Abstract: Massive amounts of medical data such as from electronic health records and body-worn sensors are being collected and mined by researchers, but translating findings into actionable knowledge remains difficult. The first challenge is finding causes, rather than correlations, when the data are highly noisy and often missing, and relationships are more complicated than pairwise links between variables. The second challenge is then using these relationships to explain specific cases, such as why an individual’s blood glucose is raised. In this talk I discuss new methods for both causal inference and explanation from complex and uncertain data, and how they can be used to make better decisions and provide individualized feedback.
Samantha Kleinberg (https://www.linkedin.com/in/samantha-kleinberg-2476765) is an Assistant Professor of Computer Science at Stevens Institute of Technology. She received her PhD in Computer Science from New York University in 2010 and was a Computing Innovation Fellow at Columbia University in the Department of Biomedical informatics from[masked]. She is the recipient of NSF CAREER and JSMF Complex Systems Scholar Awards. She is the author of "Causality, Probability, and Time" (Cambridge University Press, 2012) and "Why: A Guide to Finding and Using Causes (http://shop.oreilly.com/product/0636920033035.do)" (O’Reilly Media, 2015), a nontechnical introduction to causality.
6pm to 6:20 networking and "chit-chat". 6:20pm we do a lightning round of introductions for five attendees.
Talk (and periscope (https://www.periscope.tv/qplum_team)) starts at 6:30pm.
We will turn off the periscope for the last fifteen minutes of the talk, where we can talk freely about unpublished recent work.
Quiz at 7:45pm and networking after that.
The prize in the quiz will be a copy of Samantha's book (http://shop.oreilly.com/product/0636920033035.do).
The aim of the meetup is for people to share their knowledge with like-minded people.
Apply to speak in this meetup group (on a future date) (https://qplum.typeform.com/to/EqkkuA)