Hear from a leading expert in the field! Join us on Wednesday, October 7th for a seminar with Zachary B. Dozier, Assistant Professor of Pediatrics (Clinical Informatics) and of Medicine (Computational Medicine) at Stanford University School of Medicine. Dr. Dozier will present "Targeted Learning: Causal Inference in Long COVID and Pediatrics." The seminar will take place at 12:00 PM in Berkeley Way West, 5th Floor, Room 5401.
Abstract: I will discuss machine learning applications for causal inference in large electronic health record (EHR) databases. First, I will describe our recently completed work evaluating preventive interventions for Long COVID through target trial emulation in the National Clinical Cohort Collaborative (N3C), where we assessed IL-6 receptor antagonists, diabetes treatments (metformin and GLP-1 receptor agonists), and SSRIs. I will then discuss new and ongoing projects applying this approach to pediatric health in Epic Cosmos, an EHR database of more than 300 million patients across the US. Finally, I will discuss career planning and the faculty job search process.
Bio: Zach B. Dozier (formerly Butzin-Dozier) is an Assistant Professor at the Stanford University School of Medicine in the Department of Pediatrics, Division of Clinical Informatics, with a joint appointment in the Department of Medicine, Division of Computational Medicine. His research applies machine learning and artificial intelligence for causal inference via electronic health record data. He draws from large-scale databases, such as Epic Cosmos, PEDSnet, and the National Clinical Cohort Collaborative, to answer pressing questions in pediatric and infectious disease medicine. His research evaluates vaccine effectiveness, drug repurposing, and the long-term sequelae of viral infection, including Long COVID. He aims to bridge rigorous biostatistical methodology with clinically meaningful research questions. He received his PhD in Epidemiology and MPH from UC Berkeley, and he is an NIAID K01 recipient.