Dalong Zhu,1,* Alimu Tulahong,1,* Abuduhaiwaier Abuduhelili,1,* Chang Liu,1 Ayinuer Aierken,1 Yanze Lin,1 Tiemin Jiang,1 Renyong Lin,2 Yingmei Shao,1 Tuerganaili Aji1 

1Department of Hepatobiliary and Echinococcosis Surgery, Digestive and Vascular Surgery Center, the First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, People’s Republic of China; 2State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Clinical Medical Research Institute, the First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Tuerganaili Aji, Department of Hepatobiliary and Echinococcosis Surgery, Digestive and Vascular Surgery Center, the First Affiliated Hospital of Xinjiang Medical University, 137 South Liyushan Road, Urumqi, Xinjiang Uygur Autonomous Region, 830054, People’s Republic of China, Fax +8609914364556, Email tuergan78@sina.com

Purpose: Primary liver cancer, predominantly hepatocellular carcinoma (HCC), constitutes a substantial global health challenge, characterized by a poor prognosis, particularly in regions with high prevalence of hepatitis B virus (HBV) infection, such as China. This study sought to develop and validate a machine learning-based prognostic model to predict survival outcomes in patients with HBV-related HCC following radical resection, with the potential to inform personalized treatment strategies.
Patients and Methods: This study retrospectively analyzed clinical data from 146 patients at Xinjiang Medical University and 75 patients from The Cancer Genome Atlas (TCGA) database. A prognostic model was developed using a machine learning algorithm and evaluated for predictive performance using the concordance index (C-index), calibration curve, decision curve analysis (DCA), and receiver operating characteristic (ROC) curves.
Results: Key predictors for constructing the best model included body mass index (BMI), albumin (ALB) levels, surgical resection method (SRM), and the American Joint Committee on Cancer (AJCC) stage. The model achieved a C-index of 0.736 in the training set and performed well in both training and validation datasets. It accurately predicted 1-, 3-, and 5-year survival rates, with Area Under the Curve (AUC) values of 0.843, 0.797, and 0.758, respectively. Calibration curve analysis and Decision Curve Analysis (DCA) further validated the model’s predictive capability, suggesting its potential use in clinical decision-making.
Conclusion: The study highlights the importance of BMI, ALB, SRM, and AJCC staging in predicting HBV-related HCC outcomes. The machine learning model aids clinicians in making better treatment decisions, potentially enhancing patient outcomes.

Keywords: hepatocellular carcinoma, hepatitis B virus, machine learning, prognostic model