Purpose Supplementing investigator‐specified variables with large numbers of empirically
identified features that collectively serve as 'proxies' for unspecified or unmeasured factors …

Purpose The high‐dimensional propensity score (HDPS) is a semi‐automated procedure for
confounder identification, prioritisation and adjustment in large healthcare databases that …

We recently developed a machine-learning subgrouping algorithm, iterative causal forest
(iCF), to identify subgroups with heterogeneous treatment effects (HTEs) using predefined …

Large healthcare databases are increasingly used for research investigating the effects of
medications. However, a key challenge is capturing hard-to-measure concepts (often …

Background The low cost of thiazolidinediones makes them a potentially valuable
therapeutic option for the> 300 million economically disadvantaged persons worldwide with …

Electronic health records (EHR) are widely used sources of real‐world data in
pharmacoepidemiologic research. As there is no end‐to‐end guidance for generating …

Purpose Sodium‐glucose co‐transporter 2 inhibitors (SGLT‐2i) have been associated with
an increased risk of genitourinary tract infections. Through similar biological mechanisms …

Purpose Recent evidence from US claims data suggests use of high‐dimensional
propensity score (hd‐PS) methods improve adjustment for confounding in non‐randomised …

In this thesis, I investigate two related types of causal model selection: confounder selection
and constraint-based causal discovery. The aim of confounder selection is to determine a …

Background: Electronic health records (EHR) are widely used sources of real-world data in
pharmacoepidemiologic research. As there is no end-to-end guidance for generating …