Hepatitis C is a viral infection that poses severe health risks, including chronic liver disease, cirrhosis and hepatocellular carcinoma, making early detection essential for effective treatment and prevention. This study develops a predictive model combining the C5.0 decision tree algorithm with Chi-Square feature selection to identify Hepatitis C-positive cases efficiently. Using a dataset containing clinical and biochemical attributes, the Chi-Square test is applied to prioritise the most relevant features, improving the model’s interpretability and computational efficiency. The refined dataset is then classified using the C5.0 algorithm, with performance evaluated through accuracy, precision, recall and F1-score. Results demonstrate that Chi-Square feature selection significantly enhances the algorithm’s performance, achieving high classification accuracy. Comparative analyses highlight the model’s superiority over alternative approaches, emphasising its potential for reliable early diagnosis. This research illustrates the effectiveness of integrating feature selection techniques with machine learning algorithms to improve diagnostic accuracy in healthcare, offering a promising solution for timely and precise disease detection.