Hepatitisnet: Analysis and Prediction of Hepatitis using Machine Learning
Year: 2025
Type: article
Abstract: Hepatitis is a liver infection caused by the HCV virus. In hepatitis, it is hard to detect in the early stage as symptoms arise late. It can predict in advance in order that the patients may not suffer from permanent damage of liver. The main objective of this proposed method is to implement some machine learning techniques to predict this disease utilizing easily available and inexpensive data from blood test to make a diagnosis and take care of the patients in the early phase. The proposed method consists of a comparison of three machine learning techniques, those are support vector machine (SVM), logistic regression (LR), decision tree(DT), have been applied in same dataset. To achieve a appropriate strategy for disease prediction, confusion matrix, precision, recall, F1 score, accuracy, receiver operating characteristics(ROC), performance of all these algorithm results have been compared. Total accuracy of SVM model is 0.92, which is the maximum among the three models.
Authors: K. Dinesh Reddy, S. Poongodi, P. Gnanavel, K. Jyothika, K. Harish Goud, K. Kartheek
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W6893389667
FWCI:
Cites:
Cited by:
Related to: