Hepatitis C, an infectious disease that claims thousands of lives annually, affects millions globally. Disease prediction and classification are crucial in medical research, as forecasting diseases helps identify patients at risk. This study used the Electronic Health Records dataset from the UCI Machine Learning Repository, which included 615 individuals, of which 540 were healthy, and 75 had hepatitis C. Machine learning (ML) algorithms proved particularly effective in developing prediction models for the presence of the Hepatitis C Virus (HCV), thereby improving performance and efficiency. After evaluating several categories of machine learning (ML) algorithms for classification, the study employed seven algorithms: an Artificial Neural Network (ANN) and an ensemble model combining these seven distinct algorithms. The classifiers used in model assessment included K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Logistic Regression (LGR), XGBoost (XGB), and Gaussian Naive Bayes (GNB). Additionally, an ANN and an ensemble model were implemented. This study presents a comparative analysis of these algorithms, with the Random Forest (RF) classifier achieving the highest accuracy across all iterations. The experimental results demonstrate that the proposed ensemble framework achieved greater accuracy with XGB as the final estimator. Notably, the RF classifier reached an accuracy of 99.88%. In conclusion, the study demonstrates that using an ensemble model improves prediction accuracy for Hepatitis C, yielding more precise results than applying individual algorithms.