ナカイ　ヨウスケ   NAKAI Yousuke   中井　陽介    所属   医学部 医学科（東京女子医科大学病院）    職種   教授・基幹分野長
論文種別	原著
言語種別	英語
査読の有無	査読あり
表題	Prognostic model for pancreatic cancer based on machine learning of routine slides and transcriptomic tumor analysis
掲載誌名	正式名：British journal of cancer 略　 称：Br J Cancer ISSNコード：15321827/00070920
掲載区分	国外
巻・号・頁	134(6),pp.849-859
著者・共著者	TAKEMATSU Manabu,TANAKA Mariko,MASUGI Yohei,INOUE Yosuke,NAGANO Hiroko, Tho Ngoc-Quynh Le,NISHIDA Kenji,SAWA Yui,SUGIURA Kota,KAWAGUCHI Yoshikuni,KAZAMI Yusuke,NAKAI Yosuke,HAMADA Tsuyoshi,SUZUKI Tatsunori,HARA Kensuke,KUREBAYASHI Yutaka,TAKEDA Tsuyoshi,SASAHIRA Naoki,UEMATSU Yosuke,UEMURA Sho,FUJISHIRO Mitsuhiro,HASEGAWA Kiyoshi,KITAGO Minoru,TAKAHASHI Yu,SEKINE Shigeki,USHIKU Tetsuo,TAKEUCHI Kengo
発行年月	2026/03
概要	BACKGROUND:Prognostication for pancreatic ductal adenocarcinoma (PDAC) using histologic images is difficult due to tumor heterogeneity. We developed an artificial intelligence (AI) model to predict postoperative recurrence using histologic image patches.METHODS:We included 591 patients with resected PDAC to train an AI model for recurrence prediction at 12 or 24 months and validated it using external cohorts (n = 302 in total). Image patches from hematoxylin and eosin-stained slides were clustered via uniform manifold approximation and projection (UMAP) and used to train a random forest model. Predictive performance was evaluated using area under the receiver operating characteristic curve (AUC). Gene expression analysis was conducted to characterise survival-related clusters.RESULTS:Seventeen patch clusters were identified. Two were linked to high recurrence risk, and one to low risk. In external validation, the model achieved an AUC of up to 0.792. The random forest score independently predicted recurrence. Greater heterogeneity in patch composition correlated with shorter time to recurrence (P < 0.01). High-risk clusters showed elevated CSF3R expression; the low-risk cluster showed increased IGFBP3 expression.CONCLUSIONS:Our AI model, using only archival histologic slides, accurately predicted postoperative recurrence in PDAC and revealed image features linked to outcomes and gene expression.
DOI	10.1038/s41416-025-03308-7
PMID	41507565