{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T22:49:53Z","timestamp":1792363793711,"version":"4.4.0"},"reference-count":44,"publisher":"Wiley","issue":"6-7","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":15,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Statistics in Medicine"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Factor analysis (FA) can be used to identify key biomarkers in biological processes by assuming that latent biological pathways (statistically, \u201clatent factors\u201d) drive the activity of measurable biomarkers (\u201cobserved variables\u201d). However, biological pathways often interact, meaning that the classical FA assumption of independence between factors is questionable. Motivated by sparsely and irregularly collected longitudinal measurements of metabolites in a COVID\u201019 study, we propose a dynamic factor analysis model that accounts for cross\u2010correlations between pathways via a multi\u2010output Gaussian processes (MOGP) prior on the factor trajectories. To mitigate against overfitting caused by sparsity of longitudinal measurements, we introduce a roughness penalty upon MOGP hyperparameters and allow for non\u2010zero mean functions. We also propose a scalable stochastic expectation maximization (StEM) algorithm that, in simulations, is both 20 times faster and provides more accurate and stable MOGP hyperparameter estimates than a previously\u2010proposed Monte Carlo Expectation Maximization algorithm. In the motivating COVID\u201019 study, our methodology identifies a kynurenine pathway that affects the clinical severity of patients with COVID\u201019 disease and uncovers the role of the biomarker taurine. Our R package DFA4SIL implements the proposed method.<\/jats:p>","DOI":"10.1002\/sim.70499","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T04:34:07Z","timestamp":1773722047000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Dynamic Factor Analysis for Sparse and Irregular Longitudinal Data: An Application to Metabolite Measurements in a COVID\u201019 Study"],"prefix":"10.1002","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3260-2551","authenticated-orcid":false,"given":"Jiachen","family":"Cai","sequence":"first","affiliation":[{"name":"MRC Biostatistics Unit University of Cambridge  Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert J. B.","family":"Goudie","sequence":"additional","affiliation":[{"name":"MRC Biostatistics Unit University of Cambridge  Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3335-9322","authenticated-orcid":false,"given":"Brian D. M.","family":"Tom","sequence":"additional","affiliation":[{"name":"MRC Biostatistics Unit University of Cambridge  Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41590-022-01380-2"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-041715-033506"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.ap10611"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214508000000869"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/biom.13168"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/rssc.12060"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000001745"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01343-9"},{"issue":"7","key":"e_1_2_11_10_1","first-page":"1","article-title":"Discovering Pathway Cross\u2010Talks Based on Functional Relations Between Pathways","volume":"13","author":"Hsu C. L.","year":"2012","journal-title":"BMC Genomics"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomtc\/ujae131"},{"key":"e_1_2_11_12_1","first-page":"73","article-title":"The SEM Algorithm: A Probabilistic Teacher Algorithm Derived From the EM Algorithm for the Mixture Problem","volume":"2","author":"Celeux G.","year":"1985","journal-title":"Computational Statistics"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1201\/b11038"},{"key":"e_1_2_11_14_1","article-title":"Multi\u2010Task Gaussian Process Prediction","volume":"20","author":"Bonilla E. V.","year":"2007","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_15_1","unstructured":"P.Boyle Gaussian Processes for Regression and Optimisation. (PhD Thesis. Victoria University of Wellington 2007)."},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jspi.2019.09.005"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-1069-4"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-023-01972-2"},{"key":"e_1_2_11_19_1","first-page":"217","article-title":"Dependent Gaussian Processes","volume":"17","author":"Boyle P.","year":"2005","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_20_1","unstructured":"H.TopaandA.Honkela Gaussian Process Modelling of Multiple Short Time Series(2012). arXiv preprint arXiv:1210.2503."},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2023.100487"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06118-z"},{"key":"e_1_2_11_23_1","unstructured":"V.Fortuin H.Strathmann andG.R\u00e4tsch Meta\u2010Learning Mean Functions for Gaussian Processes. arXiv preprint arXiv:1901.08098(2019)."},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1088\/1475-7516\/2023\/02\/014"},{"key":"e_1_2_11_25_1","unstructured":"W.Ruth A Review of Monte Carlo\u2010Based Versions of the EM Algorithm. arXiv preprint arXiv:2401.00945(2024)."},{"key":"e_1_2_11_26_1","volume-title":"Markov Chain Monte Carlo in Practice","author":"Diebolt J.","year":"1995"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jspi.2009.06.014"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/02664763.2020.1786676"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.2307\/3318671"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/bmsp.12153"},{"key":"e_1_2_11_31_1","unstructured":"E.Konzen Y.Cheng andJ. Q.Shi Gaussian process for functional data analysis: The GPFDA Package for R. arXiv preprint arXiv:2102.00249(2021)."},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-022-10084-4"},{"key":"e_1_2_11_33_1","doi-asserted-by":"crossref","unstructured":"J.Cai DGP4LCF: Dependent Gaussian processes for longitudinal correlated factors. 2024. R package version 1.0.0.","DOI":"10.32614\/CRAN.package.DGP4LCF"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.abn9257"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1042\/BSR20230595"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11845-021-02522-5"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0304522"},{"issue":"3","key":"e_1_2_11_38_1","first-page":"234","article-title":"Early Taurine Administration as a Means for Halting the Cytokine Storm Progression in COVID\u201019 Patients","volume":"3","author":"Rubio\u2010Casillas A.","year":"2022","journal-title":"Explore (New York, NY)"},{"key":"e_1_2_11_39_1","first-page":"3","volume-title":"Advances in Experimental Medicine and Biology","author":"Eijk L. E.","year":"2022"},{"issue":"41","key":"e_1_2_11_40_1","first-page":"1459","article-title":"Computationally Efficient Convolved Multiple Output Gaussian Processes","volume":"12","author":"\u00c1lvarez M. A.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_41_1","first-page":"567","volume-title":"Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics. 5 of Proceedings of Machine Learning Research","author":"Titsias M.","year":"2009"},{"key":"e_1_2_11_42_1","first-page":"25","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. 9 of Proceedings of Machine Learning Research","author":"\u00c1lvarez M. A.","year":"2010"},{"key":"e_1_2_11_43_1","unstructured":"J.Hensman N.Fusi andN. D.Lawrence Gaussian Processes for Big Data(2013). arXiv preprint arXiv:1309.6835."},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2015.1064434"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmse.2019.03.001"}],"container-title":["Statistics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/sim.70499","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/sim.70499","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/sim.70499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:15:13Z","timestamp":1789992913000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/sim.70499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":44,"journal-issue":{"issue":"6-7","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1002\/sim.70499"],"URL":"https:\/\/doi.org\/10.1002\/sim.70499","archive":["Portico"],"relation":{},"ISSN":["0277-6715","1097-0258"],"issn-type":[{"value":"0277-6715","type":"print"},{"value":"1097-0258","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"2024-08-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70499"}}