Lectures and seminars SFOepi Seminar Series in Biostatistics: Andrea Bellavia, Harvard Medical School
Title: Defining Interpretability in Machine Learning for Epidemiology: Challenges and Paths Forward
Speaker: Andrea Bellavia, TIMI Study Group, Brigham and Women’s Hospital, Harvard Medical School, Boston, USA
Please note that this event is not filmed nor streamed – only participation in person.
Abstract
Complex multidimensional data are becoming more widely available and are drastically affecting the way epidemiological studies are designed and conducted. This data revolution is accompanied by a growing interest in semi-parametric and non-parametric statistical and machine learning (ML) methodologies that provide compelling frameworks for analyzing large-scale databases. Application of ML in epidemiologic studies, however, provide unique challenges in terms of results interpretability. This seminar will discuss the main challenges that arise when applying ML in epidemiology and provide a revised definition of interpretability in this context, together with an overview of approaches that can be used to address such interpretability.
Registration: No registration is needed
If you have any questions, please contact Marie Jansson at marie.jansson@ki.se