Upcoming Events

Alert Design in The Real World: A Cross-Sectional Analysis of Interruptive Alerting at 9 Academic Pediatric Health Systems

As part of the Department of Energy’s partnership with the National Cancer Institute, the Modeling Outcomes Using Surveillance Data and Scalable AI for Cancer (MOSSAIC) project aims to develop deep learning models to support near-real-time cancer surveillance at the population level. Through the NCI’s Surveillance, Epidemiology, and End Results (SEER) program, we deploy models for the automated coding of cancer cases across state and regional cancer registries throughout the United States.

In this talk, James Zou, PhD explores how generative AI agents can enable drug discovery and development. He introduces the Virtual Lab—a collaborative team of AI scientist agents conducting in silico research meetings to tackle open-ended R&D projects. The Virtual Lab designed new nanobody binders to recent COVID variants, which were experimentally validated. He then discusses some interesting opportunities in designing and optimizing multi-agent interactions.

Traditional machine learning classifiers using structured representations of text, such as randomly initialized concept embeddings (concept unique identifiers - CUIs), have demonstrated strong performance in clinical risk prediction tasks. In prior work, we developed a CUI-based convolutional neural network substance misuse classifier trained on clinical notes for hospital-based screening. While effective, such models require extensive feature engineering and are limited in their semantic understanding. Recent advances in large language models (LLMs) enable richer contextualization of clinical narratives through prompt engineering and parameter-efficient tuning for computable phenotyping. 

Presented by the Industry Partnership Council

Merck & Co., Inc. is a leading pharmaceutical company that is focused on advancing science to deliver medicines and vaccines that save lives. This panel will focus on different ways biomedical and health informatics experts contribute to this important mission. Specifically, panelists will discuss their career journeys in Real-World Evidence and how their work in advanced analytics, epidemiology, strategic partnerships, and innovative platforms is shaping health research.

The panel offers a unique opportunity for students and professionals to learn about informatics careers in pharmaceutical research, expand knowledge about informatics applications in industry, and connect with experts to learn about the future of Real-World Evidence.

This contribution from the University of Utah to the AMIA 10x10 program is an in-depth course about Clinical Decision Support (CDS) tools, standards, and implementation. The course is designed and taught by leaders and experts in the field. The instructors are affiliated with the Department of Biomedical Informatics at the University of Utah, which has a five-decade-long history of innovations in CDS.

The CIBRC Bundle is a Premium Package offering all of AMIA’s clinical informatics board review tools at a discount. Participants have the opportunity to engage in self-paced learning using CIBRC Online Plus, with its 27 lectures of content directly related to the Delineation of Practice along with the 250 practice test questions. Learners also engage in the 3-day experience of the live meeting where they interact with CIBRC’s renowned faculty and with colleagues.

The AMIA Annual Symposium is the world’s premier meeting for the research and practice of biomedical and health informatics.

The AMIA Annual Symposium is the world’s premier meeting for the research and practice of biomedical and health informatics.

The AMIA Annual Symposium is the world’s premier meeting for the research and practice of biomedical and health informatics. The meeting gathers the whole AMIA community of students and professionals, plus academic and corporate members, and government and non-profit partners.