Preliminary Outline of the Day 9 AM: Welcome, followed by DBEI Distinguished Faculty talks...Vincent Lo Re III, MD, MSCE (Epidemiology Division): "Risk of Arterial and Venous Thrombotic Events in Patients with COVID-19 Compared to Influenza: A Large-Scale Cohort Study Within the US FDA's Sentinel System"Graciela Gonzalez Hernandez, MS, PhD (Informatics Division): "Text Mining for Digital Epidemiology: Overcoming the Challenges of Dealing with Real World Data."10 AM: Ten flash talks illustrate the work behind our highest-ranked research gallery presentations.

Title: A flexible approach for the analysis of repeated attempt designsAbstract: It is not uncommon in follow-up studies to make multiple attempts to collect a measurement after baseline. Recording whether these attempts are successful or not provides useful information for the purposes of assessing the missing at random (MAR) assumption and facilitating missing not at random (MNAR) modeling. This is because measurements from subjects who provide this data after multiple failed attempts may differ from those who provide the measurement after fewer attempts.

Title: Study Efficacy and Safety of COVID-19 Vaccines using Modern Statistical MethodsAbstract: In this talk, I will present my current research on studying effectiveness and safety of COVID-19 vaccines. In the efficacy studies, we applied the state-of-art statistical techniques to compare BNT162b2, mRNA-1273 and Ad26.COV2.S vaccines against the Delta variant in a large cohort of patients in the Michigan Medicine healthcare system. We also evaluated their effectiveness among individuals who take immunosuppressants.

Title: A Statistical Journey through Trustworthy AIAbstract: Our lab believes that the next generation of AI is mainly driven by trustworthiness, beyond performance. This talk attempts to offer statistical perspectives to embrace three challenges in trustworthy AI: privacy, robustness and fairness. Specifically, we consider privacy protection by machine un-learning, enhance adversarial robustness by utilizing artificially generated data, and establish fair Bayes-optimal classifiers.