Uses of causal inference and prediction models during the Covid-19 pandemic

​​​​​

Speaker:  Noam Barda MD, PhD & Noa Dagan, MD, PhD, MPH

Title: Uses of causal inference and prediction models during the Covid-19 pandemic

"BNT162b2 mRNA Covid-19 Vaccine in a Nationwide Mass Vaccination Setting"
N. Dagan*, N. Barda*, E. Kepten, O. Miron, S. Perchik, M. Katz., M. Hernán, M. Lipsitch, B. Reis, R. Balicer.
New England Journal of Medicine. 2021

As an example of a prediction problem we will present this publication: 
"Developing a COVID-19 mortality risk prediction model when individual-level data are not available"
N. Barda, D. Riesel, A. Akriv, J. Levy, U. Finkel, G. Yona, D. Greenfeld, S. Sheiba, J. Somer, E. Bachmat, GN. Rothblum, U. Shalit, D. Netzer, R. Balicer, N. Dagan.
Nature Communications. 2020


​Bio:

Noa Dagan is a public health physician and researcher. She holds an MD and an MPH from the Hebrew University, and a Ph.D. in Computer Science from Ben-Gurion University. She completed her post-doctorate in the Department of Biomedical Informatics (DBMI), Harvard Medical School. Dr. Dagan is a lecturer in the department of Software and Information Systems Engineering in Ben-Gurion University.

Dr. Dagan is also the director of data and AI-driven medicine at the Clalit Research Institute – the research institute of Israel's largest healthcare organization, insuring and treating over 50% of the Israeli population. Her responsibilities include the development and implementation of digital healthcare solutions to promote preventive, proactive and personalized medicine. She leads the entire lifecycle of AI-driven interventions, from conception, through machine-learning modeling, to implementation in medical practice.

Dr. Dagan's research focuses on practical implementations of machine-learning algorithms using clinical data, with a specific interest in the prevention of cardiovascular events and osteoporotic fractures. Dr. Dagan is also active in research of ethical aspects of machine-learning models such as fairness.  

Noam Barda is a public health physician, epidemiologist, statistician and computer scientist in unequal parts. On the medical side - he received his MD from Tel-Aviv University and did his residency in public health (epidemiology tract) in Clalit Health Services. On the non-medical side –  received his BSc in computer science from the Open University and my PhD from Ben-Gurion University, where his doctoral dissertation, co-advised by public health and computer science, focused on computational methods to improve models to predict cardiovascular disease. His post-doctorate was at the department of biomedical informatics at Harvard.

Currently Noam is a lecturer at the department of Software and Information Systems Engineering at BGU and head of epidemiology and research at Clalit Research Institute.

Noam's research lies on the intersection of epidemiology, machine learning and biostatistics – specifically around causal inference from electronic health record-based observational data and predictive modeling in healthcare.