Combining high quality data with rigorous methods: emulation of a target trial using electronic health records and a nested case-control design
Bahareh Rasouli, Jessica Chubak, James S. Floyd, Bruce M. Psaty, Matthew Nguyen, Rod Walker, Kerri L. Wiggins, Roger Logan, Goodarz Danaei
Abstract
Emulating a target trial reduces the potential for bias in observational comparative effectiveness research. Owing to feasibility constraints, large cohort studies often use electronic health records without validating key variables or collecting additional data. A case-control design allows researchers to validate, supplement, or collect additional data on key measurements in a much smaller sample compared with the entire cohort. In this article, Rasouli and colleagues describe methods to emulate a target trial using a nested case-control design, and provide a detailed guideline, an analytical program, and results of a clinical example.