A novel model based on non invasive methods for prediction of liver fibrosis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

15 Scopus citations

Abstract

Serial liver biopsies are typically the gold standard for diagnosis of liver fibrosis progression. However, It is associated with serious complications, inconvenient to patients and expensive, the challenge is to substitute the liver biopsy with non-invasive method. The proposed technique is employed to resolve this issue with average accuracy 99.48% for 5-folds cross validation. This accuracy pave the way to utilize classification models as a clinically non-invasive and reliable method to assess the degree of liver fibrosis.

Original languageEnglish
Title of host publicationICENCO 2017 - 13th International Computer Engineering Conference
Subtitle of host publicationBoundless Smart Societies
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages276-281
Number of pages6
ISBN (Electronic)9781538642665
DOIs
StatePublished - 2 Jul 2017
Externally publishedYes
Event13th International Computer Engineering Conference, ICENCO 2017 - Giza, Egypt
Duration: 27 Dec 201728 Dec 2017

Publication series

NameICENCO 2017 - 13th International Computer Engineering Conference: Boundless Smart Societies
Volume2018-January

Conference

Conference13th International Computer Engineering Conference, ICENCO 2017
Country/TerritoryEgypt
CityGiza
Period27/12/1728/12/17

Keywords

  • Classification
  • Knowledge representation
  • Minimal unique rules
  • Subsumption

Fingerprint

Dive into the research topics of 'A novel model based on non invasive methods for prediction of liver fibrosis'. Together they form a unique fingerprint.

Cite this