Our 2022 morning program opened with talks by our most recent class of DBEI Disitinguished Faculty. Below, view full versions and excerpts of talks by Vincent Lo Re III, MD, MSCE, and Graciela Gonzalez Hernandez, MS, PhD.
Dr. Lo Re recounted how in March 2020, he was suddenly called to a newly converted critical care ward of Penn Presbyterian Medical Center. As he took care of Covid-19 patients, he and colleagues at Penn Medicine, the FDA, and the FDA Sentinel team realized there were major knowledge gaps on Covid-19 patients’ and both arterial thromboembolism (ATE) and venous thromboembolism (VTE): Were these patients at higher risk of thrombotic complications, compared to other respiratory viral infections? Here, his full talk describes the resulting study.
In this excerpt, Dr. Lo Re describes the broad questions that his study of "Risk of Arterial and Venous Thrombotic Events in Patients with COVID-19" would address.
In this second excerpt, Dr. Lo Re summarizes the study’s conclusions — Covid-19 patients were at especially high risk of only one form of thrombotic event — and he discusses next steps.
Health records and patient generated data (in health forums or social media) constitute what the FDA and the CDC refer to as "real world data." With the right machine learning and natural language processing (NLP) methods, Dr. Gonzalez Hernandez pointed out, these data can be extremely valuable and become ‘real world evidence.’ Here, in her full talk, she showcases some of the approaches her team has deployed to identify cohorts, reduce bias, find what drives patients to switch medications, and enrich metadata for SARS-CoV-2 sequences in public repositories.
In this excerpt, Dr. Gonzalez Hernandez gives an overview of the kinds of data patients are producing and the challenges of extracting it, incorporating it in studies, and “proving” its value.