{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T23:03:25Z","timestamp":1743635005248,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"BHF-Turing Cardiovascular Data Science Award","award":["SP\/19\/6\/34809","SP\/19\/6\/34809","SP\/19\/6\/34809","SP\/19\/6\/34809","SP\/19\/6\/34809"]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["MR\/W003988\/1","MR\/W003988\/1","MR\/W003988\/1","MR\/W003988\/1","MR\/W003988\/1","MR\/W003988\/1"],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"Abstract<\/jats:title>\n Objective<\/jats:title>\n Precision medicine requires reliable identification of variation in patient-level outcomes with different available treatments, often termed treatment effect heterogeneity. We aimed to evaluate the comparative utility of individualized treatment selection strategies based on predicted individual-level treatment effects from a causal forest machine learning algorithm and a penalized regression model.<\/jats:p>\n <\/jats:sec>\n Methods<\/jats:title>\n Cohort study characterizing individual-level glucose-lowering response (6\u00a0month reduction in HbA1c) in people with type 2 diabetes initiating SGLT2-inhibitor or DPP4-inhibitor therapy. Model development set comprised 1,428 participants in the CANTATA-D and CANTATA-D2 randomised clinical trials of SGLT2-inhibitors versus DPP4-inhibitors. For external validation, calibration of observed versus predicted differences in HbA1c in patient strata defined by size of predicted HbA1c benefit was evaluated in 18,741 patients in UK primary care (Clinical Practice Research Datalink).<\/jats:p>\n <\/jats:sec>\n Results<\/jats:title>\n Heterogeneity in treatment effects was detected in clinical trial participants with both approaches (proportion predicted to have a benefit on SGLT2-inhibitor therapy over DPP4-inhibitor therapy: causal forest: 98.6%; penalized regression: 81.7%). In validation, calibration was good with penalized regression but sub-optimal with causal forest. A strata with an HbA1c benefit\u2009>\u200910\u00a0mmol\/mol with SGLT2-inhibitors (3.7% of patients, observed benefit 11.0\u00a0mmol\/mol [95%CI 8.0\u201314.0]) was identified using penalized regression but not causal forest, and a much larger strata with an HbA1c benefit 5\u201310\u00a0mmol with SGLT2-inhibitors was identified with penalized regression (regression: 20.9% of patients, observed benefit 7.8\u00a0mmol\/mol (95%CI 6.7\u20138.9); causal forest 11.6%, observed benefit 8.7\u00a0mmol\/mol (95%CI 7.4\u201310.1).<\/jats:p>\n <\/jats:sec>\n Conclusions<\/jats:title>\n Consistent with recent results for outcome prediction with clinical data, when evaluating treatment effect heterogeneity researchers should not rely on causal forest or other similar machine learning algorithms alone, and must compare outputs with standard regression, which in this evaluation was superior.<\/jats:p>\n <\/jats:sec>","DOI":"10.1186\/s12911-023-02207-2","type":"journal-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T13:02:33Z","timestamp":1686920553000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Comparison of causal forest and regression-based approaches to evaluate treatment effect heterogeneity: an application for type 2 diabetes precision medicine"],"prefix":"10.1186","volume":"23","author":[{"given":"Ashwini","family":"Venkatasubramaniam","sequence":"first","affiliation":[]},{"given":"Bilal A.","family":"Mateen","sequence":"additional","affiliation":[]},{"given":"Beverley M.","family":"Shields","sequence":"additional","affiliation":[]},{"given":"Andrew T.","family":"Hattersley","sequence":"additional","affiliation":[]},{"given":"Angus G.","family":"Jones","sequence":"additional","affiliation":[]},{"given":"Sebastian J.","family":"Vollmer","sequence":"additional","affiliation":[]},{"given":"John M.","family":"Dennis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,16]]},"reference":[{"issue":"10","key":"2207_CR1","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1016\/S0895-4356(97)00149-2","volume":"50","author":"JP Ioannidis","year":"1997","unstructured":"Ioannidis JP, Lau J. The impact of high-risk patients on the results of clinical trials. J Clin Epidemiol. 1997;50(10):1089\u201398.","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"2207_CR2","doi-asserted-by":"publisher","first-page":"35","DOI":"10.7326\/M18-3667","volume":"172","author":"DM Kent","year":"2020","unstructured":"Kent DM, Paulus JK, van Klaveren D, D\u2019Agostino R, Goodman S, Hayward R, et al. The Predictive Approaches to Treatment effect Heterogeneity (PATH) statement. Ann Intern Med. 2020;172(1):35\u201345.","journal-title":"Ann Intern Med"},{"key":"2207_CR3","doi-asserted-by":"publisher","first-page":"k4245","DOI":"10.1136\/bmj.k4245","volume":"363","author":"DM Kent","year":"2018","unstructured":"Kent DM, Steyerberg E, van Klaveren D. Personalized evidence based medicine: predictive approaches to heterogeneous treatment effects. BMJ (Clinical research ed). 2018;363:k4245.","journal-title":"BMJ (Clinical research ed)"},{"issue":"11","key":"2207_CR4","doi-asserted-by":"publisher","first-page":"3166","DOI":"10.1177\/0962280220921415","volume":"29","author":"B Van Calster","year":"2020","unstructured":"Van Calster B, van Smeden M, De Cock B, Steyerberg EW. Regression shrinkage methods for clinical prediction models do not guarantee improved performance: Simulation study. Stat Methods Med Res. 2020;29(11):3166\u201378.","journal-title":"Stat Methods Med Res"},{"issue":"27","key":"2207_CR5","doi-asserted-by":"publisher","first-page":"7353","DOI":"10.1073\/pnas.1510489113","volume":"113","author":"S Athey","year":"2016","unstructured":"Athey S, Imbens G. Recursive partitioning for heterogeneous causal effects. Proc Natl Acad Sci USA. 2016;113(27):7353\u201360.","journal-title":"Proc Natl Acad Sci USA"},{"issue":"523","key":"2207_CR6","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","volume":"113","author":"S Wager","year":"2018","unstructured":"Wager S, Athey S. Estimation and inference of heterogeneous treatment effects using random forests. J Am Stat Assoc. 2018;113(523):1228\u201342.","journal-title":"J Am Stat Assoc"},{"issue":"11","key":"2207_CR7","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1002\/psp4.12715","volume":"10","author":"X Gong","year":"2021","unstructured":"Gong X, Hu M, Basu M, Zhao L. Heterogeneous treatment effect analysis based on machine-learning methodology. CPT Pharmacometr Syst Pharmacol. 2021;10(11):1433\u201343.","journal-title":"CPT Pharmacometr Syst Pharmacol"},{"key":"2207_CR8","doi-asserted-by":"publisher","first-page":"5961","DOI":"10.1002\/sim.9154","volume":"40","author":"J Hoogland","year":"2021","unstructured":"Hoogland J, IntHout J, Belias M, Rovers MM, Riley RD, E Harrell FJ, et al. A tutorial on individualized treatment effect prediction from randomized trials with a binary endpoint. Stat Med. 2021;40:5961.","journal-title":"Stat Med."},{"issue":"7","key":"2207_CR9","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1111\/dom.13687","volume":"21","author":"JM Dennis","year":"2019","unstructured":"Dennis JM, Henley WE, McGovern AP, Farmer AJ, Sattar N, Holman RR, et al. Time trends in prescribing of type 2 diabetes drugs, glycaemic response and risk factors: a retrospective analysis of primary care data, 2010\u20132017. Diabetes Obes Metab. 2019;21(7):1576\u201384.","journal-title":"Diabetes Obes Metab"},{"issue":"2","key":"2207_CR10","doi-asserted-by":"publisher","first-page":"487","DOI":"10.2337\/dci19-0066","volume":"43","author":"JB Buse","year":"2020","unstructured":"Buse JB, Wexler DJ, Tsapas A, Rossing P, Mingrone G, Mathieu C, et al. 2019 Update to: management of hyperglycemia in type 2 diabetes, 2018. A consensus report by the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD). Diabetes care. 2020;43(2):487\u201393.","journal-title":"Diabetes care."},{"issue":"2","key":"2207_CR11","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1111\/bcp.13807","volume":"85","author":"H Inoue","year":"2019","unstructured":"Inoue H, Tamaki Y, Kashihara Y, Muraki S, Kakara M, Hirota T, et al. Efficacy of DPP-4 inhibitors, GLP-1 analogues, and SGLT2 inhibitors as add-ons to metformin monotherapy in T2DM patients: a model-based meta-analysis. Br J Clin Pharmacol. 2019;85(2):393\u2013402.","journal-title":"Br J Clin Pharmacol"},{"issue":"10","key":"2207_CR12","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.2337\/dbi20-0002","volume":"69","author":"JM Dennis","year":"2020","unstructured":"Dennis JM. Precision medicine in type 2 diabetes: using individualized prediction models to optimize selection of treatment. Diabetes. 2020;69(10):2075\u201385.","journal-title":"Diabetes"},{"issue":"12","key":"2207_CR13","doi-asserted-by":"publisher","first-page":"2582","DOI":"10.1007\/s00125-013-3039-1","volume":"56","author":"FJ Lavalle-Gonz\u00e1lez","year":"2013","unstructured":"Lavalle-Gonz\u00e1lez FJ, Januszewicz A, Davidson J, Tong C, Qiu R, Canovatchel W, et al. Efficacy and safety of canagliflozin compared with placebo and sitagliptin in patients with type 2 diabetes on background metformin monotherapy: a randomised trial. Diabetologia. 2013;56(12):2582\u201392.","journal-title":"Diabetologia"},{"issue":"9","key":"2207_CR14","doi-asserted-by":"publisher","first-page":"2508","DOI":"10.2337\/dc12-2491","volume":"36","author":"G Schernthaner","year":"2013","unstructured":"Schernthaner G, Gross JL, Rosenstock J, Guarisco M, Fu M, Yee J, et al. Canagliflozin compared with sitagliptin for patients with type 2 diabetes who do not have adequate glycemic control with metformin plus sulfonylurea: a 52-week randomized trial. Diabetes Care. 2013;36(9):2508\u201315.","journal-title":"Diabetes Care"},{"issue":"3","key":"2207_CR15","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1093\/ije\/dyv098","volume":"44","author":"E Herrett","year":"2015","unstructured":"Herrett E, Gallagher AM, Bhaskaran K, Forbes H, Mathur R, van Staa T, et al. Data resource profile: Clinical Practice Research Datalink (CPRD). Int J Epidemiol. 2015;44(3):827\u201336.","journal-title":"Int J Epidemiol"},{"issue":"10","key":"2207_CR16","doi-asserted-by":"publisher","first-page":"e017989","DOI":"10.1136\/bmjopen-2017-017989","volume":"7","author":"LR Rodgers","year":"2017","unstructured":"Rodgers LR, Weedon MN, Henley WE, Hattersley AT, Shields BM. Cohort profile for the MASTERMIND study: using the Clinical Practice Research Datalink (CPRD) to investigate stratification of response to treatment in patients with type 2 diabetes. BMJ Open. 2017;7(10):e017989.","journal-title":"BMJ Open"},{"issue":"1","key":"2207_CR17","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1111\/dom.13865","volume":"22","author":"BM Shields","year":"2020","unstructured":"Shields BM, Hattersley AT, Farmer AJ. Identifying routine clinical predictors of non-adherence to second-line therapies in type 2 diabetes: a retrospective cohort analysis in a large primary care database. Diabetes Obes Metab. 2020;22(1):59\u201365.","journal-title":"Diabetes Obes Metab"},{"issue":"1","key":"2207_CR18","first-page":"112","volume":"28","author":"DJ Stekhoven","year":"2012","unstructured":"Stekhoven DJ, B\u00fchlmann P. MissForest\u2013non-parametric missing value imputation for mixed-type data. Bioinformatics (Oxford, England). 2012;28(1):112\u20138.","journal-title":"Bioinformatics (Oxford, England)"},{"issue":"6","key":"2207_CR19","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1002\/pds.1934","volume":"19","author":"L Marston","year":"2010","unstructured":"Marston L, Carpenter JR, Walters KR, Morris RW, Nazareth I, Petersen I. Issues in multiple imputation of missing data for large general practice clinical databases. Pharmacoepidemiol Drug Saf. 2010;19(6):618\u201326.","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"330","key":"2207_CR20","first-page":"14","volume":"2017","author":"FE Harrell","year":"2018","unstructured":"Harrell FE. Regression modeling strategies. Bios. 2018;2017(330):14.","journal-title":"Bios"},{"issue":"10","key":"2207_CR21","first-page":"1340","volume":"26","author":"A Altmann","year":"2010","unstructured":"Altmann A, Tolo\u015fi L, Sander O, Lengauer T. Permutation importance: a corrected feature importance measure. Bioinformatics (Oxford, England). 2010;26(10):1340\u20137.","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2207_CR22","doi-asserted-by":"crossref","unstructured":"Bleich J, Kapelner A, George EI, Jensen ST. Variable selection for BART: an application to gene regulation. Ann Appl Stat. 2014:1750\u201381.","DOI":"10.1214\/14-AOAS755"},{"issue":"9","key":"2207_CR23","doi-asserted-by":"publisher","first-page":"e74818","DOI":"10.1371\/journal.pone.0074818","volume":"8","author":"G Wangge","year":"2013","unstructured":"Wangge G, Putzeist M, Knol MJ, Klungel OH, Gispen-De Wied CC, de Boer A, et al. Regulatory scientific advice on non-inferiority drug trials. PLoS One. 2013;8(9):e74818.","journal-title":"PLoS ONE"},{"key":"2207_CR24","unstructured":"Tibshirani J, Athey S, Wager S. grf: Generalized Random Forests. R package version 1.2.0. 2020. https:\/\/CRAN.R-project.org\/package=grf."},{"key":"2207_CR25","unstructured":"Breiman L, et al. Classification and regression trees. Boca Raton: CRC press; 1984."},{"issue":"6","key":"2207_CR26","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1093\/aje\/kwn164","volume":"168","author":"SR Cole","year":"2008","unstructured":"Cole SR, Hern\u00e1n MA. Constructing inverse probability weights for marginal structural models. Am J Epidemiol. 2008;168(6):656\u201364.","journal-title":"Am J Epidemiol"},{"issue":"1","key":"2207_CR27","doi-asserted-by":"publisher","first-page":"e000435","DOI":"10.1136\/bmjdrc-2017-000435","volume":"5","author":"A Gottlieb","year":"2017","unstructured":"Gottlieb A, Yanover C, Cahan A, Goldschmidt Y. Estimating the effects of second-line therapy for type 2 diabetes mellitus: retrospective cohort study. BMJ Open Diabetes Res Care. 2017;5(1):e000435.","journal-title":"BMJ Open Diabetes Res Care"},{"key":"2207_CR28","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","volume":"110","author":"E Christodoulou","year":"2019","unstructured":"Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY, Van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019;110:12\u201322.","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"2207_CR29","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s41512-020-00075-2","volume":"4","author":"AL Lynam","year":"2020","unstructured":"Lynam AL, Dennis JM, Owen KR, Oram RA, Jones AG, Shields BM, et al. Logistic regression has similar performance to optimised machine learning algorithms in a clinical setting: application to the discrimination between type 1 and type 2 diabetes in young adults. Diagn and Progn Res. 2020;4(1):6.","journal-title":"Diagn and Progn Res"},{"issue":"2","key":"2207_CR30","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1001\/jamacardio.2016.3956","volume":"2","author":"JD Frizzell","year":"2017","unstructured":"Frizzell JD, Liang L, Schulte PJ, Yancy CW, Heidenreich PA, Hernandez AF, et al. Prediction of 30-day all-cause readmissions in patients hospitalized for heart failure: comparison of machine learning and other statistical approaches. JAMA cardiology. 2017;2(2):204\u20139.","journal-title":"JAMA cardiology"},{"issue":"3","key":"2207_CR31","doi-asserted-by":"publisher","first-page":"e190005","DOI":"10.1001\/jamanetworkopen.2019.0005","volume":"2","author":"J Scarpa","year":"2019","unstructured":"Scarpa J, Bruzelius E, Doupe P, Le M, Faghmous J, Baum A. Assessment of risk of harm associated with intensive blood pressure management among patients with hypertension who smoke: a secondary analysis of the systolic blood pressure intervention trial. JAMA Network Open. 2019;2(3):e190005.","journal-title":"JAMA Network Open"},{"issue":"3","key":"2207_CR32","doi-asserted-by":"publisher","first-page":"604","DOI":"10.2337\/dc17-2252","volume":"41","author":"S Basu","year":"2018","unstructured":"Basu S, Raghavan S, Wexler DJ, Berkowitz SA. Characteristics associated with decreased or increased mortality risk from glycemic therapy among patients with type 2 diabetes and high cardiovascular risk: machine learning analysis of the ACCORD trial. Diabetes Care. 2018;41(3):604\u201312.","journal-title":"Diabetes Care"},{"key":"2207_CR33","doi-asserted-by":"crossref","unstructured":"Raghavan S, Josey K, Bahn G, Reda D, Basu S, Berkowitz SA, et al. Generalizability of heterogeneous treatment effects based on causal forests applied to two randomized clinical trials of intensive glycemic control.\u00a0Ann\u00a0Epidemiol. 2022;65:101-8.","DOI":"10.1016\/j.annepidem.2021.07.003"},{"issue":"6","key":"2207_CR34","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/S2213-8587(19)30087-7","volume":"7","author":"JM Dennis","year":"2019","unstructured":"Dennis JM, Shields BM, Henley WE, Jones AG, Hattersley AT. Disease progression and treatment response in data-driven subgroups of type 2 diabetes compared with models based on simple clinical features: an analysis using clinical trial data. Lancet Diabetes Endocrinol. 2019;7(6):442\u201351.","journal-title":"Lancet Diabetes Endocrinol"},{"key":"2207_CR35","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.jclinepi.2020.05.022","volume":"125","author":"TL Nguyen","year":"2020","unstructured":"Nguyen TL, Collins GS, Landais P, Le Manach Y. Counterfactual clinical prediction models could help to infer individualized treatment effects in randomized controlled trials-an illustration with the International Stroke Trial. J Clin Epidemiol. 2020;125:47\u201356.","journal-title":"J Clin Epidemiol"},{"issue":"8","key":"2207_CR36","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1002\/sim.9665","volume":"42","author":"O Efthimiou","year":"2023","unstructured":"Efthimiou O, Hoogland J, Debray TPA, Seo M, Furukawa TA, Egger M, et al. Measuring the performance of prediction models to personalize treatment choice. Stat Med. 2023;42(8):1188\u2013206.","journal-title":"Stat Med"},{"issue":"12","key":"2207_CR37","doi-asserted-by":"publisher","first-page":"e873","DOI":"10.1016\/S2589-7500(22)00174-1","volume":"4","author":"JM Dennis","year":"2022","unstructured":"Dennis JM, Young KG, McGovern AP, Mateen BA, Vollmer SJ, Simpson MD, et al. Development of a treatment selection algorithm for SGLT2 and DPP-4 inhibitor therapies in people with type 2 diabetes: a retrospective cohort study. Lancet Digit Health. 2022;4(12):e873\u201383.","journal-title":"Lancet Digit Health"},{"issue":"1","key":"2207_CR38","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1214\/16-BA1044","volume":"13","author":"PR Hahn","year":"2018","unstructured":"Hahn PR, Carvalho CM, Puelz D, He J. Regularization and confounding in linear regression for treatment effect estimation. Bayesian Anal. 2018;13(1):163\u201382, 20.","journal-title":"Bayesian Anal"},{"issue":"3","key":"2207_CR39","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1214\/19-BA1195","volume":"15","author":"PR Hahn","year":"2020","unstructured":"Hahn PR, Murray JS, Carvalho CM. Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects (with Discussion). Bayesian Analysis. 2020;15(3):965-1056,92.","journal-title":"Bayesian Analysis"},{"issue":"1","key":"2207_CR40","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1198\/jcgs.2010.08162","volume":"20","author":"JL Hill","year":"2011","unstructured":"Hill JL. Bayesian nonparametric modeling for causal inference. J Comput Graph Stat. 2011;20(1):217\u201340.","journal-title":"J Comput Graph Stat"},{"issue":"7733","key":"2207_CR41","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1038\/d41586-018-07535-2","volume":"563","author":"S Senn","year":"2018","unstructured":"Senn S. Statistical pitfalls of personalized medicine. Nature. 2018;563(7733):619\u201321.","journal-title":"Nature"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-023-02207-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-023-02207-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-023-02207-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T13:04:52Z","timestamp":1686920692000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-023-02207-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,16]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["2207"],"URL":"https:\/\/doi.org\/10.1186\/s12911-023-02207-2","relation":{},"ISSN":["1472-6947"],"issn-type":[{"type":"electronic","value":"1472-6947"}],"subject":[],"published":{"date-parts":[[2023,6,16]]},"assertion":[{"value":"7 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Approval for CPRD data access and the study protocol was granted by the CPRD Independent Scientific Advisory Committee (Project-ID: ISAC 13_177R), informed consent was waived for this retrospective study. Individual patients can opt-out of sharing their data for CPRD, and CPRD does not collect data for these patients.\u00a0Approval for the study protocol and access to the CANTATA-D and CANTATA-D2 datasets was granted by the Yale University Open Data Access (YODA) Project Steering Committee and JANSSEN RESEARCH & DEVELOPMENT, L.L.C (Project-ID: # 2017\u20131816), as part of which informed consent was waived for this retrospective study. All methods were carried out in accordance with relevant guidelines and regulations.","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":"BAM is an employee of Wellcome Trust; holds honorary posts at the Alan Turing Institute and University College London for the purposes of carrying out independent research; and declares payments from the Medical Research Council, Health Data Research UK, British Heart Foundation, and Engineering and Physical Sciences Research Council (grant EP\/N510129\/); the views expressed in this manuscript do not necessarily reflect the views of the Wellcome Trust. SJV declares support from the University of Warwick, University of Kaiserslautern, and German Research Center for Artificial Intelligence; consulting fees from PUMAS; stock from Freshflow; and grant funding from The Alan Turing Institute (EP\/N510129), Engineering and Physical Sciences Research Council, and Massachusetts Institute of Technology. All other authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"110"}}