Silvia Crivelli
Affiliation: Lawrence Berkeley Lab, UC Davis
Country: USA
Workshop: BioCARLA
Title: AI and the Future of Precision Medicine
Advancements in Large Language Models (LLMs) combined with the exponential growth of medical literature and the availability of large-scale electronic health records (EHR), have fueled significant interest in building LLMs for healthcare and medicine. Noteworthy examples include GatorTron, BioBERT, and BioGPT, which perform tasks such as medical question answering, inference, information extraction, diagnosis classification, and clinical outcome predictions.
Through a collaboration between the US Department of Energy (DOE) and the US Department of Veterans Affairs (VA), teams from eight DOE labs have access to genomic and EHR data from millions of Veterans for collaboratively tackling diseases such as mental health, obstructive sleep apnea, long COVID, and lung cancer. I will discuss the development of a clinical LLM built using the vast VA data and show that clinical LLMs have the potential to revolutionize medical practice
and precision medicine.
Bio
Dr. Crivelli has conducted research at the intersection of science, high-performance computing, human-computer interaction, and applied mathematics for 30 years. Her research has focused on two main goals: 1) to bring scientists together, both seasoned and young and from all walks of science, to tackle long-standing, extremely hard, and multidisciplinary problems and 2) to develop methods and software tools that empower physicians and researchers to predict the behavior of biological systems and, more recently, healthcare outcomes. Her interest in developing AI technologies for scientific research and for societal benefit resulted in projects tackling a wide range of topics, which include the development of protein structure prediction methods, the creation of innovative software tools for protein and drug design, and the development of predictive models to decrease the number of deaths due to suicide and overdose.
She has tirelessly worked on the mission to diversify the workforce to include more women and people from underrepresented groups. She believes that progress in science will come from the rich combination of ideas that only a highly diverse community can create. She earned a Ph.D. in Computer Science from the University of Colorado, Boulder, and a M.S in Applied Mathematics from the Universidad Nacional del Litoral, Argentina. She was a postdoctoral fellow at the University of California, Berkeley and the Lawrence Berkeley National Laboratory (LBNL).
https://crivelligroup.lbl.gov/
https://scholar.google.com/citations?user=g2dgJ-IAAAAJ&hl=en