Speaker: Dr. Elisa Warner - University of Michigan/VISA

Title: Advancing Clinical Outcome Prediction through Innovative Multimodal and Domain-Generalized AI that Accommodates Limited Data
Abstract: Clinical decision support systems are computer-based systems developed with the goal of assisting health care providers in arduous clinical tasks or improving decision-making. In routine clinical care, medical practices tend to be dynamic and must account for diversity of data. In my presentation, I will describe development of innovative multimodal and multidomain AI models for clinical decision support, with a focus on applications with limited data availability. I start with describing the motivation followed by three case studies of multimodal/multidomain proof-of-concept Clinical Decision Support (CDS) models that accommodate limited data. My research seeks to address questions regarding constructing machine-learning-based models that mimic real-world mental models and bridge domain gaps in cases of limited data.

Biography: Elisa Warner, PhD, is a machine learning scientist and bioinformatician whose work bridges computational modeling, biomedical imaging, and multimodal data integration. She received her PhD and MS in Bioinformatics and an MPH in Molecular Epidemiology from the University of Michigan, where her research focused on developing novel multimodal learning methods for disease prediction across MRI, histopathology, and clinical data modalities. Her doctoral work has resulted in over 20 peer-reviewed publications with more than 500 citations.