Neural network detects the effects of p-CPA pre-treatment on brain electrophysiology in a rat model of focal brain injury.

Objective: To examine the performance of Artificial Neural Network (ANN) in evaluation of the effects of pretreatment of para-Chlorophenylalanine (p-CPA), a serotonin blocker, in experimental brain injury.

Methods: Continuous 4 h digital electroencephalogram (EEG) recordings from male Charles Foster rats and its power spectrum analysis by using fast Fourier transform (FFT) were performed in two experimental (i) drug untreated injury group; (ii) p-CPA pretreated injury group as well as a control group. The EEG power spectrum data were tested by ANN containing 60 nodes in input layer, weighted from the digital values of power spectrum from 0 to 30 Hz, 18 nodes in hidden layer and an output node. The effects of injury and of the drug pretreatment were confirmed with the help of calculation of edematous swelling in the brain.

Results: The changes in EEG spectral patterns were compared with the ANN and the accuracy was determined in terms of percent (%). Overall performance of the network was found the best in control group (97.9%) in comparison to p-CPA untreated injury group (96.3%) and p-CPA pretreated injury group (71.9%). The decrease in accuracy in p-CPA pretreated injury group of subjects have occurred due to increase in misclassified patterns due to faster recovery in brain cortical potentials.

Conclusion: EEG spectrum analysis with ANN was found successful in identifying the changes due to brain swelling as well as the effect of pretreatment of p-CPA in focal brain injury condition. Thus, the training and testing of ANN with EEG power spectra can be used as an effective diagnostic tool for early prediction and monitoring of brain injury as well as the effects of drugs in this condition.