Hepatitis C is a liver inflammation contracted from the Hepatitis C Virus (HCV). This disease is characterized by symptoms that appear relatively late into the course of the disease, thus, the diagnosis at an early stage is very challenging. In short, the efficiency of the prediction before permanent liver damage will annually save several patients. This work focuses on the following core purpose: To apply different machine learning algorithms for classifying this disease using cost-efficient tests to identify the disease’s initial stages for early diagnosis and treatment of patients. Seven machine learning algorithms have been used in this study; logistic regression, K-nearest neighbors, decision tree, Random Forest, support vector machine, Naive Bayes, and LGBM on HCV datasets collected from the UCI repository. We evaluated the performance of those ML models with or without applying the SMOTE algorithm. In comparing these techniques from the perspective of confusion matrix, precision, recall, F1 score, accuracy, ROC, and AUC, it is found that LGBM provides 94.61% and 93.50% accuracy with and without SMOTE, respectively.