Computing That Serves

Machine Learning for Healthcare


Thursday, November 19, 2009 - 10:00am


David Page
Professor of Biostatistics and Medical Informatics and of Computer Sciences
University of Wisconsin-Madison

Machine learning has great potential for impact on society through its use in predictive personalized medicine (PPM).  In PPM, predictive models can be used to better make treatment decisions, including diagnosis, selection of drugs and drug dosages, and preventive medicine.  This talk will present the use of machine learning for building predictive models from clinical and genetic data.  It will also present advantages in particular of statistical relational learning (SRL) for analyzing such data.  The talk will include applications to mammography, coumadin (warfarin) therapy, and drug adverse events.  It will discuss a particular SRL approach called "View Learning", where the SRL system learns to define a new view of the database being analyzed.  It will also present plans of the Wisconsin Genomics Initiative for PPM.


David Page received his Ph.D. in computer science from the University of Illinois at Urbana-Champaign in 1993.  He was a research scientist in the Oxford University Computing Laboratory from 1993 to 1997, where he also served as a visiting member of the Faculty of Mathematics from 1995-1997. David is now a professor at the University of Wisconsin-Madison, in the Dept. of Biostatistics and Medical Informatics (School of Medicine and Public Health) and Dept. of Computer Sciences.  He is also a member of the University of Wisconsin Comprehensive Cancer Center and the Genome Center of Wisconsin, and he is a member of the scientific advisory boards for the Wisconsin Genomics Initiative and the Observational Medical Outcomes Partnership.  David's primary research interests are in machine learning analysis of combined clinical and genetic data and in learning statistical models from multi-relational data.