Artificial neural networks to evaluate the boron concentration decreasing profile in blood-BPA samples of BNCT patients
| Autor: | Alejandro García-Reiriz, Jorge Magallanes, Sara Líberman, Jure Zupan |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Boron Compounds
Validation study Concentration profile prediction Radiation Artificial neural network Chemistry Phenylalanine Ciencias Químicas Boron Neutron Capture Therapy computer.software_genre Kohonen neural network Boron concentration p-Boronophenylalanie BNCT Humans Química Analítica Data mining Neural Networks Computer Biological system computer Kohonen neural networks CIENCIAS NATURALES Y EXACTAS Boron |
| Zdroj: | Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine. 69(12) |
| ISSN: | 1872-9800 |
| Popis: | For the prediction of decay concentration profiles of the p-boronophenylalanine (BPA) in blood during BNCT treatment, a method is suggested based on Kohonen neural networks. The results of a model trained with the concentration profiles from the literature are described. The prediction of the model was validated by the leave-one-out method. Its robustness shows that it is mostly independent on small variations. The ability to fit retrospective experimental data shows an uncertainty lower than the two compartment model used previously. Fil: Garcia Reiriz, Alejandro Gabriel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Química Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Instituto de Química Rosario; Argentina Fil: Magallanes, Jorge Federico. Comisión Nacional de Energía Atómica; Argentina Fil: Zupan, Jure. National Institute of Chemistry; Eslovenia Fil: Líberman, Sara. Comisión Nacional de Energía Atómica; Argentina |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect