Inferring and Summarizing Multi-source Graph Data && Learning Actionable & Credible Risk Stratification Models for Healthcare

Professor Koutra: Networks naturally capture a host of real-world interactions, from social interactions and email communication to brain activity. However, graphs are not always directly observed, especially in scientific domains, such as neuroscience, where monitored brain activity is often captured as time series. How can we efficiently infer networks from time series data (e.g., model the functional organization of brain activity as a network) and speed up the network construction process to scale up to millions of nodes and thousands of graphs? Further, what can be learned about the structure of the graph data? How can we automatically summarize a network `conditionally' to its domain, i.e., summarize its most important properties by taking into account the properties of other graphs in that domain (e.g., neuroscience)? In this talk I will present our recent work on scalable algorithms for inferring, summarizing and mining large collections of graph data coming from different sources. I will also discuss applications in various domains, including connectomics and social science. Professor Wiens: The increasing availability of electronic health data has led to the investigation of machine learning (ML) techniques for improving clinical decision making. In particular, patient risk stratification models could, in theory, facilitate the targeting of specific interventions to high-risk groups. However, for data-driven systems to become widely and safely adopted in clinical care, there remain several key research challenges. More specifically, many existing risk stratification models while accurate lack credibility and actionability. In this talk, I will present and motivate these challenges in the context of building models to predict patient risk of healthcare-associated infections. I will discuss new and ongoing research directions in ML that aim to increase the credibility and actionability of such models without sacrificing accuracy.
Professor Koutra: Danai Koutra is an Assistant Professor in Computer Science and Engineering at University of Michigan, where she direct the GEMS Lab. Her research interests include large-scale graph mining, graph summarization, graph similarity and matching, and anomaly detection. Danai's research has been applied mainly to social, collaboration and web networks, as well as brain connectivity graphs. She holds one "rate-1" patent and has six (pending) patents on bipartite graph alignment. Danai won the 2016 ACM SIGKDD Dissertation Award and an honorable mention for the SCS Doctoral Dissertation Award (CMU). She has multiple papers in top data mining conferences, including 4 award-winning papers, and her work has been covered by the popular press, such as the MIT Technology Review. Danai served as a SIGKDD Cup co-chair in KDD 2017 and she is currently a Ph.D. Forum co-chair for IEEE ICDM 2017. Moreover, she is serving as the secretary of the SIAM Activity Group on Data Mining and Analytics (SIAG/DMA). She earned her Ph.D. and M.S. in Computer Science from CMU in 2015 and her diploma in Electrical and Computer Engineering at the National Technical University of Athens in 2010. Professor Wiens: enna Wiens is an Assistant Professor of Computer Science and Engineering (CSE) at the University of Michigan in Ann Arbor. Her primary research interests lie at the intersection of machine learning, data mining, and healthcare. She is particularly interested in time-series analysis and transfer/multitask learning. The overarching goal of her research agenda is to develop the computational methods needed to help organize, process, and transform patient data into actionable knowledge. Jenna received her PhD from MIT in 2014. In 2015 she was named Forbes 30 under 30 in Science and Healthcare; she received an NSF CAREER Award in 2016; and recently she was named to the MIT Tech Review's list of Innovators Under 35.