{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T03:10:30Z","timestamp":1792725030954,"version":"4.5.0"},"reference-count":72,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T00:00:00Z","timestamp":1672012800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["ascpt.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clinical Translational Sci"],"published-print":{"date-parts":[[2023,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>An increasing number of studies have reported using natural language processing (NLP) to assist observational research by extracting clinical information from electronic health records (EHRs). Currently, no standardized reporting guidelines for NLP\u2010assisted observational studies exist. The absence of detailed reporting guidelines may create ambiguity in the use of NLP\u2010derived content, knowledge gaps in the current research reporting practices, and reproducibility challenges. To address these issues, we conducted a scoping review of NLP\u2010assisted observational clinical studies and examined their reporting practices, focusing on NLP methodology and evaluation. Through our investigation, we discovered a high variation regarding the reporting practices, such as inconsistent use of references for measurement studies, variation in the\u00a0reporting location (reference, appendix, and manuscript), and different granularity of NLP methodology and evaluation details. To promote the wide adoption and utilization of NLP solutions in clinical research, we outline several perspectives that align with the six principles released by the World Health Organization (WHO) that guide the ethical use of artificial intelligence for health.<\/jats:p>","DOI":"10.1111\/cts.13463","type":"journal-article","created":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T16:10:03Z","timestamp":1670429403000},"page":"398-411","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Recommended practices and ethical considerations for natural language processing\u2010assisted observational research: A scoping review"],"prefix":"10.1111","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1691-5179","authenticated-orcid":false,"given":"Sunyang","family":"Fu","sequence":"first","affiliation":[{"name":"Department of AI and Informatics Research Mayo Clinic Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9970-8604","authenticated-orcid":false,"given":"Liwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of AI and Informatics Research Mayo Clinic Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9191-3897","authenticated-orcid":false,"given":"Sungrim","family":"Moon","sequence":"additional","affiliation":[{"name":"Department of AI and Informatics Research Mayo Clinic Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0066-9524","authenticated-orcid":false,"given":"Nansu","family":"Zong","sequence":"additional","affiliation":[{"name":"Department of AI and Informatics Research Mayo Clinic Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1312-4195","authenticated-orcid":false,"given":"Huan","family":"He","sequence":"additional","affiliation":[{"name":"Department of AI and Informatics Research Mayo Clinic Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1943-0284","authenticated-orcid":false,"given":"Vikas","family":"Pejaver","sequence":"additional","affiliation":[{"name":"Institute for Genomic Health, Icahn School of Medicine at Mount Sinai New York New York USA"},{"name":"Department of Genetics and Genomic Sciences Icahn School of Medicine at Mount Sinai New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rose","family":"Relevo","sequence":"additional","affiliation":[{"name":"The National Center for Data to Health Bethesda Maryland USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3327-7423","authenticated-orcid":false,"given":"Anita","family":"Walden","sequence":"additional","affiliation":[{"name":"The National Center for Data to Health Bethesda Maryland USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9114-8737","authenticated-orcid":false,"given":"Melissa","family":"Haendel","sequence":"additional","affiliation":[{"name":"Center for Health AI University of Colorado Anschutz Medical Campus Aurora Colorado USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5437-2545","authenticated-orcid":false,"given":"Christopher G.","family":"Chute","sequence":"additional","affiliation":[{"name":"Department of Medicine Johns Hopkins University Baltimore Maryland USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2570-3741","authenticated-orcid":false,"given":"Hongfang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of AI and Informatics Research Mayo Clinic Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,12,26]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1006114"},{"key":"e_1_2_11_3_1","unstructured":"Health NIo.Mission Vision and Goals of the NIH Office of Clinical Research2022https:\/\/ocr.od.nih.gov\/"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1136\/emj.20.1.54"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwt443"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.7326\/M19-0873"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103526"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.11.011"},{"key":"e_1_2_11_9_1","doi-asserted-by":"crossref","unstructured":"FuS WenA PagaliS St SauverJ SohnS FanJ et al.The Implication of Latent Information Quality to the Reproducibility of Secondary Use of Electronic Health Records. MEDINFO2021.","DOI":"10.3233\/SHTI220055"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1093\/gerona\/glaa275"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1017\/S104161022100106X"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.2196\/12109"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(14)60994-6"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2020.07.076"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2019.07.025"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000012602"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000439"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2020.00556"},{"key":"e_1_2_11_19_1","first-page":"1554","article-title":"Leveraging collaborative filtering to accelerate rare disease diagnosis","volume":"2017","author":"Shen F","year":"2017","journal-title":"AMIA Annu Symp Proc"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.31357"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.2106\/JBJS.19.00071"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamadermatol.2017.4060"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpain.2015.01.011"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0196-0644(96)70264-0"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12890-018-0593-9"},{"key":"e_1_2_11_26_1","first-page":"171","article-title":"Natural language processing for the evaluation of methodological standards and best practices of EHR\u2010based clinical research","volume":"2020","author":"Fu S","year":"2020","journal-title":"AMIA Summits Transl Sci Proc"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2021.05.033"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.3109\/15622975.2012.669499"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40842-020-00115-2"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2021.01.003"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.22.00006"},{"key":"e_1_2_11_32_1","first-page":"28","article-title":"Incidence and risk factors of pneumonitis in patients with non\u2010small cell lung cancer: an observational analysis of real\u2010world data","volume":"28","author":"Tyczynski JE","year":"2021","journal-title":"Oncologia"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaip.2016.12.006"},{"key":"e_1_2_11_34_1","volume-title":"Evaluation methods in biomedical informatics","author":"Friedman CP","year":"2005"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0038-1634806"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4809(88)90046-8"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-018-0723-6"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsych.2018.01.011"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2019.09.084"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.1994.95236146"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.002733"},{"key":"e_1_2_11_42_1","volume-title":"The KnowledgeMap project: development of a concept\u2010based medical school curriculum database. AMIA Annual Symposium Proceedings","author":"Denny JC","year":"2003"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001560"},{"key":"e_1_2_11_44_1","volume-title":"A suite of natural language processing tools developed for the I2B2 project. AMIA Annual Symposium Proceedings","author":"Goryachev S","year":"2006"},{"key":"e_1_2_11_45_1","first-page":"149","article-title":"An information extraction framework for cohort identification using electronic health records","volume":"2013","author":"Liu H","year":"2013","journal-title":"AMIA Summits Transl Sci Proc"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0208-8"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1123"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18"},{"key":"e_1_2_11_49_1","volume-title":"TRUST: Clinical Text Retrieval and Use towards Scientific Rigor and Transparent Process","author":"Fu S","year":"2021"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-1072-9"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.7326\/M16-0838"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.17.17983"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.2147\/RRU.S234178"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-019-05445-1"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eatbeh.2016.03.013"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1093\/schbul\/sbx197"},{"key":"e_1_2_11_57_1","article-title":"Stratifying risk for dementia onset using large\u2010scale electronic health record data: a retrospective cohort study","author":"McCoy TH","year":"2019","journal-title":"Alzheimers Dement"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-015297"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-014-3165-6"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-042949"},{"key":"e_1_2_11_61_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-017-0645-7"},{"key":"e_1_2_11_62_1","doi-asserted-by":"publisher","DOI":"10.14309\/ctg.0000000000000147"},{"key":"e_1_2_11_63_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1201850"},{"key":"e_1_2_11_64_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1211374"},{"issue":"6242","key":"e_1_2_11_65_1","article-title":"Assessment of EHR for cancer research and patient care through a scoping review of cancer natural language processing","volume":"348","author":"Wang L","year":"2022","journal-title":"JCO Clin Cancer Informat"},{"key":"e_1_2_11_66_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab2374"},{"key":"e_1_2_11_67_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa196"},{"key":"e_1_2_11_68_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2014-002747"},{"key":"e_1_2_11_69_1","first-page":"574","article-title":"Observational Health Data Sciences and Informatics (OHDSI): opportunities for observational researchers","volume":"216","author":"Hripcsak G","year":"2015","journal-title":"Stud Health Technol Inform"},{"key":"e_1_2_11_70_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.3595"},{"key":"e_1_2_11_71_1","unstructured":"ConsortiumO.OHNLP Consortium2022http:\/\/ohnlp.org\/"},{"key":"e_1_2_11_72_1","unstructured":"Health NCfDt.Cloud\u2010based Sandbox for Analytics (Natural Language Processing)2022https:\/\/cd2h.org\/node\/152"},{"key":"e_1_2_11_73_1","doi-asserted-by":"publisher","DOI":"10.2310\/JIM.0b013e318250871d"}],"container-title":["Clinical and Translational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cts.13463","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cts.13463","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cts.13463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T01:29:13Z","timestamp":1728523753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/10.1111\/cts.13463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,26]]},"references-count":72,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["10.1111\/cts.13463"],"URL":"https:\/\/doi.org\/10.1111\/cts.13463","archive":["Portico"],"relation":{},"ISSN":["1752-8054","1752-8062"],"issn-type":[{"value":"1752-8054","type":"print"},{"value":"1752-8062","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,26]]},"assertion":[{"value":"2022-06-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-11-18","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}