用于预测不符合内镜治愈标准的早期胃癌淋巴结转移的机器学习模型。
A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria.
发表日期：2024 May 25
作者：
Minoru Kato, Yoshito Hayashi, Ryotaro Uema, Takashi Kanesaka, Shinjiro Yamaguchi, Akira Maekawa, Takuya Yamada, Masashi Yamamoto, Shinji Kitamura, Takuya Inoue, Shunsuke Yamamoto, Takashi Kizu, Risato Takeda, Hideharu Ogiyama, Katsumi Yamamoto, Kenji Aoi, Koji Nagaike, Yasutaka Sasai, Satoshi Egawa, Haruki Akamatsu, Hiroyuki Ogawa, Masato Komori, Nishihara Akihiro, Takeo Yoshihara, Yoshiki Tsujii, Tetsuo Takehara
来源：
Gastric Cancer
摘要：
我们开发了一种机器学习（ML）模型来预测不符合现有日本内镜治愈标准的早期胃癌（EGC）患者淋巴结转移（LNM）的风险，并将其性能与最常见的临床结果进行比较风险评分系统，eCura系统。我们使用了2010年至2021年间来自21个机构的4,042名连续接受内镜粘膜下剥离术（ESD）和/或手术的EGC患者的数据。所有切除的EGC均经组织学证实不满足当前日本内镜检查的要求固化性标准。在所有患者中，3,506 名构成开发基于神经网络的 ML 模型的训练队列，536 名构成验证队列。我们的 ML 模型的性能（通过受试者工作特征曲线 (AUC) 下的面积来衡量）与验证队列中 eCura 系统的性能进行了比较。LNM 率分别为 14% (503/3,506) 和 7% (39 /536）分别在训练和验证队列中。 ML 模型在验证队列中识别出 AUC 为 0.83（95% 置信区间，0.76-0.89）的 LNM 患者，而 eCura 系统识别出 AUC 为 0.77（95% 置信区间，0.70-0.85）的 LNM 患者（P = 0.006，DeLong 检验）。对于不符合现有日本内镜治愈标准的 EGC 患者，我们的 ML 模型在预测 LNM 风险方面表现优于 eCura 系统。我们开发了一种基于神经网络的机器学习模型，可以预测不符合内镜治愈标准的早期胃癌患者淋巴结转移的风险。© 2024。作者。
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.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.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).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. 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.© 2024. The Author(s).