Digital Services        F A Q

SCHOLARLY TALKS

Preserving Individual and Institutional Privacy in Distributed Regression Models

Dept. of Computer Science (April 9, 2014)
635









SEMINAR SERIES : Distinguished lecture

MAJOR SPEAKER : Ohno-Machado, Lucila
LENGTH : 68 min.
ACCESS : Open to all
SUMMARY : Building predictive models using clinical and molecular data requires a large number of observations. The wide adoption of electronic health records in the USA allows the collection of data about a large number of patients. Learning healthcare systems are built from federated networks of clinical data warehouses. Their goal is to build data-driven models that improve patient outcomes. These models usually require adjustment for confounders such as co-morbidities and demographics. Distributed multivariate models help promote privacy by allowing data to remain at their origin and aggregating calculations made locally. I will describe methods and tools we have developed to perform privacy-preserving distributed computing on clinical data warehouses at the University of California San Diego and collaborating institutions.  [Go to the full record in the library's catalogue]



  ●  Persistent link: http://hkbutube.lib.hkbu.edu.hk/st/display.php?bibno=b3660315
  ●  XML Dublin Core code for metadata harvesting


Recommended for You


This video is presented here with the permission of the speakers. Any downloading, storage, reproduction, and redistribution are strictly prohibited without the prior permission of the respective speakers. Go to Full Disclaimer.

  For enquiries, please contact Digital and Multimedia Services Section




© 2009-2021 All rights reserved