{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T22:24:31Z","timestamp":1787783071622,"version":"build-2784847793"},"reference-count":37,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>People who use drugs (PWUD) are at heightened risk of severe injection\u2013related infections. Current research relies on billing codes to identify PWUD\u2014a methodology with suboptimal accuracy that may underestimate the economic, racial, and ethnic diversity of hospitalized PWUD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The goal of this study is to examine the impact of natural language processing (NLP) on enhancing identification of PWUD in electronic medical records, with a specific focus on determining improved systems of identifying populations who may previously been missed, including people who have low income or those from racially and ethnically minoritized populations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Health informatics specialists assisted in querying a cohort of likely PWUD hospital admissions at Tufts Medical Center between 2020\u20102022 using the following criteria: (1)\n                      <jats:italic>ICD-10<\/jats:italic>\n                      codes indicative of drug use, (2) positive drug toxicology results, (3) prescriptions for medications for opioid use disorder, and (4) applying NLP-detected presence of \u201ctoken\u201d keywords in the electronic medical records likely indicative of the patient being a PWUD. Hospital admissions were split into two groups: highly documented (all four criteria present) and minimally documented (NLP-only). These groups were examined to assess the impact of race, ethnicity, and social vulnerability index. With chart review as the \u201cgold standard,\u201d the positive predictive value was calculated.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The cohort included 4548 hospitalization admissions, with broad heterogeneity in how people entered the cohort and subcohorts; a total of 288 hospital admissions entered the cohort through NLP token presence alone. NLP demonstrated a 54% positive predictive value, outperforming biomarkers, prescription for medications for opioid use disorder, and\n                      <jats:italic>ICD<\/jats:italic>\n                      codes in identifying hospitalizations of PWUD. Additionally, NLP significantly enhanced these methods when integrated into the identification algorithm. The study also found that people from racially and ethnically minoritized communities and those with lower social vulnerability index were significantly more likely to have lower rates of PWUD-related documentation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>NLP proved effective in identifying hospitalizations of PWUD, surpassing traditional methods. While further refinement is needed, NLP shows promising potential in minimizing health care disparities.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/63147","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T10:20:08Z","timestamp":1742206808000},"page":"e63147-e63147","source":"Crossref","is-referenced-by-count":2,"title":["Natural Language Processing for Identification of Hospitalized People Who Use Drugs: Cohort Study"],"prefix":"10.2196","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6830-2812","authenticated-orcid":false,"given":"Taisuke","family":"Sato","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9596-2197","authenticated-orcid":false,"given":"Emily D","family":"Grussing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3243-1849","authenticated-orcid":false,"given":"Ruchi","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6939-6096","authenticated-orcid":false,"given":"Jessica","family":"Ridgway","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-6147","authenticated-orcid":false,"given":"Joji","family":"Suzuki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3837-3289","authenticated-orcid":false,"given":"Benjamin","family":"Sweigart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1787-2855","authenticated-orcid":false,"given":"Robert","family":"Miller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8255-8387","authenticated-orcid":false,"given":"Alysse G","family":"Wurcel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-023-09773-1","article-title":"A multimorbidity model for estimating health outcomes from the syndemic of injection drug use and associated infections in the United States","volume":"23","author":"Chiosi","journal-title":"BMC Health Serv Res"},{"issue":"6","key":"R2","doi-asserted-by":"publisher","first-page":"202","DOI":"10.15585\/mmwr.mm7006a4","article-title":"Trends and geographic patterns in drug and synthetic opioid overdose deaths - United States, 2013-2019","volume":"70","author":"Mattson","journal-title":"MMWR Morb Mortal Wkly Rep"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1111\/add.15659","article-title":"Mortality among people who inject drugs: a prospective cohort followed over three\u2009decades in Baltimore, MD, USA","volume":"117","author":"Sun","journal-title":"Addiction"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2021.108927","article-title":"Racial inequity in medication treatment for opioid use disorder: exploring potential facilitators and barriers to use","volume":"227","author":"Hollander","journal-title":"Drug Alcohol Depend"},{"issue":"11","key":"R5","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1089\/apc.2022.0165","article-title":"Racial and ethnic disparities in HIV testing in people who use drugs admitted to a tertiary care hospital","volume":"36","author":"Hamdan","journal-title":"AIDS Patient Care STDS"},{"issue":"5","key":"R6","doi-asserted-by":"publisher","DOI":"10.1093\/ofid\/ofae204","article-title":"National HIV and HCV screening rates for hospitalized people who use drugs are suboptimal and heterogeneous across 11 US hospitals","volume":"11","author":"Westgard","journal-title":"Open Forum Infect Dis"},{"issue":"12","key":"R7","doi-asserted-by":"publisher","first-page":"e53","DOI":"10.2105\/AJPH.2015.302885","article-title":"Leaving the hospital against medical advice among people who use illicit drugs: a systematic review","volume":"105","author":"Ti","journal-title":"Am J Public Health"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsat.2021.108465","article-title":"Association between discharges against medical advice and readmission in patients treated for drug injection-related skin and soft tissue infections","volume":"126","author":"Hazen","journal-title":"J Subst Abuse Treat"},{"issue":"3","key":"R9","doi-asserted-by":"publisher","DOI":"10.1093\/ofid\/ofaa074","article-title":"In-Hospital illicit drug use and patient-directed discharge: barriers to care for patients with injection-related infections","volume":"7","author":"Eaton","journal-title":"Open Forum Infect Dis"},{"issue":"9","key":"R10","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1002\/jhm.12908","article-title":"Management of opioid use disorder, opioid withdrawal, and opioid overdose prevention in hospitalized adults: A systematic review of existing guidelines","volume":"17","author":"Calcaterra","journal-title":"J Hosp Med"},{"issue":"9","key":"R11","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1007\/s40264-019-00838-x","article-title":"Evaluation of use of technologies to facilitate medical chart review","volume":"42","author":"Straub","journal-title":"Drug Saf"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1037\/a0037968","article-title":"Substance use disorder patient privacy and comprehensive care in integrated health care settings","volume":"13","author":"Schaper","journal-title":"Psychol Serv"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1002\/pds.2313","article-title":"A systematic review of validated methods for identifying heart failure using administrative data","volume":"21 Suppl 1","author":"Saczynski","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"11","key":"R14","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCHEARTFAILURE.121.009401","article-title":"Race, social determinants of health, and length of stay among hospitalized patients with heart failure: an analysis from the Get With The Guidelines-Heart Failure Registry","volume":"15","author":"Segar","journal-title":"Circ: Heart Failure"},{"issue":"5","key":"R15","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1080\/00952990.2022.2047713","article-title":"Sensitivity, specificity and predictive values of ICD-10 substance use codes in a cohort of substance use-related endocarditis patients","volume":"48","author":"Campanile","journal-title":"Am J Drug Alcohol Abuse"},{"issue":"10","key":"R16","doi-asserted-by":"publisher","first-page":"e70","DOI":"10.1097\/MLR.0000000000000838","article-title":"Validation of an algorithm to identify infective endocarditis in people who inject drugs","volume":"56","author":"Ball","journal-title":"Med Care"},{"issue":"5","key":"R17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0063959","article-title":"Current and future disease progression of the chronic HCV population in the United States","volume":"8","author":"Zalesak","journal-title":"PLoS ONE"},{"issue":"Suppl 2","key":"R18","doi-asserted-by":"publisher","first-page":"441","DOI":"10.18865\/ed.29.S2.441","article-title":"Development of a natural language processing algorithm to identify and evaluate transgender patients in electronic health record systems","volume":"29","author":"Ehrenfeld","journal-title":"Ethn Dis"},{"issue":"4","key":"R19","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1016\/j.jbi.2006.10.004","article-title":"Surveillance of methadone-related adverse drug events using multiple public health data sources","volume":"40","author":"Sims","journal-title":"J Biomed Inform"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","DOI":"10.2196\/23456","article-title":"Natural language processing of clinical notes to identify mental illness and substance use among people living with HIV: retrospective cohort study","volume":"9","author":"Ridgway","journal-title":"JMIR Med Inform"},{"issue":"5","key":"R21","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1136\/amiajnl-2013-002411","article-title":"Learning regular expressions for clinical text classification","volume":"21","author":"Bui","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.1186\/s13326-024-00311-4","article-title":"Multi-task transfer learning for the prediction of entity modifiers in clinical text: application to opioid use disorder case detection","volume":"15","author":"Almudaifer","journal-title":"J Biomed Semantics"},{"issue":"9","key":"R23","doi-asserted-by":"publisher","DOI":"10.1093\/ofid\/ofac471","article-title":"Natural language processing and machine learning to identify people who inject drugs in electronic health records","volume":"9","author":"Goodman-Meza","journal-title":"Open Forum Infect Dis"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1080\/07853890.2022.2105391","article-title":"Application of machine learning algorithms for localized syringe services program policy implementation \u2013 Florida, 2017","volume":"54","author":"Bartholomew","journal-title":"Ann Med"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1080\/00952990.2021.1995739","article-title":"Practical foundations of machine learning for addiction research. Part I. Methods and techniques","volume":"48","author":"Cresta Morgado","journal-title":"Am J Drug Alcohol Abuse"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0227188","article-title":"Using machine learning methods to determine a typology of patients with HIV-HCV infection to be treated with antivirals","volume":"15","author":"Rivero-Ju\u00e1rez","journal-title":"PLoS ONE"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.1177\/26334895231203410","article-title":"Implementation of a bundle to improve HIV testing during hospitalization for people who inject drugs","volume":"4","author":"D Grussing","journal-title":"Implement Res Pract"},{"issue":"8","key":"R28","doi-asserted-by":"publisher","first-page":"e1827","DOI":"10.1097\/PTS.0000000000000721","article-title":"Implementation of a patient-provider agreement to improve healthcare delivery for patients with substance use disorder in the inpatient setting","volume":"17","author":"Wurcel","journal-title":"J Patient Saf"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-016-0293-6","article-title":"The HCV care continuum among people who use drugs: protocol for a systematic review and meta-analysis","volume":"5","author":"Reed","journal-title":"Syst Rev"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-019-4751-4","article-title":"Opioid use disorder and treatment: challenges and opportunities","volume":"19","author":"Hoffman","journal-title":"BMC Health Serv Res"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2019.107825","article-title":"Validity of International Classification of Diseases codes in identifying illicit drug use target conditions using medical record data as a reference standard: a systematic review","volume":"208","author":"McGrew","journal-title":"Drug Alcohol Depend"},{"key":"R32","unstructured":"Social vulnerability index. ATSDR Place and Health - Geospatial Research, Analysis, and Services Program (GRASP). 2024. URL: https:\/\/www.atsdr.cdc.gov\/place-health\/php\/svi\/index.html [Accessed 09-07-2025]"},{"issue":"4","key":"R33","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1080\/15332640.2018.1548323","article-title":"Anti-racism and substance use treatment: addiction does not discriminate, but do we?","volume":"19","author":"Matsuzaka","journal-title":"J Ethn Subst Abuse"},{"issue":"4","key":"R34","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/s11414-018-9586-y","article-title":"Disparities in the treatment of substance use disorders: does where you live matter?","volume":"45","author":"Acevedo","journal-title":"J Behav Health Serv Res"},{"issue":"1088","key":"R35","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1136\/postgradmedj-2015-133720","article-title":"Optimising health and safety of people who inject drugs during transition from acute to outpatient care: narrative review with clinical checklist","volume":"92","author":"Thakarar","journal-title":"Postgrad Med J"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsat.2020.108266","article-title":"Increased HIV testing in people who use drugs hospitalized in the first wave of the COVID-19 pandemic","volume":"124","author":"Zubiago","journal-title":"J Subst Abuse Treat"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1016\/j.josat.2024.209392","article-title":"Perspectives on benefits and risks of creation of an \u201cinjection drug use\u201d billing code","volume":"164","author":"Sundaram","journal-title":"J Subst Use Addict Treat"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e63147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:31:13Z","timestamp":1785537073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e63147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":37,"URL":"https:\/\/doi.org\/10.2196\/63147","relation":{},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,18]]},"article-number":"v4i1e63147"}}