Automatic blood glucose classification for gestational diabetes with feature selection: decision trees vs neural networks

Caballero Ruiz, E. and García Sáez, Gema and Rigla Cros, Mercedes and Balsells, M. and Pons, Belén and Morillo, Marta and Gómez Aguilera, Enrique J. and Hernando Pérez, María Elena (2014). Automatic blood glucose classification for gestational diabetes with feature selection: decision trees vs neural networks. In: "XIII Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON 2013)", 25/09/2013 - 28/09/2013, Sevilla, Spain. pp. 1370-1371.

Description

Title: Automatic blood glucose classification for gestational diabetes with feature selection: decision trees vs neural networks
Author/s:
  • Caballero Ruiz, E.
  • García Sáez, Gema
  • Rigla Cros, Mercedes
  • Balsells, M.
  • Pons, Belén
  • Morillo, Marta
  • Gómez Aguilera, Enrique J.
  • Hernando Pérez, María Elena
Item Type: Presentation at Congress or Conference (Article)
Event Title: XIII Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON 2013)
Event Dates: 25/09/2013 - 28/09/2013
Event Location: Sevilla, Spain
Title of Book: IFMBE Proceedings
Date: 2014
Volume: 41
Subjects:
Freetext Keywords: Classification, decision support, diabetes, decision trees neural networks
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Tecnología Fotónica [hasta 2014]
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (217kB)

Abstract

Automatic blood glucose classification may help specialists to provide a better interpretation of blood glucose data, downloaded directly from patients glucose meter and will contribute in the development of decision support systems for gestational diabetes. This paper presents an automatic blood glucose classifier for gestational diabetes that compares 6 different feature selection methods for two machine learning algorithms: neural networks and decision trees. Three searching algorithms, Greedy, Best First and Genetic, were combined with two different evaluators, CSF and Wrapper, for the feature selection. The study has been made with 6080 blood glucose measurements from 25 patients. Decision trees with a feature set selected with the Wrapper evaluator and the Best first search algorithm obtained the best accuracy: 95.92%.

Funding Projects

TypeCodeAcronymLeaderTitle
Madrid Regional GovernmentPI10/01125SINEDIEUnspecifiedSistemas inteligentes y de educación para el control de la diabetes diagnosticada en el embarazo

More information

Item ID: 26141
DC Identifier: http://oa.upm.es/26141/
OAI Identifier: oai:oa.upm.es:26141
Official URL: http://link.springer.com/chapter/10.1007%2F978-3-319-00846-2_339
Deposited by: Memoria Investigacion
Deposited on: 31 May 2014 11:32
Last Modified: 17 Oct 2016 13:20
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM