{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T18:07:04Z","timestamp":1792001224374,"version":"4.4.0"},"reference-count":62,"publisher":"Wiley","issue":"25","license":[{"start":{"date-parts":[[2021,7,30]],"date-time":"2021-07-30T00:00:00Z","timestamp":1627603200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Statistics in Medicine"],"published-print":{"date-parts":[[2021,11,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>One of the key challenges of personalized medicine is to identify which patients will respond positively to a given treatment. The area of subgroup identification focuses on this challenge, that is, identifying groups of patients that experience desirable characteristics, such as an enhanced treatment effect. A crucial first step towards the subgroup identification is to identify the baseline variables (eg, biomarkers) that influence the treatment effect, which are known as predictive variables. Many subgroup discovery algorithms return importance scores that capture the variables' predictive strength. However, a major limitation of these scores is that they do not answer the core question: \u201cWhich variables are actually predictive?\u201d With our work we answer this question by using the knockoff framework, which is a general framework for controlling the false discovery rate when performing<jats:italic>prognostic<\/jats:italic>variable selection. In contrast, our work is the first that uses knockoffs for<jats:italic>predictive<\/jats:italic>variable selection. We introduce two novel knockoff filters: one parametric, building on variable importance scores derived from a penalized linear regression model, and one non\u2010parametric, building on causal forest variable importance scores. We conduct extensive simulations to validate performance of the proposed methodology and we also apply the proposed methods to data from a randomized clinical trial.<\/jats:p>","DOI":"10.1002\/sim.9134","type":"journal-article","created":{"date-parts":[[2021,7,30]],"date-time":"2021-07-30T14:10:45Z","timestamp":1627654245000},"page":"5453-5473","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Using knockoffs for controlled predictive biomarker identification"],"prefix":"10.1002","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6582-7453","authenticated-orcid":false,"given":"Konstantinos","family":"Sechidis","sequence":"first","affiliation":[{"name":"Advanced Methodology and Data Science Novartis Pharma AG Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6579-5321","authenticated-orcid":false,"given":"Matthias","family":"Kormaksson","sequence":"additional","affiliation":[{"name":"Advanced Methodology and Data Science Novartis Pharmaceuticals Corporation East Hanover New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Ohlssen","sequence":"additional","affiliation":[{"name":"Advanced Methodology and Data Science Novartis Pharmaceuticals Corporation East Hanover New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,7,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(12)70156-0"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1804710"},{"key":"e_1_2_9_4_1","first-page":"211","volume-title":"Clinical and Statistical Considerations in Personalized Medicine","author":"Lipkovich I","year":"2014"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.7064"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.7416"},{"issue":"1","key":"e_1_2_9_7_1","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini Y","year":"1995","journal-title":"J Royal Stat Soci Ser B (Methodol)"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/03610926.2017.1361982"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12265"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOS1337"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa770"},{"issue":"2","key":"e_1_2_9_12_1","article-title":"Subgroup analysis via recursive partitioning","volume":"10","author":"Su X","year":"2009","journal-title":"J Mach Learn Res"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4289"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2014.951443"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1510489113"},{"key":"e_1_2_9_16_1","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","author":"Pearl J","year":"2014"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1214\/16-EJS1129"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asy033"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2019.1660174"},{"key":"e_1_2_9_20_1","unstructured":"JordonJ YoonJ Van Der SchaarM. KnockoffGAN: Generating knockoffs for feature selection using generative adversarial networks. Paper presented at: Proceedings of the 7th International Conference on Learning Representations ICLR; Vol. 2019 2019:1\u201025."},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1729163"},{"issue":"1","key":"e_1_2_9_22_1","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani R","year":"1996","journal-title":"J Royal Stat Soc Ser B (Methodol)"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.8955"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0037350"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/24709360.2019.1670513"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1162\/003465304323023651"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139025751"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1515\/ijb-2015-0032"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1319839"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/econometrics7040049"},{"key":"e_1_2_9_32_1","unstructured":"TibshiraniJ AtheyS FriedbergR et al. grf: Generalized Random Forests. R package version 0.10.3;2019."},{"key":"e_1_2_9_33_1","doi-asserted-by":"crossref","unstructured":"XieY ChenN ShiX. False discovery rate controlled heterogeneous treatment effect detection for online controlled experiments;2018:876\u2010885.","DOI":"10.1145\/3219819.3219860"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.7623"},{"issue":"5","key":"e_1_2_9_35_1","first-page":"1","article-title":"Machine learning methods for estimating heterogeneous causal effects stat","volume":"1050","author":"Athey S","year":"2015","journal-title":"Stat"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4322"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(15)61134-5"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780360601"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-018-1551-x"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40744-019-0163-5"},{"issue":"6","key":"e_1_2_9_41_1","first-page":"890","article-title":"Secukinumab improves active psoriatic arthritis symptoms and inhibits radiographic progression: primary results from the randomised, double\u2010blind, phase III FUTURE 5 study","volume":"77","author":"Mease P","year":"2018","journal-title":"Ann Rheum Dis"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1002\/pst.2012"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02075.x"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1136\/ard.2006.060079"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clim.2019.108318"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1186\/1477-7525-1-79"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/key140"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1080\/14397595.2016.1193105"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx174"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1214\/17-STS612"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1080\/10543406.2013.856024"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.8452"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6454"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty357"},{"issue":"4","key":"e_1_2_9_55_1","first-page":"49","article-title":"Causal random forests model using instrumental variable quantile regression","volume":"7","author":"Je C","year":"2019","journal-title":"Dent Econ"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-25"},{"key":"e_1_2_9_57_1","unstructured":"O'NeillE WeeksM. Causal tree estimation of heterogeneous household response to time\u2010of\u2010use electricity pricing schemes. technical report Cambridge Working Papers in Economics CWPE18653 University of Cambridge;2018"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2014.938812"},{"key":"e_1_2_9_59_1","unstructured":"LimM HastieT. glinternet: Learning Interactions via Hierarchical Group\u2010Lasso Regularization. R package version 1.0.10;2019."},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw690"},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2081-x"},{"key":"e_1_2_9_62_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v033.i01"},{"key":"e_1_2_9_63_1","unstructured":"PattersonE SesiaM. knockoff: the knockoff filter for controlled variable selection. R package version 0.3.2;2018."}],"container-title":["Statistics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/sim.9134","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/sim.9134","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/sim.9134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T13:14:15Z","timestamp":1725542055000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/sim.9134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,30]]},"references-count":62,"journal-issue":{"issue":"25","published-print":{"date-parts":[[2021,11,10]]}},"alternative-id":["10.1002\/sim.9134"],"URL":"https:\/\/doi.org\/10.1002\/sim.9134","archive":["Portico"],"relation":{},"ISSN":["0277-6715","1097-0258"],"issn-type":[{"value":"0277-6715","type":"print"},{"value":"1097-0258","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,30]]},"assertion":[{"value":"2020-12-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-22","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}