{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:12:05Z","timestamp":1772115125984,"version":"3.50.1"},"posted":{"date-parts":[[2025,7,18]]},"group-title":"Emergency Medicine","reference-count":37,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T00:00:00Z","timestamp":1752796800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,7,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Emergency department (ED) encounters represent valuable opportunities to initiate evidence-based treatments for patients with opioid misuse, but few receive such care. Universal manual screening has been proposed to improve patient identification but is uncommon due to its time and resource-intensive nature. We sought to determine the feasibility of identifying patients with opioid misuse at the time of ED triage using machine learning (ML).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We conducted a retrospective cohort study of 1,123 ED encounters (September 2020 \u2013 March 2023) at a tertiary hospital. Encounters were enriched for opioid misuse, manually annotated, and chronologically split for training, validation, and testing. Candidate triage-time features included patient demographics, Emergency Severity Index, arrival time of day, chief complaint, comorbidities, and chronic medications. Model performance was evaluated using F1 score, area under the precision\u2013recall curve (AUPRC), accuracy, recall, and AUROC. Post-hoc explainability analyses included SHapley Additive exPlanations (SHAP) and feature importance.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>All models performed comparably to opioid-related diagnosis codes placed at any time during the encounter. Random Forest (F1=0.75 [95%CI 0.70-0.83], AUPRC=0.88 [0.81-0.93], accuracy=0.79 [0.70-0.83]) and Gradient Boosting (F1=0.77 [0.71-0.82], AUPRC=0.89 [0.85-0.93], accuracy=0.81 [0.720.84]) had among the highest F1 score and AUPRC but confidence intervals overlapped with other methods. Explainability analyses highlighted prior drug-use diagnosis codes, triage acuity, and age as top predictors.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>ML classifiers leveraging routinely collected triage data offer a feasible alternative to manual screening in flagging opioid misuse before physician evaluation, potentially enabling early harm-reduction interventions. Prospective multi-site validation, calibration, and bias assessments are warranted.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.07.18.25331782","type":"posted-content","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T23:45:14Z","timestamp":1752882314000},"source":"Crossref","is-referenced-by-count":1,"title":["Machine learning models to detect opioid misuse in Emergency Department patients at triage"],"prefix":"10.64898","author":[{"given":"Chirag","family":"Chhablani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Usman","family":"Shahid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0072-7499","authenticated-orcid":false,"given":"Natalie","family":"Parde","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sami","family":"Muslmani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyi","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dillon","family":"Thorpe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6368-4652","authenticated-orcid":false,"given":"Majid","family":"Afshar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7650-3008","authenticated-orcid":false,"given":"Niranjan","family":"Karnik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0945-1233","authenticated-orcid":false,"given":"Neeraj","family":"Chhabra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025072209100453000_2025.07.18.25331782v1.1","doi-asserted-by":"crossref","unstructured":"Dowell D. Treatment for Opioid Use Disorder: Population Estimates \u2014 United States, 2022. MMWR Morb Mortal Wkly Rep [Internet] 2024 [cited 2025 Apr 2];73. Available from: https:\/\/www.cdc.gov\/mmwr\/volumes\/73\/wr\/mm7325a1.htm","DOI":"10.15585\/mmwr.mm7325a1"},{"key":"2025072209100453000_2025.07.18.25331782v1.2","unstructured":"CDC. Statement from CDC\u2019s National Center for Injury Prevention and Control on Provisional 2024 Overdose Death Data [Internet]. CDC Newsroom. 2025 [cited 2025 Jun 25];Available from: https:\/\/www.cdc.gov\/media\/releases\/2025\/2025-statement-from-cdcs-national-center-for-injury-prevention-and-control-on-provisional-2024.html"},{"key":"2025072209100453000_2025.07.18.25331782v1.3","unstructured":"Das S. Trends in Opioid-Involved Emergency Department Visits: Overall and by Type of Opioid, 2021\u20132024."},{"key":"2025072209100453000_2025.07.18.25331782v1.4","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1811988"},{"issue":"5","key":"2025072209100453000_2025.07.18.25331782v1.5","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.annemergmed.2022.06.015","article-title":"Principles of Screening for Disease and Health Risk Factors in the Emergency Department","volume":"81","year":"2023","journal-title":"Ann Emerg Med"},{"key":"2025072209100453000_2025.07.18.25331782v1.6","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.ajem.2023.01.009","article-title":"Variability in opioid use disorder clinical presentations and treatment in the emergency department: A mixed-methods study","volume":"66","year":"2023","journal-title":"Am J Emerg Med"},{"issue":"9","key":"2025072209100453000_2025.07.18.25331782v1.7","doi-asserted-by":"crossref","first-page":"e2435603","DOI":"10.1001\/jamanetworkopen.2024.35603","article-title":"Trends and Disparities in Initiation of Buprenorphine in US Emergency Departments, 2013-2022","volume":"7","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2025072209100453000_2025.07.18.25331782v1.8","doi-asserted-by":"crossref","unstructured":"Chhabra N , Smith D , Parde N , et al. Racial, ethnic, and sex disparities in buprenorphine treatment from emergency departments by discharge diagnosis. Acad Emerg Med Off J Soc Acad Emerg Med 2025;","DOI":"10.1111\/acem.70035"},{"issue":"1","key":"2025072209100453000_2025.07.18.25331782v1.9","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1186\/s12245-024-00616-2","article-title":"Screening for harmful substance use in emergency departments: a systematic review","volume":"17","year":"2024","journal-title":"Int J Emerg Med"},{"key":"2025072209100453000_2025.07.18.25331782v1.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2023.03.033"},{"issue":"6","key":"2025072209100453000_2025.07.18.25331782v1.11","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1016\/j.jemermed.2019.03.018","article-title":"Screening Tools Validated in the Outpatient Pain Management Setting Poorly Predict Opioid Misuse in the Emergency Department: A Pilot Study","volume":"56","year":"2019","journal-title":"J Emerg Med"},{"issue":"4","key":"2025072209100453000_2025.07.18.25331782v1.12","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1016\/j.annemergmed.2023.04.030","article-title":"Death by a Thousand Screens: A Practical Role for Machine Learning in Emergency Medicine","volume":"82","year":"2023","journal-title":"Ann Emerg Med"},{"key":"2025072209100453000_2025.07.18.25331782v1.13","doi-asserted-by":"crossref","unstructured":"Shahid U , Parde N , Smith DL , et al. Development and Evaluation of Machine Learning Models for the Detection of Emergency Department Patients with Opioid Misuse from Clinical Notes. MedRxiv Prepr Serv Health Sci 2024;2024.12.11.24318875.","DOI":"10.1101\/2024.12.11.24318875"},{"key":"2025072209100453000_2025.07.18.25331782v1.14","doi-asserted-by":"crossref","first-page":"104963","DOI":"10.1016\/j.ijmedinf.2022.104963","article-title":"Using natural language processing to identify opioid use disorder in electronic health record data","volume":"170","year":"2023","journal-title":"Int J Med Inf"},{"issue":"6","key":"2025072209100453000_2025.07.18.25331782v1.15","doi-asserted-by":"crossref","first-page":"e426","DOI":"10.1016\/S2589-7500(22)00041-3","article-title":"Development and multimodal validation of a substance misuse algorithm for referral to treatment using artificial intelligence (SMART-AI): a retrospective deep learning study","volume":"4","year":"2022","journal-title":"Lancet Digit Health"},{"key":"2025072209100453000_2025.07.18.25331782v1.16","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1038\/s41746-024-01377-1","article-title":"Clinical entity augmented retrieval for clinical information extraction","volume":"8","year":"2025","journal-title":"NPJ Digit Med"},{"issue":"4","key":"2025072209100453000_2025.07.18.25331782v1.17","first-page":"766","article-title":"Performance of International Classification of Disease-10 codes in detecting emergency department patients with opioid misuse","volume":"119","year":"2024","journal-title":"Addict Abingdon Engl"},{"key":"2025072209100453000_2025.07.18.25331782v1.18","doi-asserted-by":"crossref","unstructured":"Sharma B , Dligach D , Swope K , et al. Publicly available machine learning models for identifying opioid misuse from the clinical notes of hospitalized patients. BMC Med Inform Decis Mak [Internet] 2020 [cited 2021 Jan 17];20. Available from: https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC7191715\/","DOI":"10.1186\/s12911-020-1099-y"},{"key":"2025072209100453000_2025.07.18.25331782v1.19","unstructured":"2022 NSDUH Annual National Report | CBHSQ Data [Internet]. [cited 2025 Apr 2];Available from: https:\/\/www.samhsa.gov\/data\/report\/2022-nsduh-annual-national-report"},{"issue":"5","key":"2025072209100453000_2025.07.18.25331782v1.20","first-page":"293","article-title":"Prescription Opioid Use, Misuse, and Use Disorders in U.S","volume":"167","year":"2017","journal-title":"Adults: 2015 National Survey on Drug Use and Health. Ann Intern Med"},{"key":"2025072209100453000_2025.07.18.25331782v1.21","unstructured":"Abuse NI on D. Summary of Misuse of Prescription Drugs | National Institute on Drug Abuse (NIDA) [Internet]. -- [cited 2025 Apr 30];Available from: https:\/\/nida.nih.gov\/publications\/research-reports\/misuse-prescription-drugs\/overview"},{"key":"2025072209100453000_2025.07.18.25331782v1.22","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"issue":"3","key":"2025072209100453000_2025.07.18.25331782v1.23","doi-asserted-by":"crossref","first-page":"e233404","DOI":"10.1001\/jamanetworkopen.2023.3404","article-title":"Evaluation of Version 4 of the Emergency Severity Index in US Emergency Departments for the Rate of Mistriage","volume":"6","year":"2023","journal-title":"JAMA Netw Open"},{"issue":"3","key":"2025072209100453000_2025.07.18.25331782v1.24","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1111\/j.1553-2712.2000.tb01066.x","article-title":"Reliability and validity of a new five-level triage instrument","volume":"7","year":"2000","journal-title":"Acad Emerg Med Off J Soc Acad Emerg Med"},{"key":"2025072209100453000_2025.07.18.25331782v1.25","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-199801000-00004"},{"key":"2025072209100453000_2025.07.18.25331782v1.26","unstructured":"Elixhauser Comorbidity Software Refined for ICD-10-CM [Internet]. [cited 2025 Apr 22];Available from: https:\/\/hcup-us.ahrq.gov\/toolssoftware\/comorbidityicd10\/comorbidity_icd10.jsp"},{"key":"2025072209100453000_2025.07.18.25331782v1.27","unstructured":"Concept: Elixhauser Comorbidity Index [Internet]. [cited 2025 Apr 22];Available from: http:\/\/mchp-appserv.cpe.umanitoba.ca\/viewConcept.php?printer=Y&conceptID=1436"},{"key":"2025072209100453000_2025.07.18.25331782v1.28","unstructured":"USP DC | USP [Internet]. [cited 2025 Apr 22];Available from: https:\/\/www.usp.org\/health-quality-safety\/usp-drug-classification-system"},{"key":"#cr-split#-2025072209100453000_2025.07.18.25331782v1.29.1","unstructured":"Weiss AJ , McDermott KW , Heslin KC . Opioid-Related Hospital Stays Among Women in the United States, 2016: Statistical Brief #247 [Internet]. In: Healthcare Cost and Utilization Project (HCUP) Statistical Briefs. Rockville (MD): Agency for Healthcare Research and Quality (US)"},{"key":"#cr-split#-2025072209100453000_2025.07.18.25331782v1.29.2","unstructured":"2006 [cited 2021 Feb 11]. Available from: http:\/\/www.ncbi.nlm.nih.gov\/books\/NBK538344\/"},{"key":"2025072209100453000_2025.07.18.25331782v1.30","unstructured":"scikit-learn: machine learning in Python \u2014 scikit-learn 1.7.0 documentation [Internet]. [cited 2025 Jun 26];Available from: https:\/\/scikit-learn.org\/stable\/"},{"issue":"14","key":"2025072209100453000_2025.07.18.25331782v1.31","doi-asserted-by":"crossref","first-page":"8882","DOI":"10.3390\/ijerph19148882","article-title":"The Identification of Subphenotypes and Associations with Health Outcomes in Patients with Opioid-Related Emergency Department Encounters Using Latent Class Analysis","volume":"19","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"2025072209100453000_2025.07.18.25331782v1.32","doi-asserted-by":"crossref","unstructured":"Montiel Ishino FA , Gilreath T , Williams F. Finding the Hidden Risk Profiles of the United States Opioid Epidemic: Using a Person-Centered Approach on a National Dataset of Noninstitutionalized Adults Reporting Opioid Misuse. Int J Environ Res Public Health [Internet] 2020 [cited 2021 Jan 17];17(12). Available from: https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC7345624\/","DOI":"10.3390\/ijerph17124321"},{"key":"2025072209100453000_2025.07.18.25331782v1.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2019.107671"},{"issue":"5","key":"2025072209100453000_2025.07.18.25331782v1.34","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1016\/j.ajem.2016.02.005","article-title":"Characteristics of heroin-dependent patients seeking asthma care in the","volume":"34","year":"2016","journal-title":"Am J Emerg Med"},{"key":"2025072209100453000_2025.07.18.25331782v1.35","doi-asserted-by":"publisher","DOI":"10.1542\/hpeds.2020-002402"},{"key":"2025072209100453000_2025.07.18.25331782v1.36","doi-asserted-by":"publisher","DOI":"10.2196\/55499"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.18.25331782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:41:06Z","timestamp":1768509666000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.07.18.25331782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1101\/2025.07.18.25331782","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"subtype":"preprint"}}