A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria

Kato, Minoru; Hayashi, Yoshito; Uema, Ryotaro; Kanesaka, Takashi; Yamaguchi, Shinjiro; Maekawa, Akira; Yamada, Takuya; Yamamoto, Masashi; Kitamura, Shinji; Inoue, Takuya; Yamamoto, Shunsuke; Kizu, Takashi; Takeda, Risato; Ogiyama, Hideharu; Yamamoto, Katsumi; Aoi, Kenji; Nagaike, Koji; Sasai, Yasutaka; Egawa, Satoshi; Akamatsu, Haruki; Ogawa, Hiroyuki; Komori, Masato; Akihiro, Nishihara; Yoshihara, Takeo; Tsujii, Yoshiki; Takehara, Tetsuo

doi:https://doi.org/10.1007/s10120-024-01511-8

A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria

Kato, Minoru; Hayashi, Yoshito; Uema, Ryotaro et al.

Gastric Cancer, 2024, 27(5), 1069-1077

アクセス数:2,751件（2025-07-02 00:45 集計）

固定URL: https://hdl.handle.net/11094/97124

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
GastricCancer_1s0120_024_01511_8	pdf	なし	851 KB	84	2024.07.05

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria
著者	NRID 1000080939249 1000080939249 著者名 Kato, Minoru
	NRID 1000080647123 1000080647123 researchmap permalink y-h y-h Scopus Author ID 35219993200 35219993200 著者名 Hayashi, Yoshito
	NRID 1000030939161 1000030939161 researchmap permalink ryotarouema ryotarouema 著者名 Uema, Ryotaro
	著者名 Kanesaka, Takashi
	著者名 Yamaguchi, Shinjiro
	著者名 Maekawa, Akira
	著者名 Yamada, Takuya
	著者名 Yamamoto, Masashi
	著者名 Kitamura, Shinji
	著者名 Inoue, Takuya
	NRID 1000070531747 1000070531747 researchmap permalink shunsuke_xs shunsuke_xs 著者名 Yamamoto, Shunsuke
	NRID 1000030748299 1000030748299 著者名 Kizu, Takashi
	著者名 Takeda, Risato
	著者名 Ogiyama, Hideharu
	著者名 Yamamoto, Katsumi
	著者名 Aoi, Kenji
	著者名 Nagaike, Koji
	著者名 Sasai, Yasutaka
	著者名 Egawa, Satoshi
	著者名 Akamatsu, Haruki
	著者名 Ogawa, Hiroyuki
	著者名 Komori, Masato
	著者名 Akihiro, Nishihara
	NRID 1000020814601 1000020814601 researchmap permalink ty_gh ty_gh 著者名 Yoshihara, Takeo
	NRID 1000080795170 1000080795170 researchmap permalink yhcks yhcks Scopus Author ID 57192176408 57192176408 著者名 Tsujii, Yoshiki
	NRID 1000070335355 1000070335355 researchmap permalink takeharatetsuo takeharatetsuo Scopus Author ID 7103332258 7103332258 著者名 Takehara, Tetsuo
キーワード等	Artificial intelligence
	Early gastric cancer
	Endoscopic submucosal dissection
	Lymph node metastasis
	Machine learning
内容	The version of record of this article, first published in Gastric Cancer, is available online at Publisher’s website: https://doi.org/10.1007/s10120-024-01511-8.
抄録	Background: We developed a machine learning (ML) model to predict the risk of lymph node metastasis (LNM) in patients with early gastric cancer (EGC) who did not meet the existing Japanese endoscopic curability criteria and compared its performance with that of the most common clinical risk scoring system, the eCura system. Methods: We used data from 4,042 consecutive patients with EGC from 21 institutions who underwent endoscopic submucosal dissection (ESD) and/or surgery between 2010 and 2021. All resected EGCs were histologically confirmed not to satisfy the current Japanese endoscopic curability criteria. Of all patients, 3,506 constituted the training cohort to develop the neural network-based ML model, and 536 constituted the validation cohort. The performance of our ML model, as measured by the area under the receiver operating characteristic curve (AUC), was compared with that of the eCura system in the validation cohort. Results: LNM rates were 14% (503/3,506) and 7% (39/536) in the training and validation cohorts, respectively. The ML model identified patients with LNM with an AUC of 0.83 (95% confidence interval, 0.76–0.89) in the validation cohort, while the eCura system identified patients with LNM with an AUC of 0.77 (95% confidence interval, 0.70–0.85) (P = 0.006, DeLong’s test). Conclusions: Our ML model performed better than the eCura system for predicting LNM risk in patients with EGC who did not meet the existing Japanese endoscopic curability criteria. Mini-abstract: We developed a neural network-based machine learning model that predicts the risk of lymph node metastasis in patients with early gastric cancer who did not meet the endoscopic curability criteria.
出版者	Springer
収録物名	Gastric Cancer
巻(号)	27(5)
ページ	1069-1077
刊行年月	2024-05-25
言語	英語
ハンドルURL	https://hdl.handle.net/11094/97124
PISSN	14363291
eISSN	14363305
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1007/s10120-024-01511-8
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 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
DCTERMS.bibliographicCitation	Gastric Cancer. 2024, 27(5), p. 1069-1077
DC.title	A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria
DC.creator	Kato, Minoru
	Hayashi, Yoshito
	Uema, Ryotaro
	Kanesaka, Takashi
	Yamaguchi, Shinjiro
	Maekawa, Akira
	Yamada, Takuya
	Yamamoto, Masashi
	Kitamura, Shinji
	Inoue, Takuya
	Yamamoto, Shunsuke
	Kizu, Takashi
	Takeda, Risato
	Ogiyama, Hideharu
	Yamamoto, Katsumi
	Aoi, Kenji
	Nagaike, Koji
	Sasai, Yasutaka
	Egawa, Satoshi
	Akamatsu, Haruki
	Ogawa, Hiroyuki
	Komori, Masato
	Akihiro, Nishihara
	Yoshihara, Takeo
	Tsujii, Yoshiki
	Takehara, Tetsuo
DC.publisher	Springer
DC.language' scheme='DCTERMS.RFC1766	英語
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2024-05-25
DC.identifier	https://doi.org/10.1007/s10120-024-01511-8
DC.subject	Artificial intelligence
	Early gastric cancer
	Endoscopic submucosal dissection
	Lymph node metastasis
	Machine learning
DC.description	The version of record of this article, first published in Gastric Cancer, is available online at Publisher’s website: https://doi.org/10.1007/s10120-024-01511-8.
DCTERMS.abstract	Background: We developed a machine learning (ML) model to predict the risk of lymph node metastasis (LNM) in patients with early gastric cancer (EGC) who did not meet the existing Japanese endoscopic curability criteria and compared its performance with that of the most common clinical risk scoring system, the eCura system. Methods: We used data from 4,042 consecutive patients with EGC from 21 institutions who underwent endoscopic submucosal dissection (ESD) and/or surgery between 2010 and 2021. All resected EGCs were histologically confirmed not to satisfy the current Japanese endoscopic curability criteria. Of all patients, 3,506 constituted the training cohort to develop the neural network-based ML model, and 536 constituted the validation cohort. The performance of our ML model, as measured by the area under the receiver operating characteristic curve (AUC), was compared with that of the eCura system in the validation cohort. Results: LNM rates were 14% (503/3,506) and 7% (39/536) in the training and validation cohorts, respectively. The ML model identified patients with LNM with an AUC of 0.83 (95% confidence interval, 0.76–0.89) in the validation cohort, while the eCura system identified patients with LNM with an AUC of 0.77 (95% confidence interval, 0.70–0.85) (P = 0.006, DeLong’s test). Conclusions: Our ML model performed better than the eCura system for predicting LNM risk in patients with EGC who did not meet the existing Japanese endoscopic curability criteria. Mini-abstract: We developed a neural network-based machine learning model that predicts the risk of lymph node metastasis in patients with early gastric cancer who did not meet the endoscopic curability criteria.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	97124
citation_title	A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria
citation_author	Kato, Minoru
	Hayashi, Yoshito
	Uema, Ryotaro
	Kanesaka, Takashi
	Yamaguchi, Shinjiro
	Maekawa, Akira
	Yamada, Takuya
	Yamamoto, Masashi
	Kitamura, Shinji
	Inoue, Takuya
	Yamamoto, Shunsuke
	Kizu, Takashi
	Takeda, Risato
	Ogiyama, Hideharu
	Yamamoto, Katsumi
	Aoi, Kenji
	Nagaike, Koji
	Sasai, Yasutaka
	Egawa, Satoshi
	Akamatsu, Haruki
	Ogawa, Hiroyuki
	Komori, Masato
	Akihiro, Nishihara
	Yoshihara, Takeo
	Tsujii, Yoshiki
	Takehara, Tetsuo
citation_publisher	Springer
citation_language	英語
citation_date	2024-05-25
citation_journal_title	Gastric Cancer
citation_volume	27
citation_issue	5
citation_firstpage	1069
citation_lastpage	1077
citation_doi	https://doi.org/10.1007/s10120-024-01511-8
citation_public_url	https://hdl.handle.net/11094/97124

A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria

閲覧可能ファイル

論文情報

論文詳細を表示