medigraphic.com
SPANISH

Revista Cubana de Informática Médica

ISSN 1684-1859 (Print)
  • Contents
  • View Archive
  • Information
    • General Information        
    • Directory
  • Publish
    • Instructions for authors        
  • medigraphic.com
    • Home
    • Journals index            
    • Register / Login
  • Mi perfil

2014, Number 1

Next >>

Revista Cubana de Informática Médica 2014; 6 (1)

Web component for the analysis of clinical information using the technique of clustering data mining

Ochoa RAJ, Orellana GA, Sánchez CY, Davila HF
Full text How to cite this article

Language: Spanish
References: 10
Page:
PDF size: 131.52 Kb.


Key words:

data warehouse, knowledge extraction, artificial intelligence, data mining, Simple K-Means, analysis view.

ABSTRACT

The digitization of the different processes and automation services generate large volumes of information. Data mining (DM) is an artificial intelligence technique that allows finding non-trivial information residing in stored data. This research aims to develop a view of analysis for the Integral System for Primary Health Care (SIAPS), using grouping technique framed on Simple K-Means algorithm, with the goal of completing an analysis of the patients' clinical information, for it raises the extraction of knowledge from data warehouse powered by the repository of electronic medical records. The research is based on the free distribution tool WEKA, it works in isolation of SIAPS, the interface, as well as the views, models and reports generated by WEKA are sometimes difficult to understand by health professionals, who do not necessarily have to possess advanced knowledge of new information technologies. For the development of the solution was used Java 1.6 as a programming language, JBoss 4.2 as the application Server and Eclipse 3.4 as a development platform. PostgreSQL 8.4 was used as Database Management System and the integration framework SEAM. Java Enterprise Edition 5.0 platform was used during the whole process. An analysis view to facilitate the understanding of the generated models is expected as a result, to support the process of making clinical decisions.


REFERENCES

  1. Orallo Hernández J, Ramírez Quintana JM, Ferri Ramírez, C. Introducción a la minería de datos. s/l: Pearson; 2004.

  2. Xu R, Wunsch DC. Clustering. New Jersey: IEEE Press; 2009.

  3. González Bernaldo de Quirós F, Luna D, Otero P. Sistema de Información en los Sistemas de Salud. Buenos Aires: Instituto Universitario del Hospital Italiano; 2009. [Citado: 10 Mar 2014]. Disponible en: http://www.hospitalitaliano.org.ar/campus/index.php?contenido=ver_conf.php&id_curso=842

  4. Pautsch JGA. Minería de datos aplicada al análisis de la deserción en la carrera de Analista en Sistemas de Computación. Misiones, Argentina: Universidad Nacional de Misiones, Facultad de Ciencias Exactas, Químicas y Naturales; 2009.

  5. Bressán GE. Almacenes de datos y minería de datos. Buenos Aires: Universidad Nacional del Nordeste, Facultad de Ciencias Exactas y Naturales y Agrimensura; 2003.

  6. Fayyad UM, Piatetsky-Shapiro G, Smith P, Uthurusamy. Advances in Knowledge Discovery and Data-Mining. s.l.: AAAI Press / The MIT Press; 1996.

  7. Frank E, Witten IH. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. s.l.: Morgan Kaufmann; 2000.

  8. Aplicación de minería de datos para el diagnóstico de accidentes cerebrovasculares agudos (ACVAs). [En línea] [Citado el: 20 de enero de 2012.] Disponible en: http://www.daedalus.es/fileadmin/daedalus/doc/MineriaDeDatos/DAEDALUS-MD19-Accidentes_Cardiovasculares.pdf

  9. A Tutorial on Clustering Algorithms [En línea] [Citado el: 6 de febrero de 2012.] Disponible en: http://home.dei.polimi.it/matteucc/Clustering/tutorial_html/kmeans.html

  10. DAEDALUS.es [home page en Internet] [citado el 7 de febrero de 2012.] Disponible en: http://www.daedalus.es




2020     |     www.medigraphic.com

Mi perfil

C?MO CITAR (Vancouver)

Revista Cubana de Informática Médica. 2014;6