EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudieOpen Access · CC BY-NC-ND 4.0

An XGBoost ‐Based Multicenter Model for Predicting HBV ‐Related Hepatocellular Carcinoma: Development and Validation

Yong Lin iD, Hai-Yan Zhuo, Hui-Wen Song, Li-Na Zhou, Mei-Zhu Hong, Chun Lin, Peng-Fei Guo, Jin-Shui Pan

Cancer Medicine · 2026-05 · 15 (5)

DOI: 10.1002/cam4.71887 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Cancer Medicine, online erschienen am 24.04.2026. Verfasst von Yong Lin und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Hepatology, the First Affiliated Hospital of Fujian Medical University, Fuzhou, China. Hauptthemen laut MEDLINE: Liver Neoplasms, Carcinoma, Hepatocellular, Hepatitis B, Hepatitis B, Chronic. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Fujian Province Natural Science Foundation of China, Fujian Provincial Traditional Chinese Medicine Science and Technology Program, Integrated Chinese and Western Medicine "Flagship" Department (Construction Project) of National Health Commission of the People's Republic of China and Nation….

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The 5‐year survival rate for hepatocellular carcinoma (HCC) is stage‐dependent, yet existing models lack accuracy in predicting hepatitis B virus‐associated HCC (HBV‐HCC). We therefore aimed to develop and validate an interpretable machine learning (ML) model integrating multidimensional biomarkers for HBV‐HCC risk stratification.

Methods

This retrospective multicenter study included 3568 participants (1872 HBV‐infected and 1696 HBV‐HCC). Patients from Mengchao Hepatobiliary Hospital were divided into training and validation sets (3:1 ratio), while those from Eastern Hepatobiliary Surgery Hospital and the First Affiliated Hospital of Xiamen University formed the external validation set. Five key predictors were identified through random forest, LASSO regression, and XGBoost methods. Seven ML models were evaluated using area under the curve (AUC), sensitivity, specificity, accuracy, and F 1‐score, with the top model compared against previous models (GALAD, C‐GALAD, C‐GALAD II, and ASAP).

Results

Key predictors were log 10 DCP (mean SHAP value 1.784), log 10 HBVDNA (1.063), log 10 ALT (0.753), AFP‐L3% (0.444), and log 10 AFP (0.392). The XGBoost model achieved AUCs of 0.985 (95% CI: 0.981–0.989) in the training set, 0.978 (0.969–0.987) in the validation set, and 0.942 (0.911–0.973) in the external validation set. XGBoost significantly outperformed previous models in both the training and validation sets (DeLong test; p < 0.001). In the external validation set, XGBoost demonstrated superior individualized risk prediction accuracy (IDI = 0.228), net clinical benefit, calibration, and high‐risk patient identification compared to the ASAP model. An interactive web tool was developed to facilitate clinical implementation.

Conclusions

We developed a novel diagnostic model for HBV‐HCC that demonstrates higher accuracy in identifying HBV‐HCC compared to existing models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Liver NeoplasmsCarcinoma, HepatocellularHepatitis BHepatitis B, ChronicHumansBoosting Machine Learning AlgorithmsRetrospective StudiesFemaleMaleHepatitis B virusMiddle AgedPredictive Learning ModelsPrognosisRisk AssessmentBiomarkers, Tumor

Stichwörter der Autor:innen

hepatitis B virushepatocellular carcinomamachine learningpredictive model

Substanzen

Biomarkers, Tumor

Autor:innen und Institutionen

  • Department of Hepatology, the First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
  • Department of Hepatology, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou, China.
  • Department of Infectious Diseases, Sanming First Hospital Affiliated With Fujian Medical University, Sanming, China.
  • Department of Integrated Traditional Chinese and Western Medicine, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou, China.
  • The Big Data Institute of Southeast Hepatobiliary Health Information, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou, China.
  • Hepatology Research Institute, Fujian Medical University, Fuzhou, China.

ORCID-Profile: Yong Lin

Förderung

  • Fujian Province Natural Science Foundation of China
  • Fujian Provincial Traditional Chinese Medicine Science and Technology Program
  • Integrated Chinese and Western Medicine "Flagship" Department (Construction Project) of National Health Commission of the People's Republic of China and Nation…

Zitieren

APA

Lin, Y., Zhuo, H. Y., Song, H. W., Zhou, L. N., Hong, M. Z., Lin, C., Guo, P. F., & Pan, J. S. (2026). An XGBoost ‐Based Multicenter Model for Predicting HBV ‐Related Hepatocellular Carcinoma: Development and Validation. Cancer Medicine, 15(5). https://doi.org/10.1002/cam4.71887

Vancouver

Lin Y, Zhuo HY, Song HW, Zhou LN, Hong MZ, Lin C, et al. An XGBoost ‐Based Multicenter Model for Predicting HBV ‐Related Hepatocellular Carcinoma: Development and Validation. Cancer Medicine. 2026;15(5). doi:10.1002/cam4.71887

BibTeX
@article{Lin2026,
  author = {Lin, Yong and Zhuo, Hai-Yan and Song, Hui-Wen and Zhou, Li-Na and Hong, Mei-Zhu and Lin, Chun and Guo, Peng-Fei and Pan, Jin-Shui},
  title = {An XGBoost ‐Based Multicenter Model for Predicting HBV ‐Related Hepatocellular Carcinoma: Development and Validation},
  journal = {Cancer Medicine},
  year = {2026},
  volume = {15},
  number = {5},
  doi = {10.1002/cam4.71887}
}
Kostenlos starten →