IBIIS-AIMI Seminar: 'Fair' AI Modeling for Digital Healthcare - Imon Banerjee, PhD

Title: 'Fair' AI Modeling for Digital Healthcare 

Abstract: With the rapid advancements in AI models, there has been growing concern in recent literature about the risk of unintended biases affecting individuals unfairly based on factors like race, gender, and other clinical characteristics. One of the key challenges in analyzing AI bias is that the factors contributing to unfairness are often interconnected and can amplify one another. It is crucial to understand how individual, institutional, and societal biases may be either mitigated or exacerbated when adopting AI systems. Common approaches to eliminating bias, such as developing demographic-specific models, often face the challenge of insufficient demographic representation. In this talk, we present an alternative computational approach to creating 'fair' models that aim to reduce bias without relying on demographically balanced datasets. Our observations indicate that techniques aimed at decoupling demographic information from task predictions typically fail to match the performance of baseline models. While preserving the model performance, we will explore a novel 'fair' AI modeling approach that incorporates adversarial, causal, and contrastive learning techniques, with a focus on applications in digital healthcare. 

About: Imon Banerjee is an Associate Professor and Director of AI Innovation Hub at Mayo Clinic Arizona. She is a graduate faculty at Arizona State University.  Her research is focused on fairness in AI, multimodal deep learning, and AI translation for digital healthcare. With a deep interest in understanding and mitigating biases in AI systems, Imon works at the intersection of adversarial, causal, and contrastive learning techniques. Her research explores ways to ensure that AI models are not only accurate but also equitable, addressing concerns related to race, gender, and other demographic factors. She is dedicated to advancing AI technology that can be both innovative and socially responsible, particularly in healthcare and related domains. She is currently leading multiple federal and non-federal multi-institutional research grants aimed at advancing AI to support digital healthcare solutions. 

Attendance is open to the Stanford and AIMI affiliate community. Please contact aimicenter@stanford.edu for the Zoom link if you would like to attend virtually.