Polar labeling: silver standard algorithm for training disease classifiers.

Journal: Bioinformatics (Oxford, England)
Published Date: May 1, 2020

Abstract

MOTIVATION: Expert-labeled data are essential to train phenotyping algorithms for cohort identification. However expert labeling is time and labor intensive, and the costs remain prohibitive for scaling phenotyping to wider use-cases.

Authors

  • Kavishwar B Wagholikar
    Laboratory of Computer Science, Massachusetts General Hospital, 50 Staniford Street, Suite 750, Boston, MA, 02114, USA.
  • Hossein Estiri
    Harvard Medical School, Boston, MA, USA; Massachusetts General Hospital, Boston, MA, USA; Partners Healthcare, Somerville, MA, USA. Electronic address: hestiri@hms.harvard.edu.
  • Marykate Murphy
    Partners Healthcare, Somerville, MA 02145, USA.
  • Shawn N Murphy

Keywords

External Resources

Popular Topics
Recent Journals