{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:00:35Z","timestamp":1792083635140,"version":"4.4.0"},"reference-count":52,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T00:00:00Z","timestamp":1671062400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Digital Health CRC","award":["DH-00071"],"award-info":[{"award-number":["DH-00071"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Opioid Use Disorder (OUD) and opioid overdose (OD) impose huge social and economic burdens on society and health care systems. Research suggests that Medication for Opioid Use Disorder (MOUD) is effective in the treatment of OUD. We use machine learning to investigate the association between patient\u2019s adherence to prescribed MOUD along with other risk factors in patients diagnosed with OUD and potential OD following the treatment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used longitudinal Medicaid claims for two selected US states to subset a total of 26,685 patients with OUD diagnosis and appropriate Medicaid coverage between 2015 and 2018. We considered patient age, sex, region level socio-economic data, past comorbidities, MOUD prescription type and other selected prescribed medications along with the Proportion of Days Covered (PDC) as a proxy for adherence to MOUD as predictive variables for our model, and overdose events as the dependent variable. We applied four different machine learning classifiers and compared their performance, focusing on the importance and effect of PDC as a variable. We also calculated results based on risk stratification, where our models separate high risk individuals from low risk, to assess usefulness in clinical decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the selected classifiers, the XGBoost classifier has the highest AUC (0.77) closely followed by the Logistic Regression (LR). The LR has the best stratification result: patients in the top 10% of risk scores account for 35.37% of overdose events over the next 12 month observation period. PDC score calculated over the treatment window is one of the most important features, with better PDC lowering risk of OD, as expected. In terms of risk stratification results, of the 35.37% of overdose events that the predictive model could detect within the top 10% of risk scores, 72.3% of these cases were non-adherent in terms of their medication (PDC &lt;0.8). Targeting the top 10% outcome of the predictive model could decrease the total number of OD events by 10.4%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The best performing models allow identification of, and focus on, those at high risk of opioid overdose. With MOUD being included for the first time as a factor of interest, and being identified as a significant factor, outreach activities related to MOUD can be targeted at those at highest risk.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0278988","type":"journal-article","created":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T13:46:47Z","timestamp":1671112007000},"page":"e0278988","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":26,"title":["Using machine learning to study the effect of medication adherence in Opioid Use Disorder"],"prefix":"10.1371","volume":"17","author":[{"given":"David","family":"Warren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2783-223X","authenticated-orcid":true,"given":"Amir","family":"Marashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arwa","family":"Siddiqui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7106-4229","authenticated-orcid":true,"given":"Asim Adnan","family":"Eijaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pooja","family":"Pradhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2837-0973","authenticated-orcid":true,"given":"David","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary","family":"Call","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9908-7182","authenticated-orcid":true,"given":"Mark","family":"Dras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,12,15]]},"reference":[{"key":"pone.0278988.ref001","article-title":"P S. Provisional drug overdose death counts","volume":"2020","author":"F Ahmad","journal-title":"National Center for Health Statistics"},{"issue":"1","key":"pone.0278988.ref002","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1176\/appi.prcp.20180006","article-title":"Pharmacological and Behavioral Treatment of Opioid Use Disorder","volume":"1","author":"M Sofuoglu","year":"2019","journal-title":"Psychiatric Research and Clinical Practice"},{"issue":"1","key":"pone.0278988.ref003","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1038\/clpt.1988.13","article-title":"A clinical trial of buprenorphine: comparison with methadone in the detoxification of heroin addicts","volume":"43","author":"W Bickel","year":"1988","journal-title":"Clinical Pharmacology and Therapeutics"},{"issue":"2","key":"pone.0278988.ref004","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1097\/HRP.0000000000000075","article-title":"Medication-Assisted Treatment of Opioid Use Disorder: Review of the Evidence and Future Directions","volume":"23","author":"HS Connery","year":"2015","journal-title":"Harvard Review of Psychiatry"},{"key":"pone.0278988.ref005","first-page":"33","volume-title":"Medications for Opioid Use Disorder Save Lives","author":"National Academies of Sciences, Engineering, and Medicine; Health and Medicine Division; Board on Health Sciences Policy; Committee on Medication-Assisted Treatment for Opioid Use Disorder","year":"2019"},{"key":"pone.0278988.ref006","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1186\/s13063-019-3995-y","article-title":"A call for consensus in defining efficacy in clinical trials for opioid addiction: combined results from a systematic review and qualitative study in patients receiving pharmacological assisted therapy for opioid use disorder","volume":"21","author":"BB Dennis","year":"2020","journal-title":"Trials"},{"key":"pone.0278988.ref007","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.jsat.2015.05.001","article-title":"Risk Factors for Relapse and Higher Costs among Medicaid Members with Opioid Dependence or Abuse: Opioid Agonists, Comorbidities, and Treatment History","volume":"57","author":"RE Clark","year":"2015","journal-title":"Journal of Substance Abuse Treatment"},{"issue":"6","key":"pone.0278988.ref008","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1097\/ADM.0000000000000245","article-title":"Understanding Risk Factors for Opioid Overdose in Clinical Populations to Inform Treatment and Policy","volume":"10","author":"TW Park","year":"2016","journal-title":"Journal of Addiction Medicine"},{"key":"pone.0278988.ref009","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nmeth.4642","article-title":"Statistics versus machine learning","volume":"15","author":"NAMK Danilo Bzdok","year":"2018","journal-title":"Nature Methods"},{"issue":"1","key":"pone.0278988.ref010","article-title":"A prediction model for COPD readmissions: catching up, catching our breath, and improving a national problem","volume":"2","author":"B Amalakuhan","year":"2012","journal-title":"J Community Hosp Intern Med Perspect"},{"issue":"1","key":"pone.0278988.ref011","doi-asserted-by":"crossref","first-page":"e1918962","DOI":"10.1001\/jamanetworkopen.2019.18962","article-title":"Comparison of Machine Learning Methods With Traditional Models for Use of Administrative Claims With Electronic Medical Records to Predict Heart Failure Outcomes","volume":"3","author":"RJ Desai","year":"2020","journal-title":"JAMA Network Open"},{"issue":"2","key":"pone.0278988.ref012","doi-asserted-by":"crossref","first-page":"e162","DOI":"10.1097\/CCM.0000000000005286","article-title":"Comparison of Machine Learning Methods for Predicting Outcomes After In-Hospital Cardiac Arrest","volume":"50","author":"A Mayampurath","year":"2022","journal-title":"Crit Care Med"},{"issue":"3","key":"pone.0278988.ref013","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":"WH Lo-Ciganic","year":"2019","journal-title":"JAMA Network Open"},{"issue":"4","key":"pone.0278988.ref014","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1073\/pnas.1905355117","article-title":"Predicting high-risk opioid prescriptions before they are given","volume":"117","author":"JS Hastings","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"7","key":"pone.0278988.ref015","doi-asserted-by":"crossref","first-page":"e0235981","DOI":"10.1371\/journal.pone.0235981","article-title":"Using machine learning to predict risk of incident opioid use disorder among fee-for-service Medicare beneficiaries: A prognostic study","volume":"15","author":"WH Lo-Ciganic","year":"2020","journal-title":"PLoS ONE"},{"issue":"3","key":"pone.0278988.ref016","doi-asserted-by":"crossref","first-page":"e0248360","DOI":"10.1371\/journal.pone.0248360","article-title":"Integrating human services and criminal justice data with claims data to predict risk of opioid overdose among Medicaid beneficiaries: A machine-learning approach","volume":"16","author":"W-H Lo-Ciganic","year":"2021","journal-title":"PLoS ONE"},{"key":"pone.0278988.ref017","doi-asserted-by":"crossref","first-page":"e455","DOI":"10.1016\/S2589-7500(22)00062-0","article-title":"Developing and validating a machine-learning algorithm to predict opioid overdose in Medicaid beneficiaries in two US states: a prognostic modelling study","volume":"4","author":"W-H Lo-Ciganic","year":"2022","journal-title":"Lancet Digit Health"},{"key":"pone.0278988.ref018","first-page":"389","article-title":"Machine Learning Based Opioid Overdose Prediction Using Electronic Health Records","volume":"2019","author":"X Dong","year":"2020","journal-title":"AMIA Annu Symp Proc"},{"issue":"1","key":"pone.0278988.ref019","doi-asserted-by":"crossref","DOI":"10.1093\/jamia\/ocab218","article-title":"Ensemble learning to predict opioid-related overdose using statewide prescription drug monitoring program and hospital discharge data in the state of Tennessee","volume":"29","author":"M Ripperger","year":"2022","journal-title":"Journal of the American Medical Informatics Association"},{"key":"pone.0278988.ref020","doi-asserted-by":"crossref","first-page":"e043964","DOI":"10.1136\/bmjopen-2020-043964","article-title":"Safe opioid prescribing: a prognostic machine learning approach to predicting 30-day risk after an opioid dispensation in Alberta","volume":"11","author":"V Sharma","year":"2021","journal-title":"Canada BMJ Open"},{"issue":"4","key":"pone.0278988.ref021","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1161\/HYPERTENSIONAHA.111.171074","article-title":"Participation in a clinical trial enhances adherence and persistence to treatment: a retrospective cohort study","volume":"58","author":"HAW van Onzenoort","year":"2011","journal-title":"Hypertension"},{"key":"pone.0278988.ref022","article-title":"Buprenorphine physician\u2013pharmacist collaboration in the management of patients with opioid use disorder: results from a multisite study of the National Drug Abuse Treatment Clinical Trials Network","author":"L Wu","year":"2021","journal-title":"Addiction"},{"issue":"3","key":"pone.0278988.ref023","article-title":"Predicting opioid dependence from electronic health records with machine learning","volume":"12","author":"RJ Ellis","year":"2019","journal-title":"BioData Mining"},{"issue":"0","key":"pone.0278988.ref024","article-title":"Individualized Prospective Prediction of Opioid Use Disorder","volume":"0","author":"YS Liu","year":"2022","journal-title":"The Canadian Journal of Psychiatry"},{"key":"pone.0278988.ref025","doi-asserted-by":"crossref","first-page":"100144","DOI":"10.1016\/j.mlwa.2021.100144","article-title":"A machine learning framework to predict the risk of opioid use disorder","volume":"6","author":"MM Hasan","year":"2021","journal-title":"Machine Learning with Applications"},{"issue":"4","key":"pone.0278988.ref026","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"},{"key":"pone.0278988.ref027","article-title":"Using Machine Learning to Predict Treatment Adherence in Patients on Medication for Opioid Use Disorder","author":"AJ Burgess-Hull","year":"2022","journal-title":"J Addict Med"},{"issue":"6","key":"pone.0278988.ref028","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1111\/j.1526-4637.2005.00072.x","article-title":"Predicting aberrant behaviors in opioid-treated patients: preliminary validation of the Opioid Risk Tool","volume":"6","author":"LR Webster","year":"2005","journal-title":"Pain Medicine"},{"issue":"12","key":"pone.0278988.ref029","first-page":"897","article-title":"Analytic models to identify patients at risk for prescription opioid abuse","volume":"15","author":"AG White","year":"2009","journal-title":"The American Journal of Managed Care"},{"issue":"9","key":"pone.0278988.ref030","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1111\/j.1526-4637.2012.01450.x","article-title":"A Model to Identify Patients at Risk for Prescription Opioid Abuse, Dependence, and Misuse","volume":"13","author":"JB Rice","year":"2012","journal-title":"Pain Medicine"},{"issue":"5","key":"pone.0278988.ref031","article-title":"Understanding Predictors of Opioid Abuse: Predictive Model Development and Validation","volume":"6","author":"R Dufour","year":"2014","journal-title":"The American Journal of Pharmacy Benefits"},{"issue":"4","key":"pone.0278988.ref032","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1016\/j.jpain.2015.01.011","article-title":"Automated prediction of risk for problem opioid use in a primary care setting","volume":"16","author":"TR Hylan","year":"2015","journal-title":"Journal of Pain"},{"issue":"7","key":"pone.0278988.ref033","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1016\/j.amjmed.2016.02.014","article-title":"A Tool to Assess Risk of De Novo Opioid Abuse or Dependence","volume":"129","author":"T Ciesielski","year":"2016","journal-title":"The American Journal of Medicine"},{"key":"pone.0278988.ref034","unstructured":"U.S. States;. Available from: https:\/\/countryeconomy.com\/countries\/usa-states."},{"key":"pone.0278988.ref035","unstructured":"Barrientos M. United States Facts;. Available from: https:\/\/www.indexmundi.com\/facts\/united-states\/quick-facts."},{"issue":"16","key":"pone.0278988.ref036","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.1001\/jama.2015.3474","article-title":"Emergency Department\u2013Initiated Buprenorphine\/Naloxone Treatment for Opioid Dependence: A Randomized Clinical Trial","volume":"313","author":"G D\u2019Onofrio","year":"2015","journal-title":"JAMA"},{"issue":"7918","key":"pone.0278988.ref037","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1016\/S0140-6736(75)92192-3","article-title":"Randomised clinical trial of strategies for improving medication compliance in primary hypertension","volume":"1","author":"D Sackett","year":"1975","journal-title":"Lancet"},{"issue":"9","key":"pone.0278988.ref038","doi-asserted-by":"crossref","first-page":"2303","DOI":"10.1185\/03007990903126833","article-title":"Good and poor adherence: optimal cut-point for adherence measures using administrative claims data","volume":"25","author":"S Karve","year":"2009","journal-title":"Current Medical Research and Opinion"},{"key":"pone.0278988.ref039","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1097\/00005650-199801000-00004","article-title":"Comorbidity measures for use with administrative data","author":"A Elixhauser","year":"1998","journal-title":"Medical Care"},{"key":"pone.0278988.ref040","author":"R Core Team","year":"2020","journal-title":"icd: Comorbidity Calculations and Tools for ICD-9 and ICD-10 Codes"},{"issue":"10","key":"pone.0278988.ref041","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1001\/jamainternmed.2017.3317","article-title":"Social Determinants of Health in Managed Care Payment Formulas","volume":"177","author":"AS Ash","year":"2017","journal-title":"JAMA Intern Med"},{"key":"pone.0278988.ref042","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12889-020-08735-0","article-title":"Incorporating machine learning and social determinants of health indicators into prospective risk adjustment for health plan payments","volume":"20","author":"JA Irvin","year":"2020","journal-title":"BMC Public Health"},{"key":"pone.0278988.ref043","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1007\/978-3-642-23166-7_12","volume-title":"Data mining: Foundations and intelligent paradigms","author":"T Raeder","year":"2012"},{"key":"pone.0278988.ref044","first-page":"1189","article-title":"Greedy function approximation: a gradient boosting machine","author":"JH Friedman","year":"2001","journal-title":"Annals of Statistics"},{"issue":"1","key":"pone.0278988.ref045","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1080\/10618600.2014.907095","article-title":"Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation","volume":"24","author":"A Goldstein","year":"2015","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"1","key":"pone.0278988.ref046","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1080\/00273171.2011.540475","article-title":"A Systematic Review of Propensity Score Methods in the Social Sciences","volume":"46","author":"FJ Thoemmes","year":"2011","journal-title":"Multivariate Behavioral Research"},{"key":"pone.0278988.ref047","volume-title":"The Elements of Statistical Learning","author":"T Hastie","year":"2008","edition":"2"},{"issue":"10","key":"pone.0278988.ref048","doi-asserted-by":"crossref","first-page":"2255","DOI":"10.1097\/j.pain.0000000000001612","article-title":"The contribution of obesity to prescription opioid use in the United States","volume":"160","author":"A Stokes","year":"2019","journal-title":"Pain"},{"issue":"4","key":"pone.0278988.ref049","doi-asserted-by":"crossref","first-page":"e202012","DOI":"10.1001\/jamanetworkopen.2020.2012","article-title":"Association of Obesity With Prescription Opioids for Painful Conditions in Patients Seeking Primary Care in the US","volume":"3","author":"A Stokes","year":"2020","journal-title":"JAMA Network Open"},{"key":"pone.0278988.ref050","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.drugalcdep.2018.06.014","article-title":"Prevalence of obesity for opioid-and stimulant-dependent participants in substance use treatment clinical trials","volume":"190","author":"L Hu","year":"2018","journal-title":"Drug and Alcohol Dependence"},{"key":"pone.0278988.ref051","doi-asserted-by":"crossref","first-page":"108293","DOI":"10.1016\/j.drugalcdep.2020.108293","article-title":"Prevalence of obesity among US population with substance dependence","volume":"217:","author":"L Hu","year":"2020","journal-title":"Drug and Alcohol Dependence"},{"key":"pone.0278988.ref052","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0278988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T13:47:39Z","timestamp":1671112059000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0278988"}},"subtitle":[],"editor":[{"given":"Kathiravan","family":"Srinivasan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,12,15]]},"references-count":52,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,12,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0278988","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,15]]}}}