基于机器学习的个体化预测：干扰素抗病毒治疗后肝细胞癌发展的研究
Machine learning for individualized prediction of hepatocellular carcinoma development after the eradication of hepatitis C virus with antivirals.
发表日期：2023 Jun 24
作者：
Tatsuya Minami, Masaya Sato, Hidenori Toyoda, Satoshi Yasuda, Tomoharu Yamada, Takuma Nakatsuka, Kenichiro Enooku, Hayato Nakagawa, Hidetaka Fujinaga, Masashi Izumiya, Yasuo Tanaka, Motoyuki Otsuka, Takamasa Ohki, Masahiro Arai, Yoshinari Asaoka, Atsushi Tanaka, Kiyomi Yasuda, Hideaki Miura, Itsuro Ogata, Toshiro Kamoshida, Kazuaki Inoue, Ryo Nakagomi, Masatoshi Akamatsu, Hiroshi Mitsui, Hajime Fujie, Keiji Ogura, Koji Uchino, Hideo Yoshida, Kazuyuki Hanajiri, Tomonori Wada, Kiyohiko Kurai, Hisato Maekawa, Yuji Kondo, Shuntaro Obi, Takuma Teratani, Naohiko Masaki, Kayo Nagashima, Takashi Ishikawa, Naoya Kato, Hiroshi Yotsuyanagi, Kyoji Moriya, Takashi Kumada, Mitsuhiro Fujishiro, Kazuhiko Koike, Ryosuke Tateishi
来源：
Disease Models & Mechanisms
摘要：
在达到持续病毒学应答（SVR）后，准确的肝细胞癌（HCC）风险分层对于最佳的监测是必需的。我们旨在开发和验证一个机器学习（ML）模型，以预测个体患者在达到SVR后的HCC风险。在这个多中心队列研究中，纳入了1742例达到SVR的慢性丙型肝炎患者。开发了五个ML模型，包括DeepSurv模型、梯度提升生存分析、随机生存森林(RSF)、生存支持向量机和传统的Cox比例风险模型。使用Harrel' c指数评估模型性能，并在一个独立队列（977例患者）中进行外部验证。在平均5.4年的观察期内，122例患者发生了HCC（83例于衍生队列，39例于外部验证队列）。RSF模型在达到SVR时使用了七个参数，显示出最佳的判别能力，外部验证队列的c指数为0.839，当将患者分为三个风险组时，显示出很高的判别能力（P <0.001）。此外，该RSF模型还能为每位患者生成HCC发生的个体化预测曲线，并可在网上使用的应用程序中获得。我们开发并进行了外部验证了一个具有良好预测性能的RSF模型，用于SVR后HCC的风险。这一创新模型的应用已经在网站上实现。该模型能够提供数据，以考虑有效的监测方法。进一步的研究有待于为每个国家的医疗情况量身定制监测策略的建议。利用机器学习算法，我们开发了一种新型的预测模型，用于预测丙型肝炎病毒清除后患者的HCC发生。该模型使用了七个常见的测量参数，已经显示出良好的HCC发展预测能力，并可以提供个性化的监测系统。版权所有©2023欧洲肝病学研究协会。由Elsevier B.V.出版，保留所有权利。
Accurate risk stratification for hepatocellular carcinoma (HCC) after achieving a sustained viral response (SVR) is necessary for optimal surveillance. We aimed to develop and validate a machine learning (ML) model to predict the risk of HCC after achieving an SVR in individual patients.In this multicenter cohort study, 1742 patients with chronic hepatitis C who achieved an SVR were enrolled. Five ML models were developed including DeepSurv, gradient boosting survival analysis, random survival forest (RSF), survival support vector machine, and a conventional Cox proportional hazard model. Model performance was evaluated using Harrel' c-index and was externally validated in an independent cohort (977 patients).During the mean observation period of 5.4 years, 122 patients developed HCC (83 in the derivation cohort and 39 in the external validation cohort). The RSF model showed the best discrimination ability using seven parameters at the achievement of an SVR with a c-index of 0.839 in the external validation cohort and a high discriminative ability when the patients were categorized into three risk groups (P <0.001). Furthermore, this RSF model enabled the generation of an individualized predictive curve for HCC occurrence for each patient with an app available online.We developed and externally validated an RSF model with good predictive performance for the risk of HCC after an SVR. The application of this novel model is available on the website. This model could provide the data to consider an effective surveillance method. Further studies are needed to make recommendations for surveillance policies tailored to the medical situation in each country.A novel prediction model for HCC occurrence in patients after hepatitis C virus eradication was developed using machine learning algorithms. This model, using seven commonly measured parameters, has been shown to have a good predictive ability for HCC development and could provide a personalized surveillance system.Copyright © 2023 European Association for the Study of the Liver. Published by Elsevier B.V. All rights reserved.