EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Comparison of machine learning and Cox regression models for prognostic analysis in hepatocellular carcinoma patients with distant metastasis

Hailan Li, Junbo Wang, Xin Ming, Mingsha Zhou, Li Zhou

Surgery Open Science · 2025-09 · 27 · 36-44

DOI: 10.1016/j.sopen.2025.06.007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Surgery Open Science, 2025-09. Verfasst von Hailan Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Epidemiology, School of Public Health, Chongqing Medical University, Chongqing, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Science Foundation Project of Chongqing, Natural Science Foundation of Chongqing Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

With the development of conversion therapy, there has been a significant improvement in advanced stage hepatocellular carcinoma (HCC) patients' survival outcomes. Accurate prognostic assessment of patients with distant metastasis (DM) is therefore pivotal in improving quality of life, guiding treatment, and optimizing patient management.

Methods

This study extracted patients with distant metastatic HCC from the Surveillance, Epidemiology, and End Results database. Univariate and multivariate Cox regression were used to identify prognostic factors. Then, Cox regression, DeepSurv, Decision Tree, and Random Survival Forests models were used to predict overall survival. Model performance was evaluated by area under the curve (AUC), decision curve analysis, calibration curve, and Brier score. The visualization of Cox regression and machine learning algorithms utilized nomogram and Shapley additive explanations, respectively.

Results

The study included 3051 HCC patients with DM. Factors such as tumor size, lung metastasis, N stage, ace, chemotherapy, radiotherapy, AFP, fibrosis, treatment interval, and number of metastases were independently associated with patient prognosis. Among all models, Cox regression and Random Survival Forest models showed stable performance, achieving AUCs of 0.746/0.760, 0.745/0.749, and 0.729/0.718 at 3, 6, and 12 months, respectively. Meanwhile, Cox regression showed the lowest Brier score (0.180 and 0.125) at 6 and 12 months.

Conclusions

Cox regression and Random Survival Forest models demonstrated robust prognostic performance for HCC, with Cox regression exhibiting superior temporal stability. The Cox-based nomogram provides an intuitive tool for rapid 3-, 6-, and 12-month survival stratification in metastatic HCC patients.

Schlagwörter

Stichwörter der Autor:innen

Distant metastasisHepatocellular carcinomaMachine learningNomogram

Autor:innen und Institutionen

  • Department of Epidemiology, School of Public Health, Chongqing Medical University, Chongqing, China.
  • Women and Children's Hospital of Chongqing Medical University, Chongqing, China.
  • Chongqing Health Center for Women and Children, Chongqing, China.

Förderung

  • Natural Science Foundation Project of Chongqing
  • Natural Science Foundation of Chongqing Municipality

Zitieren

APA

Li, H., Wang, J., Ming, X., Zhou, M., & Zhou, L. (2025). Comparison of machine learning and Cox regression models for prognostic analysis in hepatocellular carcinoma patients with distant metastasis. Surgery Open Science, 27, 36-44. https://doi.org/10.1016/j.sopen.2025.06.007

Vancouver

Li H, Wang J, Ming X, Zhou M, Zhou L. Comparison of machine learning and Cox regression models for prognostic analysis in hepatocellular carcinoma patients with distant metastasis. Surgery Open Science. 2025;27:36-44. doi:10.1016/j.sopen.2025.06.007

BibTeX
@article{Li2025,
  author = {Li, Hailan and Wang, Junbo and Ming, Xin and Zhou, Mingsha and Zhou, Li},
  title = {Comparison of machine learning and Cox regression models for prognostic analysis in hepatocellular carcinoma patients with distant metastasis},
  journal = {Surgery Open Science},
  year = {2025},
  volume = {27},
  pages = {36--44},
  doi = {10.1016/j.sopen.2025.06.007}
}
Kostenlos starten →