Knowledge discovery in cardiology: A systematic literature review

TitreKnowledge discovery in cardiology: A systematic literature review
Publication TypeJournal Article
Year of Publication2017
AuthorsKadi, Ia, Idri, Ab, Fernández-Alemán, JLb
JournalInternational Journal of Medical Informatics
Volume97
Pagination12-32
Abstract

Context Data mining (DM) provides the methodology and technology needed to transform huge amounts of data into useful information for decision making. It is a powerful process employed to extract knowledge and discover new patterns embedded in large data sets. Data mining has been increasingly used in medicine, particularly in cardiology. In fact, DM applications can greatly benefit all those involved in cardiology, such as patients, cardiologists and nurses. Objective The purpose of this paper is to review papers concerning the application of DM techniques in cardiology so as to summarize and analyze evidence regarding: (1) the DM techniques most frequently used in cardiology; (2) the performance of DM models in cardiology; (3) comparisons of the performance of different DM models in cardiology. Method We performed a systematic literature review of empirical studies on the application of DM techniques in cardiology published in the period between 1 January 2000 and 31 December 2015. Results A total of 149 articles published between 2000 and 2015 were selected, studied and analyzed according to the following criteria: DM techniques and performance of the approaches developed. The results obtained showed that a significant number of the studies selected used classification and prediction techniques when developing DM models. Neural networks, decision trees and support vector machines were identified as being the techniques most frequently employed when developing DM models in cardiology. Moreover, neural networks and support vector machines achieved the highest accuracy rates and were proved to be more efficient than other techniques. © 2016 Elsevier Ireland Ltd

URLhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84988689033&doi=10.1016%2fj.ijmedinf.2016.09.005&partnerID=40&md5=9bd4f89bacb9b8dea94dd1f7eefef431
DOI10.1016/j.ijmedinf.2016.09.005
Revues: 

Partenaires

Localisation


Location map

Suivez-nous sur

  

Contactez-nous

ENSIAS

Avenue Mohammed Ben Abdallah Regragui, Madinat Al Irfane, BP 713, Agdal Rabat, Maroc

Résultat de recherche d'images pour "icone fax" Télécopie : (+212) 5 37 77 72 30

    Compteur de visiteurs:312,757
    Education - This is a contributing Drupal Theme
    Design by WeebPal.