Speaker

Prof. Huang Shuai(美国华盛顿大学）

　　Title

Large-Scale Health Surveillance by Collaborative Learning and Selective Sensing

　　Time

　　Venue

N702

　　Abstract

An unprecedented opportunity for disease research and management offered by the era of big data is the abundance of data for individuals easily acquired from a wide range of perspectives over many years. In the context of a specific disease such as Alzheimer's Disease, Depression, or Type 1 diabetes, one central question is how could we translate the big disease data into better health management of millions of preclinical or diseased patients. While many diseases manifest complex progression process, involving both temporal dynamics and spatial evolution, how could we model, monitor, and modify these processes, have been great challenges that are beyond the scope of either statistics or operations research alone. All these issues demand technological breakthroughs rather than incremental extensions of the current methodology. In this talk, I will introduce some of my research works that collectively aim to answer the following question: how can we transform the role of current sensing technologies from passive information collection into smart monitoring, which can proactively characterize the underlying complex time-varying disease process shaped by individual's risk factors and environmental exposures? Such a "smart monitoring" method will provide powerful data-driven decision-making capabilities for better disease management, leading to more efficient targeted screening and affordable care, better treatment planning, and improved quality of life for both patients and caregivers.

　　Affiliation

 Shuai is a Statistician and also a System Engineer. He enjoys working with healthcare professionals to formulate complex healthcare problems and pursue data-driven solutions for effective management of these problems. With theoretical training in his undergraduate study for Mathematics & Statistics from the School of Gifted Young at the University of Science and Technology of China and Ph.D. training in the Industrial Engineering program at the Arizona State University, his academic training prepares him well for developing holistic methodologies for real-world problems by seamless combination of theory, computation, and practice. He develops methodologies for modeling, monitoring, diagnosis, and prognosis of complex networked systems where the stochasticity of the system entities are interdependent, such as the brain connectivity networks, social networks, manufacturing processes, and disease progression process of Type 1 diabetes and other progressive diseases that have multiple stages and pathways. He also develops novel statistical and data mining models to integrate the massive and heterogeneous datasets such as neuroimaging, genomics, proteomics, laboratory tests, demographics, and clinical variables, for facilitating scientific discoveries in biomedical research and better decision-makings in clinical practices. More information can be found in https://sites.google.com/site/shuaihuang28/. His research has been funded by the National Science Foundation, Juvenile Diabetes Research Foundation, and several biomedical research institutes.