653000_ocaa350-B18","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.amepre.2019.08.027","article-title":"Online searching and social media to detect alcohol use risk at population scale","volume":"58","author":"Weitzman","year":"2020","journal-title":"Am J Prev Med"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/6\/1216\/38615561\/ocaa350.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/6\/1216\/38615561\/ocaa350.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,13]],"date-time":"2021-06-13T19:02:14Z","timestamp":1623610934000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/6\/1216\/6133131"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,11]]},"references-count":18,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,2,11]]},"published-print":{"date-parts":[[2021,6,12]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaa350","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,6,1]]},"published":{"date-parts":[[2021,2,11]]}}}