使用机器学习识别免疫特征的先导研究，用于预测在终止HBeAg

StephenW

Pilot Study Using Machine Learning to Identify Immune Profiles for the Prediction of Early Virological Relapse After Stopping Nucleos(t)ide Analogues in HBeAg-Negative CHB
Maximilian Wübbolding  1   2   3 , Juan Carlos Lopez Alfonso  2   4 , Chun-Yen Lin  5   6 , Sebastian Binder  2   4 , Christine Falk  7 , Jennifer Debarry  2   8 , Paul Gineste  9 , Anke R M Kraft  1   2   3 , Rong-Nan Chien  5   6   10 , Benjamin Maasoumy  1 , Heiner Wedemeyer  1   3 , Wen-Juei Jeng  5   6 , Michael Meyer Hermann  2   4   11 , Markus Cornberg  1   2   3   8 , Christoph Höner Zu Siederdissen  1
Affiliations
Affiliations

    1
    Department of Gastroenterology, Hepatology, and Endocrinology Hannover Medical School Hannover Germany.
    2
    Centre for Individualised Infection Medicine a joint venture of Helmholtz Centre for Infection Research and Hannover Medical School Hannover Germany.
    3
    German Center for Infection Research Partner-Site Hannover-Braunschweig Hannover Germany.
    4
    Department of Systems Immunology and Braunschweig Integrated Centre of Systems Biology Helmholtz Centre for Infection Research Braunschweig Germany.
    5
    Department of Gastroenterology and Hepatology Chang Gung Memorial Hospital Linkou branch Taoyuan Taiwan.
    6
    College of Medicine Chang Gung University Taipei Taiwan.
    7
    Institute of Transplantation Immunology Hannover Medical School Hannover Germany.
    8
    TWINCORE a joint venture of Helmholtz Centre for Infection Research and Hannover Medical School Hannover Germany.
    9
    Abivax Paris France.
    10
    Liver Research Unit Chang Gung Memorial Hospital Linkou Taiwan.
    11
    Institute for Biochemistry, Biotechnology and Bioinformatics Technische Universität Braunschweig Braunschweig Germany.

    PMID: 33437904 PMCID: PMC7789842 DOI: 10.1002/hep4.1626

Free PMC article
Abstract

Treatment with nucleos(t)ide analogues (NAs) may be stopped after 1-3 years of hepatitis B virus DNA suppression in hepatitis B e antigen (HBeAg)-negative patients according to Asian Pacific Association for the Study of Liver and European Association for the Study of Liver guidelines. However, virological relapse (VR) occurs in most patients. We aimed to analyze soluble immune markers (SIMs) and use machine learning to identify SIM combinations as predictor for early VR after NA discontinuation. A validation cohort was used to verify the predictive power of the SIM combination. In a post hoc analysis of a prospective, multicenter therapeutic vaccination trial (ABX-203, NCT02249988), hepatitis B surface antigen, hepatitis B core antigen, and 47 SIMs were repeatedly determined before NA was stopped. Forty-three HBeAg-negative patients were included. To detect the highest predictive constellation of host and viral markers, a supervised machine learning approach was used. Data were validated in a different cohort of 49 patients treated with entecavir. VR (hepatitis B virus DNA ≥ 2,000 IU/mL) occurred in 27 patients. The predictive value for VR of single SIMs at the time of NA stop was best for interleukin (IL)-2, IL-17, and regulated on activation, normal T cell expressed and secreted (RANTES/CCL5) with a maximum area under the curve of 0.65. Hepatitis B core antigen had a higher predictive power than hepatitis B surface antigen but lower than the SIMs. A supervised machine-learning algorithm allowed a remarkable improvement of early relapse prediction in patients treated with entecavir. The combination of IL-2, monokine induced by interferon γ (MIG)/chemokine (C-C motif) ligand 9 (CCL9), RANTES/CCL5, stem cell factor (SCF), and TNF-related apoptosis-inducing ligand (TRAIL) was reliable in predicting VR (0.89; 95% confidence interval: 0.5-1.0) and showed viable results in the validation cohort (0.63; 0.1-0.99). Host immune markers such as SIMs appear to be underestimated in guiding treatment cessation in HBeAg-negative patients. Machine learning can help find predictive SIM patterns that allow a precise identification of patients particularly suitable for NA cessation.

© 2020 The Authors. Hepatology Communications published by Wiley Periodicals LLC on behalf of the American Association for the Study of Liver Diseases.

StephenW

使用机器学习识别免疫特征的先导研究，用于预测在终止HBeAg阴性CHB中的核苷酸类似物后的早期病毒学复发。
MaximilianWübbolding1 2 3，Juan Carlos Lopez Alfonso 2 4，Lin-Yen Lin 5 6，Sebastian Binder 2 4，Christine Falk 7，Jennifer Debarry 2 8，Paul Gineste 9，Anke RM Kraft 1 2 3，Rong-Nan Chien 5 6 10，本杰明·马苏米1，海纳·韦德迈尔1 3，简文瑞5 6，迈克尔·迈尔·赫尔曼2 4 11，马库斯·康伯格1 2 3 8，克里斯托弗·霍纳·祖西德迪森1
隶属关系
隶属关系

    1个
    德国汉诺威汉诺威医学院消化内科，肝内科和内分泌科。
    2
    个性化感染医学中心是亥姆霍兹感染研究中心和德国汉诺威汉诺威医学院的合资企业。
    3
    德国感染研究中心合作伙伴-汉诺威-不伦瑞克德国汉诺威。
    4
    系统免疫学系和不伦瑞克系统生物学综合中心亥姆霍兹感染研究中心德国不伦瑞克。
    5
    台湾桃园长庚纪念医院消化内科
    6
    台湾长庚大学医学院。
    7
    德国汉诺威汉诺威医学院移植免疫学研究所。
    8
    TWINCORE亥姆霍兹感染研究中心和德国汉诺威汉诺威医学院的合资企业。
    9
    Abivax法国巴黎。
    10
    台湾林口长庚纪念医院肝脏研究室。
    11
    德国不伦瑞克生物化学，生物技术和生物信息学研究所。

    PMID：33437904 PMCID：PMC7789842 DOI：10.1002 / hep4.1626

免费PMC文章
抽象

根据亚太肝病研究协会和欧洲肝炎学会的报告，在乙型肝炎e抗原（HBeAg）阴性患者中，乙型肝炎病毒DNA抑制1-3年后，可能会停止使用核苷酸类似物（NAs）进行治疗。肝研究指南。但是，大多数患者会发生病毒学复发（VR）。我们旨在分析可溶性免疫标记（SIM），并使用机器学习来识别SIM组合作为NA停用后早期VR的预测因子。验证队列用于验证SIM组合的预测能力。在一项前瞻性，多中心治疗性疫苗接种试验（ABX-203，NCT02249988）的事后分析中，在停止NA之前，反复测定了乙型肝炎表面抗原，乙型肝炎核心抗原和47个SIM。包括43例HBeAg阴性患者。为了检测宿主和病毒标记的最高预测星座，使用了监督式机器学习方法。在另一组接受恩替卡韦治疗的患者中验证了数据。 27例患者发生了VR（乙肝病毒DNA≥2,000 IU / mL）。 NA停止时单个SIM卡VR的预测值最适合白介素（IL）-2，IL-17，并受激活，正常T细胞表达和分泌（RANTES / CCL5）的调节，最大区域位于曲线为0.65。乙型肝炎核心抗原具有比乙型肝炎表面抗原更高的预测能力，但低于SIM。有监督的机器学习算法使恩替卡韦治疗的患者的早期复发预测显着改善。 IL-2，干扰素γ（MIG）/趋化因子（CC基序）配体9（CCL9），RANTES / CCL5，干细胞因子（SCF）和TNF相关凋亡诱导配体（TRAIL）诱导的单因子组合为在预测VR（0.89; 95％置信区间：0.5-1.0）方面可靠，在验证队列中显示可行的结果（0.63; 0.1-0.99）。在指导HBeAg阴性患者停止治疗中，宿主免疫标记（如SIM）似乎被低估了。机器学习可以帮助找到可预测的SIM模式，从而准确识别特别适合于NA戒断的患者。

©2020作者。 Wiley Periodicals LLC代表美国肝病研究协会出版的《肝病学通讯》。

StephenW

https://aasldpubs.onlinelibrary. ... t/10.1002/hep4.1626