Publishing Service

Polishing & Checking

Journal of Zhejiang University SCIENCE B

ISSN 1673-1581(Print), 1862-1783(Online), Monthly

Development and validation of a risk-prediction model for immune-related adverse events in patients with non-small-cell lung cancer receiving PD-1/PD-L1 inhibitors

Abstract: Lung cancer remains the leading cause of cancer deaths worldwide and is the most common cancer in males. Immune-checkpoint inhibitors (ICIs) that target programmed cell death protein-1 (PD-1) or programmed cell death-ligand 1 (PD-L1) have achieved impressive efficacy in the treatment of non-small-cell lung cancer (NSCLC) (Pardoll, 2012; Champiat et al., 2016; Gao et al., 2022). Although ICIs are usually well tolerated, they are often accompanied by immune-related adverse events (irAEs) (Doroshow et al., 2019). Non-specific activation of the immune system produces off-target immune and inflammatory responses that can affect virtually any organ or system (O'Kane et al., 2017; Puzanov et al., 2017). Compared with adverse events caused by chemotherapy, irAEs are often characterized by delayed onset and prolonged duration and can occur in any organ at any stage of treatment, including after cessation of treatment (Puzanov et al., 2017; von Itzstein et al., 2020). They range from rash, pneumonitis, hypothyroidism, enterocolitis, and autoimmune hepatitis to cardiovascular, hematological, renal, neurological, and ophthalmic irAEs (Nishino et al., 2016; Kumar et al., 2017; Song et al., 2020). Hence, we conducted a retrospective study to identify validated factors that could predict the magnitude of the risk of irAEs in patients receiving PD-1/PD-L1 inhibitors; our approach was to analyze the correlation between the clinical characteristics of patients at the start of treatment and relevant indicators such as hematological indices and the risk of developing irAEs. Then, we developed an economical, practical, rapid, and simple model to assess the risk of irAEs in patients receiving ICI treatment, as early as possible.

Key words: Non-small cell lung cancer; PD-1/PD-L1 inhibitor; Immune-related adverse events; Systemic immune-inflammation index; Body mass index; Age

Chinese Summary  <10> 无监督域自适应的动态参数化学习

蒋润华1,2,韩亚洪1,2
1天津大学智能与计算学部,中国天津市,300350
2天津大学天津市机器学习重点实验室,中国天津市,300350
摘要:无监督领域自适应通过学习域不变表示实现神经网络从有标签数据组成的源域到无标签数据组成的目标域迁移。近期研究通过直接匹配这两个域的边缘分布实现这一目标。然而,已有研究大多数忽略域对齐和语义判别学习之间的动态平衡,因此容易受负迁移和异常样本影响。为解决这些问题,引入动态参数化学习框架。首先,通过探索领域级语义知识,提出动态对齐参数自适应地调整域对齐和语义判别学习的优化过程。此外,为获得判别能力强和域不变的表示,提出在源域和目标域上对齐优化过程。本文通过综合实验证明了所提出方法的有效性,并在3个视觉任务的7个数据集上进行广泛比较,证明可行性。

关键词组:无监督领域自适应;优化步骤;跨域判别表示;语义判别


Share this article to: More

Go to Contents

References:

<Show All>

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





DOI:

10.1631/jzus.B2200631

CLC number:

Download Full Text:

Click Here

Downloaded:

468

Download summary:

<Click Here> 

Downloaded:

169

Clicked:

639

Cited:

0

On-line Access:

2023-06-26

Received:

2022-12-07

Revision Accepted:

2023-04-20

Crosschecked:

2023-09-26

Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952276; Fax: +86-571-87952331; E-mail: jzus@zju.edu.cn
Copyright © 2000~ Journal of Zhejiang University-SCIENCE