Diagnosing congenital heart defects using the Fallot computational model

Nancy E. Reed, Maria L Gini, Paul E. Johnson, James H. Moller

Research output: Contribution to journalReview articlepeer-review

7 Scopus citations

Abstract

This paper describes a computational model developed for the diagnosis of multiple defects. If multiple defects interact, meaning that the cues observable for multiple defects are not a sum of the cues observable for the component defects, diagnosis is particularly difficult. We developed a description and classification of the ways cues changes when defects interact. A computational model (named Fallot) was implemented and a knowledge-base was constructed for the diagnosis of congenital heart defects. On each case, Fallot performs recognition-based reasoning followed by solution construction and evaluation with the cute combination methods. Fallot was tested on cases from hospital files and correctly diagnoses cases with multiple interacting defects of which conventional methods are not applicable or fail.

Original languageEnglish (US)
Pages (from-to)25-40
Number of pages16
JournalArtificial Intelligence in Medicine
Volume10
Issue number1
DOIs
StatePublished - May 1 1997

Keywords

  • Cardiology
  • Diagnosis
  • Expert systems
  • Multiple defects or diseases

Fingerprint Dive into the research topics of 'Diagnosing congenital heart defects using the Fallot computational model'. Together they form a unique fingerprint.

Cite this