Agreement between two diagnostic tests when accounting for test–retest variation: application to FFR versus iFR

In medicine, there are often two diagnostic tests that serve the same purpose. Typically, one of the tests will have a lower diagnostic performance but be less invasive, easier to perform, or cheaper. Clinicians must assess the agreement between the tests while accounting for test–retest variation in both techniques. In this paper, we investigate a specific example from interventional cardiology, studying the agreement between the fractional flow reserve and the instantaneous wave-free ratio. We analyze potential definitions of the agreement (accuracy) between the two tests and compare five families of statistical estimators. We contrast their statistical behavior both theoretically and using numerical simulations. Surprisingly for clinicians, seemingly natural and equivalent definitions of the concept of agreement can lead to discordant and even nonsensical estimates.