{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:18:11Z","timestamp":1783383491765,"version":"3.54.6"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":56,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Res Methodol"],"DOI":"10.1186\/s12874-026-02858-5","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T11:09:37Z","timestamp":1778584177000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A comparative analysis in a clinical cohort: multiple imputation by chained equations and a novel super learner-based imputation approach"],"prefix":"10.1186","volume":"26","author":[{"given":"Tony","family":"Zbysinski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lezhou","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Dale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Coates","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karan","family":"Sapiah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamie","family":"Reuben","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"Markson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ujjwal","family":"Kulkarni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazmul","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,12]]},"reference":[{"issue":"3","key":"2858_CR1","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1093\/biomet\/63.3.581","volume":"63","author":"RUBIN DB","year":"1976","unstructured":"RUBIN DB. Inference and missing data. Biometrika. 1976;63(3):581\u201392.","journal-title":"Biometrika"},{"issue":"2","key":"2858_CR2","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1037\/1082-989X.7.2.147","volume":"7","author":"JL Schafer","year":"2002","unstructured":"Schafer JL, Graham JW. Missing data: our view of the state of the art. Psychol Methods. 2002;7(2):147\u201377.","journal-title":"Psychol Methods"},{"key":"2858_CR3","unstructured":"Roderick JA, Little, Donald B, Rubin. (2002) Statistical Analysis with Missing Data, 2nd ed. John Wiley & Sons | RTI . [cited 2025 Jul 3]. Available from: https:\/\/www.rti.org\/publication\/roderick-j-little-donald-b-rubin-2002-statistical-analysis-missing-data-2nd-ed-john-wiley-amp-sons-b"},{"key":"2858_CR4","doi-asserted-by":"publisher","first-page":"157","DOI":"10.2147\/CLEP.S191437","volume":"11","author":"I Petersen","year":"2019","unstructured":"Petersen I, Welch CA, Nazareth I, Walters K, Marston L, Morris RW, et al. Health indicator recording in UK primary care electronic health records: key implications for handling missing data. Clin Epidemiol. 2019;11:157\u201367.","journal-title":"Clin Epidemiol"},{"key":"2858_CR5","doi-asserted-by":"publisher","first-page":"102587","DOI":"10.1016\/j.artmed.2023.102587","volume":"142","author":"M Liu","year":"2023","unstructured":"Liu M, Li S, Yuan H, Ong MEH, Ning Y, Xie F, et al. Handling missing values in healthcare data: A systematic review of deep learning-based imputation techniques. Artif Intell Med. 2023;142:102587.","journal-title":"Artif Intell Med"},{"key":"2858_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","volume":"45","author":"S van Buuren","year":"2011","unstructured":"van Buuren S, Groothuis-Oudshoorn K. mice: Multivariate Imputation by Chained Equations in R. J Stat Softw. 2011;45:1\u201367.","journal-title":"J Stat Softw"},{"key":"2858_CR7","doi-asserted-by":"publisher","first-page":"44483","DOI":"10.1109\/ACCESS.2022.3160841","volume":"10","author":"M Alabadla","year":"2022","unstructured":"Alabadla M, Sidi F, Ishak I, Ibrahim H, Affendey LS, Che Ani Z, et al. Systematic Review of Using Machine Learning in Imputing Missing Values. IEEE Access. 2022;10:44483\u2013502.","journal-title":"IEEE Access"},{"issue":"1","key":"2858_CR8","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","volume":"28","author":"DJ Stekhoven","year":"2012","unstructured":"Stekhoven DJ, B\u00fchlmann P. MissForest\u2013non-parametric missing value imputation for mixed-type data. Bioinformatics. 2012;28(1):112\u20138.","journal-title":"Bioinformatics"},{"issue":"2","key":"2858_CR9","doi-asserted-by":"publisher","first-page":"143","DOI":"10.18196\/jrc.v3i2.13133","volume":"3","author":"AR Ismail","year":"2022","unstructured":"Ismail AR, Abidin NZ, Maen MK. Systematic Review on Missing Data Imputation Techniques with Machine Learning Algorithms for Healthcare. J Rob Control (JRC). 2022;3(2):143\u201352.","journal-title":"J Rob Control (JRC)"},{"issue":"1","key":"2858_CR10","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1186\/s12874-024-02310-6","volume":"24","author":"M Afkanpour","year":"2024","unstructured":"Afkanpour M, Hosseinzadeh E, Tabesh H. Identify the most appropriate imputation method for handling missing values in clinical structured datasets: a systematic review. BMC Med Res Methodol. 2024;24(1):188.","journal-title":"BMC Med Res Methodol"},{"key":"2858_CR11","doi-asserted-by":"publisher","first-page":"120201","DOI":"10.1016\/j.eswa.2023.120201","volume":"227","author":"Y Sun","year":"2023","unstructured":"Sun Y, Li J, Xu Y, Zhang T, Wang X. Deep learning versus conventional methods for missing data imputation: A review and comparative study. Expert Syst Appl. 2023;227:120201.","journal-title":"Expert Syst Appl"},{"issue":"4","key":"2858_CR12","doi-asserted-by":"publisher","first-page":"533","DOI":"10.3390\/e24040533","volume":"24","author":"S Batra","year":"2022","unstructured":"Batra S, Khurana R, Khan MZ, Boulila W, Koubaa A, Srivastava P. A Pragmatic Ensemble Strategy for Missing Values Imputation in Health Records. Entropy. 2022;24(4):533.","journal-title":"Entropy"},{"key":"2858_CR13","unstructured":"Super Learner In Prediction by, Eric C, Polley, Mark J. van der Laan . [cited 2025 Jun 25]. Available from: https:\/\/biostats.bepress.com\/ucbbiostat\/paper266\/"},{"key":"2858_CR14","doi-asserted-by":"publisher","unstructured":"van der Laan MJ, Polley EC, Hubbard AE. Super Learner. Statistical Applications in Genetics and Molecular Biology . 2007 Sep 16 [cited 2025 Aug 6];6(1). Available from: https:\/\/www.degruyterbrill.com\/document\/doi\/https:\/\/doi.org\/10.2202\/1544-6115.1309\/html","DOI":"10.2202\/1544-6115.1309\/html"},{"key":"2858_CR15","unstructured":"Carpenito T, Manjourides J, MISL. Multiple imputation by super learning. Statistical Methods in Medical Research . 2022 Jun 5 [cited 2025 Sep 30]; Available from: https:\/\/journals.sagepub.com\/doi\/full\/. https:\/\/doi.org\/10.1177\/09622802221104238?casa_token=a4zKe63PN7wAAAAA%3AT5UReTqofKOpADbdbYGF_fm78d-oGRJBK4Bba-RgMiY556k6xoTxn8JxjJhQ_wVrBfNS5fFt6jfwYQ."},{"key":"2858_CR16","doi-asserted-by":"publisher","unstructured":"Murugesan S, Bhuvaneswaran RS, Nehemiah HK, Sankari SK, Jane YN. Feature Selection and Classification of Clinical Datasets Using Bioinspired Algorithms and Super Learner. Computational and Mathematical Methods in Medicine . 2021 May 18 [cited 2025 Sep 30]; Available from: https:\/\/onlinelibrary.wiley.com\/doi\/https:\/\/doi.org\/10.1155\/2021\/6662420","DOI":"10.1155\/2021\/6662420"},{"key":"2858_CR17","unstructured":"Li S, Zhang Y, Fu K, Fang K, Zheng L, Lin Y et al. Machine learning ensemble meets clinical practice: developing a real-world risk prediction model for metabolic syndrome using super learner and scorecard approaches. Journal of Advanced Research . 2025 Jun 27 [cited 2025 Sep 30]; Available from: https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2090123225004813"},{"key":"2858_CR18","doi-asserted-by":"crossref","unstructured":"Petersen ML, LeDell E, Schwab J, Sarovar V, Gross R, Reynolds N, et al. J Acquir Immune Defic Syndr. 2015;69(1):109\u201318. Super Learner Analysis of Electronic Adherence Data Improves Viral Prediction and May Provide Strategies for Selective HIV RNA Monitoring.","DOI":"10.1097\/QAI.0000000000000548"},{"issue":"23","key":"2858_CR19","doi-asserted-by":"publisher","first-page":"7313","DOI":"10.3390\/jcm12237313","volume":"12","author":"W Jin","year":"2023","unstructured":"Jin W, Hao W, Shi X, Fritsche LG, Salvatore M, Admon AJ, et al. Using Multi-Modal Electronic Health Record Data for the Development and Validation of Risk Prediction Models for Long COVID Using the Super Learner Algorithm. J Clin Med. 2023;12(23):7313.","journal-title":"J Clin Med"},{"issue":"1","key":"2858_CR20","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1186\/s12874-024-02179-5","volume":"24","author":"X Zhu","year":"2024","unstructured":"Zhu X, Zhang P, Jiang H, Kuang J, Wu L. Using the Super Learner algorithm to predict risk of major adverse cardiovascular events after percutaneous coronary intervention in patients with myocardial infarction. BMC Med Res Methodol. 2024;24(1):59.","journal-title":"BMC Med Res Methodol"},{"key":"2858_CR21","doi-asserted-by":"publisher","unstructured":"Ma X, Long L, Moon S, Adamson BJS, Baxi SS. Comparison of Population Characteristics in Real-World Clinical Oncology Databases in the US: Flatiron Health, SEER, and NPCR . medRxiv; 2023 [cited 2025 Aug 5]. p. 2020.03.16.20037143. Available from: https:\/\/www.medrxiv.org\/content\/https:\/\/doi.org\/10.1101\/2020.03.16.20037143v3","DOI":"10.1101\/2020.03.16.20037143v3"},{"key":"2858_CR22","unstructured":"Birnbaum B, Nussbaum N, Seidl-Rathkopf K, Agrawal M, Estevez M, Estola E et al. Model-assisted cohort selection with bias analysis for generating large-scale cohorts from the EHR for oncology research . arXiv; 2020 [cited 2025 Aug 5]. Available from: http:\/\/arxiv.org\/abs\/2001.09765"},{"key":"2858_CR23","doi-asserted-by":"publisher","unstructured":"Islam N, Reuben JS, Dale JL, Zhang J, Coates JW, Sapiah K et al. A simplified risk model for pretreatment stratification of newly diagnosed acute myeloid leukemia patients treated with venetoclax and azacitidine . medRxiv; 2024 [cited 2025 Jul 3]. p. 2024.12.02.24318344. Available from: https:\/\/www.medrxiv.org\/content\/https:\/\/doi.org\/10.1101\/2024.12.02.24318344v1","DOI":"10.1101\/2024.12.02.24318344v1"},{"key":"2858_CR24","unstructured":"Tierney N, Cook D, McBain M, Fay C, O\u2019Hara-Wild M, Hester J et al. naniar: Data Structures, Summaries, and Visualisations for Missing Data . 2024 [cited 2025 Jul 30]. Available from: https:\/\/cran.r-project.org\/web\/packages\/naniar\/index.html"},{"issue":"13","key":"2858_CR25","doi-asserted-by":"publisher","first-page":"4075","DOI":"10.1182\/blood.V96.13.4075","volume":"96","author":"ML Slovak","year":"2000","unstructured":"Slovak ML, Kopecky KJ, Cassileth PA, Harrington DH, Theil KS, Mohamed A, et al. Karyotypic analysis predicts outcome of preremission and postremission therapy in adult acute myeloid leukemia: a Southwest Oncology Group\/Eastern Cooperative Oncology Group study. Blood. 2000;96(13):4075\u201383.","journal-title":"Blood"},{"issue":"1","key":"2858_CR26","doi-asserted-by":"publisher","first-page":"e54740","DOI":"10.2196\/54740","volume":"10","author":"N Islam","year":"2024","unstructured":"Islam N, Reuben JS, Dale J, Coates JW, Sapiah K, Markson FR, et al. Predictive Models for Long Term Survival of AML Patients Treated with Venetoclax and Azacitidine or 7\u2009+\u20093 Based on Post Treatment Events and Responses: Retrospective Cohort Study. JMIR Cancer. 2024;10(1):e54740.","journal-title":"JMIR Cancer"},{"key":"2858_CR27","unstructured":"Bengtsson H. future: Unified Parallel and Distributed Processing in R for Everyone . 2025 [cited 2025 Jul 29]. Available from: https:\/\/cran.r-project.org\/web\/packages\/future\/index.html"},{"key":"2858_CR28","doi-asserted-by":"publisher","unstructured":"Islam N, Dale JL, Reuben JS, Sapiah K, Coates JW, Markson FR et al. Development of a dynamic counterfactual risk stratification strategy for newly diagnosed acute myeloid leukemia patients treated with venetoclax and azacitidine . medRxiv; 2025 [cited 2025 Jul 25]. p. 2024.11.25.24317750. Available from: https:\/\/www.medrxiv.org\/content\/https:\/\/doi.org\/10.1101\/2024.11.25.24317750v4","DOI":"10.1101\/2024.11.25.24317750v4"},{"key":"2858_CR29","unstructured":"R Development Core Team. R: A Language and Environment for Statistical Computing . Vienna, Austria: R Foundation for Statistical Computing. 2025. Available from: https:\/\/cran.r-project.org\/"},{"key":"2858_CR30","doi-asserted-by":"crossref","unstructured":"von Elm E, Altman DG, Egger M, Pocock SJ, G\u00f8tzsche PC, Vandenbroucke JP; STROBE Initiative. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies. J Clin Epidemiol. 2008;61(4):344-9. PMID: 18313558.","DOI":"10.1016\/j.jclinepi.2007.11.008"},{"issue":"2","key":"2858_CR31","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.artmed.2010.05.002","volume":"50","author":"JM Jerez","year":"2010","unstructured":"Jerez JM, Molina I, Garc\u00eda-Laencina PJ, Alba E, Ribelles N, Mart\u00edn M, et al. Missing data imputation using statistical and machine learning methods in a real breast cancer problem. Artif Intell Med. 2010;50(2):105\u201315.","journal-title":"Artif Intell Med"},{"issue":"2","key":"2858_CR32","first-page":"30","volume":"4","author":"Z Zhang","year":"2016","unstructured":"Zhang Z. Multiple imputation with multivariate imputation by chained equation (MICE) package. Ann Transl Med. 2016;4(2):30.","journal-title":"Ann Transl Med"},{"key":"2858_CR33","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s12874-015-0022-1","volume":"15","author":"P Hayati Rezvan","year":"2015","unstructured":"Hayati Rezvan P, Lee KJ, Simpson JA. The rise of multiple imputation: a review of the reporting and implementation of the method in medical research. BMC Med Res Methodol. 2015;15:30.","journal-title":"BMC Med Res Methodol"},{"issue":"1","key":"2858_CR34","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s13040-021-00274-7","volume":"14","author":"BO Petrazzini","year":"2021","unstructured":"Petrazzini BO, Naya H, Lopez-Bello F, Vazquez G, Spangenberg L. Evaluation of different approaches for missing data imputation on features associated to genomic data. BioData Min. 2021;14(1):44.","journal-title":"BioData Min"},{"issue":"4","key":"2858_CR35","first-page":"558","volume":"55","author":"T Thomas","year":"2021","unstructured":"Thomas T, Rajabi E. A systematic review of machine learning-based missing value imputation techniques. Data Technol Appl. 2021;55(4):558\u201385.","journal-title":"Data Technol Appl"},{"issue":"7","key":"2858_CR36","doi-asserted-by":"publisher","first-page":"e0254720","DOI":"10.1371\/journal.pone.0254720","volume":"16","author":"M Mera-Gaona","year":"2021","unstructured":"Mera-Gaona M, Neumann U, Vargas-Canas R, L\u00f3pez DM. Evaluating the impact of multivariate imputation by MICE in feature selection. PLoS ONE. 2021;16(7):e0254720.","journal-title":"PLoS ONE"},{"issue":"2","key":"2858_CR37","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1007\/s10462-019-09709-4","volume":"53","author":"WC Lin","year":"2020","unstructured":"Lin WC, Tsai CF. Missing value imputation: a review and analysis of the literature (2006\u20132017). Artif Intell Rev. 2020;53(2):1487\u2013509.","journal-title":"Artif Intell Rev"},{"key":"2858_CR38","doi-asserted-by":"publisher","unstructured":"Gelman A, Su YS. arm: Data Analysis Using Regression and Multilevel\/Hierarchical Models [Internet]. 2007 [cited 2025 Jul 29]. p. 1.14-4. Available from: https:\/\/doi.org\/10.32614\/CRAN.package.arm.","DOI":"10.32614\/CRAN.package.arm"},{"key":"2858_CR39","doi-asserted-by":"publisher","unstructured":"Kuhn M. caret: Classification and Regression Training [Internet]. 2007 [cited 2025 Jul 29]. p. 7.0-1. Available from: https:\/\/doi.org\/10.32614\/CRAN.package.caret.","DOI":"10.32614\/CRAN.package.caret"},{"key":"2858_CR40","doi-asserted-by":"publisher","unstructured":"Strobl C, Boulesteix AL, Zeileis A, Hothorn T. Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics. 2007;8(1):25. https:\/\/doi.org\/10.1186\/1471-2105-8-25.","DOI":"10.1186\/1471-2105-8-25"},{"key":"2858_CR41","unstructured":"R Development Core Team. R: A Language and Environment for Statistical Computing [Internet]. Vienna, Austria: R Foundation for Statistical Computing; 2010. Available from: https:\/\/cran.r-project.org\/."},{"key":"2858_CR42","unstructured":"Regularization Paths for Generalized Linear Models via Coordinate Descent | Journal of Statistical Software [Internet]. [cited 2025 Jul 29]. Available from: https:\/\/www.jstatsoft.org\/article\/view\/v033i01."},{"key":"2858_CR43","doi-asserted-by":"publisher","unstructured":"Friedman J, Hastie T, Tibshirani R, Narasimhan B, Tay K, Simon N, et al. glmnet: Lasso and Elastic-Net Regularized Generalized Linear Models [Internet]. 2008 [cited 2025 Jul 29]. p. 4.1-10. Available from: https:\/\/doi.org\/10.32614\/CRAN.package.glmnet.","DOI":"10.32614\/CRAN.package.glmnet"},{"key":"2858_CR44","unstructured":"Mouselimis L, Parks M. KernelKnn: Kernel k Nearest Neighbors [Internet]. 2023 [cited 2025 Jul 29]. Available from: https:\/\/cran.r-project.org\/web\/packages\/KernelKnn\/index.html."},{"key":"2858_CR45","doi-asserted-by":"publisher","unstructured":"Karatzoglou A, Smola A, Hornik K, Zeileis A. kernlab - An S4 Package for Kernel Methods in R. Journal of Statistical Software. 2004;11:1\u201320. https:\/\/doi.org\/10.18637\/jss.v011.i09.","DOI":"10.18637\/jss.v011.i09"},{"key":"2858_CR46","doi-asserted-by":"publisher","unstructured":"Venables WN, Ripley BD. Modern Applied Statistics with S [Internet]. New York, NY: Springer; 2002 [cited 2025 Jul 29]. (Chambers J, Eddy W, H\u00e4rdle W, Sheather S, Tierney L, editors. Statistics and Computing). Available from: https:\/\/doi.org\/10.1007\/978-0-387-21706-2.","DOI":"10.1007\/978-0-387-21706-2"},{"key":"2858_CR47","doi-asserted-by":"publisher","unstructured":"Breiman L. Random Forests. Machine Learning. 2001 Oct 1;45(1):5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324.","DOI":"10.1023\/A:1010933404324"},{"key":"2858_CR48","unstructured":"Breiman L, Cutler A, Liaw A, Wiener M. randomForest: Breiman and Cutlers Random Forests for Classification and Regression [Internet]. 2024 [cited 2025 Jul 29]. Available from: https:\/\/cran.r-project.org\/web\/packages\/randomForest\/index.html."},{"key":"2858_CR49","doi-asserted-by":"publisher","unstructured":"Wright MN, Ziegler A. ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R. Journal of Statistical Software. 2017 Mar 31;77:1\u201317. https:\/\/doi.org\/10.18637\/jss.v077.i01.","DOI":"10.18637\/jss.v077.i01"},{"key":"2858_CR50","doi-asserted-by":"crossref","unstructured":"Therneau T, Atkinson B, port BR (producer of the initial R, maintainer 1999-2017). rpart: Recursive Partitioning and Regression Trees [Internet]. 2025 [cited 2025 Jul 29]. Available from: https:\/\/cran.r-project.org\/web\/packages\/rpart\/index.html.","DOI":"10.32614\/CRAN.package.rpart"},{"key":"2858_CR51","doi-asserted-by":"crossref","unstructured":"Enea M, Meiri R, Kalimi T. speedglm: Fitting Linear and Generalized Linear Models to Large Data Sets [Internet]. 2023 [cited 2025 Jul 29]. Available from: https:\/\/cran.r-project.org\/web\/packages\/speedglm\/index.html.","DOI":"10.32614\/CRAN.package.speedglm"},{"key":"2858_CR52","unstructured":"Ripley B, Venables B, Bates DM, ca 1998) KH (partial port, ca 1998) AG (partial port, polr) DF (support functions for. MASS: Support Functions and Datasets for Venables and Ripley\u2019s MASS [Internet]. 2025 [cited 2025 Jul 29]. Available from: https:\/\/cran.r-project.org\/web\/packages\/MASS\/index.html."},{"key":"2858_CR53","unstructured":"Chen T, He T, Benesty M, Khotilovich V, Tang Y, Cho H, et al. xgboost: Extreme Gradient Boosting [Internet]. 2025 [cited 2025 Jul 29]. Available from: https:\/\/cran.r-project.org\/web\/packages\/xgboost\/index.html."}],"container-title":["BMC Medical Research Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12874-026-02858-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12874-026-02858-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12874-026-02858-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:04:24Z","timestamp":1783382664000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12874-026-02858-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,12]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2858"],"URL":"https:\/\/doi.org\/10.1186\/s12874-026-02858-5","relation":{},"ISSN":["1471-2288"],"issn-type":[{"value":"1471-2288","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,12]]},"assertion":[{"value":"18 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 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":"This study was conducted in accordance with the principles of the Declaration of Helsinki. This study was reviewed and approved under the \u201c2018 Requirements\u201d of the Federal Policy for the Protection of Human. Subjects. A Waiver of Consent and a HIPAA Waiver of Authorization were granted for this study by the Colorado Multiple Institution Review Board (COMIRB). All criteria for waiving consent and HIPAA authorization were met. The Flatiron Health data that supported the findings of this study were originated by and are the property of Flatiron Health, Inc.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"All authors are affiliated with RefinedScience and receive compensation as part of employment under RefinedScience. The authors declare no other competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"148"}}