Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195562,
        author = {A.Sagar and D.N.B.T Sundari and J.Priyathaman and K. Raghu and B.  Vinaykumar},
        title = {AI-POWERED LIVER CARE: A MACHINE LEARNING MODEL FOR HEPATITIS DIAGNOSIS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {954-961},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195562},
        abstract = {Hepatitis is a life-threatening disease that affects the liver, often caused by viral infections, and can lead to severe complications such as liver failure or cancer if not diagnosed early. Traditional diagnostic methods can sometimes fall short in identifying the disease at an early stage, especially when clinical symptoms overlap with other conditions. To address this, researchers have turned to machine learning (ML) techniques, which are capable of analysing, complex patterns in medical data to improve diagnostic accuracy. In this study, various ML algorithms were applied to patient data containing features such as age, gender, liver function test results, and symptoms like fatigue or jaundice. Among the methods tested, Support Vector Machines (SVM) and Logistic Regression were prominent. To overcome the issues, the researchers employed a technique known as SMOTE (Synthetic Minority Over-sampling Technique), which artificially generates new instances of the minority class (hepatitis cases) to balance the data-set. The application of SMOTE significantly improved model performance, especially in terms of classification accuracy. Among the models tested, Logistic Regression emerged as the most accurate, achieving a diagnostic accuracy of 93.93%.},
        keywords = {Demographic Information, Clinical-symptoms, Medical-history, Target-variables, SMOTE, Patient Data Features, Performance Outcome},
        month = {April},
        }