{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T10:51:16Z","timestamp":1782384676240,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:00:00Z","timestamp":1778889600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":40,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100017691","name":"Guangxi Key Research and Development Program","doi-asserted-by":"publisher","award":["AB25069049"],"award-info":[{"award-number":["AB25069049"]}],"id":[{"id":"10.13039\/501100017691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"DOI":"10.1186\/s13040-026-00562-0","type":"journal-article","created":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T10:04:32Z","timestamp":1778925872000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated candidate confounder scoping for adjustment in clinical research: a retrieval-augmented generation approach"],"prefix":"10.1186","volume":"19","author":[{"given":"Jingjing","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kesong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruolin","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinyao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanlin","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueqian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,16]]},"reference":[{"issue":"1","key":"562_CR1","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1214\/23-STS889","volume":"39","author":"B Colnet","year":"2024","unstructured":"Colnet B, Mayer I, Chen G, Dieng A, Li R, Varoquaux G, Yang S. Causal inference methods for combining randomized trials and observational studies: a review. Stat Sci. 2024;39(1):165\u201391.","journal-title":"Stat Sci"},{"issue":"21","key":"562_CR2","doi-asserted-by":"publisher","first-page":"1845","DOI":"10.1001\/jama.2024.7741","volume":"331","author":"IJ Dahabreh","year":"2024","unstructured":"Dahabreh IJ, Bibbins-Domingo K. Causal inference about the effects of interventions from observational studies in medical journals. JAMA. 2024;331(21):1845\u201353.","journal-title":"JAMA"},{"issue":"5","key":"562_CR3","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1111\/j.1742-1241.2009.02056.x","volume":"63","author":"CY Lu","year":"2009","unstructured":"Lu CY. Observational studies: a review of study designs, challenges and strategies to reduce confounding. Int J Clin Pract. 2009;63(5):691\u20137.","journal-title":"Int J Clin Pract"},{"issue":"1","key":"562_CR4","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1146\/annurev-clinpsy-032816-045030","volume":"16","author":"BM D\u2019Onofrio","year":"2020","unstructured":"D\u2019Onofrio BM, Sj\u00f6lander A, Lahey BB, Lichtenstein P, \u00d6berg AS. Accounting for confounding in observational studies. Ann Rev Clin Psychol. 2020;16(1):25\u201348.","journal-title":"Ann Rev Clin Psychol"},{"issue":"1","key":"562_CR5","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/1472-6947-7-16","volume":"7","author":"C Schardt","year":"2007","unstructured":"Schardt C, Adams MB, Owens T, Keitz S, Fontelo P. Utilization of the PICO framework to improve searching PubMed for clinical questions. BMC Med Inf Decis Mak. 2007;7(1):16.","journal-title":"BMC Med Inf Decis Mak"},{"key":"562_CR6","doi-asserted-by":"crossref","unstructured":"Mintzker Y, Blum D, Adler L. Replacing PICO in non-interventional studies. BMJ evidence-based medicine; 2022.","DOI":"10.1136\/bmjebm-2021-111889"},{"issue":"4","key":"562_CR7","first-page":"420","volume":"106","author":"MB Eriksen","year":"2018","unstructured":"Eriksen MB, Frandsen TF. The impact of patient, intervention, comparison, outcome (PICO) as a search strategy tool on literature search quality: a systematic review. J Med Libr Association: JMLA. 2018;106(4):420.","journal-title":"J Med Libr Association: JMLA"},{"issue":"3","key":"562_CR8","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s10654-019-00494-6","volume":"34","author":"TJ VanderWeele","year":"2019","unstructured":"VanderWeele TJ. Principles of confounder selection. Eur J Epidemiol. 2019;34(3):211\u20139.","journal-title":"Eur J Epidemiol"},{"issue":"3","key":"562_CR9","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1136\/oem.60.3.227","volume":"60","author":"R McNamee","year":"2003","unstructured":"McNamee R. Confounding and confounders. Occup Environ Med. 2003;60(3):227\u201334.","journal-title":"Occup Environ Med"},{"issue":"4","key":"562_CR10","doi-asserted-by":"publisher","first-page":"1406","DOI":"10.1111\/j.1541-0420.2011.01619.x","volume":"67","author":"TJ Vander Weele","year":"2011","unstructured":"Vander Weele TJ, Shpitser I. A new criterion for confounder selection. Biometrics. 2011;67(4):1406\u201313.","journal-title":"Biometrics"},{"issue":"3","key":"562_CR11","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1111\/cts.13463","volume":"16","author":"S Fu","year":"2023","unstructured":"Fu S, Wang L, Moon S, Zong N, He H, Pejaver V, Liu H. Recommended practices and ethical considerations for natural language processing-assisted observational research: a scoping review. Clin Transl Sci. 2023;16(3):398\u2013411.","journal-title":"Clin Transl Sci"},{"key":"562_CR12","doi-asserted-by":"crossref","unstructured":"Lee PH, Lin YC, Ku CT, Hsu C, Huang PC, Wu PH, Kang Y. LLM-Based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference. In 2025 IEEE International Conference on Information Reuse and Integration and Data Science (IRI); 2025 Aug; pp. 265\u2013270. IEEE.","DOI":"10.1109\/IRI66576.2025.00055"},{"key":"562_CR13","unstructured":"Ma Y, Frauen D, Schweisthal J, Feuerriegel S. (2025). LLM-driven treatment effect estimation under inference time text confounding. arXiv preprint arXiv:2507.02843."},{"key":"562_CR14","doi-asserted-by":"crossref","unstructured":"Panda M, Mukherjee S. Enhancing privacy and security in rag-based generative AI applications. In CS & IT Conference Proceedings. CS & IT Conference Proceedings; 2025, (Vol. 15, No. 3).","DOI":"10.2139\/ssrn.5162147"},{"issue":"6","key":"562_CR15","doi-asserted-by":"publisher","first-page":"e428","DOI":"10.1016\/S2589-7500(24)00061-X","volume":"6","author":"JCL Ong","year":"2024","unstructured":"Ong JCL, Chang SYH, William W, Butte AJ, Shah NH, Chew LST, Ting DSW. Ethical and regulatory challenges of large language models in medicine. Lancet Digit Health. 2024;6(6):e428\u201332.","journal-title":"Lancet Digit Health"},{"key":"562_CR16","doi-asserted-by":"publisher","first-page":"103719","DOI":"10.1016\/j.jbi.2021.103719","volume":"117","author":"SA Malec","year":"2021","unstructured":"Malec SA, Wei P, Bernstam EV, Boyce RD, Cohen T. Using computable knowledge mined from the literature to elucidate confounders for EHR-based pharmacovigilance. J Biomed Inform. 2021;117:103719.","journal-title":"J Biomed Inform"},{"issue":"1","key":"562_CR17","doi-asserted-by":"publisher","first-page":"7355","DOI":"10.1038\/s41467-025-62783-x","volume":"16","author":"X Shi","year":"2025","unstructured":"Shi X, Zhao W, Chen T, Yang C, Du J. Evidence triangulator: using large language models to extract and synthesize causal evidence across study designs. Nat Commun. 2025;16(1):7355.","journal-title":"Nat Commun"},{"issue":"23","key":"562_CR18","doi-asserted-by":"publisher","first-page":"3158","DOI":"10.1093\/bioinformatics\/bts591","volume":"28","author":"H Kilicoglu","year":"2012","unstructured":"Kilicoglu H, Shin D, Fiszman M, Rosemblat G, Rindflesch TC. SemMedDB: a PubMed-scale repository of biomedical semantic predications. Bioinformatics. 2012;28(23):3158\u201360.","journal-title":"Bioinformatics"},{"key":"562_CR19","unstructured":"National Center for Biotechnology Information. PubMed database. Bethesda (MD): National Library of Medicine (US). Available from: https:\/\/pubmed.ncbi.nlm.nih.gov\/. Accessed 12\/01\/2025."},{"key":"562_CR20","unstructured":"National Library of Medicine. SemMedDB Database Download. https:\/\/lhncbc.nlm.nih.gov\/temp\/SemRep_SemMedDB_SKR\/SemMedDB_download.html. Accessed 12\/01\/2025."},{"key":"562_CR21","unstructured":"Malec SA, Wei P, Xu H, Bernstam EV, Myneni S, Cohen T. Literature-based discovery of confounding in observational clinical data. In AMIA annual symposium proceedings; 2017, (Vol. 2016, p. 1920)."},{"key":"562_CR22","first-page":"104368","volume":"142","author":"SA Malec","year":"2023","unstructured":"Malec SA, Taneja SB, Albert SM, Shaaban CE, Karim HT, Levine AS, Boyce biomedical, R. D. Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies:a use case studying depression as a risk factor for Alzheimer\u2019s disease. J Inf. 2023;142:104368.","journal-title":"J Inf"},{"issue":"15","key":"562_CR23","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1056\/NEJMoa1606220","volume":"375","author":"FC Hamdy","year":"2016","unstructured":"Hamdy FC, Donovan JL, Lane JA, Mason M, Metcalfe C, Holding P, Neal DE. 10-year outcomes after monitoring, surgery, or radiotherapy for localized prostate cancer. N Engl J Med. 2016;375(15):1415\u201324.","journal-title":"N Engl J Med"},{"issue":"17","key":"562_CR24","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1056\/NEJMoa2214122","volume":"388","author":"FC Hamdy","year":"2023","unstructured":"Hamdy FC, Donovan JL, Lane JA, Metcalfe C, Davis M, Turner EL, Neal DE. Fifteen-year outcomes after monitoring, surgery, or radiotherapy for prostate cancer. N Engl J Med. 2023;388(17):1547\u201358.","journal-title":"N Engl J Med"},{"issue":"18","key":"562_CR25","doi-asserted-by":"publisher","first-page":"1887","DOI":"10.1056\/NEJMoa0801369","volume":"358","author":"NS Beckett","year":"2008","unstructured":"Beckett NS, Peters R, Fletcher AE, Staessen JA, Liu L, Dumitrascu D, Bulpitt CJ. Treatment of hypertension in patients 80 years of age or older. N Engl J Med. 2008;358(18):1887\u201398.","journal-title":"N Engl J Med"},{"key":"562_CR26","doi-asserted-by":"crossref","unstructured":"Yan VKC, Ju C, MacDonald TM, Mackenzie IS, Flynn R, Williams B, Wei L. Comparative effectiveness and prescribing trends of modified release versus immediate release indapamide in patients with hypertension: cohort study. BMJ Med. 2025;4(1):e000857.","DOI":"10.1136\/bmjmed-2024-000857"},{"issue":"1","key":"562_CR27","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1097\/01.jcp.0000104909.75206.6f","volume":"24","author":"M Van Ameringen","year":"2004","unstructured":"Van Ameringen M, Oakman J, Mancini C, Pipe B, Chung H. Predictors of response in generalized social phobia: effect of age of onset. J Clin Psychopharmacol. 2004;24(1):42\u20138.","journal-title":"J Clin Psychopharmacol"},{"issue":"1","key":"562_CR28","doi-asserted-by":"publisher","first-page":"12214","DOI":"10.1038\/s41598-022-16476-w","volume":"12","author":"M Zuin","year":"2022","unstructured":"Zuin M, Cherubini A, Volpato S, Ferrucci L, Zuliani G. Acetyl-cholinesterase-inhibitors slow cognitive decline and decrease overall mortality in older patients with dementia. Sci Rep. 2022;12(1):12214.","journal-title":"Sci Rep"},{"issue":"6","key":"562_CR29","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1007\/s13300-020-00834-w","volume":"11","author":"WD Strain","year":"2020","unstructured":"Strain WD, Tsang C, Hurst M, McEwan P, Unadkat M, Meadowcroft S, Evans M. What next after metformin in type 2 diabetes? Selecting the right drug for the right patient. Diabetes Therapy. 2020;11(6):1381\u201395.","journal-title":"Diabetes Therapy"},{"issue":"1","key":"562_CR30","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1186\/s12859-020-3517-7","volume":"21","author":"H Kilicoglu","year":"2020","unstructured":"Kilicoglu H, Rosemblat G, Fiszman M, Shin D. Broad-coverage biomedical relation extraction with SemRep. BMC Bioinformatics. 2020;21(1):188. https:\/\/doi.org\/10.1186\/s12859-020-3517-7.","journal-title":"BMC Bioinformatics"},{"key":"562_CR31","unstructured":"Clarivate Analytics. Journal Citation Reports. 2025. Available from: https:\/\/jcr.clarivate.com\/. Accessed 12\/14\/2025."},{"key":"562_CR32","unstructured":"Web-based prototype. of the pipeline (non-commercial academic use). Available from: http:\/\/47.94.183.113:9994\/. Accessed 12\/01\/2025."}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13040-026-00562-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-026-00562-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-026-00562-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T10:29:19Z","timestamp":1782383359000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13040-026-00562-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,16]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["562"],"URL":"https:\/\/doi.org\/10.1186\/s13040-026-00562-0","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,16]]},"assertion":[{"value":"6 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Institutional Review Board approval was not required for this study as it was a review of previously published literature and did not involve any human subjects.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Institutional review board statement"}},{"value":"Not applicable. This study was a review of data from previously published studies, and no human subjects were directly involved.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"51"}}