HealthScope++: A Data Scientist’s Microscope for (hopefully healthy) health outcomes and other stories

Feb. 11, 2015 from 3:30 to 4:20 p.m. — Physics/Astronomy Auditorium, room A102

Professor, University of Washington, Tacoma


As the increasing availability of digital health records should ideally improve accountability in care, a principled study of predictive modeling of healthcare risks and associated costs is fundamentally needed at both the population- and individual patient-level. This talk will have two parts. We will first present a data scientist’s deep-dive perspective on challenges faced and how they were addressed while working with multiple healthcare industry partners on real-world healthcare data, both claims and clinical. We will discuss and demonstrate prototypes of our solutions for cost prediction and risk-of-readmission care management, and how we leveraged big data machine learning frameworks. The second part will be a short overview of other efforts for social good at the Center for Data Science; each a story in its own.


Ankur M. Teredesai is a Professor of Computer Science & Systems, and Graduate Program Coordinator at the Institute of Technology, University of Washington Tacoma. He obtained a doctorate from SUNY, University at Buffalo in 2002. His research interests focus on data science principles for societal impact and social good.
Apart from his academic appointments at RIT and within the University of Washington, Prof. Teredesai has significant industry experience, having held various positions at C-DAC Pune, Microsoft, IBM T.J. Watson Labs, and a variety of technology startups. He has published over 70 papers on data mining and machine learning, has managed large teams of data scientists/engineers, and deployed numerous data science solutions in various verticals (internet advertising, social networks, handwritten zip code recognizers, healthcare analytics). His recent applied research contributions include risk prediction for heart failure and ACO cost prediction in healthcare analytics, trust-enhanced recommendations, distributed data mining algorithms for big data, novelty detection in video, and dietary volume estimation, to name a few.
Teredesai heads the UW Center for Data Science, and serves as the Information Officer for ACM SIGKDD (Special Interest Group in Knowledge Discovery and Data Mining). He is currently an associate editor for ACM SIGKDD Explorations and has served on program committees of major international conferences in data mining, maching learning and related areas.