Development of Methods to Improve the Identification of Patients with Rare or Underdiagnosed Diseases in Distributed Research Networks (Rare Disease)
PI(s): Dan Herman, University of Pennsylvania
Purpose: In this study, the research team is developing methods for creating computable phenotypes -- or sets of markers such as symptoms or physical traits -- for rare diseases with machine learning. Machine learning uses data to learn how to perform tasks with little or no human input.
Study Design: PaTH Data only Observational
PCORnet® Partners:
- University of Pennsylvania
- Vanderbilt University (STAR)
PaTH Partners:
- University of Michigan, James Brian Byrd
- University of Pittsburgh, Kathleen McTigue
Sponsor: PCORI®
Coordinating Center: University of Pennsylvania
