Differentiation of speech in Parkinson's disease and spinocerebellar degeneration using deep neural networks

Eguchi, Katsuki; Yaguchi, Hiroaki; Kudo, Ikue; Kimura, Ibuki; Nabekura, Tomoko; Kumagai, Ryuto; Fujita, Kenichi; Nakashiro, Yuichi; Iida, Yuki; Hamada, Shinsuke; Honma, Sanae; Takei, Asako; Moriwaka, Fumio; Yabe, Ichiro

Differentiation of speech in Parkinson's disease and spinocerebellar degeneration using deep neural networks

Eguchi, Katsuki; Yaguchi, Hiroaki; Kudo, Ikue et al.

Journal of neurology, 2024, 271(2), 1004-1012

Permalink : https://hdl.handle.net/2115/94213

このアイテムのアクセス数:183件（2026-07-15 01:16 集計）

閲覧可能ファイル

ファイル	フォーマット	サイズ	閲覧回数	説明
manuscript_revise	pdf	1.13 MB	146

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権	open access
URI	https://hdl.handle.net/2115/94213
タイトル	Differentiation of speech in Parkinson's disease and spinocerebellar degeneration using deep neural networks
著者	Eguchi, Katsuki ; Yaguchi, Hiroaki ; Kudo, Ikue ; Kimura, Ibuki ; Nabekura, Tomoko ; Kumagai, Ryuto ; Fujita, Kenichi ; Nakashiro, Yuichi ; Iida, Yuki ; Hamada, Shinsuke ; Honma, Sanae ; Takei, Asako ; Moriwaka, Fumio ; Yabe, Ichiro
著者名 Eguchi, Katsuki
著者名 Yaguchi, Hiroaki
著者名 Kudo, Ikue
著者名 Kimura, Ibuki
著者名 Nabekura, Tomoko
著者名 Kumagai, Ryuto
著者名 Fujita, Kenichi
著者名 Nakashiro, Yuichi
著者名 Iida, Yuki
著者名 Hamada, Shinsuke
著者名 Honma, Sanae
著者名 Takei, Asako
著者名 Moriwaka, Fumio
e-Rad_Researcher 60372273 著者名 Yabe, Ichiro
言語	英語
キーワード	Parkinson's disease
	Spinocerebellar degeneration
	Dysarthria
	Machine learning
	Deep learning
発行日	2024-02
出版者	Springer
収録物名	Journal of neurology
巻(号)	271(2)
ページ	1004-1012
抄録	Introduction Assessing dysarthria features in patients with neurodegenerative diseases helps diagnose underlying pathologies. Although deep neural network (DNN) techniques have been widely adopted in various audio processing tasks, few studies have tested whether DNNs can help differentiate neurodegenerative diseases using patients’ speech data. This study evaluated whether a DNN model using a transformer architecture could differentiate patients with Parkinson’s disease (PD) from patients with spinocerebellar degeneration (SCD) using speech data. Methods Speech data were obtained from 251 and 101 patients with PD and SCD, respectively, while they read a passage. We fine-tuned a pre-trained DNN model using log-mel spectrograms generated from speech data. The DNN model was trained to predict whether the input spectrogram was generated from patients with PD or SCD. We used fivefold cross-validation to evaluate the predictive performance using the area under the receiver operating characteristic curve (AUC) and accuracy, sensitivity, and specificity. Results Average ± standard deviation of the AUC, accuracy, sensitivity, and specificity of the trained model for the fivefold cross-validation were 0.93 ± 0.04, 0.87 ± 0.03, 0.83 ± 0.05, and 0.89 ± 0.05, respectively. Conclusion The DNN model can differentiate speech data of patients with PD from that of patients with SCD with relatively high accuracy and AUC. The proposed method can be used as a non-invasive, easy-to-perform screening method to differentiate PD from SCD using patient speech and is expected to be applied to telemedicine.
資源タイプ	学術雑誌論文
出版タイプ	Accepted Manuscript
権利情報	This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s00415-023-12091-5
PISSN	0340-5354
関連情報 (isVersionOf)	出版社版DOI https://doi.org/10.1007/s00415-023-12091-5