{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T21:57:42Z","timestamp":1782251862821,"version":"3.54.5"},"reference-count":24,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100031315","name":"AstraZeneca UK","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031315","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Pharmacoepidemiology and Drug"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To apply various dimensionality reduction techniques for propensity score (PS) estimation in high\u2010dimensional data and evaluate their performance against more conventional approaches in achieving covariate balance and confounding control in pharmacoepidemiological studies using claims data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We undertook a cohort study investigating the association between dialysis and mortality in older patients with heart failure and advanced chronic kidney disease using Optum's de\u2010identified Clinformatics Data Mart Database. We compared PS estimated using investigator\u2010specified covariates, high\u2010dimensional propensity score (hdPS) algorithm, and three dimensionality reduction techniques: principal component analysis (PCA), logistic PCA, and autoencoders. Covariate balance was assessed using standardized mean differences (SMD) and propensity score overlap plots. Hazard ratios for in\u2010hospital mortality were estimated using Cox proportional hazards models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The analysis included 485 dialysis\u2010exposed and 1455 unexposed individuals after matching. Autoencoder\u2010based PS achieved the best covariate balance (8 covariates with SMD &gt;\u20090.1), followed by PCA (20 covariates), logistic PCA (25 covariates), hdPS (37 covariates), and investigator\u2010specified (83 covariates). Hazard ratios for in\u2010hospital mortality were similar across PS methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Dimensionality reduction techniques, particularly autoencoders, outperformed traditional methods in achieving covariate balance when estimating PS in high\u2010dimensional claims data. These methods may offer improved covariate balance in pharmacoepidemiological studies PS\u2010matched designs in large healthcare databases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/pds.70258","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T02:05:10Z","timestamp":1764036310000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Dimensionality Reduction Techniques for Improving Propensity Score Specification: An Application to a\u00a0Cohort\u00a0Study Using Claims Data"],"prefix":"10.1002","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2093-5781","authenticated-orcid":false,"given":"Sudhir","family":"Venkatesan","sequence":"first","affiliation":[{"name":"BPM Evidence Statistics, BioPharmaceuticals Medical, AstraZeneca  Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6242-1810","authenticated-orcid":false,"given":"Jonatan","family":"N\u00e5tman","sequence":"additional","affiliation":[{"name":"BPM Evidence Statistics, BioPharmaceuticals Medical, AstraZeneca  Gothenburg Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2198-4382","authenticated-orcid":false,"given":"Eva","family":"Les\u00e9n","sequence":"additional","affiliation":[{"name":"CVRM Evidence Strategy, BioPharmaceuticals Medical, AstraZeneca  Gothenburg Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9640-0927","authenticated-orcid":false,"given":"Stefan","family":"Franz\u00e9n","sequence":"additional","affiliation":[{"name":"BPM Evidence Statistics, BioPharmaceuticals Medical, AstraZeneca  Gothenburg Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6377-3284","authenticated-orcid":false,"given":"Sima","family":"Shahsavari","sequence":"additional","affiliation":[{"name":"Data Science, Late CVRM Biometrics, AstraZeneca  Gothenburg Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2849-3145","authenticated-orcid":false,"given":"Lucy","family":"Carty","sequence":"additional","affiliation":[{"name":"BPM Evidence Statistics, BioPharmaceuticals Medical, AstraZeneca  Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8357-8080","authenticated-orcid":false,"given":"Mario","family":"Ouwens","sequence":"additional","affiliation":[{"name":"BPM Evidence Statistics, BioPharmaceuticals Medical, AstraZeneca  Gothenburg Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/70.1.41"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwj149"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0b013e3181a663cc"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-016-0119-1"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwr001"},{"issue":"66","key":"e_1_2_8_7_1","first-page":"13","article-title":"Dimensionality Reduction: A Comparative Review","volume":"10","author":"Van Der Maaten L.","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1515\/sagmb-2017-0054"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.3168\/jds.2022-22694"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12982-016-0047-x"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0000000000001338"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0262706"},{"key":"e_1_2_8_13_1","unstructured":"\u201cThe Optum De\u2010Identifed Clinformatics Data Mart Database (2007\u20132024).\u201d"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2767063"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep26094"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9681(66)90062-2"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"e_1_2_8_18_1","unstructured":"I.Goodfellow \u201cNips 2016 Tutorial: Generative Adversarial Networks \u201d2016."},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3697"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_2_8_22_1","volume-title":"International Workshop on Artificial Intelligence and Statistics","author":"Schein A. I.","year":"2003"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.1555"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwaa242"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.5678"}],"container-title":["Pharmacoepidemiology and Drug Safety"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/pds.70258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T07:27:43Z","timestamp":1767079663000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/pds.70258"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":24,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1002\/pds.70258"],"URL":"https:\/\/doi.org\/10.1002\/pds.70258","archive":["Portico"],"relation":{},"ISSN":["1053-8569","1099-1557"],"issn-type":[{"value":"1053-8569","type":"print"},{"value":"1099-1557","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"2025-04-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70258"}}