{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:43:09Z","timestamp":1783100589472,"version":"3.54.6"},"reference-count":29,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/100000026","name":"National Institute on Drug Abuse","doi-asserted-by":"publisher","award":["T32DA013911"],"award-info":[{"award-number":["T32DA013911"]}],"id":[{"id":"10.13039\/100000026","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["P20GM139664"],"award-info":[{"award-number":["P20GM139664"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Substance Use &amp; Addiction Journal"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:sec>\n                    <jats:title>Background\/Significance:<\/jats:title>\n                    <jats:p>Alcohol use carries significant morbidity and mortality, yet accurate identification of alcohol use disorder (AUD) remains a multi-layered problem for both researchers and clinicians.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective:<\/jats:title>\n                    <jats:p>To fine-tune a language model to AUD in the clinical narrative and to detect AUDs not accounted for by ICD-9 coding in the MIMIC-III database.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods:<\/jats:title>\n                    <jats:p>We applied clinicalBERT to unique patient discharge summaries. For classification, patients were divided into nonoverlapping groups stratified by the presence\/absence of AUD ICD diagnosis for model training (80%), validation (10%), and testing (10%). For detection, the model was trained (80%) and validated (20%) on 1:1 positive\/negative patients, then applied to remaining negative patient population. Physicians adjudicated 600 samples from the full model confidence spectrum to confirm AUD by Diagnostic and Statistical Manual of Mental Disorders-V criteria.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The model exhibited the following characteristics (mean, standard deviation): precision (0.9, 0.02), recall (0.65, 0.03), F-1 (0.75, 0.02), area under the receiver operating curve (0.97, 0.01), and area under the precision-recall curve (0.86, 0.01). Adjudication produced an estimated 4% under-documentation rate for the total study population. As model confidence increased, AUD under-documentation rate rose to 30% of the number of patients identified as positive by ICD-9 coding.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>\n                      Our model improves the identification of patients meeting AUD criteria, outperforming ICD codes in detecting cases of AUD. Detection discrepancy between ICD and free-text highlights clinician\n                      <jats:italic>under documentation<\/jats:italic>\n                      , not under recognition. Adjudication revealed model over-sensitivity to language around substance use, withdrawal, and chronic liver disease; future study requires application to a broader set of patient age and acuity. This model has the potential to improve rapid identification of patients with AUD and enhance treatment allocation.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/29767342241288112","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T05:43:09Z","timestamp":1735018989000},"page":"328-336","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":9,"title":["One Third of Alcohol Use Disorder Diagnoses are Missed by ICD Coding"],"prefix":"10.1177","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4346-8773","authenticated-orcid":false,"given":"Laura","family":"Mercurio","sequence":"first","affiliation":[{"name":"Departments of Emergency Medicine &amp; Pediatrics, Alpert Medical School of Brown University, Providence, RI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Augusto","family":"Garcia","sequence":"additional","affiliation":[{"name":"Division of Rheumatology, University of California San Francisco, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephanie","family":"Ruest","sequence":"additional","affiliation":[{"name":"Departments of Emergency Medicine &amp; Pediatrics, Alpert Medical School of Brown University, Providence, RI, USA"},{"name":"Injury Prevention Center of Rhode Island Hospital-Hasbro Children\u2019s Hospital, Providence, RI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susan J.","family":"Duffy","sequence":"additional","affiliation":[{"name":"Departments of Emergency Medicine &amp; Pediatrics, Alpert Medical School of Brown University, Providence, RI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carsten","family":"Eickhoff","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Brown University, Providence, RI, USA"},{"name":"School of Medicine, University of Tubingen, Tubingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"National Institute on Drug Abuse and Alcoholism. Alcohol Use in the United States: Age Groups and Demographic Characteristics. Alcohol Facts and Statistics. 2022. Accessed December 14 2023. https:\/\/www.niaaa.nih.gov\/alcohols-effects-health\/alcohol-topics\/alcohol-facts-and-statistics\/alcohol-use-united-states-age-groups-and-demographic-characteristics"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amepre.2017.02.014"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2021.109150"},{"key":"e_1_3_3_5_2","unstructured":"National Institute on Drug Abuse. Marijuana and hallucinogen use among young adults reached all time-high in 2021. August 22 2022. Accessed December 14 2023. https:\/\/nida.nih.gov\/news-events\/news-releases\/2022\/08\/marijuana-and-hallucinogen-use-among-young-adults-reached-all-time-high-in-2021"},{"key":"e_1_3_3_6_2","unstructured":"Berger D. Medical Complications: Common Alcohol-Related Concerns. National Institute on Alcohol Abuse and Alcoholism: core resource on alcohol. 2022. Accessed June 5 2024. https:\/\/www.niaaa.nih.gov\/health-professionals-communities\/core-resource-on-alcohol\/medical-complications-common-alcohol-related-concerns#pub-toc0"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1080\/02813430500475282"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-200412000-00002"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1093\/alcalc\/agv127"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsat.2019.11.008"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1097\/ADM.0000000000000260"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2018.01.035"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugalcdep.2017.05.048"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2022.850619"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsat.2011.10.010"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI190386"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.2196\/23456"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10620-017-4714-8"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1080\/08897077.2021.1986767"},{"key":"e_1_3_3_20_2","first-page":"2121","article-title":"Automated extraction of substance use information from clinical texts","volume":"2015","author":"Wang Y","year":"2015","unstructured":"Wang Y, Chen ES, Pakhomov S, et al. Automated extraction of substance use information from clinical texts. AMIA Annu Symp Proc. 2015;2015:2121-2130. eCollection 2015.","journal-title":"AMIA Annu Symp Proc"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocab116"},{"key":"e_1_3_3_22_2","unstructured":"Alsentzer E Murphy JR Boag W et al. Publicly available clinical BERT embeddings. arXiv. 2019. arXiv:1904.03323. Submitted on 6 Apr 2019 (v1) last revised 20 Jun 2019 (this version v3). https:\/\/arxiv.org\/abs\/1904.03323"},{"key":"e_1_3_3_23_2","unstructured":"Huang K Altosaar J Ranganath R. Clinicalbert: modeling clinical notes and predicting hospital readmission. arXiv. arXiv:1904.05342. Accessed April 10 2019. https:\/\/arxiv.org\/abs\/1904.05342"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9780890425787"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"issue":"1","key":"e_1_3_3_26_2","first-page":"39","article-title":"Alcohol-related morbidity and mortality","volume":"27","author":"Rehm J","year":"2003","unstructured":"Rehm J, Gmel G, Sempos CT, Trevisan M. Alcohol-related morbidity and mortality. Alcohol Res Health. 2003;27(1):39-51.","journal-title":"Alcohol Res Health"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(19)31775-1"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1111\/acer.13594"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1177\/00333549141291S206"},{"key":"e_1_3_3_30_2","first-page":"823","article-title":"Social determinant of health documentation trends and their association with emergency department admissions","volume":"2020","author":"McCormack LA","year":"2020","unstructured":"McCormack LA, Madlock-Brown C. Social determinant of health documentation trends and their association with emergency department admissions. AMIA Annu Symp Proc. 2020; 2020:823-832.","journal-title":"AMIA Annu Symp Proc"}],"container-title":["Substance Use &amp; Addiction Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/29767342241288112","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/29767342241288112","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/29767342241288112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T01:50:28Z","timestamp":1777600228000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/29767342241288112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":29,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1177\/29767342241288112"],"URL":"https:\/\/doi.org\/10.1177\/29767342241288112","relation":{},"ISSN":["2976-7342","2976-7350"],"issn-type":[{"value":"2976-7342","type":"print"},{"value":"2976-7350","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,7]]}}}