A comparative study on feature selection for a risk prediction model for colorectal cancer.

Journal: Computer methods and programs in biomedicine
Published Date: Jun 4, 2019

Abstract

BACKGROUND AND OBJECTIVE: Risk prediction models aim at identifying people at higher risk of developing a target disease. Feature selection is particularly important to improve the prediction model performance avoiding overfitting and to identify the leading cancer risk (and protective) factors. Assessing the stability of feature selection/ranking algorithms becomes an important issue when the aim is to analyze the features with more prediction power.

Authors

  • Nahúm Cueto-López
    Department of Electrical, Systems and Automatic Engineering, Universidad of León, Campus de Vegazana s/n, León 24071, Spain. Electronic address: ncuetl00@unileon.es.
  • Maria Teresa García-Ordás
    Department of Electrical, Systems and Automatic Engineering, Universidad of León, Campus de Vegazana s/n, León 24071, Spain. Electronic address: mgaro@unileon.es.
  • Verónica Dávila-Batista
    Grupo Investigación Interacciones Gen-Ambiente y Salud (GIIGAS), Centro de Investigación Biomédica en Red (CIBER), Spain. Electronic address: vdavb@unileon.es.
  • Víctor Moreno
    Unit of Biomarkers and Susceptibility, Cancer Prevention and Control Programme, Catalan Institute of Oncology-IDIBELL, L'Hospitalet de Llobregat, Spain; CIBER Epidemiologia y Salud Publica (CIBERESP), Madrid, Spain; Department of Clinical Sciences, Faculty of Medicine, University of Barcelona, Barcelona, Spain. Electronic address: v.moreno@iconcologia.net.
  • Nuria Aragonés
    Epidemiology Section, Public Health Division, Department of Health of Madrid CIBER Epidemiología y Salud Pública (CIBERESP), Madrid, Spain. Electronic address: nuria.aragones@salud.madrid.org.
  • Rocío Alaiz-Rodríguez
    Department of Electrical, Systems and Automatic Engineering, Universidad of León, Campus de Vegazana s/n, León 24071, Spain. Electronic address: rocio.alaiz@unileon.es.

Keywords

External Resources

Popular Topics
Recent Journals