MT-clinical BERT: scaling clinical information extraction with multitask learning.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date: Sep 18, 2021

Abstract

OBJECTIVE: Clinical notes contain an abundance of important, but not-readily accessible, information about patients. Systems that automatically extract this information rely on large amounts of training data of which there exists limited resources to create. Furthermore, they are developed disjointly, meaning that no information can be shared among task-specific systems. This bottleneck unnecessarily complicates practical application, reduces the performance capabilities of each individual solution, and associates the engineering debt of managing multiple information extraction systems.

Authors

  • Andriy Mulyar
    Computer Science Department, Virginia Commonwealth University, Richmond, Virginia, USA.
  • Ozlem Uzuner
    Department of Information Studies, University at Albany, SUNY. Albany, NY.
  • Bridget McInnes
    Information Sciences and Technology, George Mason University, Fairfax, Virginia, USA.

Keywords

External Resources

Popular Topics
Recent Journals