The knowledge acquisition problem is one of the most difficult issues
in elaborating a medical expert system. This is more true in the conte
xt of automated brain signal diagnosis. This kind of knowledge does no
t lend itself to be represented in a classical rule-based system and i
s not easily put in quantitative terms by the specialists. Artificial
neural networks (ANNs) provide a useful alternative for capturing this
information. In this work, an application of ANNs to brain maturation
prediction is presented. The problem is essentially a supervised clas
sification. A case data base consisting of data extracted from electro
encephalographic (EEG) signals and diagnoses carried out by an expert
neurologist serves to test the ability of several statistical classifi
ers and several kinds of ANNs in reproducing the expert results. There
is also a discussion on how to integrate ANNs in a higher-level knowl
edge-based system for brain signal interpretation.