Clinically meaningful risk factors for recurrence in T1 colorectal cancer treated with endoscopic resection alone identified by unsupervised machine learning: a multicenter study
Endoscopy · 01.11.2026 · 58 (11) · 1238-1247
DOI: 10.1055/a-2917-8805 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Endoscopy, erschienen am 01.11.2026. Verfasst von Xue Zhou und 24 weiteren Autor:innen. Beteiligte Einrichtung: The University of Aizu, Division of Information Systems, Japan, Aizuwakamatsu. Hauptthemen laut MEDLINE: Neoplasm Recurrence, Local, Colorectal Neoplasms, Unsupervised Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben.
Abstract (Originalsprache)
Identifying patients at high risk for recurrence after endoscopic resection of T1 colorectal cancer (CRC) remains challenging. This study aimed to identify recurrence risk subtypes and develop an interpretable risk stratification framework. This retrospective study analyzed 1123 patients with T1 CRC treated with endoscopic resection alone across 26 Japanese institutions (July 2009–December 2016). Patients were divided into development (68%) and evaluation (32%) cohorts based on institutional stratification. K-means clustering was applied to clinicopathologic variables to identify recurrence risk subtypes. A decision tree classifier was subsequently developed to generate transparent risk stratification rules. Three distinct subtypes were identified in the development cohort. Subtype 1 exhibited a numerically higher recurrence rate (5.4%) than Subtype 2 (0.9%) and Subtype 3 (1.4%). Although subtypes 2 and 3 showed comparable recurrence rates, they were clearly differentiated by morphology (flat vs. polypoid). In the evaluation cohort, Subtype 1 continued to show a numerically higher recurrence (4.8%) compared with subtypes 2 (1.6%) and 3 (1.1%). The decision tree model stratified recurrence risk hierarchically: submucosal invasion
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- The University of Aizu, Division of Information Systems, Japan, Aizuwakamatsu.
- Fukushima Medical University Aizu Medical Center, Department of Gastroenterology, Japan, Aizuwakamatsu.
- Institute of Science Tokyo, M&D Data Science Center, Institute of Integrated Research, Japan, Tokyo.
- National Defense Medical College, Department of Surgery, Japan, Tokorozawa.
- Hiroshima University Hospital, Department of endoscopy, Japan, Hiroshima.
- JA Onomichi General Hospital, Department of Endoscopy, Japan, Onomichi.
ORCID-Profile: Kazutomo Togashi, Shinji Tanaka, Kinichi Hotta, Masayoshi Yamada
Zitieren
APA
Zhou, X., Togashi, K., Zhu, X., Kajiwara, Y., Oka, S., Tanaka, S., Takamatsu, M., Hotta, K., Yamada, M., Ikematsu, H., Nagata, S., Yamada, K., Hashimoto, K., Ishihara, S., Saitoh, Y., Matsuda, K., Komori, K., Ishiguro, M., Tamaru, Y., …, & Ueno, H. (2026). Clinically meaningful risk factors for recurrence in T1 colorectal cancer treated with endoscopic resection alone identified by unsupervised machine learning: a multicenter study. Endoscopy, 58(11), 1238-1247. https://doi.org/10.1055/a-2917-8805
Vancouver
Zhou X, Togashi K, Zhu X, Kajiwara Y, Oka S, Tanaka S, et al. Clinically meaningful risk factors for recurrence in T1 colorectal cancer treated with endoscopic resection alone identified by unsupervised machine learning: a multicenter study. Endoscopy. 2026;58(11):1238-1247. doi:10.1055/a-2917-8805
BibTeX
@article{Zhou2026,
author = {Zhou, Xue and Togashi, Kazutomo and Zhu, Xin and Kajiwara, Yoshiki and Oka, Shiro and Tanaka, Shinji and Takamatsu, Manabu and Hotta, Kinichi and Yamada, Masayoshi and Ikematsu, Hiroaki and Nagata, Shinji and Yamada, Kazutaka and Hashimoto, Kosei and Ishihara, Soichiro and Saitoh, Yusuke and Matsuda, Kenji and Komori, Koji and Ishiguro, Megumi and Tamaru, Yuzuru and Okuyama, Takashi and Minami, Shinpei and Ohnuma, Shinobu and Sakamoto, Kazuhiro and Sugihara, Kenichi and Ueno, Hideki},
title = {Clinically meaningful risk factors for recurrence in T1 colorectal cancer treated with endoscopic resection alone identified by unsupervised machine learning: a multicenter study},
journal = {Endoscopy},
year = {2026},
volume = {58},
number = {11},
pages = {1238--1247},
doi = {10.1055/a-2917-8805}
}
EUVIMED