{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:53:31Z","timestamp":1790902411326,"version":"4.1.0"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":22,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K08DK131286"],"award-info":[{"award-number":["K08DK131286"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Exploratory data analysis (EDA) is foundational to clinical research yet inaccessible to clinician-scientists without programming training. Existing large language model (LLM) tools improve accessibility but struggle with hallucinations. We developed and evaluated data reflector (DR), a hybrid agentic platform pairing natural language interaction with deterministic statistical computation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>Data reflector restricts the LLM to intent interpretation, tool selection, and filter parsing while routing all numerical computation through predefined deterministic functions executed locally. We piloted DR with 6 participants of diverse technical backgrounds across 6 clinical (MIMIC-IV, eICU Collaborative Research Database, National Health and Nutrition Examination Survey) and nonclinical (energy, COVID-19, urban mobility) datasets, assessing usability (system usability scale, SUS), task completion time, analytical output correctness against participant-generated manual reference results, hallucination prevention, and independent reproducibility by a second operator. A head-to-head comparison with ChatGPT 5.3 chatbot was also conducted.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Data reflector achieved a mean SUS of 94.58, with reduced task completion time across all evaluable participants. Statistical outputs and generated distribution curves demonstrated complete agreement with participant-generated manual reference results across all evaluable outputs. Independent reexecution by a different operator using independently constructed prompts also demonstrated complete agreement with the original DR outputs across all evaluated tasks. Hallucination-prevention safeguards correctly declined out-of-scope and impossible queries. ChatGPT produced incomplete, internally inconsistent outputs on identical tasks where DR returned complete, accurate results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Data reflector\u2019s architectural separation of LLM reasoning from numerical computation removes dependence on prompt phrasing, session history, and stochastic LLM sampling while preserving conversational accessibility, addressing reproducibility limitations of general-purpose LLM tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Data reflector offers a practical pattern for reproducible, accessible artificial intelligence-assisted EDA across heterogeneous data sources in modern clinical and translational research.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamiaopen\/ooag194","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T11:42:29Z","timestamp":1789213349000},"source":"Crossref","is-referenced-by-count":0,"title":["Data-reflector: an agentic exploratory data analysis platform for researchers"],"prefix":"10.1093","volume":"9","author":[{"given":"Moein","family":"Sabounchi","sequence":"first","affiliation":[{"name":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nimay","family":"Hazare","sequence":"additional","affiliation":[{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"Mount Sinai AI Assurance Lab, Mount Sinai Health System , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Capone","sequence":"additional","affiliation":[{"name":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"Mount Sinai AI Assurance Lab, Mount Sinai Health System , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mateen","family":"Jangda","sequence":"additional","affiliation":[{"name":"University of Miami Miller School of Medicine , Miami, FL 33136,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wonsuk","family":"Oh","sequence":"additional","affiliation":[{"name":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pushkala","family":"Jayaraman","sequence":"additional","affiliation":[{"name":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shashank","family":"Gupta","sequence":"additional","affiliation":[{"name":"Mount Sinai AI Assurance Lab, Mount Sinai Health System , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1525-8541","authenticated-orcid":false,"given":"Ashwin","family":"Sawant","sequence":"additional","affiliation":[{"name":"Department of Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zachary","family":"Kuschner","sequence":"additional","affiliation":[{"name":"Institute for Critical Care Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prathamesh","family":"Parchure","sequence":"additional","affiliation":[{"name":"Mount Sinai AI Assurance Lab, Mount Sinai Health System , New York, NY 10029,","place":["United States"]},{"name":"Clinical Data Science, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prem","family":"Timsina","sequence":"additional","affiliation":[{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"Mount Sinai AI Assurance Lab, Mount Sinai Health System , New York, NY 10029,","place":["United States"]},{"name":"Clinical Data Science, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Kaplan","sequence":"additional","affiliation":[{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditi","family":"Vakil","sequence":"additional","affiliation":[{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roopa","family":"Kohli-Seth","sequence":"additional","affiliation":[{"name":"Institute for Critical Care Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patricia","family":"Kovatch","sequence":"additional","affiliation":[{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"Scientific Computing, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4058-5050","authenticated-orcid":false,"given":"Alexis","family":"Zebrowski","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4515-8090","authenticated-orcid":false,"given":"Benjamin","family":"Glicksberg","sequence":"additional","affiliation":[{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pulkit","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Improbable AI Lab, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruce","family":"Darrow","sequence":"additional","affiliation":[{"name":"Cardiovascular Research Center and Cardiovascular Institute, Mount Sinai Health System , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Stump","sequence":"additional","affiliation":[{"name":"Mount Sinai Health System and Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Charney","sequence":"additional","affiliation":[{"name":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Girish N","family":"Nadkarni","sequence":"additional","affiliation":[{"name":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankit","family":"Sakhuja","sequence":"additional","affiliation":[{"name":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]},{"name":"Mount Sinai AI Assurance Lab, Mount Sinai Health System , New York, NY 10029,","place":["United States"]},{"name":"Institute for Critical Care Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"2026100119541846800_ooag194-B1","volume-title":"Exploratory Data Analysis","author":"Tukey","year":"1977"},{"key":"2026100119541846800_ooag194-B2","doi-asserted-by":"publisher","first-page":"73","DOI":"10.12793\/tcp.2024.32.e8","article-title":"Data science through natural language with ChatGPT\u2019s code interpreter","volume":"32","author":"Ahn","year":"2024","journal-title":"Transl Clin Pharmacol"},{"key":"2026100119541846800_ooag194-B3","author":"Zeng","year":"2025"},{"key":"2026100119541846800_ooag194-B4","author":"Chakroborti","year":"2025"},{"key":"2026100119541846800_ooag194-B5","doi-asserted-by":"publisher","first-page":"e2723","DOI":"10.1002\/smr.2723","article-title":"LLMs for science: usage for code generation and data analysis","volume":"37","author":"Nejjar","year":"2025","journal-title":"J Softw"},{"key":"2026100119541846800_ooag194-B6","author":"Cui","year":"2026"},{"key":"2026100119541846800_ooag194-B7","author":"Wu","year":"2024"},{"key":"2026100119541846800_ooag194-B8","doi-asserted-by":"publisher","first-page":"22315","DOI":"10.18653\/v1\/2024.emnlp-main.1245","article-title":"Ehragent: code empowers large language models for few-shot complex tabular reasoning on electronic health records","volume":"2024","author":"Shi","year":"2024","journal-title":"Proc Conf Empir Methods Nat Lang Process"},{"key":"2026100119541846800_ooag194-B9","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1145\/169059.169166","author":"Nielsen","year":"1993"},{"key":"2026100119541846800_ooag194-B10","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1177\/001872089203400407","article-title":"Refining the test phase of usability evaluation: how many subjects is enough?","volume":"34","author":"Virzi","year":"1992","journal-title":"Hum Factors"},{"key":"2026100119541846800_ooag194-B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"2026100119541846800_ooag194-B12","doi-asserted-by":"publisher","first-page":"180178","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU collaborative research database, a freely available multi-center database for critical care research","volume":"5","author":"Pollard","year":"2018","journal-title":"Sci Data"},{"key":"2026100119541846800_ooag194-B13","first-page":"1","article-title":"Plan and operations of the national health and nutrition examination survey, August 2021-August 2023","volume":"1","author":"Terry","year":"2024","journal-title":"Vital Health Stat 1"},{"key":"2026100119541846800_ooag194-B14","first-page":"333","author":"Yang","year":"2023"},{"key":"2026100119541846800_ooag194-B15","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s12911-020-1056-9","article-title":"FHIR PIT: an open software application for spatiotemporal integration of clinical data and environmental exposures data","volume":"20","author":"Xu","year":"2020","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026100119541846800_ooag194-B16","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1186\/s12889-023-15768-8","article-title":"Multimorbidity and social determinants of health in the US prior to the COVID-19 pandemic and implications for health outcomes: a cross-sectional analysis based on NHANES 2017-2018","volume":"23","author":"Mossadeghi","year":"2023","journal-title":"BMC Public Health"},{"key":"2026100119541846800_ooag194-B17","doi-asserted-by":"publisher","author":"Data","year":"2020","DOI":"10.25832\/time_series\/2020-10-06"},{"key":"2026100119541846800_ooag194-B18","author":"Kim","year":"2020"},{"key":"2026100119541846800_ooag194-B19","author":"headsortails"},{"key":"2026100119541846800_ooag194-B20","first-page":"4","article-title":"SUS\u2014A quick and dirty usability scale","volume":"189","author":"Brooke","year":"1996","journal-title":"Usability Evaluation in Industry"},{"key":"2026100119541846800_ooag194-B21","first-page":"114","article-title":"Determining what individual SUS scores mean: adding an adjective rating scale","volume":"4","author":"Bangor","year":"2009","journal-title":"J Usability Stud"},{"key":"2026100119541846800_ooag194-B22","doi-asserted-by":"publisher","first-page":"e63550","DOI":"10.2196\/63550","article-title":"ChatGPT for univariate statistics: validation of AI-assisted data analysis in healthcare research","volume":"27","author":"Ruta","year":"2025","journal-title":"J Med Internet Res"},{"key":"2026100119541846800_ooag194-B23"},{"key":"2026100119541846800_ooag194-B24"},{"key":"2026100119541846800_ooag194-B25"},{"key":"2026100119541846800_ooag194-B26"},{"key":"2026100119541846800_ooag194-B27"},{"key":"2026100119541846800_ooag194-B28","author":"Singh"},{"key":"2026100119541846800_ooag194-B29","author":"Hong","year":"2023"},{"key":"2026100119541846800_ooag194-B30","author":"Tableau Next","year":"2026"},{"key":"2026100119541846800_ooag194-B31","author":"Cloud"},{"key":"2026100119541846800_ooag194-B32","doi-asserted-by":"publisher","first-page":"btaf359","DOI":"10.1093\/bioinformatics\/btaf359","article-title":"AI-HOPE: an AI-driven conversational agent for enhanced clinical and genomic data integration in precision medicine research","volume":"41","author":"Yang","year":"2025","journal-title":"Bioinformatics"},{"key":"2026100119541846800_ooag194-B33","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1038\/s41587-024-02534-3","article-title":"A platform for the biomedical application of large language models","volume":"43","author":"Lobentanzer","year":"2025","journal-title":"Nat Biotechnol"},{"key":"2026100119541846800_ooag194-B34","doi-asserted-by":"publisher","first-page":"btaf159","DOI":"10.1093\/bioinformatics\/btaf159","article-title":"Automatic biomarker discovery and enrichment with BRAD","volume":"41","author":"Pickard","year":"2025","journal-title":"Bioinformatics"},{"key":"2026100119541846800_ooag194-B35","author":"Zhang","year":"2023"},{"key":"2026100119541846800_ooag194-B36","first-page":"346","author":"Ma","year":"2023"},{"key":"2026100119541846800_ooag194-B37","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1109\/TVCG.2023.3326585","article-title":"Data formulator: AI-powered concept-driven visualization authoring","volume":"30","author":"Wang","year":"2024","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"2026100119541846800_ooag194-B38","doi-asserted-by":"publisher","first-page":"bbag110","DOI":"10.1093\/bib\/bbag110","article-title":"Large language model agents for biological intelligence across genomics, proteomics, spatial biology, and biomedicine","volume":"27","author":"Dip","year":"2026","journal-title":"Brief Bioinform"}],"container-title":["JAMIA Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/9\/5\/ooag194\/71562242\/ooag194.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/9\/5\/ooag194\/71562242\/ooag194.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T23:54:22Z","timestamp":1790898862000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article\/doi\/10.1093\/jamiaopen\/ooag194\/8859356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,9]]}},"URL":"https:\/\/doi.org\/10.1093\/jamiaopen\/ooag194","relation":{},"ISSN":["2574-2531"],"issn-type":[{"value":"2574-2531","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,9,9]]},"article-number":"ooag194"}}