Addressing Generalizability, Robustness and Equity Synergistically in Machine Learning Risk Prediction Models
Rumi Chunara
October 20, 2021, Wednesday, 3:00 PM - 4:00 PM EDT
Abstract
Implementation of machine learning methods in new environments with different populations brings computational challenges, while simultaneously could also augment health disparities. In this talk, I will show how leveraging principles of community and equity, machine learning methods that address realistic challenges of data collection and model use across environments inclusively and robustly can be designed. Examples will include the use of causal models and machine learning in a domain adaptation approach that improves prediction in under-represented population sub-groups by leveraging invariant information across groups when possible, and an algorithmic fairness method which specifically incorporates structural factors to better account for and address sources of bias and disparities. As machine learning methods become embedded in society, it has become clear that the data used, objectives selected, and questions we ask should be based on computational and social principles.
Bio
Dr. Rumi Chunara is an Associate Professor at NYU, jointly appointed at the Tandon School of Engineering (in Computer Science) and the School of Global Public Health (in Biostatistics/Epidemiology). Her PhD is from the Harvard-MIT Division of Health Sciences and Technology and her BSc from Caltech. Her research group focuses on developing computational and statistical approaches for acquiring, integrating and using data to improve population-level public health. She is an MIT TR35, NSF Career, Facebook Research and Max Planck Sabbatical award winner.