{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:58:57Z","timestamp":1782845937324,"version":"3.54.5"},"reference-count":67,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Infodemiology"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Medication-assisted treatment (MAT) is an effective method for treating opioid use disorder (OUD), which combines behavioral therapies with one of three Food and Drug Administration\u2013approved medications: methadone, buprenorphine, and naloxone. While MAT has been shown to be effective initially, there is a need for more information from the patient perspective about the satisfaction with medications. Existing research focuses on patient satisfaction with the entirety of the treatment, making it difficult to determine the unique role of medication and overlooking the views of those who may lack access to treatment due to being uninsured or concerns over stigma. Studies focusing on patients\u2019 perspectives are also limited by the lack of scales that can efficiently collect self-reports across domains of concerns.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>A broad survey of patients\u2019 viewpoints can be obtained through social media and drug review forums, which are then assessed using automated methods to discover factors associated with medication satisfaction. Because the text is unstructured, it may contain a mix of formal and informal language. The primary aim of this study was to use natural language processing methods on text posted on health-related social media to detect patients\u2019 satisfaction with two well-studied OUD medications: methadone and buprenorphine\/naloxone.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We collected 4353 patient reviews of methadone and buprenorphine\/naloxone from 2008 to 2021 posted on WebMD and Drugs.com. To build our predictive models for detecting patient satisfaction, we first employed different analyses to build four input feature sets using the vectorized text, topic models, duration of treatment, and biomedical concepts by applying MetaMap. We then developed six prediction models: logistic regression, Elastic Net, least absolute shrinkage and selection operator, random forest classifier, Ridge classifier, and extreme gradient boosting to predict patients\u2019 satisfaction. Lastly, we compared the prediction models\u2019 performance over different feature sets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Topics discovered included oral sensation, side effects, insurance, and doctor visits. Biomedical concepts included symptoms, drugs, and illnesses. The F-score of the predictive models across all methods ranged from 89.9% to 90.8%. The Ridge classifier model, a regression-based method, outperformed the other models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Assessment of patients\u2019 satisfaction with opioid dependency treatment medication can be predicted using automated text analysis. Adding biomedical concepts such as symptoms, drug name, and illness, along with the duration of treatment and topic models, had the most benefits for improving the prediction performance of the Elastic Net model compared to other models. Some of the factors associated with patient satisfaction overlap with domains covered in medication satisfaction scales (eg, side effects) and qualitative patient reports (eg, doctors\u2019 visits), while others (insurance) are overlooked, thereby underscoring the value added from processing text on online health forums to better understand patient adherence.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/37207","type":"journal-article","created":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T15:30:22Z","timestamp":1672414222000},"page":"e37207","source":"Crossref","is-referenced-by-count":5,"title":["Predicting Patient Satisfaction With Medications for Treating Opioid Use Disorder: Case Study Applying Natural Language Processing to Reviews of Methadone and Buprenorphine\/Naloxone on Health-Related Social Media"],"prefix":"10.2196","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8974-2614","authenticated-orcid":false,"given":"Samaneh","family":"Omranian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4484-2990","authenticated-orcid":false,"given":"Maryam","family":"Zolnoori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7367-3626","authenticated-orcid":false,"given":"Ming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7376-1842","authenticated-orcid":false,"given":"Celeste","family":"Campos-Castillo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4826-0947","authenticated-orcid":false,"given":"Susan","family":"McRoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2023,1,23]]},"reference":[{"key":"ref1","unstructured":"Key Substance Use and Mental Health Indicators in the United States: Results from the 2018 National Survey on Drug Use and HealthSubstance Abuse and Mental Health Services Administration20192023-01-06https:\/\/store.samhsa.gov\/product\/key-substance-use-and-mental-health-indicators-in-the-united-states-results-from-the-2018-national-survey-on-Drug-Use-and-Health\/PEP19-5068"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1151\/spp021113"},{"key":"ref3","unstructured":"Commonly used terms: opioidsCenters for Disease Control and Prevention2023-01-06https:\/\/www.cdc.gov\/opioids\/basics\/terms.html"},{"key":"ref4","year":"2018","journal-title":"Medication-Assisted Treatment for Opioid Use Disorder: Proceedings of a Workshop\u2014in Brief"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s12954-021-00521-4"},{"issue":"7-8","key":"ref6","first-page":"8","volume":"14","author":"Ali, S","year":"2017","journal-title":"Innov Clin Neurosci"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1151\/spp021113"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2165\/00003495-200969050-00006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s40263-019-00637-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfda.2013.09.037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/08897077.2021.2010251"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsat.2020.108146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.31887\/dcns.2017.19.3\/tcicero"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsat.2014.03.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2016.03.014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1159\/000456612"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/105504999305848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0738-3991(03)00126-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2147\/PPA.S52060"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1331\/JAPhA.2011.09154"},{"key":"ref21","unstructured":"Key facts about uninsured adults with opioid use disorderKFF201907152020-02-19https:\/\/www.kff.org\/uninsured\/issue-brief\/key-facts-about-uninsured-adults-with-opioid-use-disorder\/"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2196\/cancer.9050"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.7975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/hex.12439"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1186\/1471-244x-11-88"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/1359105306061187"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1136\/bmjgh-2017-000694"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15265\/IY-2017-029"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.0968"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-019-0193-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100144"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0000000000005527"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2196\/15293"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2196\/15645"},{"key":"ref35","unstructured":"HedegaardHMini\u00f1oAMWarnerMDrug overdose deaths in the United States, 1999-2018. NCHS Data Brief No. 356Centers for Disease Control and Prevention2020012023-01-06http:\/\/www.cdc.gov\/nchs\/data\/databriefs\/db356-h.pdf"},{"key":"ref36","unstructured":"Better information. Better healthWebMD20052023-01-06https:\/\/www.webmd.com\/"},{"key":"ref37","unstructured":"Drugs.com20002023-01-06https:\/\/www.drugs.com\/"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.7087"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1045\/september2016-meschenmoser"},{"key":"ref40","unstructured":"Natural Language Toolkit20212023-01-06https:\/\/www.nltk.org"},{"key":"ref41","unstructured":"MayCCotterellRVan DurmeBAn analysis of lemmatization on topic models of morphologically rich languagearXiv201905102023-01-06https:\/\/arxiv.org\/abs\/1608.03995"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.4103\/0974-2077.74491"},{"key":"ref43","unstructured":"OmranianSInformation retrieval of opioid dependence medications reviews from health-related social media. Masters thesisUniversity of Wisconsin-Milwaukee Digital Commons20202023-01-06https:\/\/dc.uwm.edu\/cgi\/viewcontent.cgi?article=3575&context=etd"},{"key":"ref44","author":"Ramachandran, KM","year":"2014","journal-title":"Mathematical Statistics with Applications in R. 2nd ed"},{"key":"ref45","unstructured":"Unified Medical Language System\u00ae (UMLS\u00ae). MetamapNational Library of Medicine20212023-01-06https:\/\/www.nlm.nih.gov\/research\/umls\/implementation_resources\/metamap.html"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.002733"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1006\/jbin.2001.1029"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.3.4-5.993"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2597008.2597150"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2145204.2145329"},{"key":"ref51","unstructured":"WangSPaulMDredzeMExploring health topics in Chinese social media: an analysis of Sina Weibo2014The AAAI Workshop on the World Wide Web and Public Health IntelligenceJuly 27-28, 2014Quebec, QC, Canada2728"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.7779"},{"key":"ref53","unstructured":"Latent Dirichlet allocationGensim: topic modelling for humans2023-01-06https:\/\/radimrehurek.com\/gensim\/models\/ldamodel.html"},{"key":"ref54","first-page":"1","author":"Steyvers, T","year":"2007","journal-title":"Latent semantic analysis: a road to meaning"},{"key":"ref55","unstructured":"RosnerFHinneburgAR\u00f6derMNettlingMBothAEvaluating topic coherence measuresarXiv201403252023-01-06https:\/\/arxiv.org\/abs\/1403.6397"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1111\/j.1526-4637.2007.00370.x"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-017-0642-0"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.4097\/kjae.2013.64.5.402"},{"key":"ref59","author":"Hastie, T","year":"2008","journal-title":"The elements of statistical learning: data mining, inference, and prediction. 2nd ed"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2022.770585"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1080\/10485252.2015.1010532"},{"key":"ref62","doi-asserted-by":"crossref","DOI":"10.1002\/9781118646106","author":"Hei, H","year":"2013","journal-title":"Imbalanced learning: foundations, algorithms, and applications"},{"key":"ref63","author":"Han, J","year":"2012","journal-title":"Data mining concepts and techniques 3rd Edition"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.02.003"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1111\/jcpt.13114"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.2196\/13316"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.14209"}],"container-title":["JMIR Infodemiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/infodemiology.jmir.org\/2023\/1\/e37207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:00:57Z","timestamp":1782842457000},"score":1,"resource":{"primary":{"URL":"https:\/\/infodemiology.jmir.org\/2023\/1\/e37207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,23]]},"references-count":67,"URL":"https:\/\/doi.org\/10.2196\/37207","relation":{},"ISSN":["2564-1891"],"issn-type":[{"value":"2564-1891","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,23]]}}}