Year: 2025
Type: article
Abstract: This study focuses on predicting liver disease using machine learning, highlighting the importance of accurate diagnosis and early detection. Through thorough data preprocessing—such as handling missing values, addressing class imbalance with SMOTE, and applying iterative imputation—a high-quality dataset is created. The performance of SVM, KNN, HVC, and Random Forest algorithms is evaluated, with Random Forest achieving an accuracy of 85%. Ultimately, this research makes a significant contribution to healthcare analytics by providing a systematic, data-driven framework for the diagnosis and management of liver disease. This research enhances data-driven decision support for timely and accurate liver disease diagnosis, ultimately improving patient outcomes.
Authors: K. K. Archana, Mahalakshmi R S, Narmatha Bharathi A, Reem A
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4410207640