Causal Inference in Epidemiology: Pregnancy and Prostate Cancer

This lecture by the instructor covers the application of target trial principles in epidemiology, focusing on the impact of COVID-19 during pregnancy on preterm birth risk and the use of biomarker characteristics in refining treatment strategies for prostate cancer. The presentation delves into the complexities of causal inference, addressing issues like immortal time bias and time-varying confounding. Through examples and study designs, the lecture explores how observational data can be used to emulate randomized trials and estimate counterfactual quantities. The discussion also includes the analysis of data from the International Registry of Coronavirus Exposure in Pregnancy and the CaPSURE study on prostate cancer, highlighting the challenges and implications of treatment strategies based on PSA doubling time.