Seminars and Events
Interpretability and Fairness of Deep Learning Models on Health Dataset
Event Details
Abstract: The recent release of large-scale healthcare datasets has greatly propelled the research of data-driven deep learning models for healthcare applications. However, due to the nature of black-boxed models, concerns about interpretability, fairness, and biases in healthcare scenarios where human lives are at stake call for a careful and thorough examination of both datasets and models. In this work, we focus on MIMIC-IV, the largest publicly available healthcare dataset, and conduct comprehensive analyses of interpretability as well as dataset representation bias and prediction fairness of deep learning models for in-hospital mortality prediction.
Host: Michael Pazzani, Principal Scientist
To promote discussion, we have arranged a lunch after our Artificial Intelligence Research for Health Seminar: Monday, June 19, 2023, 11:00am – 12:00pm PDT.
Sign up for in-person attendance and lunch here.
The AI Research for Health seminar features AI and health researchers presenting their research on AI and Data Science with an impact on human health. The goal is to foster new collaborations among researchers in these fields. The talks will be live at The USC-Information Science Institute in Marina Del Rey (room 1135/1137) and on zoom.
We have also received inquiries about attending in person if you are not affiliated with ISI. This requires checking in with reception on the 10th-floor where you will be directed to the 11th floor conference room. We will also validate parking.
Students and postdocs are welcome. There is a shuttle from campus: Marina del Rey Shuttle – USC Transportation
Register for zoom by clicking here: Webinar Registration – Zoom