讲座题目：Large-scale Personalized Health Surveillance by Collaborative Learning and Selective Sensing
演讲人：Ying Lin (University of Houston)
The rapid advances in sensing and information technology have provided unprecedented information infrastructure, such as electronic health record (EHR), holding great promises to develop new approaches for personalized health surveillance and accelerate the paradigm transition of the U.S. healthcare sector from reactive care to preventive care. However, leveraging the sensing technology for personalized health surveillance in large-scale population is challenging due to the complexity of disease progression, the widely reported heterogeneity in population, the limited sensing resources, as well as the lack of efficient and cost-effective sensing strategy. This talk will present (a) a novel statistical learning framework, collaborative learning, to effectively model heterogeneous disease trajectories from sparse and irregular sensing data by exploiting the progression patterns and similarities between individuals; (b) a decision support algorithm, selective sensing, to adaptively allocate the limited sensing resources to large population and maximally detect the high-risk individuals by integrating the disease progression, individual prognostics and sensing strategy design into a unified framework. The proposed methods were further applied in the context of cognitive decline monitoring in Alzheimer’s Disease (AD) and depression trajectory monitoring to facilitate the effective use of sensing technology in chronic disease management.
Dr. Ying Lin is an Assistant Professor in the Department of Industrial Engineering at the University of Houston. She got her Ph.D. degree from the Department of Industrial and Systems Engineering at the University of Washington and Bachelor’s degree in Statistics from the University of Science and Technology in China. Her research interests lie at the intersections of statistics, operations research, biomedical informatics and medical decision making. She has proposed innovative methodologies in statistics and optimization for disease dynamics modeling, personalized prognostics, and adaptive monitoring in large-scale heterogeneous population, including Depression, Alzheimer’s Disease (AD) and Diabetes. She has also developed efficient computational tools to discover interpretable and actionable knowledge from sparse and irregular longitudinal datasets and inform better decision making in clinical practice. Her works have been published papers on engineering journals, medical journals and data mining conference, i.e. IISE Transactions, Mathematical Bioscience and SDM. She also serves as the board director of Data Analytics & Information Systems Division in the Institute of Industrial & Systems Engineers.