肝细胞癌综合机器学习框架下的新型预后相关签名

Aug 5, 2026

Upload by Noah

Hepatocellular carcinoma (HCC) remains highly aggressive, with delayed diagnosis and limited prognostic models that reliably support clinicians. This study develops an HCC prognosis-related gene signature (HPRGS) by integrating transcriptomic evidence and multiple machine-learning methods. TCGA-LIHC is used for training, while independent cohorts and a cDNA microarray serve for validation. The resulting four-gene model (SOCS2, LCAT, ECT2, TMEM106C) demonstrates robust discrimination of overall survival risk groups and links risk status to differential treatment responses and therapy guidance via a clinical nomogram.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages21

Reading Time53 min

AccessFree to download

Background

Methods

Results

Conclusion

Introduction

TYPE Original Research PUBLISHED 24 September 2024 DOI 10.3389/fimmu.2024.1454977 OPEN ACCESS EDITED BY Qiang Wang, Houston Methodist Research Institute, United States REVIEWED BY Xiaoyu Lin, Harbin Institute of Technology, China Yongqiang Zhang, Guangzhou Medical University, China *CORRESPONDENCE Zhenhua Liu [liuzhenhua6909@163.com](liuzhenhua6909@163.com)[ ](liuzhenhua6909@163.com)Lihu Lu [623778291@qq.com](623778291@qq.com)[ ](623778291@qq.com)Jingbo Chen [13635294192@163.com](13635294192@163.com) †These authors have contributed equally to this work RECEIVED 26 June 2024 ACCEPTED 05 September 2024 PUBLISHED 24 September 2024 CITATION Zheng S, Su Z, He Y, You L, Zhang G, Chen J, Lu L and Liu Z (2024) Novel prognostic signature for hepatocellular carcinoma using a comprehensive machine learning framework to predict prognosis and guide treatment. Front. Immunol. 15:1454977 . doi: 10.3389/fimmu.2024.1454977 COPYRIGHT © 2024 Zheng, Su, He, You, Zhang, Chen, Lu and Liu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Novel prognostic signature for hepatocellular carcinoma using a comprehensive machine learning framework to predict prognosis and guide treatment Shengzhou Zheng 1,2†, Zhixiong Su 2†, Yufang He 2†, Lijie You 2†, Guifeng Zhang 2, Jingbo Chen 2*, Lihu Lu 3* and Zhenhua Liu 2* 1 Department of Emergency, Fujian Medical University Union Hospital, Fuzhou, China, 2 Department of Oncology, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou University Afﬁliated Provincial Hospital, Fuzhou, Fujian, China, 3 Department of Radiation Oncology, Fujian Medical University Union Hospital, Fuzhou, China Background: Hepatocellular carcinoma (HCC) is highly aggressive, with delayed diagnosis, poor prognosis, and a lack of comprehensive and accurate prognostic models to assist clinicians. This study aimed to construct an HCC prognosisrelated gene signature (HPRGS) and explore its clinical application value. Methods: TCGA-LIHC cohort was used for training, and the LIRI-JP cohort and HCC cDNA microarray were used for validation. Machine learning algorithms constructed a prognostic gene label for HCC. Kaplan–Meier (K-M), ROC curve, multiple analyses, algorithms, and online databases were used to analyze differences between high- and low-risk populations. A nomogram was constructed to facilitate clinical application. Results: We identiﬁed 119 differential genes based on transcriptome sequencing data from ﬁve independent HCC cohorts, and 53 of these genes were associated with overall survival (OS) . Using 101 machine learning algorithms, the 10 most prognostic genes were selected. We constructed an HCC HPRGS with four genes (SOCS2, LCAT, ECT2, and TMEM106C) . Good predictive performance of the HPRGS was conﬁrmed by ROC, C-index, and K-M curves. Mutation analysis showed signiﬁcant differences between the low- and high-risk patients. The low-risk group had a higher response to transcatheter arterial chemoembolization (TACE) and immunotherapy. Treatment response of highand low-risk groups to small-molecule drugs was predicted. Linifanib was a Frontiers in Immunology 01 [frontiersin.org](frontiersin.org) potential drug for high-risk populations. Multivariate analysis conﬁrmed that HPRGS were independent prognostic factors in TCGA-LIHC. A nomogram provided a clinical practice reference. Conclusion: We constructed an HPRGS for HCC, which can accurately predict OS and guide the treatment decisions for patients with HCC. KEYWORDS hepatoce

FAQs

What problem does this study address in hepatocellular carcinoma?

The study targets the lack of comprehensive and accurate prognostic models for HCC, given its aggressiveness, delayed diagnosis, and poor outcomes.

How is the HCC prognosis-related gene signature constructed?

It uses the TCGA-LIHC cohort for training, validates with independent cohorts and a cDNA microarray, applies multiple machine-learning algorithms to select prognostic genes, and builds a four-gene HPRGS.

What clinical value does the HPRGS provide?

The HPRGS predicts overall survival, differentiates low- vs high-risk populations, and supports treatment decision-making, including associations with responses to TACE, immunotherapy, and prediction of small-molecule drug responses.

Aug 5, 2026

Upload by Noah