Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 31 min ago
Peer-reviewedCC BY 4.0Frontiers in Public Health

Machine learning-based prediction of HCV-related cirrhosis and the exploratory analysis of drug use influence

  • Shuanglin Gu1
  • Lingling Ye2
  • Jiasheng Tang3
  • Wenxian Qian1
  • Zheng Hu1
  • Xiuchang Ma1
  • Apeng Chen4
  • Qin Zheng5
  • Lei Wang6
  • Guoping Yin2
  • Changhua Yi1
6 affiliations
  1. 1Department of Clinical Research Center, The Second Hospital of Nanjing, Affiliated to Nanjing University of Chinese Medicine
  2. 2Department of Anesthesiology, The Second Hospital of Nanjing, Affiliated to Nanjing University of Chinese Medicine
  3. 3The Second Hospital of Nanjing, Affiliated to Nanjing University of Chinese Medicine
  4. 4Nanjing Key Laboratory of Pediatrics, Children’s Hospital of Nanjing Medical University
  5. 5Department of Oncology, The Second Hospital of Nanjing, Affiliated to Nanjing University of Chinese Medicine
  6. 6Department of Hepatology, The Second Hospital of Nanjing, Affiliated to Nanjing University of Chinese Medicine
Read full textPDFDOICite

Abstract

Introduction: Chronic hepatitis C virus (HCV) infection easily progresses to liver cirrhosis, and drug users represent a special high-risk population with accelerated liver damage and insufficient early screening strategies.

Methods: This study aimed to develop a machine learning model for identifying HCV-related cirrhosis, with stratified analysis between drug-using and non-drug-using subgroups. We enrolled patients with chronic HCV infection and collected blood routine, liver function, lymphocyte subsets, and drug use data.

Results: Among the seven models compared, the XGBoost model achieved the best performance, with an AUC of 0.86 on the test set. Stratified analysis showed significantly better predictive performance in drug users (AUC = 0.87) than in non-drug users (AUC = 0.72, p < 0.05). Drug use did not independently improve model performance and showed significant interactions with only a limited number of key features (e.g., ADA). SHAP and decision curve analysis validated the model’s reliability and clinical benefit, especially in drug users.

Discussion: The XGBoost model enables noninvasive and accurate cirrhosis prediction and is suitable for early screening in high-risk drug-using populations.

Related

  1. Explainable machine learning–based prediction of postoperative pulmonary infection after aneurysmal subarachnoid hemorrhage clipping and exploratory analysis of enteral nutrition timing: a dual-cohort retrospective study
    Lin Li, Xiang Li, Shufang Shi
    Frontiers in neurologyPeer-reviewedCC BYFull textNeurologyEurope PMCCrossref
  2. Machine learning-based risk prediction for invasive pulmonary aspergillosis in non-neutropenic intensive care unit patients, with an exploratory analysis of pathogen-related risk factors.
    Jijia Bai, Tao Feng, Bofei Liu +4
    Frontiers in cellular and infection microbiologyPeer-reviewedCC BYFull textInfectious diseaseEurope PMCPMC
  3. Development and validation of an interpretable machine learning model for predicting in-hospital mortality among critically ill patients with liver cirrhosis
    Fengjie Guo, Shijie Zhong, Yang Tan +6
    Scientific ReportsPeer-reviewedCC BYFull text1 citedGeneral medicineDOAJ
  4. Machine learning model for ACLF risk in decompensated cirrhosis.
    Liwen Chen, Peipei Ren, Yi Kang
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  5. CT Radiomics and Machine Learning for Three-Class Bone Density Classification: An Exploratory Comparison Across Lumbar Vertebral Levels
    Asiye Sozeri, Halitcan Batur, Nurdan Cay
    TomographyPeer-reviewedCC BYFull textMedical imaging & radiologyEurope PMC

Cite

BibTeXRIS
BibTeX
@article{gu2026machine,
  title = {{Machine learning-based prediction of HCV-related cirrhosis and the exploratory analysis of drug use influence}},
  author = {Shuanglin Gu and Lingling Ye and Jiasheng Tang and Wenxian Qian and Zheng Hu and Xiuchang Ma and Apeng Chen and Qin Zheng and Lei Wang and Guoping Yin and Changhua Yi},
  journal = {Frontiers in Public Health},
  year = {2026},
  month = oct,
  doi = {10.3389/fpubh.2026.1980930},
  url = {https://www.frontiersin.org/articles/10.3389/fpubh.2026.1980930/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Machine learning-based prediction of HCV-related cirrhosis and the exploratory analysis of drug use influence
AU  - Shuanglin Gu
AU  - Lingling Ye
AU  - Jiasheng Tang
AU  - Wenxian Qian
AU  - Zheng Hu
AU  - Xiuchang Ma
AU  - Apeng Chen
AU  - Qin Zheng
AU  - Lei Wang
AU  - Guoping Yin
AU  - Changhua Yi
PY  - 2026
DA  - 2026/10/13
JO  - Frontiers in Public Health
DO  - 10.3389/fpubh.2026.1980930
UR  - https://www.frontiersin.org/articles/10.3389/fpubh.2026.1980930/full
AB  - Introduction: Chronic hepatitis C virus (HCV) infection easily progresses to liver cirrhosis, and drug users represent a special high-risk population with accelerated liver damage and insufficient early screening strategies.  Methods: This study aimed to develop a machine learning model for identifying HCV-related cirrhosis, with stratified analysis between drug-using and non-drug-using subgroups. We enrolled patients with chronic HCV infection and collected blood routine, liver function, lymphocyte subsets, and drug use data.  Results: Among the seven models compared, the XGBoost model achieved the best performance, with an AUC of 0.86 on the test set. Stratified analysis showed significantly better predictive performance in drug users (AUC = 0.87) than in non-drug users (AUC = 0.72, p < 0.05). Drug use did not independently improve model performance and showed significant interactions with only a limited number of key features (e.g., ADA). SHAP and decision curve analysis validated the model’s reliability and clinical benefit, especially in drug users.  Discussion: The XGBoost model enables noninvasive and accurate cirrhosis prediction and is suitable for early screening in high-risk drug-using populations.
SN  - 2296-2565
ER  -