{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:17:16Z","timestamp":1783145836101,"version":"3.54.6"},"reference-count":115,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM011934"],"award-info":[{"award-number":["R01LM011934"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM014508"],"award-info":[{"award-number":["R01LM014508"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.jbi.2026.105050","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:08:32Z","timestamp":1776874112000},"page":"105050","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Clinical document metadata extraction: A scoping review"],"prefix":"10.1016","volume":"179","author":[{"given":"Kurt","family":"Miller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuhao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Hersh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kirk","family":"Roberts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven","family":"Bedrick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2570-3741","authenticated-orcid":false,"given":"Hongfang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0005","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1370\/afm.3047","article-title":"More tethered to the EHR: EHR workload trends among academic primary care physicians, 2019-2023","volume":"22","author":"Arndt","year":"2024","journal-title":"Ann. Fam. Med."},{"issue":"2","key":"10.1016\/j.jbi.2026.105050_b0010","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1136\/jamia.2010.007237","article-title":"Data from clinical notes: a perspective on the tension between structure and flexible documentation","volume":"18","author":"Rosenbloom","year":"2011","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"4","key":"10.1016\/j.jbi.2026.105050_b0015","doi-asserted-by":"crossref","first-page":"301","DOI":"10.7326\/M14-2128","article-title":"Clinical documentation in the 21st century: executive summary of a policy position paper from the American college of physicians","volume":"162","author":"Kuhn","year":"2015","journal-title":"Ann. Intern. Med."},{"key":"10.1016\/j.jbi.2026.105050_b0020","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.jbi.2016.04.005","article-title":"Using phrases and document metadata to improve topic modeling of clinical reports","volume":"61","author":"Speier","year":"2016","journal-title":"J. Biomed. Inform."},{"issue":"3","key":"10.1016\/j.jbi.2026.105050_b0025","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1186\/s12911-019-0786-z","article-title":"Developing a portable natural language processing based phenotyping system","volume":"19","author":"Sharma","year":"2019","journal-title":"BMC Med. Inf. Decis. Making"},{"key":"10.1016\/j.jbi.2026.105050_b0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpi.2025.100520","article-title":"Retrieval-augmented generation for interpreting clinical laboratory regulations using large language models","volume":"19","author":"Nanua","year":"2025","journal-title":"J. Pathol. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0035","unstructured":"G. Keerthana, M. Gupta, CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs, 2025, https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250706715K (accessed July 01, 2025)."},{"issue":"4","key":"10.1016\/j.jbi.2026.105050_b0040","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1093\/jamiaopen\/ooz035","article-title":"Heterogeneity introduced by EHR system implementation in a de-identified data resource from 100 non-affiliated organizations","volume":"2","author":"Glynn","year":"2019","journal-title":"JAMIA Open"},{"issue":"11","key":"10.1016\/j.jbi.2026.105050_b0045","doi-asserted-by":"crossref","first-page":"2355","DOI":"10.1007\/s11606-019-05025-3","article-title":"Variation in physicians\u2019 electronic health record documentation and potential patient harm from that variation","volume":"34","author":"Cohen","year":"2019","journal-title":"J. Gen. Intern. Med."},{"issue":"12","key":"10.1016\/j.jbi.2026.105050_b0050","first-page":"845","article-title":"Nursing documentation variation across different medical facilities within an integrated healthcare system","volume":"39","author":"Kang","year":"2021","journal-title":"Comput. Inform. Nurs."},{"issue":"5","key":"10.1016\/j.jbi.2026.105050_b0055","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1055\/s-0040-1718535","article-title":"Transitions from one electronic health record to another: challenges, pitfalls, and recommendations","volume":"11","author":"Huang","year":"2020","journal-title":"Appl. Clin. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0060","doi-asserted-by":"crossref","unstructured":"Y. Shao, G. Divita, T.E. Workman, D. Redd, J. Garvin, Q. Zeng-Treitler, Clinical Sublanguage Trend and Usage Analysis from a Large Clinical Corpus, 2020.","DOI":"10.1109\/BigData50022.2020.9378203"},{"key":"#cr-split#-10.1016\/j.jbi.2026.105050_b0065.1","unstructured":"K. Miller, S. Moon, S. Fu, H. Liu, Contextual Variation of Clinical Notes induced by EHR Migration, AMIA Annu. Symp. Proc. 2023"},{"key":"#cr-split#-10.1016\/j.jbi.2026.105050_b0065.2","unstructured":"2023:1155-64 [published Online First: 2024\/01\/15]."},{"issue":"5","key":"10.1016\/j.jbi.2026.105050_b0070","doi-asserted-by":"crossref","first-page":"856","DOI":"10.3390\/math13050856","article-title":"Hallucination mitigation for retrieval-augmented large language models: a review","volume":"13","author":"Zhang","year":"2025","journal-title":"Mathematics"},{"key":"10.1016\/j.jbi.2026.105050_b0075","unstructured":"On Context Utilization in Summarization with Large Language Models; 2024 August; Bangkok, Thailand. Association for Computational Linguistics."},{"issue":"8","key":"10.1016\/j.jbi.2026.105050_b0080","doi-asserted-by":"crossref","first-page":"e2425981","DOI":"10.1001\/jamanetworkopen.2024.25981","article-title":"Use of generative AI to identify helmet status among patients with micromobility-related injuries from unstructured clinical notes","volume":"7","author":"Burford","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"10.1016\/j.jbi.2026.105050_b0085","unstructured":"J. Zhao, Z. Ji, Y. Feng, et al., Meta-chunking: learning text segmentation and semantic completion via logical perception, 2024, https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv241012788Z (accessed October 01, 2024)."},{"key":"10.1016\/j.jbi.2026.105050_b0090","unstructured":"M. G\u00fcnther, I. Mohr, D.J. Williams, B. Wang, H. Xiao, Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models, 2024, https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240904701G (accessed September 01, 2024)."},{"issue":"6","key":"10.1016\/j.jbi.2026.105050_b0095","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000877","article-title":"Retrieval augmented generation for large language models in healthcare: A systematic review","volume":"4","author":"Amugongo","year":"2025","journal-title":"PLOS Digital Health"},{"key":"10.1016\/j.jbi.2026.105050_b0100","unstructured":"Precise zero-shot dense retrieval without relevance labels. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2023."},{"key":"10.1016\/j.jbi.2026.105050_b0105","unstructured":"Anthropic, Introducing Contextual Retrieval, 2024."},{"key":"10.1016\/j.jbi.2026.105050_b0110","article-title":"Comparison of prompt engineering and fine-tuning strategies in large language models in the classification of clinical notes","volume":"2024","author":"Zhang","year":"2024","journal-title":"AMIA Jt. Summits Transl. Sci. Proc."},{"key":"10.1016\/j.jbi.2026.105050_b0115","unstructured":"F.L. Piya, R. Beheshti, ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs, 2025, https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250416394P (accessed April 01, 2025)."},{"key":"10.1016\/j.jbi.2026.105050_b0120","unstructured":"J. Riley, Understanding metadata. Washington DC, United States: National Information Standards Organization (http:\/\/www.niso.org\/publications\/press\/UnderstandingMetadata.pdf) 2017;23:7-10."},{"key":"10.1016\/j.jbi.2026.105050_b0125","unstructured":"LOINC Document Ontology. Secondary LOINC Document Ontology, https:\/\/loinc.org\/document-ontology\/."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0130","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1186\/s12874-018-0611-x","article-title":"Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach","volume":"18","author":"Munn","year":"2018","journal-title":"BMC Med. Res. Method."},{"issue":"7","key":"10.1016\/j.jbi.2026.105050_b0135","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1000097","article-title":"Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement","volume":"6","author":"Moher","year":"2009","journal-title":"PLoS Med."},{"issue":"7","key":"10.1016\/j.jbi.2026.105050_b0140","doi-asserted-by":"crossref","first-page":"467","DOI":"10.7326\/M18-0850","article-title":"PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation","volume":"169","author":"Tricco","year":"2018","journal-title":"Ann. Intern. Med."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0145","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.jbi.2011.08.020","article-title":"Building an automated SOAP classifier for emergency department reports","volume":"45","author":"Mowery","year":"2012","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0150","first-page":"604","article-title":"Identification of patients with family history of pancreatic cancer-investigation of an NLP system portability","volume":"216","author":"Mehrabi","year":"2015","journal-title":"Stud. Health Technol. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0155","article-title":"Scaling out and evaluation of OBSecAn, an automated section annotator for semi-structured clinical documents, on a large VA clinical corpus","volume":"2015","author":"Tran","year":"2015","journal-title":"AMIA Annu. Symp. Proc."},{"key":"10.1016\/j.jbi.2026.105050_b0160","article-title":"JSONize: a scalable machine learning pipeline to model medical notes as semi-structured documents","volume":"2020","author":"Rush","year":"2020","journal-title":"AMIA Jt. Summits Transl. Sci. Proc."},{"key":"10.1016\/j.jbi.2026.105050_b0165","doi-asserted-by":"crossref","DOI":"10.63317\/3tsi2bjytv6w","article-title":"Statistical section segmentation in free-text clinical records","author":"Tepper","year":"2012","journal-title":"LREC"},{"key":"10.1016\/j.jbi.2026.105050_b0170","unstructured":"Explicit and Implicit Section Identification from Clinical Discharge Summaries, 2022 16th International Conference on Ubiquitous Information Management and Communication (IMCOM); 2022 3-5 Jan. 2022."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0175","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1093\/jamia\/ocad190","article-title":"Improving model transferability for clinical note section classification models using continued pretraining","volume":"31","author":"Zhou","year":"2023","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105050_b0180","first-page":"125","article-title":"Improving the transferability of clinical note section classification models with BERT and large language model ensembles","volume":"2023","author":"Zhou","year":"2023","journal-title":"Proc. Conf. Assoc. Comput. Linguist Meet"},{"key":"10.1016\/j.jbi.2026.105050_b0185","doi-asserted-by":"crossref","unstructured":"W. Zhou, T.A. Miller, Generalizable Clinical Note Section Identification with Large Language Models, medRxiv 2024:2024.02.18.24303014 doi: 10.1101\/2024.02.18.24303014.","DOI":"10.1101\/2024.02.18.24303014"},{"key":"10.1016\/j.jbi.2026.105050_b0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2015.07.001","article-title":"Identifying risk factors for heart disease over time: overview of 2014 i2b2\/UTHealth shared task Track 2","volume":"58","author":"Stubbs","year":"2015","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2015.09.013","article-title":"A context-aware approach for progression tracking of medical concepts in electronic medical records","volume":"58","author":"Chang","year":"2015","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0200","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1162\/tacl_a_00172","article-title":"Temporal annotation in the clinical domain","volume":"2","author":"Styler","year":"2014","journal-title":"Trans. Assoc. Comput. Linguist"},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0205","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105050_b0210","unstructured":"Automated clinical diagnosis: The role of content in various sections of a clinical document, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); 2017 13-16 Nov. 2017."},{"key":"10.1016\/j.jbi.2026.105050_b0215","article-title":"A preliminary characterization of canonicalized and non-canonicalized section headers across variable clinical note types","volume":"2020","author":"Wang","year":"2020","journal-title":"AMIA Annu. Symp. Proc."},{"key":"10.1016\/j.jbi.2026.105050_b0220","doi-asserted-by":"crossref","unstructured":"M. Saleh, S. Baghdadi, S. Paquelet, TocBERT: Medical Document Structure Extraction Using Bidirectional Transformers, 2024, https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240619526S (accessed June 01, 2024).","DOI":"10.1109\/IS61756.2024.10705189"},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0225","first-page":"1","article-title":"Context parameters retrieval framework from electronic healthcare record through biomedical NLP for clinical support","volume":"11","author":"Paliwal","year":"2023","journal-title":"Int. J. Intelligent Eng. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0230","unstructured":"LLM-Powered Diagnostic Decision Support System Integrated with Electronic Health Records, 2025 6th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2025; 2025."},{"key":"10.1016\/j.jbi.2026.105050_b0235","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2025.104927","article-title":"TriMedPrompt: A unified prompting framework for realistic and layout-conformant clinical progress note synthesis","volume":"171","author":"Keerthana","year":"2025","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0240","unstructured":"A New Public Corpus for Clinical Section Identification: MedSecId; 2022 October; Gyeongju, Republic of Korea. International Committee on Computational Linguistics."},{"key":"#cr-split#-10.1016\/j.jbi.2026.105050_b0245.1","doi-asserted-by":"crossref","unstructured":"Y. Gao, D. Dligach, T. Miller, et al., Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding, LREC Int Conf Lang Resour Eval 2022","DOI":"10.63317\/23marhcyka8y"},{"key":"#cr-split#-10.1016\/j.jbi.2026.105050_b0245.2","unstructured":"2022: 5484-93 [published Online First: 2022\/08\/09]."},{"key":"10.1016\/j.jbi.2026.105050_b0250","unstructured":"Y.C.J. Gao, T. Miller, B. Sharma, M. Churpek, D. Dligach, M. Afshar, Tasks 1 and 3 from Progress Note Understanding Suite of Tasks: SOAP Note Tagging and Problem List Summarization (version 1.0.0). 1.0.0 ed: PhysioNet."},{"issue":"7","key":"10.1016\/j.jbi.2026.105050_b0255","doi-asserted-by":"crossref","first-page":"1164","DOI":"10.1093\/jamia\/ocaf084","article-title":"Dynamic few-shot prompting for clinical note section classification using lightweight, open-source large language models","volume":"32","author":"Miller","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105050_b0260","unstructured":"MTSamples, Secondary MTSamples, https:\/\/mtsamples.com\/."},{"key":"10.1016\/j.jbi.2026.105050_b0265","doi-asserted-by":"crossref","unstructured":"J.K. Kenei, E. Opiyo, Using classification and visualization to support clinical texts review in electronic clinical documentation, Proceedings of the 6th International Conference on Medical and Health Informatics, Virtual Event, Japan: Association for Computing Machinery, 2022:78\u201384.","DOI":"10.1145\/3545729.3545746"},{"key":"10.1016\/j.jbi.2026.105050_b0270","unstructured":"I. de la Iglesia, A. Atutxa, K. Gojenola, M. Viv\u00f3 Pascual, P. Chocron, G. de Maeztu, ClinAIS Corpus: Automatic Identification of Sections in Spanish Clinical Documents - IberLEF 2023: Zenodo, 2023."},{"key":"10.1016\/j.jbi.2026.105050_b0275","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104461","article-title":"An open source corpus and automatic tool for section identification in Spanish health records","volume":"145","author":"de la Iglesia","year":"2023","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0280","unstructured":"A. Miranda-Escalada, A. Gonzalez-Agirre, J. Armengol-Estap\u00e9, M. Krallinger, Overview of automatic clinical coding: annotations, guidelines, and solutions for non-English clinical cases at CodiEsp track of CLEF eHealth 2020, 2020."},{"key":"10.1016\/j.jbi.2026.105050_b0285","unstructured":"Automatic Segmentation of Clinical Narratives in Sections with Pre-Trained Clinical Transformer Models, CEUR Workshop Proceedings, 2023. CEUR-WS."},{"key":"10.1016\/j.jbi.2026.105050_b0290","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/s13326-016-0084-y","article-title":"Normalizing acronyms and abbreviations to aid patient understanding of clinical texts: ShARe\/CLEF eHealth Challenge 2013, Task 2","volume":"7","author":"Mowery","year":"2016","journal-title":"J. Biomed. Semantics"},{"key":"10.1016\/j.jbi.2026.105050_b0295","unstructured":"A Supervised Abbreviation Resolution System for Medical Text, Conference and Labs of the Evaluation Forum; 2013."},{"key":"10.1016\/j.jbi.2026.105050_b0300","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/1471-244X-9-51","article-title":"The south london and maudsley NHS foundation trust biomedical research centre (SLAM BRC) case register: development and descriptive data","volume":"9","author":"Stewart","year":"2009","journal-title":"BMC Psychiatry"},{"issue":"5","key":"10.1016\/j.jbi.2026.105050_b0305","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1093\/jamia\/ocx160","article-title":"SemEHR: A general-purpose semantic search system to surface semantic data from clinical notes for tailored care, trial recruitment, and clinical research","volume":"25","author":"Wu","year":"2018","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"2","key":"10.1016\/j.jbi.2026.105050_b0310","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1136\/amiajnl-2011-000538","article-title":"iDASH: integrating data for analysis, anonymization, and sharing","volume":"19","author":"Ohno-Machado","year":"2012","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0315","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1186\/s12911-017-0556-8","article-title":"Medical subdomain classification of clinical notes using a machine learning-based natural language processing approach","volume":"17","author":"Weng","year":"2017","journal-title":"BMC Med. Inf. Decis. Making"},{"issue":"S7","key":"10.1016\/j.jbi.2026.105050_b0320","doi-asserted-by":"crossref","first-page":"3362","DOI":"10.53730\/ijhs.v6nS7.12476","article-title":"Classification of medical specialty for text medical report based on natural language processing and deep learning","volume":"6","author":"Almuhana","year":"2022","journal-title":"Int. J. Health Sci."},{"key":"10.1016\/j.jbi.2026.105050_b0325","unstructured":"CMS, Research, statistics, data, and systems."},{"key":"10.1016\/j.jbi.2026.105050_b0330","unstructured":"Medical Provider Specialty Predictions for the Detection of Anomalous Medicare Insurance Claims, 2017 IEEE International Conference on Information Reuse and Integration (IRI); 2017 4-6 Aug. 2017."},{"key":"10.1016\/j.jbi.2026.105050_b0335","unstructured":"Tanya, Medical Specialty Classification, 2022."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0340","doi-asserted-by":"crossref","DOI":"10.1155\/2023\/4919371","article-title":"Medical specialty classification based on semiadversarial data augmentation","volume":"2023","author":"Zhang","year":"2023","journal-title":"Comput. Intell. Neurosci."},{"key":"10.1016\/j.jbi.2026.105050_b0345","unstructured":"Medical Specialty Classification from A Bangla Dataset: A Token Level Approach Using Several Machine And Deep Learning Algorithms, 2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT); 2021 18-20 Nov. 2021."},{"key":"10.1016\/j.jbi.2026.105050_b0350","doi-asserted-by":"crossref","unstructured":"S. Kathirvel, L. Mookiah, Medical Specialty Classification Using Large Language Models (LLMs), The International FLAIRS Conference Proceedings 2025;38 doi: 10.32473\/flairs.38.1.138953.","DOI":"10.32473\/flairs.38.1.138953"},{"issue":"5","key":"10.1016\/j.jbi.2026.105050_b0355","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1136\/amiajnl-2011-000734","article-title":"A classification approach to coreference in discharge summaries: 2011 i2b2 challenge","volume":"19","author":"Xu","year":"2012","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105050_b0360","unstructured":"Chinese patient record triage NLP dataset on HuggingFace. Secondary Chinese patient record triage NLP dataset on HuggingFace. https:\/\/huggingface.co\/datasets\/zeng981\/nlpdataset."},{"issue":"12","key":"10.1016\/j.jbi.2026.105050_b0365","doi-asserted-by":"crossref","DOI":"10.3390\/app15126525","article-title":"Leveraging large language models for departmental classification of medical records","volume":"15","author":"Ihnaini","year":"2025","journal-title":"Appl. Sci."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0370","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1186\/s12874-019-0792-y","article-title":"Current approaches to identify sections within clinical narratives from electronic health records: a systematic review","volume":"19","author":"Pomares-Quimbaya","year":"2019","journal-title":"BMC Med. Res. Method."},{"issue":"4","key":"10.1016\/j.jbi.2026.105050_b0375","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1186\/s12911-019-0856-2","article-title":"Ontology-based venous thromboembolism risk assessment model developing from medical records","volume":"19","author":"Yang","year":"2019","journal-title":"BMC Med. Inf. Decis. Making"},{"key":"10.1016\/j.jbi.2026.105050_b0380","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104360","article-title":"Predicting relations between SOAP note sections: The value of incorporating a clinical information model","volume":"141","author":"Socrates","year":"2023","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0385","unstructured":"A general supervised approach to segmentation of clinical texts, Proceedings - 2014 IEEE International Conference on Big Data, IEEE Big Data 2014; 2014."},{"key":"#cr-split#-10.1016\/j.jbi.2026.105050_b0390.1","unstructured":"C. Lohr, S. Luther, F. Matthies, et al., CDA-compliant section annotation of german-language discharge summaries: guideline development, annotation campaign, section classification, AMIA Annu Symp Proc 2018"},{"key":"#cr-split#-10.1016\/j.jbi.2026.105050_b0390.2","unstructured":"2018:770-79 [published Online First: 2019\/03\/01]."},{"key":"10.1016\/j.jbi.2026.105050_b0395","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2020.104302","article-title":"Automatic classification of scanned electronic health record documents","volume":"144","author":"Goodrum","year":"2020","journal-title":"Int. J. Med. Inf."},{"key":"10.1016\/j.jbi.2026.105050_b0400","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooac045","article-title":"Deep learning-based NLP data pipeline for EHR-scanned document information extraction","author":"Hsu","year":"2022","journal-title":"JAMIA Open"},{"issue":"3","key":"10.1016\/j.jbi.2026.105050_b0405","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0283800","article-title":"Assessing document section heterogeneity across multiple electronic health record systems for computational phenotyping: A case study of heart-failure phenotyping algorithm","volume":"18","author":"Moon","year":"2023","journal-title":"PLoS One"},{"key":"10.1016\/j.jbi.2026.105050_b0410","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.105922","article-title":"Hybrid method to automatically extract medical document tree structure","volume":"120","author":"Landolsi","year":"2023","journal-title":"Eng. Appl. Artif. Intel."},{"key":"10.1016\/j.jbi.2026.105050_b0415","doi-asserted-by":"crossref","DOI":"10.1155\/2015\/873012","article-title":"Recognition and evaluation of clinical section headings in clinical documents using token-based formulation with conditional random fields","volume":"2015","author":"Dai","year":"2015","journal-title":"Biomed Res. Int."},{"key":"10.1016\/j.jbi.2026.105050_b0420","article-title":"Normalizing clinical document titles to LOINC document ontology: an initial study","volume":"2020","author":"Zuo","year":"2020","journal-title":"AMIA Annu. Symp. Proc."},{"key":"10.1016\/j.jbi.2026.105050_b0425","unstructured":"A. Karpov, O. Jokisch, R. Potapova, (Eds.), Detecting Section Boundaries in Medical Dictations: Toward Real-Time Conversion of Medical Dictations to Clinical Reports, Speech and Computer; 2018 2018\/\/; Cham. Springer International Publishing."},{"key":"10.1016\/j.jbi.2026.105050_b0430","first-page":"35","article-title":"Fast model adaptation for automated section classification in electronic medical records","volume":"216","author":"Ni","year":"2015","journal-title":"Stud. Health Technol. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0435","article-title":"Mapping clinical documents to the logical observation identifiers, names and codes (LOINC) document ontology using electronic health record systems structured metadata","volume":"2023","author":"Khan","year":"2023","journal-title":"AMIA Annu. Symp. Proc."},{"key":"10.1016\/j.jbi.2026.105050_b0440","doi-asserted-by":"crossref","unstructured":"A. Subramanian, P.K. Suresh, S. Santhiappan, A robust section identification method for scanned electronic health records, Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD), Mumbai, India: Association for Computing Machinery, 2023:213\u201317.","DOI":"10.1145\/3570991.3571011"},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0445","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s12911-023-02105-7","article-title":"Automatic medical specialty classification based on patients\u2019 description of their symptoms","volume":"23","author":"Mao","year":"2023","journal-title":"BMC Med. Inf. Decis. Making"},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0450","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0317795","article-title":"Entity-enhanced BERT for medical specialty prediction based on clinical questionnaire data","volume":"20","author":"Lee","year":"2025","journal-title":"PLoS One"},{"key":"10.1016\/j.jbi.2026.105050_b0455","article-title":"Transformer-based active learning for multi-class text annotation and classification","volume":"10","author":"Afzal","year":"2024","journal-title":"Digit Health"},{"key":"10.1016\/j.jbi.2026.105050_b0460","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2021.103875","article-title":"A section identification tool: Towards HL7 CDA\/CCR standardization in Spanish discharge summaries","volume":"121","author":"Goenaga","year":"2021","journal-title":"J. Biomed. Inform."},{"issue":"3","key":"10.1016\/j.jbi.2026.105050_b0465","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.1109\/JBHI.2023.3346210","article-title":"EHR-HGCN: an enhanced hybrid approach for text classification using heterogeneous graph convolutional networks in electronic health records","volume":"28","author":"Wang","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0470","unstructured":"Leveraging Medical Literature for Section Prediction in Electronic Health Records; 2019 November; Hong Kong, China. Association for Computational Linguistics."},{"key":"10.1016\/j.jbi.2026.105050_b0475","unstructured":"A Joint Model of Clinical Domain Classification and Slot Filling Based on RCNN and BiGRU-CRF, 2019 IEEE International Conference on Big Data (Big Data); 2019 9-12 Dec. 2019."},{"key":"10.1016\/j.jbi.2026.105050_b0480","first-page":"162","article-title":"From proprietary printed forms to standardized digital exchange formats - care transition records to FHIR as an example","volume":"331","author":"Werlitz","year":"2025","journal-title":"Stud. Health Technol. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0485","unstructured":"Leveraging Task Transferability to Meta-learning for Clinical Section Classification with Limited Data; 2022 May; Dublin, Ireland. Association for Computational Linguistics."},{"key":"10.1016\/j.jbi.2026.105050_b0490","first-page":"769","article-title":"Comparative analysis of NLP models for automatic LOINC document ontology named entity recognition in clinical note titles","volume":"329","author":"Bowles","year":"2025","journal-title":"Stud. Health Technol. Inform."},{"key":"10.1016\/j.jbi.2026.105050_b0495","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.123046","article-title":"SOAP classifier for free-text clinical notes with domain-specific pre-trained language models","volume":"245","author":"de Oliveira","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.jbi.2026.105050_b0500","unstructured":"P. Richter-Pechanski, P. Wiesenbach, D.M. Schwab, et al., Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting, 2024, https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240313369R (accessed March 01, 2024)."},{"issue":"9","key":"10.1016\/j.jbi.2026.105050_b0505","doi-asserted-by":"crossref","first-page":"2040","DOI":"10.1093\/jamia\/ocae157","article-title":"Disambiguation of acronyms in clinical narratives with large language models","volume":"31","author":"Kugic","year":"2024","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105050_b0510","doi-asserted-by":"crossref","DOI":"10.1038\/s43856-025-01091-3","article-title":"Development and evaluation of a clinical note summarization system using large language models","author":"Oliveira","year":"2025","journal-title":"Commun. Med."},{"key":"10.1016\/j.jbi.2026.105050_b0515","unstructured":"R. Bellazzi, J.M. Juarez Herrero, L. Sacchi, B. Zupan, (Eds.), ELMTEX: Fine-Tuning LLMs for Structured Clinical Information Extraction, A Case Study on Clinical Reports, Artificial Intelligence in Medicine; 2025 2025\/\/; Cham. Springer Nature Switzerland."},{"key":"10.1016\/j.jbi.2026.105050_b0520","doi-asserted-by":"crossref","DOI":"10.2196\/52967","article-title":"Use of metadata-driven approaches for data harmonization in the medical domain: scoping review","volume":"12","author":"Peng","year":"2024","journal-title":"JMIR Med. Inform."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0525","doi-asserted-by":"crossref","DOI":"10.2196\/25440","article-title":"Understanding the nature of metadata: systematic review","volume":"24","author":"Ulrich","year":"2022","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.jbi.2026.105050_b0530","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.3389\/fninf.2011.00016","article-title":"A bottom-up approach to data annotation in neurophysiology","volume":"5","author":"Grewe","year":"2011","journal-title":"Front. Neuroinf."},{"key":"10.1016\/j.jbi.2026.105050_b0535","first-page":"418","article-title":"Towards data value-level metadata for clinical studies","volume":"234","author":"Zozus","year":"2017","journal-title":"Stud. Health Technol. Inform."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0540","doi-asserted-by":"crossref","first-page":"12880","DOI":"10.1038\/s41598-018-31290-z","article-title":"A survival metadata analysis responsive tool (SMART) for web-based analysis of patient survival and risk","volume":"8","author":"Chu","year":"2018","journal-title":"Sci. Rep."},{"issue":"1","key":"10.1016\/j.jbi.2026.105050_b0545","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1186\/s12911-019-0877-x","article-title":"Clinical MetaData ontology: a simple classification scheme for data elements of clinical data based on semantics","volume":"19","author":"Kim","year":"2019","journal-title":"BMC Med. Inf. Decis. Making"},{"key":"10.1016\/j.jbi.2026.105050_b0550","article-title":"A metadata extraction approach for clinical case reports to enable advanced understanding of biomedical concepts","volume":"139","author":"Caufield","year":"2018","journal-title":"J. Vis. Exp."},{"key":"10.1016\/j.jbi.2026.105050_b0555","doi-asserted-by":"crossref","unstructured":"Automated Clinical Note Section Identification Using Transfer Learning and Contextual Embeddings, 2023 Global Conference on Information Technologies and Communications (GCITC); 2023 1-3 Dec. 2023.","DOI":"10.1109\/GCITC60406.2023.10425802"},{"key":"10.1016\/j.jbi.2026.105050_b0560","doi-asserted-by":"crossref","unstructured":"A. Nassar, A. Marafioti, M. Omenetti, et al., SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion, 2025, https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250311576N (accessed March 01, 2025).","DOI":"10.1109\/ICCV51701.2025.02040"}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426000742?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426000742?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:29:04Z","timestamp":1783142944000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046426000742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":115,"alternative-id":["S1532046426000742"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105050","relation":{},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Clinical document metadata extraction: A scoping review","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105050","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"105050"}}