{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T21:20:53Z","timestamp":1787865653995,"version":"build-2784847793"},"reference-count":32,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Generative AI can reduce the academic-writing burden on clinical health care professionals, but unsupervised use introduces citation hallucination (the confident fabrication or misattribution of references), which threatens research integrity. When a machine invents a source, it is termed \u201challucination,\u201d and when a person does it, it is termed \u201cfabrication,\u201d yet both are equally unacceptable. Existing health professions education writing workshops have rarely translated this concern into a concrete, reproducible source-verification procedure.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to describe the development and delivery of a 2-day workshop teaching the Atomic Sentence method, a source-anchored knowledge-modeling technique for AI-assisted literature synthesis, and evaluate its feasibility, acceptability, and short-term effect on research-idea development among clinical health care professionals.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We conducted a single-cohort educational program evaluation of a 2-day workshop (\u224816 contact hours) for 18 health care professionals across 4 campuses of a Buddhist medical network in Taiwan. Curriculum development used the ADDIE (Analysis, Design, Development, Implementation, and Evaluation) model; outcomes were framed with the Kirkpatrick model (levels 1\u20102). The workshop implemented a published 7-step AI-assisted research workflow (topic exploration, literature search, knowledge-base management, reading, synthesis, writing, and peer-review simulation). Citation integrity was protected by confining citation generation to a source-grounded tool (NotebookLM) combined with atomic-sentence extraction and mandatory cross-reference verification; other, nongrounded tools supported discovery, reading, and writing. Feasibility was assessed by the workshop completion rate and the questionnaire response rate. Outcomes were an acceptability questionnaire covering 5 domains (usefulness of instructional materials, curriculum planning, time allocation, personal-goal attainment, and administrative support; each rated 0\u201010) and a pre\/post research-topic-transformation analysis (4 categories; 2 independent coders, Cohen \u03ba); responses to an open-ended item on improvement suggestions were analyzed by qualitative content analysis. Reporting follows the GAMER (Guidance for AI Use in Medical Education Reporting) guidance for AI use in medical education.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n All 18 (100%) participants completed the workshop and evaluation. Acceptability was high across all 5 domains (each median 10; overall median 10, IQR 9.3-10). The most variable domain was time allocation (range 5-10). Short-term improvement in the research topic (substantial transformation or refinement) occurred in 11 (61%; \u03ba=0.77) participants; 2 (11%) had no structured question before or after. All 18 (100%) would recommend the workshop.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n A short workshop teaching the Atomic Sentence method was feasible and well accepted and was associated with short-term research-idea development in a multidisciplinary clinical cohort. Whether the method reduces citation hallucination or improves citation accuracy was not tested and requires controlled studies with objective outcomes, blinded raters, and longitudinal follow-up.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/98343","type":"journal-article","created":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T20:41:00Z","timestamp":1787863260000},"page":"e98343-e98343","source":"Crossref","is-referenced-by-count":0,"title":["Teaching the Atomic Sentence Method for Source-Verified, AI-Assisted Literature Synthesis to Clinical Health Care Professionals: Single-Cohort Feasibility and Acceptability Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0564-059X","authenticated-orcid":false,"given":"Sung-Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0702-2726","authenticated-orcid":false,"given":"Shao-Yin","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8209-8600","authenticated-orcid":false,"given":"Hung-Che","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2932-7897","authenticated-orcid":false,"given":"Ming-Shinn","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"issue":"5","key":"R1","doi-asserted-by":"publisher","DOI":"10.5688\/aj710591","article-title":"Barriers to scholarship in dentistry, medicine, nursing, and pharmacy practice faculty","volume":"71","author":"Smesny","journal-title":"Am J Pharm Educ"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1080\/10401334.2019.1659144","article-title":"Going beyond \u201cnot enough time\u201d: barriers to preparing manuscripts for academic medical journals","volume":"32","author":"Oshiro","journal-title":"Teach Learn Med"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.2196\/71125","article-title":"Applications, challenges, and prospects of generative artificial intelligence empowering medical education: scoping review","volume":"11","author":"Lin","journal-title":"JMIR Med Educ"},{"key":"R4","doi-asserted-by":"crossref","unstructured":"Bender EM Gebru T McMillan-Major A Shmitchell S . On the dangers of stochastic parrots: can language models be too big. Presented at: 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT \u201921); Mar 3-10, 2021; Canada. [doi: 10.1145\/3442188.3445922]","DOI":"10.1145\/3442188.3445922"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01157-x","article-title":"The ethics of ChatGPT in medicine and healthcare: a systematic review on large language models (LLMs)","volume":"7","author":"Haltaufderheide","journal-title":"NPJ Digit Med"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1080\/08989621.2026.2645390","article-title":"Hallucinated citations produced by generative artificial intelligence may constitute research misconduct when citations function as data in scholarly papers","author":"Resnik","journal-title":"Account Res"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-41032-5","article-title":"Fabrication and errors in the bibliographic citations generated by ChatGPT","volume":"13","author":"Walters","journal-title":"Sci Rep"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.mcpdig.2023.05.004","article-title":"Learning to fake it: limited responses and fabricated references provided by ChatGPT for medical questions","volume":"1","author":"Gravel","journal-title":"Mayo Clin Proc Digit Health"},{"issue":"5","key":"R9","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.39238","article-title":"High rates of fabricated and inaccurate references in ChatGPT-generated medical content","volume":"15","author":"Bhattacharyya","journal-title":"Cureus"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.2196\/53164","article-title":"Hallucination rates and reference accuracy of ChatGPT and bard for systematic reviews: comparative analysis","volume":"26","author":"Chelli","journal-title":"J Med Internet Res"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.2196\/80371","article-title":"Influence of topic familiarity and prompt specificity on citation fabrication in mental health research using large language models: experimental study","volume":"12","author":"Linardon","journal-title":"JMIR Ment Health"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/52935","article-title":"Evaluation of large language model performance and reliability for citations and references in scholarly writing: cross-disciplinary study","volume":"26","author":"Mugaanyi","journal-title":"J Med Internet Res"},{"issue":"7980","key":"R13","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1038\/d41586-023-02980-0","article-title":"AI and science: what 1,600 researchers think","volume":"621","author":"Van Noorden","journal-title":"Nature"},{"key":"R14","unstructured":"A. Use of AI by authors. International Committee of Medical Journal Editors. URL: https:\/\/www.icmje.org\/recommendations\/browse\/artificial-intelligence\/ai-use-by-authors.html [Accessed 07-12-2025]"},{"issue":"3","key":"R15","doi-asserted-by":"publisher","DOI":"10.25100\/cm.v54i3.5868","article-title":"Chatbots, generative AI, and scholarly manuscripts: WAME recommendations on chatbots and generative artificial intelligence in relation to scholarly publications","volume":"54","author":"Zielinski","journal-title":"Colomb Med (Cali)"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.1364","article-title":"Quotation accuracy in medical journal articles-a systematic review and meta-analysis","volume":"3","author":"Jergas","journal-title":"PeerJ"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.2196\/58766","article-title":"Generative artificial intelligence in medical education\u2014Policies and training at US osteopathic medical schools: descriptive cross-sectional survey","volume":"11","author":"Ichikawa","journal-title":"JMIR Med Educ"},{"issue":"2","key":"R18","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1207\/s15430421tip4102_2","article-title":"Becoming a self-regulated learner: an overview","volume":"41","author":"Zimmerman","journal-title":"Theory Pract"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.00422","article-title":"A review of self-regulated learning: six models and four directions for research","volume":"8","author":"Panadero","journal-title":"Front Psychol"},{"issue":"2","key":"R20","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1207\/s15516709cog1202_4","article-title":"Cognitive load during problem solving: effects on learning","volume":"12","author":"Sweller","journal-title":"Cogn Sci"},{"key":"R21","unstructured":"Kirkpatrick JD Kirkpatrick WK . Kirkpatrick\u2019s Four Levels of Training Evaluation. Association for Talent Development; 2016. ISBN: 9781607281023"},{"issue":"6","key":"R22","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1136\/bmjebm-2025-113825","article-title":"Reporting guideline for the use of generative artificial intelligence tools in medical research: the GAMER statement","volume":"30","author":"Luo","journal-title":"BMJ Evid Based Med"},{"issue":"5","key":"R23","doi-asserted-by":"publisher","first-page":"371","DOI":"10.3109\/0142159X.2014.889290","article-title":"Cognitive Load Theory: implications for medical education: AMEE Guide No. 86","volume":"36","author":"Young","journal-title":"Med Teach"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Branch RM . Instructional Design: The ADDIE Approach. Springer; 2009. [doi: 10.1007\/978-0-387-09506-6]","DOI":"10.1007\/978-0-387-09506-6"},{"key":"R25","unstructured":"Anderson LW Krathwohl DR . A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom\u2019s Taxonomy of Educational Objectives. Longman; 2001. ISBN: 9780321084057"},{"key":"R26","unstructured":"Using AI to Build Knowledge Bases and Write Documents [Book in Chinese]. Li Mingxian; 2026. URL: https:\/\/readmoo.com\/book\/210413076000101 [Accessed 13-08-2026]"},{"key":"R27","unstructured":"AI Research Literature: A Super Writing Technique for Extracting Atomic Sentences [Book in Chinese]. Li Mingxian; 2025. URL: https:\/\/readmoo.com\/book\/210426509000101 [Accessed 13-08-2026]"},{"key":"R28","unstructured":"Gemini Notebook. URL: https:\/\/notebooklm.google\/ [Accessed 13-08-2026]"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1111\/j.1365-2648.2007.04569.x","article-title":"The qualitative content analysis process","volume":"62","author":"Elo","journal-title":"J Adv Nurs"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.15766\/mep_2374-8265.10669","article-title":"A structured framework and resources to use to get your medical education work published","volume":"14","author":"Li","journal-title":"MedEdPORTAL"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.15766\/mep_2374-8265.11286","article-title":"Applying conceptual and theoretical frameworks to health professions education research: an introductory workshop","volume":"18","author":"Rougas","journal-title":"MedEdPORTAL"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.2196\/81297","article-title":"Twelve practical tips for integrating AI into medical education: tutorial to support educators across teaching, research, administration, and ethical domains","volume":"11","author":"Jalali","journal-title":"JMIR Med Educ"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T20:41:03Z","timestamp":1787863263000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e98343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":32,"URL":"https:\/\/doi.org\/10.2196\/98343","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]},"article-number":"v10i5e98343"}}