Classification accuracy of pain intensity induced by leg blood flow restriction during walking using machine learning based on electroencephalography

Imai, Hirotatsu; Kanie, Yuya; Yoshimoto, Shusuke; Yamamoto, Natsuki; Furuya, Masayuki; Fujimori, Takahito; Okada, Seiji

doi:https://doi.org/10.1038/s41598-025-13433-1

Classification accuracy of pain intensity induced by leg blood flow restriction during walking using machine learning based on electroencephalography

Imai, Hirotatsu; Kanie, Yuya; Yoshimoto, Shusuke et al.

Scientific Reports, 2025, 15, 27955

アクセス数:308件（2026-02-15 22:22 集計）

固定URL: https://hdl.handle.net/11094/103255

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
SciRep_15_27955	pdf	なし	1.77 MB	22	2025.12.02

Creative Commons : 表示 - 非営利 - 改変禁止

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Classification accuracy of pain intensity induced by leg blood flow restriction during walking using machine learning based on electroencephalography
著者	著者名 Imai, Hirotatsu
	NRID 1000010896377 1000010896377 ORCID 0000-0001-5977-1959 0000-0001-5977-1959 researchmap permalink ykanie1985 ykanie1985 Scopus Author ID 57567389000 57567389000 著者名 Kanie, Yuya
	NRID 1000080755463 1000080755463 ORCID 0000-0002-0891-0661 0000-0002-0891-0661 researchmap permalink shusukeyoshimoto shusukeyoshimoto Scopus Author ID 60023688800 60023688800 著者名 Yoshimoto, Shusuke
	著者名 Yamamoto, Natsuki
	NRID 1000020987466 1000020987466 researchmap permalink furuya1019 furuya1019 Scopus Author ID 56879852100 56879852100 著者名 Furuya, Masayuki
	NRID 1000080546888 1000080546888 ORCID 0000-0002-2758-7919 0000-0002-2758-7919 researchmap permalink fujimori_takahito fujimori_takahito Scopus Author ID 35271904600 35271904600 著者名 Fujimori, Takahito
	NRID 1000030448435 1000030448435 ORCID 0000-0002-5107-8209 0000-0002-5107-8209 researchmap permalink okadaseiji okadaseiji Scopus Author ID 35079139100 35079139100 著者名 Okada, Seiji
キーワード等	Artificial intelligence
	Electroencephalography
	Frequency spectrum
	Leg blood flow restriction
	Movement-related pain
	Tourniquet pain
内容	Imai H., Kanie Y., Yoshimoto S., et al. Classification accuracy of pain intensity induced by leg blood flow restriction during walking using machine learning based on electroencephalography. Scientific Reports 15, 27955 (2025); https://doi.org/10.1038/s41598-025-13433-1.
抄録	Pain assessment in clinical practice largely relies on patient-reported subjectivity. Although previous studies using fMRI and EEG have attempted objective pain evaluation, their focus has been limited to resting conditions. This study aimed to classify pain levels during movement using a wearable device with three forehead electrodes and advanced machine learning. Twenty-five healthy participants performed walking tasks under tourniquet-induced pain. It was confirmed that pain increased as walking time extended. Walking time was used as an index of pain stimulus intensity, and EEG data were collected to classify pain levels. Three machine learning algorithms—Random Forest, eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine—were employed. XGBoost achieved the highest classification performance among them. Classification accuracy for 2-, 3-, and 5-class classifications was evaluated and compared with and without BrainRate (BR), a metric indicating changes in the frequency spectrum and reflecting relative shifts across all frequency bands. Without BR, accuracies were 0.82 for 2-class, 0.60 for 3-class, and 0.40 for 5-class classification. Including BR improved accuracies to 0.96, 0.75, and 0.47, respectively. These findings highlight the significant role of BR in improving pain classification accuracy and the potential of this system for objective pain assessment even during movement.
出版者	Nature Research
収録物名	Scientific Reports
巻(号)	15
ページ	27955
刊行年月	2025-07-31
言語	英語
ハンドルURL	https://hdl.handle.net/11094/103255
eISSN	20452322
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1038/s41598-025-13433-1
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Scientific Reports. 2025, 15, p. 27955
DC.title	Classification accuracy of pain intensity induced by leg blood flow restriction during walking using machine learning based on electroencephalography
DC.creator	Imai, Hirotatsu
	Kanie, Yuya
	Yoshimoto, Shusuke
	Yamamoto, Natsuki
	Furuya, Masayuki
	Fujimori, Takahito
	Okada, Seiji
DC.publisher	Nature Research
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-07-31
DC.identifier	https://doi.org/10.1038/s41598-025-13433-1
DC.subject	Artificial intelligence
	Electroencephalography
	Frequency spectrum
	Leg blood flow restriction
	Movement-related pain
	Tourniquet pain
DC.description	Imai H., Kanie Y., Yoshimoto S., et al. Classification accuracy of pain intensity induced by leg blood flow restriction during walking using machine learning based on electroencephalography. Scientific Reports 15, 27955 (2025); https://doi.org/10.1038/s41598-025-13433-1.
DCTERMS.abstract	Pain assessment in clinical practice largely relies on patient-reported subjectivity. Although previous studies using fMRI and EEG have attempted objective pain evaluation, their focus has been limited to resting conditions. This study aimed to classify pain levels during movement using a wearable device with three forehead electrodes and advanced machine learning. Twenty-five healthy participants performed walking tasks under tourniquet-induced pain. It was confirmed that pain increased as walking time extended. Walking time was used as an index of pain stimulus intensity, and EEG data were collected to classify pain levels. Three machine learning algorithms—Random Forest, eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine—were employed. XGBoost achieved the highest classification performance among them. Classification accuracy for 2-, 3-, and 5-class classifications was evaluated and compared with and without BrainRate (BR), a metric indicating changes in the frequency spectrum and reflecting relative shifts across all frequency bands. Without BR, accuracies were 0.82 for 2-class, 0.60 for 3-class, and 0.40 for 5-class classification. Including BR improved accuracies to 0.96, 0.75, and 0.47, respectively. These findings highlight the significant role of BR in improving pain classification accuracy and the potential of this system for objective pain assessment even during movement.
DC.rights	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
DC.format	103255
citation_title	Classification accuracy of pain intensity induced by leg blood flow restriction during walking using machine learning based on electroencephalography
citation_author	Imai, Hirotatsu
	Kanie, Yuya
	Yoshimoto, Shusuke
	Yamamoto, Natsuki
	Furuya, Masayuki
	Fujimori, Takahito
	Okada, Seiji
citation_publisher	Nature Research
citation_language	英語
citation_date	2025-07-31
citation_journal_title	Scientific Reports
citation_volume	15
citation_firstpage	27955
citation_doi	https://doi.org/10.1038/s41598-025-13433-1
citation_public_url	https://hdl.handle.net/11094/103255

Classification accuracy of pain intensity induced by leg blood flow restriction during walking using machine learning based on electroencephalography

閲覧可能ファイル

論文情報

論文詳細を表示