Responsible AI Seminar: Algorithmic encoding of protected characteristics

Title

Algorithmic encoding of protected characteristics

Abstract

It has been rightfully emphasized that the use of AI for clinical decision making could amplify health disparities. A machine learning model may pick up undesirable correlations, for example, between a patient's racial identity and clinical outcome. Such correlations are often present in (historical) data used for model development. This talk aims to shed some light on these issues by exploring a different methodology for assessing the inner working of disease detection models. We explore multitask learning and model inspection to assess the relationship between protected characteristics and prediction of disease. Our findings call for further research to better understand the underlying causes of performance disparities.

Speaker

Ben Glocker is Reader (eq. Associate Professor) in Machine Learning for Imaging at the Department of Computing at Imperial College London where he co-leads the Biomedical Image Analysis Group. He also leads the HeartFlow-Imperial Research Team and is Head of ML Research at Kheiron Medical Technologies. He holds a PhD from TU Munich and was a postdoc at Microsoft and a Research Fellow at the University of Cambridge. He is a member of the AI Task Group of the UK National Screening Committee advising the Government on questions around clinical deployment of AI for screening programmes. His research is at the intersection of medical imaging and artificial intelligence aiming to build computational tools for improving image-based detection and diagnosis of disease.

Attend this talk on Zoom.

This meeting is part of our Responsible AI Seminar Series. If you’d like to receive updates about future instances of this seminar series, please sign up for our newsletter (on the bottom of the page).