Assessment of Aphasia Using Artificial Neural Networks

• Published in: Iyo denshi to seitai kogaku Vol. 37; no. 2; pp. 140 - 145
• Main Authors: HANAI, Taizo, MATSUBARA, Michitaka, HONDA, Hiroyuki, KOBAYASHI, Takeshi, HIBINO, Shin, SHIRATAKI, Tatsuaki, FUKAGAWA, Kazutoshi
• Format: Journal Article
• Language: Japanese
• Published: Japanese Society for Medical and Biological Engineering 1999; 一般社団法人 日本生体医工学会
• Subjects: Electroencephalography; Electrophysiology; Fast Fourier transforms; Neural networks; Spectrum analysis
• ISSN: 0021-3292; 2185-5498
• DOI: 10.11239/jsmbe1963.37.140

In order to construct a first screening system for the home care, we investigated assessment of brain function disorder. In this study, we constructed a model for assessment of aphasia from electroencephalogram (EEG) using artificial neural networks (ANN). EEG data of the following patients were collected; the patient of total aphasia who is difficult to understand the speech and the patient of motor aphasia (Broca aphasia) who feels pain or makes some grammatical mistakes when he speaks anything while he can understand the speech. At first, power spectrum of EEG was extracted by the fast Fourier transform (FFT). Power spectrum was separated into 9 regions, corresponding to the characterized waves, and relative power values were calculated from them. The regions with 4.0 to 5.9, 6.0 to 7.9 and 8.0 to 12.9Hz were selected as the frequency band of θ1, θ2, and α waves, respectively. Assessment of linguistic ability was carried out by Western aphasia battery (WAB). The relative power values were input into each ANN model for estimation of aphasia quotient (AQ) score or score on spontaneous speech from WAB. The average error of ANN model for AQ score was 7.02 points out of 100. It was found that the model can estimate the AQ value at high accuracy. Another ANN model to estimate the score on spontaneous speech was also constructed. The average error of this model with actual spontaneous speech score was 0.27 points out of 20. Predicted score of patient with motor aphasia coincided well with the actual score. In conclusion these models can quantify the severity of aphasia from EEG.