{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:50:07Z","timestamp":1782575407361,"version":"3.54.5"},"reference-count":19,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:00:00Z","timestamp":1782518400000},"content-version":"vor","delay-in-days":53,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"PNRR"},{"name":"Advancing Lung Cancer Screening: Artificial Intelligence, Multimodal Imaging and Cutting-Edge Technologies for Early Detection and Characterization"},{"name":"NextGeneration EU","award":["PNRR-MCNT2-2023-12377755"],"award-info":[{"award-number":["PNRR-MCNT2-2023-12377755"]}]},{"name":"NextGeneration EU","award":["H53C24000320007"],"award-info":[{"award-number":["H53C24000320007"]}]},{"name":"KILOWATT"},{"DOI":"10.13039\/100000002","name":"National Institutes for Health","doi-asserted-by":"crossref","award":["NIH-R01EB030362"],"award-info":[{"award-number":["NIH-R01EB030362"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes for Health","doi-asserted-by":"crossref","award":["NIH-OT2OD032701"],"award-info":[{"award-number":["NIH-OT2OD032701"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes for Health","doi-asserted-by":"crossref","award":["NIH-U24EB037545"],"award-info":[{"award-number":["NIH-U24EB037545"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Boston-Korea Innovative Research Project through the Korea Health Industry Development Institute"},{"name":"Ministry of Health & Welfare, Republic of Korea","award":["RS-2024-00403047"],"award-info":[{"award-number":["RS-2024-00403047"]}]},{"name":"NTIS","award":["2460003034"],"award-info":[{"award-number":["2460003034"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Reuse of shared datasets is often limited by incomplete or inconsistent documentation, hindering interpretation and secondary analysis. We developed DataAtlas, an open-source system for automated generation of data dictionaries from tabular datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>DataAtlas combines deterministic structural profiling with large language model (LLM)-based semantic inference to generate human-readable descriptions of datasets, tables, and variables. The system integrates column metadata, statistical summaries, and representative sample values to produce concise, context-aware descriptions. We evaluated the approach on 3 heterogeneous clinical datasets using structural validation, blinded LLM-based comparison with official documentation, human expert review, and downstream task evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Generated descriptions were frequently preferred over official documentation, particularly when existing descriptions were incomplete or ambiguous. Human expert review showed strong agreement with high-performing models, with most descriptions rated as correct and low rates of hallucination. The system accurately reconstructed schema elements and flagged inconsistencies in existing documentation. In a text-to-SQL benchmark, augmenting database schemas with generated data dictionaries improved execution accuracy from 0.52 to 0.88.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Automated data dictionary generation improved both dataset interpretability and downstream analytical performances. Results highlight the importance of column-level metadata, particularly representative sample values, in grounding LLM-generated descriptions. Limitations include sensitivity to sample quality, potential domain-specific misinterpretation, and variability across model architectures, indicating that generated outputs should augment rather than replace expert curation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>DataAtlas provides a practical approach for generating structured data dictionaries, enhancing the accessibility, reproducibility, and reuse of clinical data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamiaopen\/ooag119","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:31:25Z","timestamp":1781004685000},"source":"Crossref","is-referenced-by-count":0,"title":["DataAtlas: automatic generation of data dictionaries using large language models"],"prefix":"10.1093","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3906-9214","authenticated-orcid":false,"given":"Raffaele","family":"Giancotti","sequence":"first","affiliation":[{"name":"Laboratory for Computational Physiology, MIT Institute for Medical Engineering and Science, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]},{"name":"Department of Computer Engineering, Modeling, Electronics, and Systems Engineering, Universit\u00e0 della Calabria , Arcavata di Rende (CS), 87036,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajna","family":"Fani","sequence":"additional","affiliation":[{"name":"Laboratory for Computational Physiology, MIT Institute for Medical Engineering and Science, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]},{"name":"TUM School of Computation, Information and Technology, Technical University of Munich , Munich, Bavaria 80333,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafi","family":"Al Attrach","sequence":"additional","affiliation":[{"name":"Laboratory for Computational Physiology, MIT Institute for Medical Engineering and Science, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]},{"name":"TUM School of Computation, Information and Technology, Technical University of Munich , Munich, Bavaria 80333,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierangelo","family":"Veltri","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Modeling, Electronics, and Systems Engineering, Universit\u00e0 della Calabria , Arcavata di Rende (CS), 87036,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5676-7898","authenticated-orcid":false,"given":"Tom","family":"Pollard","sequence":"additional","affiliation":[{"name":"Laboratory for Computational Physiology, MIT Institute for Medical Engineering and Science, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"2026062711422442700_ooag119-B1","first-page":"1","article-title":"Autoddg: automated dataset description generation using large language models","volume":"4","author":"Zhang","year":"2026","journal-title":"Proc ACM Manag Data"},{"key":"2026062711422442700_ooag119-B2","doi-asserted-by":"crossref","first-page":"11786329211070722","DOI":"10.1177\/11786329211070722","article-title":"A qualitative analysis of the impact of electronic health records (EHR) on healthcare quality and safety: clinicians\u2019 lived experiences","volume":"15","author":"Upadhyay","year":"2022","journal-title":"Health Serv Insights"},{"key":"2026062711422442700_ooag119-B3","doi-asserted-by":"crossref","first-page":"e0229182","DOI":"10.1371\/journal.pone.0229182","article-title":"The views, perspectives, and experiences of academic researchers with data sharing and reuse: a meta-synthesis","volume":"15","author":"Perrier","year":"2020","journal-title":"PLoS One"},{"key":"2026062711422442700_ooag119-B4","volume":"4","author":"Buchanan","year":"2021","journal-title":"Adv Methods Pract Psychol Sci"},{"key":"2026062711422442700_ooag119-B5","first-page":"2956","article-title":"Data dictionaries: essential tools for the ethical and transparent use of integrated data","volume":"10","author":"Pepe","year":"2025","journal-title":"Int J Popul Data Sci"},{"key":"2026062711422442700_ooag119-B6","doi-asserted-by":"crossref","first-page":"333ps8","DOI":"10.1126\/scitranslmed.aad9072","article-title":"A \u201cdatathon\u201d model to support cross-disciplinary collaboration","volume":"8","author":"Aboab","year":"2016","journal-title":"Sci Transl Med"},{"key":"2026062711422442700_ooag119-B7","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1186\/1471-2458-14-1144","article-title":"A systematic review of barriers to data sharing in public health","volume":"14","author":"van Panhuis","year":"2014","journal-title":"BMC Public Health"},{"key":"2026062711422442700_ooag119-B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.03195"},{"key":"2026062711422442700_ooag119-B9"},{"key":"2026062711422442700_ooag119-B10","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1002\/path.6232","article-title":"Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4)","volume":"262","author":"Truhn","year":"2024","journal-title":"J Pathol"},{"key":"2026062711422442700_ooag119-B11","first-page":"1","volume-title":"EAGEWorkshop on Data Science-From Fundamentals to Opportunities","author":"Menezes","year":"2023"},{"key":"2026062711422442700_ooag119-B12","first-page":"1"},{"key":"2026062711422442700_ooag119-B13","doi-asserted-by":"crossref","first-page":"107611","DOI":"10.1016\/j.infsof.2024.107611","article-title":"On the road to interactive LLM-based systematic mapping studies","volume":"178","author":"Petersen","year":"2025","journal-title":"Inf Softw Technol"},{"key":"2026062711422442700_ooag119-B14","author":"Wang","year":"2022"},{"key":"2026062711422442700_ooag119-B15","first-page":"179","volume-title":"Computers in Cardiology (Cat. 00CH37163)","author":"Moody","year":"2000"},{"key":"2026062711422442700_ooag119-B16","doi-asserted-by":"publisher","author":"Adam","year":"2024","DOI":"10.13026\/w10c-6g08"},{"key":"2026062711422442700_ooag119-B17","author":"Markov","year":"2023"},{"key":"2026062711422442700_ooag119-B18","doi-asserted-by":"publisher","author":"Lim","year":"2024","DOI":"10.13026\/1eay-yc85"},{"key":"2026062711422442700_ooag119-B19","doi-asserted-by":"crossref","first-page":"1","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"}],"container-title":["JAMIA Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/9\/3\/ooag119\/68632829\/ooag119.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/9\/3\/ooag119\/68632829\/ooag119.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:42:33Z","timestamp":1782574953000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article\/doi\/10.1093\/jamiaopen\/ooag119\/8719546"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,5]]},"references-count":19,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,5]]}},"URL":"https:\/\/doi.org\/10.1093\/jamiaopen\/ooag119","relation":{},"ISSN":["2574-2531"],"issn-type":[{"value":"2574-2531","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,5,5]]},"article-number":"ooag119"}}