{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T03:41:14Z","timestamp":1792726874975,"version":"4.5.0"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"vor","delay-in-days":265,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","award":["441891347\u2014SFB 1479"],"award-info":[{"award-number":["441891347\u2014SFB 1479"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","award":["499552394\u2014SFB 1597"],"award-info":[{"award-number":["499552394\u2014SFB 1597"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","award":["491676693\u2014TRR 359"],"award-info":[{"award-number":["491676693\u2014TRR 359"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","award":["256073931\u2014SFB 1160"],"award-info":[{"award-number":["256073931\u2014SFB 1160"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","award":["514483642\u2014TRR 384"],"award-info":[{"award-number":["514483642\u2014TRR 384"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","award":["259373024\u2014TRR 167"],"award-info":[{"award-number":["259373024\u2014TRR 167"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","award":["431984000\u2014SFB 1453"],"award-info":[{"award-number":["431984000\u2014SFB 1453"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","award":["2189"],"award-info":[{"award-number":["2189"]}],"id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Collaborative Research Centers rely on FAIR-compliant, richly structured metadata, yet manual annotation is a major bottleneck. We implemented a search-augmented large language model (LLM) workflow within a local research data management system to pre-annotate biomedical entities, using human-in-the-loop verification to ensure data quality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The pipeline uses Gemini 3 Pro in a two-step prompting strategy: (1) identify dataset deposits and stable identifiers in articles converted to Markdown; (2) extract structured fields from curated repository landing pages rendered via a headless browser. To handle a highly hierarchical metadata schema, we flattened the schema for prompting and remapped outputs to strict JSON with granular provenance tags. Authors received pre-filled metadata and could accept, edit, or delete entries (TP, FP, FN mapping). Performance metrics (precision, recall, F1) were estimated as proportions and synthesized via random-effects meta-analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 51 screened articles, the LLM identified a repository deposit in 31; authors responded for 17 (55% of articles with an identified deposit; 33% of all screened articles), yielding 39 verified datasets. False positives were rare (mean 0.23) and false negatives low (mean 1.46). Precision was consistently high at 99.65% (95% CI 98.42%\u2013100.00%). Recall showed more variability at 93.75% (95% CI 89.79%\u201396.96%), and the F1 score reached 96.17% (95% CI 93.78%\u201398.11%).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The hybrid workflow achieved high author-verified precision with moderate recall, shifting effort from drafting to reviewing while maintaining schema compliance. As these metrics rely on author acceptance and response rates were modest, broader, multi-site validation is needed.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioadv\/vbag283","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T11:56:12Z","timestamp":1790164572000},"source":"Crossref","is-referenced-by-count":0,"title":["Accelerating metadata annotation in collaborative research centers: a hybrid AI workflow for biomedical entities"],"prefix":"10.1093","volume":"6","author":[{"given":"Manuel","family":"Watter","sequence":"first","affiliation":[{"name":"Institute of Medical Biometry and Statistics, Medical Faculty and Medical Center, University of Freiburg , Freiburg,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Engel","sequence":"additional","affiliation":[{"name":"Institute of Medical Biometry and Statistics, Medical Faculty and Medical Center, University of Freiburg , Freiburg,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aref","family":"Kalantari","sequence":"additional","affiliation":[{"name":"Institute of Medical Biometry and Statistics, Medical Faculty and Medical Center, University of Freiburg , Freiburg,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Giuliani","sequence":"additional","affiliation":[{"name":"Institute of Medical Biometry and Statistics, Medical Faculty and Medical Center, University of Freiburg , Freiburg,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karin","family":"Schuller","sequence":"additional","affiliation":[{"name":"Research Data Management Scientific IT, Helmholtz M\u00fcnchen , M\u00fcnchen,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claus-Werner","family":"Franzke","sequence":"additional","affiliation":[{"name":"Institute for Infection Prevention and Control, Medical Faculty and Medical Center, University of Freiburg , Freiburg,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7689-3613","authenticated-orcid":false,"given":"Markus","family":"Sperandio","sequence":"additional","affiliation":[{"name":"Institute of Cardiovascular Physiology and Pathophysiology, Biomedical Center, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen , M\u00fcnchen,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harald","family":"Binder","sequence":"additional","affiliation":[{"name":"Institute of Medical Biometry and Statistics, Medical Faculty and Medical Center, University of Freiburg , Freiburg,","place":["Germany"]},{"name":"Center for Integrative Biological Signaling Studies (CIBSS), University of Freiburg , Freiburg,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0837-6945","authenticated-orcid":false,"given":"Klaus","family":"Kaier","sequence":"additional","affiliation":[{"name":"Institute of Medical Biometry and Statistics, Medical Faculty and Medical Center, University of Freiburg , Freiburg,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"2026102223333448600_vbag283-B1","author":"Anthuvan","year":"2025"},{"key":"2026102223333448600_vbag283-B2","doi-asserted-by":"publisher","first-page":"1659134","DOI":"10.3389\/fdgth.2025.1659134","article-title":"Large language models in real-world clinical workflows: a systematic review of applications and implementation","volume":"7","author":"Artsi","year":"2025","journal-title":"Front Digit Health"},{"key":"2026102223333448600_vbag283-B3","doi-asserted-by":"publisher","first-page":"100521","DOI":"10.1016\/j.jpi.2025.100521","article-title":"Leveraging large language models for structured information extraction from pathology reports","volume":"19","author":"Balasubramanian","year":"2025","journal-title":"J Pathol Inform"},{"key":"2026102223333448600_vbag283-B4","author":"Brokman","year":"2025"},{"key":"2026102223333448600_vbag283-B5","doi-asserted-by":"publisher","DOI":"10.60493\/k1xe3-npc10","article-title":"Development of metadata schemas for collaborative research centers","author":"Engel","year":"2025","journal-title":"FreiData"},{"key":"2026102223333448600_vbag283-B6","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1186\/s13104-026-07937-w","article-title":"From manual entry to machine precision: challenges and evolution of metadata schema development in collaborative research centers","volume":"19","author":"Engel","year":"2026","journal-title":"BMC Res Notes"},{"key":"2026102223333448600_vbag283-B7","doi-asserted-by":"publisher","first-page":"e73822","DOI":"10.2196\/73822","article-title":"Identifying biomedical entities for datasets in scientific articles: 4-step cache-augmented generation approach using GPT-4o and PubTator 3.0","volume":"9","author":"Giuliani","year":"2025","journal-title":"JMIR Formative Research"},{"key":"2026102223333448600_vbag283-B8","doi-asserted-by":"publisher","first-page":"e48633","DOI":"10.2196\/48633","article-title":"Barriers to and facilitators of artificial intelligence adoption in health care: scoping review","volume":"11","author":"Hassan","year":"2024","journal-title":"JMIR Hum Factors"},{"key":"2026102223333448600_vbag283-B9","doi-asserted-by":"publisher","first-page":"giaf070","DOI":"10.1093\/gigascience\/giaf070","article-title":"Extraction of biological terms using large language models enhances the usability of metadata in the BioSample database","volume":"14","author":"Ikeda","year":"2025","journal-title":"Gigascience"},{"key":"2026102223333448600_vbag283-B10","doi-asserted-by":"publisher","author":"Jabal","year":"2024","DOI":"10.48550\/arXiv.2409.10576"},{"key":"2026102223333448600_vbag283-B11","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13104-026-07632-w","article-title":"Identification of biomedical entities from multiple repositories using a specialized metadata schema and search-augmented large language models","volume":"19","author":"Kaier","year":"2026","journal-title":"BMC Res Notes"},{"key":"2026102223333448600_vbag283-B12","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13104-022-05908-5","article-title":"Behind every great research project is great data management","volume":"15","author":"Kanza","year":"2022","journal-title":"BMC Res Notes"},{"key":"2026102223333448600_vbag283-B13","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1080\/00031305.1978.10479283","article-title":"The inverse of the Freeman \u2013 Tukey Double Arcsine Transformation","volume":"32","author":"Miller","year":"1978","journal-title":"Am Stat"},{"key":"2026102223333448600_vbag283-B14","doi-asserted-by":"publisher","author":"Mortezaagha","year":"2025","DOI":"10.48550\/arXiv.2601.14267"},{"key":"2026102223333448600_vbag283-B15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1075\/bct.19.03nad","volume-title":"Benjamins current topics","author":"Nadeau","year":"2009"},{"key":"2026102223333448600_vbag283-B16","doi-asserted-by":"publisher","author":"Pangakis","year":"2023","DOI":"10.48550\/arXiv.2306.00176"},{"key":"2026102223333448600_vbag283-B17","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s13012-024-01357-9","article-title":"Generative AI in healthcare: an implementation science informed translational path on application, integration and governance","volume":"19","author":"Reddy","year":"2024","journal-title":"Implement Sci"},{"key":"2026102223333448600_vbag283-B18","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/978-1-0716-1566-9_10","volume-title":"Meta-research","author":"Schwarzer","year":"2022"},{"key":"2026102223333448600_vbag283-B19","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s13012-024-01346-y","article-title":"Leveraging artificial intelligence to advance implementation science: potential opportunities and cautions","volume":"19","author":"Trinkley","year":"2024","journal-title":"Implement Sci"},{"key":"2026102223333448600_vbag283-B20","doi-asserted-by":"publisher","first-page":"vbaf241","DOI":"10.1093\/bioadv\/vbaf241","article-title":"Metadata harmonization from biological datasets with language models","volume":"5","author":"Verbitsky","year":"2025","journal-title":"Bioinform Adv"},{"key":"2026102223333448600_vbag283-B21","doi-asserted-by":"publisher","author":"Wang","year":"2024","DOI":"10.48550\/arXiv.2409.10702"},{"key":"2026102223333448600_vbag283-B22","doi-asserted-by":"publisher","first-page":"1952","DOI":"10.1038\/s41598-026-35492-8","article-title":"Automated identification of contextually relevant biomedical entities with grounded LLMs","volume":"16","author":"Watter","year":"2026","journal-title":"Sci Rep"},{"key":"2026102223333448600_vbag283-B23","doi-asserted-by":"publisher","DOI":"10.11588\/heidok.00033131","volume-title":"E-Science-Tage 2023. Empower Your Research- Preserve Your Data","author":"Watter","year":"2023"},{"key":"2026102223333448600_vbag283-B24","doi-asserted-by":"publisher","first-page":"160018","DOI":"10.1038\/sdata.2016.18","article-title":"The FAIR guiding principles for scientific data management and stewardship","volume":"3","author":"Wilkinson","year":"2016","journal-title":"Sci Data"},{"key":"2026102223333448600_vbag283-B25","doi-asserted-by":"publisher","first-page":"vbag028","DOI":"10.1093\/bioadv\/vbag028","article-title":"Empowering biological knowledgebases: advances in human-in-the-loop AI-driven literature curation","volume":"6","author":"Wood","year":"2026","journal-title":"Bioinform Adv"}],"container-title":["Bioinformatics Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/advance-article-pdf\/doi\/10.1093\/bioadv\/vbag283\/71352772\/vbag283.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbag283\/71352772\/vbag283.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbag283\/71352772\/vbag283.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T03:33:38Z","timestamp":1792726418000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article\/doi\/10.1093\/bioadv\/vbag283\/8832325"}},"subtitle":[],"editor":[{"given":"Nicola","family":"Mulder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,7]]}},"URL":"https:\/\/doi.org\/10.1093\/bioadv\/vbag283","relation":{},"ISSN":["2635-0041"],"issn-type":[{"value":"2635-0041","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"vbag283"}}