Events Calendar

AI Seminar

Speaker: David Kale, USC

Talk Title: Computational Phenotyping: Combining Big Data, Flexible Models, and Domain Knowledge

Abstract: In this talk, I will discuss the challenges and opportunities of applying machine learning to digital health data in the context of computational phenotyping. Phenotyping involves the development of algorithms to answer questions like, "Does this patient have diabetes?" and has a wide variety of applications: cohort construction for genomic studies, risk adjustment, quality improvement, and diagnosis. In recent years, researchers have moved away from algorithmic disease definitions based on clinical knowledge, which are expensive to develop and validate, and toward data-driven phenotypes based on the application of machine learning to large healthcare databases. I will provide an overview of phenotyping and its applications in medicine, discuss recent trends in the field, and present my recent work on phenotyping clinical time series with recurrent neural networks. I will also discuss ongoing work to develop methods that can exploit available data and domain knowledge to train data-driven models in the absence of ground truth training

Biography: Dave Kale is a fifth year PhD student in Computer Science and an Alfred E. Mann Innovation in Engineering Fellow at the University of Southern California. He is advised by Prof. Greg Ver Steeg at the USC Information Sciences Institute, a member of Aram Galstyan's lab at ISI, and an affiliate of Nigam Shah's lab at the Stanford Center for Biomedical Informatics Research. Dave co-founded the Machine Learning for Healthcare Conference (MLHC), the preeminent venue for research on machine learning applied to health. Dave holds a BS and MS from Stanford University

Host: Emilio Ferrara

Location: Information Science Institute (ISI) - 11th floor large conference room

Audiences: Everyone Is Invited

Contact: Kary LAU