Diagnosing hepatitis C from blood tests using different machine learning modelsHepatitis C is a chronic infectious disease that attacks the liver and is mainly transmitted through the bloodstream. Without proper treatment, it can lead to serious complicat

Abstract

Hepatitis C is a chronic infectious disease that attacks the liver and is mainly transmitted through the bloodstream. Without proper treatment, it can lead to serious complications such as cirrhosis or even liver cancer. In the medical field, artificial intelligence is gaining importance all the time as a tool capable of increasing diagnostic efficiency and precision. With the passage of time, technological developments have increased the technical capabilities of computers to the point where processing large amounts of data became fast and has contributed to a huge improvement in quality of AI solutions, dramatically increasing their impact on people's daily lives. In this article, we explore the potential of using machine learning to correctly diagnose an ongoing hepatitis C virus (HCV) infection. The goal of the paper is to develop and compare four binary classifiers: logistic regression, k-nearest neighbors (kNN), support vector machines (SVMs) and random forests. The learning process was conducted using blood test results from healthy donors and infected individuals. Metrics of accuracy and sensitivity were used to assess performance. In the end, among those that were tested random forest proved to be the best suited to medical applications such as diagnosing hepatitis C.