Assessment of aphasia using artificial neural networks

Shin Hibino, Taizo Hanai, Michitaka Matsubara, Kazutoshi Fukagawa, Tatsuaki Shirataki, Hiroyuki Honda, Takeshi Kobayashi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

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 12.9 Hz 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.

Original languageEnglish
Pages (from-to)140-145
Number of pages6
JournalJapanese Journal of Medical Electronics and Biological Engineering
Volume37
Issue number2
Publication statusPublished - Jul 17 1999
Externally publishedYes

Fingerprint

Neural networks
Electroencephalography
Power spectrum
Linguistics
Fast Fourier transforms
Frequency bands
Brain
Screening

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

Hibino, S., Hanai, T., Matsubara, M., Fukagawa, K., Shirataki, T., Honda, H., & Kobayashi, T. (1999). Assessment of aphasia using artificial neural networks. Japanese Journal of Medical Electronics and Biological Engineering, 37(2), 140-145.

Assessment of aphasia using artificial neural networks. / Hibino, Shin; Hanai, Taizo; Matsubara, Michitaka; Fukagawa, Kazutoshi; Shirataki, Tatsuaki; Honda, Hiroyuki; Kobayashi, Takeshi.

In: Japanese Journal of Medical Electronics and Biological Engineering, Vol. 37, No. 2, 17.07.1999, p. 140-145.

Research output: Contribution to journalArticle

Hibino, S, Hanai, T, Matsubara, M, Fukagawa, K, Shirataki, T, Honda, H & Kobayashi, T 1999, 'Assessment of aphasia using artificial neural networks', Japanese Journal of Medical Electronics and Biological Engineering, vol. 37, no. 2, pp. 140-145.
Hibino S, Hanai T, Matsubara M, Fukagawa K, Shirataki T, Honda H et al. Assessment of aphasia using artificial neural networks. Japanese Journal of Medical Electronics and Biological Engineering. 1999 Jul 17;37(2):140-145.
Hibino, Shin ; Hanai, Taizo ; Matsubara, Michitaka ; Fukagawa, Kazutoshi ; Shirataki, Tatsuaki ; Honda, Hiroyuki ; Kobayashi, Takeshi. / Assessment of aphasia using artificial neural networks. In: Japanese Journal of Medical Electronics and Biological Engineering. 1999 ; Vol. 37, No. 2. pp. 140-145.
@article{0507007c8ea647bfad48398594415505,
title = "Assessment of aphasia using artificial neural networks",
abstract = "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 12.9 Hz 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.",
author = "Shin Hibino and Taizo Hanai and Michitaka Matsubara and Kazutoshi Fukagawa and Tatsuaki Shirataki and Hiroyuki Honda and Takeshi Kobayashi",
year = "1999",
month = "7",
day = "17",
language = "English",
volume = "37",
pages = "140--145",
journal = "Japanese Journal of Medical Electronics and Biological Engineering",
issn = "0021-3292",
publisher = "Nihon M E Gakkai",
number = "2",

}

TY - JOUR

T1 - Assessment of aphasia using artificial neural networks

AU - Hibino, Shin

AU - Hanai, Taizo

AU - Matsubara, Michitaka

AU - Fukagawa, Kazutoshi

AU - Shirataki, Tatsuaki

AU - Honda, Hiroyuki

AU - Kobayashi, Takeshi

PY - 1999/7/17

Y1 - 1999/7/17

N2 - 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 12.9 Hz 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.

AB - 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 12.9 Hz 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.

UR - http://www.scopus.com/inward/record.url?scp=0033014883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033014883&partnerID=8YFLogxK

M3 - Article

VL - 37

SP - 140

EP - 145

JO - Japanese Journal of Medical Electronics and Biological Engineering

JF - Japanese Journal of Medical Electronics and Biological Engineering

SN - 0021-3292

IS - 2

ER -