The Role of Causal Inference in Biomarker Studies
Biomarkers are objectively measured characteristics which are commonly used across a range of scientific disciplines for diagnosis, prognosis, and prediction, and potentially as surrogate measures for the actual clinical outcome. The utility of biomarker studies, however, is typically limited to evaluating associations rather than causal relationships. While statistical approaches such as propensity score methods are becoming increasingly popular for facilitating our ability to make causal inferences from observational data, they have not, to our knowledge, been applied to biomarker studies or the associated questions of interest for establishing surrogate markers. This talk describes the Consortium for Radiological Imaging Studies of Polycystic Kidney Disease, or CRISP study, as one illustration of the potential utility of causal inference methods in this setting. More specifically, while the stated goal of CRISP is to evaluate the prognostic accuracy of imaging measures (primarily kidney volume), establishing a causal relationship would substantially facilitate our ability to more efficiently test treatments in earlier stages of chronic kidney disease, and thus positively impact patient care.