The Multi-Class Detection of Five Stages of Hepatitis C Using the Machine Learning Based Random Forest Algorithm

Hepatitis C is a viral illness that primarily impacts the liver, inducing persistent inflammation and potentially resulting in significant liver harm over an extended duration. Its transmission occurs through contact with contaminated blood, and it can be efficiently managed using antiviral medications. Since Hepatitis C is very harmful disorder, this research aims as studying and analyzing it utilizing the Machine learning mechanisms. The online obtainable UCI dataset was taken in this research and trained for predicting five outcomes, which are encoded as 0,1,2,3 and 4. These being a blood donor, Hepatitis, Fibrosis, Cirrhosis and suspect blood donor. The model which is trained using the Random-Forest (RF) algorithm obtains a good performance metrics with an accuracy percentage of 93.5%. In short, this model is an impactful classifier that classifies 5 outcomes by training on the dataset.