The long-term impacts and enduring symptoms of chronic illnesses provide serious obstacles to people’s health and well-being. The chronic form of hepatitis C is caused by the hepatitis C virus (HCV) and disrupts 58 million individuals worldwide. It also causes 290,000 deaths annually due to liver cancer and cirrhosis, two conditions connected to HCV. This work focuses on using machine learning (ML) algorithms to accurately diagnose and forecast hepatitis C. It does this by utilizing ML algorithms’ capacity to scan big datasets and spot patterns and associations that help with diagnosis. Predictive models were created utilizing blood values from 615 patients, including both hepatitis patients and healthy blood donors, using a variety of approaches such as SVM, MLP, and others. The dataset was thoroughly preprocessed, including Principal Component Analysis (PCA) dimensionality reduction, scaling, and handling of missing values. Following the evaluation of numerous deep learning and machine learning techniques. The highest accuracy is achieved by deep learning and machine learning techniques. The suggested method makes use of two models according to the size of the dataset: MLP for large-scale data and SVM for small datasets. Both versions operate almost in the same way with the same level of performance. The SVM classifier obtained an F1-score of 94.16%, accuracy of 98.33%, recall of 94.17%, and precision of 93.99%. Likewise, the MLP model produced an F1-score of 91.67%, recall of 84.62%, accuracy of 98.33%, and precision of 100.00%. This study demonstrates how machine learning (ML) may enhance HCV detection using low-cost and minimally intrusive techniques. In keeping with the WHO’s objective of a 50% reduction in new HCV infections and associated deaths by 2030, it also highlights the significance of improved data preparation and feature selection to increase model efficiency.