Artificial neural networks to evaluate the boron concentration decreasing profile in blood-BPA samples of BNCT patients

Alejandro García-Reiriz; Jorge Magallanes; Jure Zupan; Sara Líberman

doi:10.1016/j.apradiso.2011.02.055

Artificial neural networks to evaluate the boron concentration decreasing profile in blood-BPA samples of BNCT patients

Appl Radiat Isot. 2011 Dec;69(12):1793-5. doi: 10.1016/j.apradiso.2011.02.055. Epub 2011 May 5.

Authors

Alejandro García-Reiriz¹, Jorge Magallanes, Jure Zupan, Sara Líberman

Affiliation

¹ Department of Analytical Chemistry, Faculty of Biochemical and Pharmaceutical Sciences, National University of Rosario, Rosario Institute of Chemistry (IQUIR-CONICET), Rosario, Argentina. [email protected]

PMID: 21592804
DOI: 10.1016/j.apradiso.2011.02.055

Abstract

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.

Publication types

Research Support, Non-U.S. Gov't
Validation Study

MeSH terms

Boron / blood*
Boron Compounds / blood*
Boron Neutron Capture Therapy*
Humans
Neural Networks, Computer*
Phenylalanine / analogs & derivatives*
Phenylalanine / blood

Substances

Boron Compounds
Phenylalanine
Boron
4-boronophenylalanine