治疗后十二个月的参数在预测慢性乙型肝炎患者的肝细胞癌

StephenW

Twelve-month post-treatment parameters are superior in predicting hepatocellular carcinoma in patients with chronic hepatitis B
Sang Bong Ahn  1 , Jun Choi  2 , Dae Won Jun  3 , Hyunwoo Oh  4 , Eileen L Yoon  5 , Hyoung Su Kim  6 , Soung Won Jeong  7 , Sung Eun Kim  8 , Jae-Jun Shim  9 , Yong Kyun Cho  10 , Hyo Young Lee  1 , Sung Won Han  11 , Mindie H Nguyen  12 , SAINT cohort
Affiliations
Affiliations

    1
    Department of Internal Medicine, Nowon Eulji Medical Center, Eulji University College of Medicine, Seoul.
    2
    Department of Fusion Data Analytics, School of Industrial Management Engineering, Korea University, Seoul.
    3
    Department of Internal Medicine, Hanyang University, College of Medicine, Seoul.
    4
    Department of Internal Medicine and Liver Research Institute, Seoul National University College of Medicine, Seoul.
    5
    Department of Internal Medicine, Sanggye Paik Hospital, Inje University College of Medicine, Seoul.
    6
    Department of Internal Medicine, Kangdong Sacred Heart Hospital, Hallym University College of Medicine, Seoul.
    7
    Department of Internal Medicine, Soonchunhyang University College of Medicine, Soonchunhyang University Seoul Hospital, Seoul.
    8
    Department of Internal Medicine, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang-si.
    9
    Department of Internal Medicine, Kyung Hee University School of Medicine, Seoul.
    10
    Department of Internal Medicine, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul.
    11
    Department of Biostatistical Consulting and Research Lab, School of Medicine, Korea University, Seoul.
    12
    Division of Gastroenterology and Hepatology, Stanford University Medical Center, Palo Alto, California, USA.

    PMID: 33550661 DOI: 10.1111/liv.14820

Abstract

Background & aims: There are currently several prediction models for hepatocellular carcinoma (HCC) in chronic hepatitis B (CHB) receiving oral antiviral therapy. However, most models are based on pre-treatment clinical parameters. The current study aimed to develop a novel and practical prediction model for HCC by using both pre- and post-treatment parameters in this population.

Methods: We included two treatment-naïve CHB cohorts who were initiated on oral antiviral therapies: the derivation cohort (n=1,480, Korea prospective SAINT cohort) and the validation cohort (n=426, the US retrospective Stanford Bay cohort). We employed logistic regression, decision tree, lasso regression, support vector machine, and random forest algorithms to develop the HCC prediction model and selected the most optimal method.

Results: We evaluated both pre-treatment and the 12-month clinical parameters on-treatment and found the 12-month on-treatment values to have superior HCC prediction performance. The lasso logistic regression algorithm using the presence of cirrhosis at baseline and alpha-fetoprotein and platelet at 12 months showed the best performance (AUROC=0.843 in the derivation cohort. The model performed well in the external validation cohort (AUROC=0.844) and better than other existing prediction models including the APA, PAGE-B, and GAG models (AUROC=0.769 to 0.818).

Conclusions: We provided a simple-to-use HCC prediction model based on presence of cirrhosis at baseline and two objective laboratory markers (AFP and platelets) measured 12 months after antiviral initiation. The model is highly accurate with excellent validation in an external cohort from a different country (AUROC 0.844). (Clinical trial number: KCT0003487).

Keywords: Antiviral agent; Hepatocellular carcinoma; Prediction model.

This article is protected by copyright. All rights reserved.

StephenW

治疗后十二个月的参数在预测慢性乙型肝炎患者的肝细胞癌方面具有优越性
Sang Bong Ahn 1，Jun Choi 2，Dae Won Jun 3，Hyunwoo Oh 4，Eileen L Yoon 5，Hyoung Su Kim 6，Soung Won Jeong 7，Sung Eun Kim 8，Jae-Jun Shim 9，Yong Kyun Cho 10，Hyo李英1，宋元翰11，敏迪·阮12，圣马丁
隶属关系
隶属关系

    1个
    首尔尤尔吉尔大学医学院诺顿尤尔吉医学中心内科。
    2
    首尔高丽大学工业管理工程学院融合数据分析系。
    3
    汉阳大学医学院内科，首尔。
    4
    首尔国立大学医学院内科与肝脏研究所，首尔。
    5
    首尔仁济大学医学院Sanggye Paik医院内科。
    6
    首尔哈里姆大学医学院康东圣心医院内科。
    7
    淳春市大学医学院内科，淳春市大学首尔医院，首尔。
    8
    哈里姆大学医学院附属哈里姆大学圣心医院内科，安阳市。
    9
    首尔庆熙大学医学院内科。
    10
    首尔成均馆大学医学院江北三星医院内科。
    11
    首尔高丽大学医学院生物统计学咨询与研究实验室系。
    12
    美国加利福尼亚州帕洛阿尔托市斯坦福大学医学中心消化内科和肝病科。

    PMID：33550661 DOI：10.1111 / liv.14820

抽象

背景与目的：目前有几种接受口服抗病毒治疗的慢性乙型肝炎（CHB）肝细胞癌（HCC）预测模型。但是，大多数模型都基于治疗前的临床参数。当前的研究旨在通过在该人群中使用治疗前和治疗后的参数，为肝癌建立一个新颖实用的预测模型。

方法：我们包括两个最初接受口服抗病毒治疗的初次CHB队列：衍生队列（n = 1,480，韩国前瞻性SAINT队列）和验证队列（n = 426，美国回顾性斯坦福湾队列）。我们采用逻辑回归，决策树，套索回归，支持向量机和随机森林算法来开发HCC预测模型，并选择最佳方法。

结果：我们评估了治疗前和治疗后12个月的临床参数，发现治疗12个月的值具有出色的HCC预测性能。使用基线存在肝硬化，甲胎蛋白和血小板存在12个月的套索逻辑回归算法显示了最佳性能（AUROC = 0.843），该模型在外部验证队列中表现良好（AUROC = 0.844），并且效果更好与其他现有的预测模型（包括APA，PAGE-B和GAG模型）相比（AUROC = 0.769至0.818）。

结论：我们提供了一个简单易用的HCC预测模型，该模型基于基线时是否存在肝硬化以及抗病毒启动后12个月测量的两个客观实验室指标（AFP和血小板）。该模型具有很高的准确性，并且在来自不同国家的外部队列中具有出色的验证性（AUROC 0.844）。 （临床试验编号：KCT0003487）。

关键词：抗病毒药；肝细胞癌；预测模型。

本文受版权保护。版权所有。