Determining Assertion Status for Medical Problems in Clinical Records

Abstract

This paper describes the MITRE system entries for the 2010 i2b2/VA community evaluation Challenges in Natural Language Processing for Clinical Data for the task of classifying assertions associated with problem concepts extracted from patient records. Our best performing system obtained an overall micro-averaged F-score of 0.9343. The methods employed were a combination of machine learning (Conditional Random Field and Maximum Entropy) and rule-based (pattern matching) techniques.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2010
Accession Number
AD1108512

Entities

People

  • Alexander Yeh
  • Ben Wellner
  • Cheryl Clark
  • David Tresner-kirsch
  • John Aberdeen
  • Lynette Hirschman
  • Matt Coarr

Organizations

  • MITRE Corporation

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Accuracy
  • Boundaries
  • Classification
  • Corporations
  • Diseases And Disorders
  • Errors
  • Families (Human)
  • Gaussian Distributions
  • Health Services
  • Language
  • Machine Learning
  • Natural Language Processing
  • Natural Languages
  • Neurobehavioral Manifestations
  • Pain
  • Test And Evaluation
  • Training

Readers

  • Computational Linguistics
  • Mathematical Modeling and Probability Theory.
  • Oncology and Biomarker-Based Cancer Detection.

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval