Document is current
Any future updates will be listed below
-
Authors
Zeng, Fanrui
Wang, Bo
Peng, Minhua https://orcid.org/0000-0003-3289-8890
Tao, Jinsheng
Tu, Xixiang
Lu, Hongbo
Qiu, Xiangcheng
Yang, Yang
Wang, Wenyang
Zeng, Meng
Fan, Jian-bing
Zeng, Qingsi
Liu, Qin
-
Funding
Funding for this research was provided by:
Leading Projects of Guangzhou Municipal Health Sciences Foundation (No. 20211A01172)
Guangdong Basic and Applied Basic Research Foundation (No. 2020A1515011454)
National Natural Science Foundation of China (No. 81902311)
Youth and Middle-aged Scientific and Technological Innovation Leading Talents Program of the Corps (No. 2017-L152)
Scheme of Guangzhou for Leading Team in Innovation (201909010010)
Science and Technology Planning Project of Guangzhou (No. 202206080013)
- License Information
-
More Information
Article History
Received: 30 October 2025
Revised: 26 January 2026
Accepted: 9 February 2026
First Online: 14 March 2026
Compliance with ethical standards
:
: The scientific guarantor of this publication is Qin Liu, from The First Affiliated Hospital of Guangzhou Medical University.
: The authors Bo Wang, Minhua Peng, Jinsheng Tao, Xixiang Tu, Hongbo Lu, Xiangcheng Qiu, Yang Yang, and Jian-bing Fan are current employees of AnchorDx Medical Co., Ltd. All authors declare no competing financial interest.
: One of the authors (Xixiang Tu) has significant statistical expertise.
: Written informed consent was obtained from all subjects (patients) in this study.
: Institutional Review Board approval was obtained.
: The 1056 cases in study NCT03181490 were previously reported in two references, and we established a model based on blood ctDNA methylation and a CIBM model incorporating nine clinical features and 58 CT radiological features. In our current research, we utilized a human reading model that also originated from the 58 clinical and radiological features described in the previous study, but was refined to include only 1 clinical feature and 25 radiological features. The key distinction of our study lies in the incorporation of radiomics features for predictive modeling and the development of a hybrid model that combines radiomics with the human reading model. [1] Liang W, Chen Z, Li C et al [ ]; . [2] He et al [ ]; .
:
