Hybrid algorithm for the classification of prostate cancer patients of the MCC-Spain study based on support vector machines and genetic algorithms


Por: Lasheras, J, Lasheras, F, Donquiles, C, Tardon, A, Castano-Vinyals, G, Palazuelos, C, Salas, D, Sanchez, V and Juez, F

Publicada: 10 sep 2021 Ahead of Print: 1 jun 2021
Resumen:
In this novel research a hybrid algorithm is presented, one capable of selecting a set of features that makes it possible to identify individuals who are healthy and those who suffer from prostate cancer. In this research the selection of features is carried out by means of evolutionary algorithms. In previous works, algorithms of this nature have proven their ability to find solutions for optimization problems in a wide range of fields. The present research proposes a novel hybrid algorithm based on genetic algorithms and support vector machines have been developed in order to find the best variables subset for classifying individuals. The results obtained show how well the method performs in comparison to other method-ologies. Cases and controls belong to the study MCC-Spain. (c) 2020 Elsevier B.V. All rights reserved.

Filiaciones:
Lasheras, J:
 Hosp Carmen & Severo Ochoa, Anesthesiol & Resuscitat Serv, Cangas De Narcea, Asturias, Spain

Lasheras, F:
 Univ Oviedo, Dept Math, Oviedo, Spain

Donquiles, C:
 Ctr Invest Biomed Red Epidemiol & Salud Publ CIBE, Madrid, Spain

 Univ Oviedo, Universitary Inst Oncol Asturias IUOPA, Oviedo, Spain

 Univ Leon, Biomed Inst IBIOMED, Res Grp Gene Environm Hlth Interact, Leon, Spain

Tardon, A:
 Ctr Invest Biomed Red Epidemiol & Salud Publ CIBE, Madrid, Spain

 Univ Oviedo, Universitary Inst Oncol Asturias IUOPA, Oviedo, Spain

Castano-Vinyals, G:
 Carlos III Inst Hlth, Consortium Biomed Res Epidemiol & Publ Hlth CIBER, Madrid, Spain

 ISGlobal, Ctr Res Environm Epidemiol CREAL, Barcelona, Spain

 Univ Pompeu Fabra UPF, Barcelona, Spain

 IMIM Hosp del Mar Med Res Inst Barcelona, Barcelona, Spain

Palazuelos, C:
 Univ Cantabria IDIVAL, Santander, Spain

:
 FISABIO Publ Hlth, Valencia Canc & Publ Hlth Area, Valencia, Spain

 Valencian Community, Gen Directorate Publ Hlth, Valencia, Spain

Sanchez, V:
 Ctr Invest Biomed Red Epidemiol & Salud Publ CIBE, Madrid, Spain

 Univ Leon, Biomed Inst IBIOMED, Res Grp Gene Environm Hlth Interact, Leon, Spain

Juez, F:
 Univ Oviedo, Dept Mines Prospecting & Exploitat, Oviedo, Spain
ISSN: 09252312





Neurocomputing
Editorial
Elsevier BV, RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS, Países Bajos
Tipo de documento: Article
Volumen: 452 Número:
Páginas: 386-394
WOS Id: 000663091800016

MÉTRICAS