2025 SYMPOSIUM Agenda

Opening Remarks delivered by Peter Tarczy-Hornoch

followed by

Short talks x 5 (IMDS Pilot Award Winners)

Facilitation by Trevor Cohen

1.       “Interpretable and Multimodal Deep Learning to Enhance Clinical Breast Cancer Risk Prediction” presented by Dr. Lee and Dr. Nyflot (presented by PhD student Ojas Ramwala)

Video Recording

2.       “Synthesizing composite tau-PET images from 3D MRI through a novel, diffusion-inspired machine learning framework” presented by Dr. Kurt and Dr. Levendovszky

Video Recording

3.       “Towards Automatic Identification of Patients in Need of Long COVID Care with Natural Language Processing Method” presented by Dr. Yetisgen and Dr. Stephens (Dr. Yetisgen to present)

Video Recording

4.       “Integration of digital pathology and multiparametric MRI features for improved prediction of patient outcome in triple negative breast cancer” presented by Dr. Partridge, Dr. Mittal, and Dr. Kazerouni

Video Recording

5.       “Using machine learning to optimize prediction of extubation failure and clinical action” presented by- Dr. Wurfel and Dr. Wang (PhD student Izzy Chaiken will present)

Video Recording

Welcome & Keynote Introduction Delivered by Peter Tarczy-Hornoch

Keynote Presentation: Eric Horvitz, MD, PhD, Chief Scientific Officer, Microsoft

“From AI Aspirations to Healthcare Futures”

Eric Horvitz

Chief Scientific Officer, Microsoft

Advances in large language models are generating significant interest and fueling enthusiasm for their potential to contribute to addressing long-standing challenges in biomedical informatics, healthcare delivery, and public health. Progress in task-specific accuracies and the emergence of new capabilities have been largely driven by the increasing scale of data and compute. Boosts in general capabilities, along with recent innovations, such as advancements in multimodal modeling, inference-time reasoning, and multiagent platforms, are framing new opportunities to enhance clinical decision support, medical education, and research. I will trace the arc of AI developments in medicine over several decades and then focus on recent advances. Through a series of studies and examples, I will explore directions and possibilities and share reflections on the opportunities and challenges that lie ahead.

Video Recording

Panel (topic: Ethical AI) Panel Intro and Facilitation by Lucy Lu Wang

Panelists:

·       Diane M. Korngiebel, DPhil, AI Ethicist, Google; Associate Professor, UW Biomedical Informatics and Medical Education, University of Washington

·       Jeff Leek, PhD, Vice President and Chief Data Officer, Fred Hutch Cancer Center

·       Yulia Tsvetkov, PhD, Associate Professor, Paul G. Allen School of Computer Science & Engineering, University of Washington

·       Andrew White, MD, SFHN, FACP, Assistant Chief Information Officer, University of Washington

 Video Recording

Short talks from poster presenters  Facilitation by Noah Hoffman

Presenters:

1.      “High-fidelity predictions of diffusion in the brain microenvironment” by Nels Schimek

Video Recording

2.      “Natural Language Processing to support nurse text messaging for maternal-child health in Kenya: a pilot study” by Keshet Ronen

Video Recording

3.      “Focus on the Patient, not the Label: Developing a Computer Vision System to Predict Drug Concentrations from Syringe Labels in the OR” by Willis Silliman

Video Recording

4.      “Cohort research with University of Washington ADVANCE network – driving local and multi-site data-driven research on Emergency Department patient cohorts” by Jimmy Phuong

Video Recording

5.      “Adaptive AI Models for Personalized Laboratory Reference Intervals” by Cindy Zhang

Video Recording