{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T00:43:28Z","timestamp":1793407408507,"version":"4.5.0"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"vor","delay-in-days":46,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R21AG087057"],"award-info":[{"award-number":["R21AG087057"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01AG080590"],"award-info":[{"award-number":["R01AG080590"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["S10OD028483"],"award-info":[{"award-number":["S10OD028483"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation Faculty Early Career Development Program (CAREER) Award","award":["2337612"],"award-info":[{"award-number":["2337612"]}]},{"name":"U.S. Department of Education Institute of Education Sciences Grant","award":["R305D200031"],"award-info":[{"award-number":["R305D200031"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Causal mediation analysis provides insights into the mechanisms through which treatments affect outcomes. While mediation effects often vary across individuals, most existing methods focus solely on population-average effects, overlooking individual-level heterogeneity. To address this limitation, we propose a Bayesian regression tree ensemble method that flexibly models nonlinear relationships and captures treatment-by-mediator interactions in the mediation process. Using hierarchical posterior sampling, our approach provides credible intervals with nominal coverage rates for inferring heterogeneous mediation effects. Additionally, we leverage regression tree summaries to identify subgroups with distinct mediation effects and employ SHapley Additive exPlanation values to highlight key moderators and their influence on the mediation process. Comprehensive simulations demonstrate the method\u2019s accuracy in estimating and inferring heterogeneous mediation effects. Finally, we apply our method to investigate the heterogeneous mediation role of Alzheimer\u2019s disease pathology burden in the effect of apolipoprotein E genotype on late-life cognition.<\/jats:p>","DOI":"10.1093\/biomtc\/ujag079","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T11:42:29Z","timestamp":1776944549000},"source":"Crossref","is-referenced-by-count":1,"title":["Heterogeneous causal mediation analysis using Bayesian additive regression trees"],"prefix":"10.1093","volume":"82","author":[{"given":"Chen","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Health Data Science, University of Pittsburgh , Pittsburgh, PA 15261 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science, University of Pittsburgh , Pittsburgh, PA 15261 ,","place":["United States"]},{"name":"Department of Health and Human Development, University of Pittsburgh , Pittsburgh, PA 15260 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor B","family":"Talisa","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science, University of Pittsburgh , Pittsburgh, PA 15261 ,","place":["United States"]},{"name":"Department of Critical Care Medicine, University of Pittsburgh , Pittsburgh, PA 15213 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3828-4400","authenticated-orcid":false,"given":"Jiebiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science, University of Pittsburgh , Pittsburgh, PA 15261 ,","place":["United States"]},{"name":"Clinical and Translational Science Institute, University of Pittsburgh , Pittsburgh, PA 15261 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,25]]},"reference":[{"key":"2026052500073541800_bib1","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1037\/0022-3514.51.6.1173","article-title":"The moderator\u2013mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations","volume":"51","author":"Baron","year":"1986","journal-title":"Journal of Personality and Social Psychology"},{"key":"2026052500073541800_bib2","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1353\/obs.2019.0002","article-title":"Examining treatment effect heterogeneity using BART","volume":"5","author":"Carnegie","year":"2019","journal-title":"Observational Studies"},{"key":"2026052500073541800_bib3","first-page":"265","article-title":"Bayesian ensemble learning","volume":"19","author":"Chipman","year":"2006","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026052500073541800_bib4","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1214\/09-AOAS285","article-title":"BART: Bayesian additive regression trees","volume":"4","author":"Chipman","year":"2010","journal-title":"The Annals of Applied Statistics"},{"key":"2026052500073541800_bib5","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1214\/18-STS667","article-title":"Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competition","volume":"34","author":"Dorie","year":"2019","journal-title":"Statistical Science"},{"key":"2026052500073541800_bib6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1037\/1082-989X.12.1.1","article-title":"Methods for integrating moderation and mediation: a general analytical framework using moderated path analysis","volume":"12","author":"Edwards","year":"2007","journal-title":"Psychological Methods"},{"key":"2026052500073541800_bib7","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1001\/jama.1997.03550160069041","article-title":"Effects of age, sex, and ethnicity on the association between apolipoprotein E genotype and Alzheimer disease: a meta-analysis","volume":"278","author":"Farrer","year":"1997","journal-title":"JAMA"},{"key":"2026052500073541800_bib8","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1214\/19-BA1195","article-title":"Bayesian regression tree models for causal inference: Regularization, confounding, and heterogeneous effects (with discussion)","volume":"15","author":"Hahn","year":"2020","journal-title":"Bayesian Analysis"},{"key":"2026052500073541800_bib9","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1201\/9780203738535-7","article-title":"Generalized additive models","volume-title":"Statistical Models in S","author":"Hastie","year":"2017"},{"key":"2026052500073541800_bib10","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1146\/annurev-statistics-031219-041110","article-title":"Bayesian additive regression trees: A review and look forward","volume":"7","author":"Hill","year":"2020","journal-title":"Annual Review of Statistics and Its Application"},{"key":"2026052500073541800_bib11","doi-asserted-by":"crossref","first-page":"a006312","DOI":"10.1101\/cshperspect.a006312","article-title":"Apolipoprotein E and apolipoprotein E receptors: normal biology and roles in Alzheimer disease","volume":"2","author":"Holtzman","year":"2012","journal-title":"Cold Spring Harbor Perspectives in Medicine"},{"key":"2026052500073541800_bib12","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1037\/a0020761","article-title":"A general approach to causal mediation analysis","volume":"15","author":"Imai","year":"2010","journal-title":"Psychological Methods"},{"key":"2026052500073541800_bib13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v070.i04","article-title":"bartMachine: Machine learning with Bayesian additive regression trees","volume":"70","author":"Kapelner","year":"2016","journal-title":"Journal of Statistical Software"},{"key":"2026052500073541800_bib14","doi-asserted-by":"crossref","first-page":"2785","DOI":"10.1080\/01621459.2023.2278202","article-title":"In nonparametric and high-dimensional models, Bayesian ignorability is an informative prior","volume":"119","author":"Linero","year":"2024","journal-title":"Journal of the American Statistical Association"},{"key":"2026052500073541800_bib15","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1037\/met0000504","article-title":"Mediation analysis using Bayesian tree ensembles","volume":"30","author":"Linero","year":"2025","journal-title":"Psychological Methods"},{"key":"2026052500073541800_bib16","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"2026052500073541800_bib17","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1037\/met0000299","article-title":"Clarifying causal mediation analysis for the applied researcher: Defining effects based on what we want to learn","volume":"26","author":"Nguyen","year":"2021","journal-title":"Psychological Methods"},{"key":"2026052500073541800_bib18","doi-asserted-by":"crossref","first-page":"2508","DOI":"10.1002\/alz.12885","article-title":"AD and non-AD mediators of the pathway between the APOE genotype and cognition","volume":"19","author":"Nichols","year":"2023","journal-title":"Alzheimer\u2019s and Dementia"},{"key":"2026052500073541800_bib19","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1145\/3501714.3501736","article-title":"Direct and indirect effects","volume-title":"Probabilistic and Causal Inference: The Works of Judea Pearl","author":"Pearl","year":"2022"},{"key":"2026052500073541800_bib20","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1080\/00273170701341316","article-title":"Addressing moderated mediation hypotheses: Theory, methods, and prescriptions","volume":"42","author":"Preacher","year":"2007","journal-title":"Multivariate Behavioral Research"},{"key":"2026052500073541800_bib21","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.3758\/s13428-023-02095-4","article-title":"Causal moderated mediation analysis: Methods and software","volume":"56","author":"Qin","year":"2024","journal-title":"Behavior Research Methods"},{"key":"2026052500073541800_bib22","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1177\/09622802231173491","article-title":"Causal mediation and sensitivity analysis for mixed-scale data","volume":"32","author":"Rene","year":"2023","journal-title":"Statistical Methods in Medical Research"},{"key":"2026052500073541800_bib23","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1097\/00001648-199203000-00013","article-title":"Identifiability and exchangeability for direct and indirect effects","volume":"3","author":"Robins","year":"1992","journal-title":"Epidemiology"},{"key":"2026052500073541800_bib24","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1214\/aos\/1176344064","article-title":"Bayesian inference for causal effects: The role of randomization","volume":"6","author":"Rubin","year":"1978","journal-title":"The Annals of Statistics"},{"key":"2026052500073541800_bib25","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/0378-3758(90)90077-8","article-title":"Formal mode of statistical inference for causal effects","volume":"25","author":"Rubin","year":"1990","journal-title":"Journal of Statistical Planning and Inference"},{"key":"2026052500073541800_bib26","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1353\/obs.2023.0023","article-title":"Causal methods madness: Lessons learned from the 2022 ACIC competition to estimate health policy impacts","volume":"9","author":"Thal","year":"2023","journal-title":"Observational Studies"},{"key":"2026052500073541800_bib27","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.1080\/01621459.2025.2491155","article-title":"Estimating heterogeneous causal mediation effects with Bayesian decision tree ensembles","volume":"120","author":"Ting","year":"2025","journal-title":"Journal of the American Statistical Association"}],"container-title":["Biometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/2\/ujag079\/68377780\/ujag079.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/2\/ujag079\/68377780\/ujag079.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T04:07:50Z","timestamp":1779682070000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biometrics\/article\/doi\/10.1093\/biomtc\/ujag079\/8691901"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,9]]},"references-count":27,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,9]]}},"URL":"https:\/\/doi.org\/10.1093\/biomtc\/ujag079","relation":{},"ISSN":["0006-341X","1541-0420"],"issn-type":[{"value":"0006-341X","type":"print"},{"value":"1541-0420","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,4,9]]},"article-number":"ujag079"}}