Sandia and Lawrence Berkeley National Laboratories: Artificial Intelligence and Machine Learning Mini Conference
Ethics in Machine Learning, Dr. Jay Lostead
AI for Healthcare and Biomedicine, Dr. Silvia Crivelli AMCR
Friday, December 9, 2022, 11:00 AM – 1:00 PM
AI FOR HEALTHCARE AND BIOMEDICINE
Healthcare and biomedical research require AI technologies to analyze large volumes of multimodal data in order to create predictive models of health and disease as well as technologies that enhance the interaction between healthcare providers and patients. Through a partnership between the Departments of Energy and Veterans Affairs, the Berkeley Lab and other DOE labs are developing technologies to predict high risk for suicide and overdose, cardiovascular disease, and response to treatments, among others. We use electronic health records and genomic data to analyze the predictive and protective factors involved. Also, we are working on the integration of other factors that affect outcomes such as social and environmental determinants of health. We believe the latter will not only inform physicians and healthcare providers but also policy makers who need to quickly make decisions and allocate resources. In this seminar I will focus on 2 main areas that my group has been working on: developing Natural Language Processing (NLP) techniques to extract dramatic life events from medical notes. These events, like housing and job instability, social isolation and troubles with the law, are poorly diagnosed in the medical records but healthcare providers’ notes are rich in information. We are also developing geospatial models to develop indexes of environmental and socio-economic vulnerability based on temperature, air quality, poverty, unemployment, crime, and many more datasets. I will highlight the potential and limitations of AI in these growing fields as well as the areas where more work is needed.
DR. SILVIA CRIVELLI AMCR
I have been conducting research at the intersection of structural biology, high-performance computing, and applied math for more than twenty-five years. My research has two main goals: to bring scientists together, both seasoned and young and from all walks of science, to tackle long-standing, extremely hard, and multidisciplinary problems and to develop methods and software tools that empower physicians and researchers to predict the behavior of biological systems and, more recently, healthcare outcomes. I have been working together with biologists, chemists, computer scientists, physicians, and applied mathematicians. I am a co-PI of the DOE-VA Million Veterans Program that aims to integrate structured and unstructured data from electronic health records from more than 20 million veterans to develop patient-specific diagnostic strategies to improve healthcare for veterans.
ETHICS IN MACHINE LEARNING
Machine learning affects our daily lives through our online activities, our ability to get a job or loan, or even our medical diagnoses. The potential for this statistical modeling is enormous, but we must consider the ethical impacts of how ML is used for things that affect our lives. While these common ML uses seem to not affect scientific and engineering ML use, science and engineering are just affected in different ways. For example, data quality and selection for model training is always important for making a model that works as intended. Understanding the linkage between existing data and what the model should do is critical for both societal ML use as well as scientific. Underlying this data selection are ethical considerations important across all ML use cases. This talk focuses on many of the places ML is used in science and engineering as well as in society and how decisions made when developing ML models can have profound effects on the outcomes. Audience participation and discussion is strongly encouraged. Topical Areas: Applied & Computational Math; Computational Science & Engineering; Computer Science; Data Science; High Performance Computing Topic/Methods/Domain: Machine Learning, Data Science, Ethics Target Audience: Undergraduate students; Masters students; Ph.D. students
DR. JAY LOFSTEAD
Dr. Jay Lofstead is a Principal Member of Technical Staff in the Scalable System Software department of the Center for Computing Research at Sandia National Laboratories in Albuquerque, NM. His work focuses on infrastructure to support all varieties of simulation, scientific, and engineering workflows with a strong emphasis on IO, middleware, storage, transactions, operating system features to support workflows, containers, software engineering and reproducibility. He is co-founder of the IO500 storage list. He also works extensively to support various student mentoring and diversity programs at several venues each year including outreach to both high school and college students. Jay graduated with a BS, MS, and PhD in Computer Science from Georgia Institute of Technology and was a recipient of a 2013 R&D 100 award for his work on the ADIOS IO library.