Effects of negation and uncertainty stratification on text-derived patient profile similarity

Research output: Contribution to journalArticlepeer-review

Abstract

Semantic similarity is a useful approach for comparing patient phenotypes, and holds the potential of an effective method for exploiting text-derived phenotypes for differential diagnosis, text and document classification, and outcome prediction. While approaches for context disambiguation are commonly used in text mining applications, forming a standard component of information extraction pipelines, their effects on semantic similarity calculations have not been widely explored. In this work, we evaluate how inclusion and disclusion of negated and uncertain mentions of concepts from text-derived phenotypes affects similarity of patients, and the use of those profiles to predict diagnosis. We report on the effectiveness of these approaches and report a very small, yet significant, improvement in performance when classifying primary diagnosis over MIMIC-III patient visits.

Original languageEnglish
Article number781227
Number of pages6
JournalFrontiers in digital health
Volume3
DOIs
Publication statusPublished - 6 Dec 2021

Keywords

  • context disambiguation
  • differential diagnosis
  • negation
  • ontology
  • phenotype profiles
  • semantic similarity

Fingerprint

Dive into the research topics of 'Effects of negation and uncertainty stratification on text-derived patient profile similarity'. Together they form a unique fingerprint.

Cite this