{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T06:32:23Z","timestamp":1788244343939,"version":"build-2803163510"},"reference-count":42,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001411","name":"Indian Council of Medical Research","doi-asserted-by":"publisher","award":["Grantathon2\/MH\u20104\/2023\u2010NCD\u20102"],"award-info":[{"award-number":["Grantathon2\/MH\u20104\/2023\u2010NCD\u20102"]}],"id":[{"id":"10.13039\/501100001411","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Drug and Alcohol Review"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Electronic health records contain both structured and unstructured data, with unstructured clinical notes widely used in addiction psychiatry. Clinical notes have numerous errors and require proofreading to ensure accuracy and readability. This study evaluates natural language processing methods and adapts a Large Language Model (LLM) for proofreading clinical notes and extracting substance\u2010related information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analysed clinical notes from a 5\u2010year addiction medicine electronic health record dataset (2018\u20132023), selecting 6500 notes. The proofreading task involved correcting spelling and expanding abbreviations, while information extraction identified the presence of substance use and quantified the time since last use. Annotations by a team of doctors and nurses provided the gold standard. Against this, we compared the performance of existing solutions, including LLMs, and adapted an LLM for these tasks. The final model (fine\u2010tuned LLAMA\u20103.2\u20103b) is also compared against a state\u2010of\u2010the\u2010art commercial model (Generative Pretrained Transformer\u20104\u2010o), and a human\u2010preference experiment is done with masked raters choosing between model\u2010generated and human\u2010generated proofread versions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Proofreading improved readability and decreased out\u2010of\u2010vocabulary words. LLM\u2010based solutions outperformed simpler approaches. The fine\u2010tuned model outperformed the Generative Pretrained Transformer\u20104\u2010o on both tasks. Masked human evaluators chose model\u2010corrected clinical notes over the human\u2010corrected version in 62% of trials (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001). On the information extraction task, while the overall performance is satisfactory (Mean F1 0.99), it is poor on rarer substance classes like hallucinogens.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion and Conclusions<\/jats:title>\n                    <jats:p>Fine\u2010tuned LLMs effectively standardised clinical notes and extracted structured information from addiction psychiatry records. Both these functionalities have important applications. Standardising improves the readability of clinical documentation and facilitates communication within and between interdisciplinary teams. Automated information extraction can decrease the burden on clinical staff, allow the creation of research cohorts from existing records and improve treatment outcomes by extracting critical information, such as \u2018time since last drink\u2019, which can be used to raise alerts. Even with limited computational resources, it is possible to adapt open\u2010source LLMs for bespoke tasks in the field of addiction psychiatry. Our proposed solution is a model that can be deployed on consumer\u2010grade servers, thus ensuring data privacy and security.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/dar.70059","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T07:23:16Z","timestamp":1761722596000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Language Models for Standardising Clinical Notes and Information Extraction in Addiction Psychiatry\u2014An Empirical Study"],"prefix":"10.1111","volume":"45","author":[{"given":"Haritha","family":"Gireesh","sequence":"first","affiliation":[{"name":"Department of Psychiatry National Institute of Mental Health and Neuro Sciences  Bengaluru India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4558-3890","authenticated-orcid":false,"given":"Lekhansh","family":"Shukla","sequence":"additional","affiliation":[{"name":"Centre for Addiction Medicine, Department of Psychiatry National Institute of Mental Health and Neuro Sciences  Bengaluru India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8761-7908","authenticated-orcid":false,"given":"Prakrithi","family":"Shivaprakash","sequence":"additional","affiliation":[{"name":"Centre for Addiction Medicine, Department of Psychiatry National Institute of Mental Health and Neuro Sciences  Bengaluru India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Animesh","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering Indian Institute of Technology  Kharagpur India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prabhat","family":"Chand","sequence":"additional","affiliation":[{"name":"Centre for Addiction Medicine, Department of Psychiatry National Institute of Mental Health and Neuro Sciences  Bengaluru India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pratima","family":"Murthy","sequence":"additional","affiliation":[{"name":"Centre for Addiction Medicine, Department of Psychiatry National Institute of Mental Health and Neuro Sciences  Bengaluru India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/wps.21073"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0b013e3182988d59"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1407298"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-025-09499-2"},{"key":"e_1_2_12_6_1","volume-title":"Drug Abuse Warning Network: Development of a New Design Methodology Report","author":"Substance Abuse and Mental Health Services Administration","year":"2002"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-024-02911-1"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2010.007237"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1177\/21501319231166921"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-022-01837-9"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-022-01528-4"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2021.606599"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac058"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2023.101260"},{"key":"e_1_2_12_15_1","volume-title":"Statistical Language Learning","author":"Charniak E.","year":"1996"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac149"},{"key":"e_1_2_12_17_1","first-page":"88","article-title":"A Quantitative and Qualitative Evaluation of Sentence Boundary Detection for the Clinical Domain","volume":"2016","author":"Griffis D.","year":"2016","journal-title":"AMIA Joint Summits on Translational Science Proceedings"},{"key":"e_1_2_12_18_1","first-page":"438","article-title":"Launching Into Clinical Space With medspaCy: A New Clinical Text Processing Toolkit in Python","volume":"2021","author":"Eyre H.","year":"2021","journal-title":"AMIA Annual Symposium Proceedings"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-56989-2"},{"key":"e_1_2_12_20_1","unstructured":"W. X.Zhao K.Zhou J.Li et\u00a0al. \u201cA Survey of Large Language Models \u201dArXiv 2023 abs\/2303.18223."},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-02954-4"},{"key":"e_1_2_12_22_1","unstructured":"Y.Hu X.Zuo Y.Zhou et\u00a0al. \u201cInformation Extraction From Clinical Notes: Are we Ready to Switch to Large Language Models?\u201darXiv e\u2010Prints 2024 arXiv:2411.10020."},{"key":"e_1_2_12_23_1","volume-title":"The ICD\u201010 Classification of Mental and Behavioural Disorders: Clinical Descriptions and Diagnostic Guidelines","author":"WHO","year":"1992"},{"key":"e_1_2_12_24_1","doi-asserted-by":"crossref","unstructured":"V.Raheja D.Kumar R.Koo andD.Kang \u201cCoEdIT: Text Editing by Task\u2010Specific Instruction Tuning \u201dArXiv 2023 abs\/2305.09857.","DOI":"10.18653\/v1\/2023.findings-emnlp.350"},{"key":"e_1_2_12_25_1","unstructured":"Y. A.Qwen B.Yang B.Zhang et\u00a0al. \u201cQwen2.5 Technical Report \u201darXiv 2024 2412.15115 https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv241215115Q."},{"key":"e_1_2_12_26_1","unstructured":"Meta \u201cLlama\u20103.1\u20108B\u2010Instruct: Meta Inc \u201d2025."},{"key":"e_1_2_12_27_1","volume-title":"Llama 3.2: Revolutionizing Edge AI and Vision With Open, Customizable Models: Meta Inc","author":"Meta","year":"2025"},{"key":"e_1_2_12_28_1","unstructured":"M.Abdin J.Aneja H.Awadalla et\u00a0al. \u201cPhi\u20103 Technical Report: A Highly Capable Language Model Locally on Your Phone \u201darXiv 2024 2404.14219 p. https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240414219A."},{"key":"e_1_2_12_29_1","unstructured":"A.Hurst A.Lerer A. P.Goucher et\u00a0al. \u201cGPT\u20104o System Card \u201darXiv 2024 2410.21276 p https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv241021276O."},{"key":"e_1_2_12_30_1","unstructured":"Open AI Inc \u201cOpen AI Trust Portal \u201d2025 https:\/\/trust.openai.com\/?product=API."},{"key":"e_1_2_12_31_1","unstructured":"Open AI Inc. \u201cData Controls on the Open AI Platform \u201d2025 https:\/\/platform.openai.com\/docs\/guides\/your\u2010data#how\u2010we\u2010use\u2010your\u2010data."},{"key":"e_1_2_12_32_1","unstructured":"K.Atkinson \u201cSpell Checking Oriented Word Lists (SCOWL) \u201d2024 http:\/\/wordlist.aspell.net\/scowl\u2010readme\/."},{"key":"e_1_2_12_33_1","unstructured":"National Library of Medicine (US) \u201cUMLS Reference Manual Bethesda (MD) \u201d2009 https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK9685\/table\/ch03.T.concept_names_and_sources_file_mr\/."},{"key":"e_1_2_12_34_1","volume-title":"METEOR: An Automatic Metric for MT Evaluation With Improved Correlation With Human Judgments","author":"Banerjee S.","year":"2005"},{"key":"e_1_2_12_35_1","unstructured":"T.Zhang V.Kishore F.Wu K. Q.Weinberger andY.Artzi \u201cBERTScore: Evaluating Text Generation With BERT \u201dArXiv 2019 abs\/1904.09675."},{"key":"e_1_2_12_36_1","first-page":"992","article-title":"Cross\u2010Entropy Loss Functions: Theoretical Analysis and Applications","volume":"202","author":"Mao A.","year":"2023","journal-title":"Proceedings of the 40th International Conference on Machine Learning"},{"issue":"2","key":"e_1_2_12_37_1","article-title":"LoRA: Low\u2010Rank Adaptation of Large Language Models","volume":"1","author":"Hu E. J.","year":"2022","journal-title":"ICLR"},{"key":"e_1_2_12_38_1","doi-asserted-by":"publisher","DOI":"10.1093\/alcalc\/agaa042"},{"key":"e_1_2_12_39_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocab116"},{"key":"e_1_2_12_40_1","doi-asserted-by":"publisher","DOI":"10.2196\/13876"},{"key":"e_1_2_12_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjsurg.2015.12.005"},{"key":"e_1_2_12_42_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.0357"},{"key":"e_1_2_12_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01429-0"}],"container-title":["Drug and Alcohol Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/dar.70059","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/dar.70059","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/dar.70059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T01:12:12Z","timestamp":1771204332000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/dar.70059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1111\/dar.70059"],"URL":"https:\/\/doi.org\/10.1111\/dar.70059","archive":["Portico"],"relation":{},"ISSN":["0959-5236","1465-3362"],"issn-type":[{"value":"0959-5236","type":"print"},{"value":"1465-3362","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"assertion":[{"value":"2025-02-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70059"}}