Poster | 6th Internet World Congress for Biomedical Sciences |
Antonio J. Serrano López(1), Gustavo Camps i Valls(2), EMILIO SORIA OLIVAS(3), NICOLÁS VICTOR JIMÉNEZ TORRÉS(4), José David Martín Guerrero(5), Jose Ramon Sepulveda Sanchis(6)
(1)(6)Dpto. Electrónica. Universidad de Valencia - Burjasot. Spain
(2)Universitat de València - Burjassot, Valencia. Spain
(3)DPTO INGENIERÍA ELECTRONICA. FACULTAD DE FISICAS - BURJASSOT/VALENCIA. Spain
(4)DPTO FARMACIA Y TECNOLOGÍA FARMACEÚTICA. FACULTAD DE FARMACIA - BURJASSOT/VALENCIA. Spain
(5)G.P.D.S. Departament d´Enginyeria Electrònica. Universitat de València - Burjassot. Spain
Contact address: |
Antonio J. Serrano López Dpto. Electrónica Universidad de Valencia Lab. GPDS Burjasot Valencia 46100 Spain antonio.j.serrano@uv.es |
[Pharmacology] |
[Health Informatics] |
[Oncology] |
The Emesis (vomits and sicknes) like a side effect for the administration of chemotherapy is the main factor in cancer treatment from the patients point of view. The control of this effect has to do with complex relations between the treatment and the organism. This is a dificult task, not yet solved, that is, the main reason to apply artificial neural networks, taking advantageof their power to establish complex relations using only real data without any initial assumption.
The neural model was developed from 748 samples corresponding to 213 patients treated with 7 diferent protocols. From the information acquired, 22 variables were selected within the patient characteristics, chemotherapy, as inputs for the Neural Network.The problem was solved like a classification in three groups for the emetic protection of the patient (no vomit,1 or 2 vomits, more than 2 vomits).
The results obtained with the neural model(sensitivity and specificity of 90% during training and a 82% for validation) are a good prospect to obtain a system for decission taking in this medical field.
[Pharmacology] |
[Health Informatics] |
[Oncology] |