Machine Learning Algorithm for Predicting Hepatocellular Carcinoma in HCV Patients

Background/Objectives: Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality worldwide and is frequently associated with chronic hepatitis C virus (HCV) infection. Early prediction of HCC in HCV patients remains challenging due to complex clinical patterns. This study aims to develop and evaluate machine learning models for the early prediction of hepatocellular carcinoma in patients with HCV. Methods: Clinical and laboratory data from HCV patients were analyzed using a machine learning–based framework. The dataset was preprocessed, and relevant features were selected prior to model development. Six supervised machine learning algorithms—CatBoost, XGBoost, LightGBM, Gaussian Naive Bayes, Extra Trees, and Random Forest—were implemented. Hyperparameter optimization was performed using the Optuna framework. Model performance was assessed using standard evaluation metrics, including accuracy, precision, recall, and F1-score. Results: The experimental results demonstrate that machine learning techniques can effectively identify patterns associated with the progression to hepatocellular carcinoma in HCV patients. Among the evaluated models, ensemble-based algorithms achieved the highest predictive performance, outperforming baseline approaches across multiple evaluation metrics. Conclusions: The findings confirm that machine learning models can serve as valuable decision-support tools for the early detection of hepatocellular carcinoma in patients with HCV. Integrating such models into clinical workflows may enhance early diagnosis and improve patient outcomes. Future work will focus on expanding the dataset and validating the models in real-world clinical settings.