Application of Machine Learning Algorithms in Predicting Hepatitis C

Hepatitis C, caused by the hepatitis C virus (HCV) infection, is a disease that can progress from initial asymptomatic stages to chronic infection if left untreated, potentially leading to cirrhosis and liver cancer. The diagnosis of hepatitis C requires at least two different types of tests: serological tests and molecular tests. These testing methods impose a financial burden on patients and contribute to patient attrition. The objective of this study is to predict this disease using various machine learning techniques based on common blood test data, in order to achieve early diagnosis and treatment for patients. In this study, we integrated features from literature and original data, applying six machine learning algorithms (logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), decision tree (DT), random forest (RF), adaptive boosting (AdaBoost)) to forecast hepatitis C. The performance of these techniques was compared using metrics such as accuracy, precision, recall, F1-score, receiver operating characteristics (ROC), and the area under the curve (AUC) to identify suitable methods for this disease. Results from the UCI dataset indicate that AdaBoost achieved the highest accuracy (97.8%) and AUC (0.994), making it an effective and cost-efficient method for predicting hepatitis C.