Identifying treatment heterogeneity in atrial fibrillation using a novel causal machine learning method
Ngufor C, Yao X, Inselman J, Ross J, Dhruva S, Graham D, Lee J, Siontis K, Desai N, Polley E, Shah N, Noseworthy P, MN; New Haven C. Identifying treatment heterogeneity in atrial fibrillation using a novel causal machine learning method. American Heart Journal 2023, 260: 124-140. PMID: 36893934, PMCID: PMC10615250, DOI: 10.1016/j.ahj.2023.02.015.Peer-Reviewed Original ResearchMeSH KeywordsAdministration, OralAgedAnticoagulantsAtrial FibrillationDabigatranFemaleHumansIschemic StrokePyridonesRivaroxabanStrokeWarfarinConceptsOral anticoagulantsAtrial fibrillationPatient subgroupsComposite outcomeIschemic strokeEffect of OACsLifelong oral anticoagulationNonvitamin K antagonistNew oral anticoagulantsNonvalvular atrial fibrillationPrimary composite outcomeGlomerular filtration rateFuture prospective studiesOptumLabs Data WarehousePopulation-level effectivenessOAC useOral anticoagulationVASc scoreCause mortalityK antagonistsPrimary endpointWarfarin usersRenal functionAF patientsEntire cohort