Name: Silvia Crivelli
Pronouns: she/her/hers
Biography:
Dr. Crivelli is a Staff Scientist at Lawrence Berkeley National Laboratory and co-Principal Investigator of an interagency collaboration between the Department of Energy (DOE) and the Department of Veterans Affairs (VA) called MVP CHAMPION (Million Veterans Program: Computational Health Analytics for Medical Precision to Improve Outcomes Now). Her team focuses on developing personalized diagnostic strategies to enhance healthcare for Veterans, with specific attention to suicide prevention, obstructive sleep apnea, and lung cancer. Her research primarily revolves around two key areas: 1) utilizing large language models (LLMs) like GPT to extract information and detect patterns from electronic health records spanning 20 years and more than 23 million Veterans, and 2) integrating social and environmental factors that influence health into comprehensive disease models. These models incorporate various types of data, ranging from genomic information to societal-level factors, with the aim of advancing precision medicine and identifying geographic regions with higher vulnerabilities.
Institution/Lab: Lawrence Berkeley National Laboratory
Website:
SRP Collaboration Topic/Title: Using AI and HPC for Healthcare and Precision Medicine
Field or research area: AI for science
Please select all the topical areas that apply to your project:
Computational Science Applications (i.e., bioscience, cosmology, chemistry, environmental science, nanotechnology, climate, etc.); Data Science (i.e., data analytics, data management & storage systems, visualization); Machine Learning and AI
Brief Abstract:
As part of our collaboration with the VA and DOE, we are currently using natural language processing to extract important life events from electronic health records that are correlated with high suicide risk. In this project, we are looking for a student intern that is interested in the cross-section of machine learning and healthcare that can help us develop a user-friendly interface for clinicians and researchers. Ideally, this UI will help accelerate better decision-making.
Desired relevant skills, background, or interests:
Knowledge of programming, frontend UI development, data visualization, problem solving
Other comments:
Do any special requirements apply? other
Other, specify: none
Keywords:
AI; precision medicine; precision healthcare; NLP; Large language models (LLM);
Lightning Talk Title: AI-Accelerated Precision Healthcare