PREDICTION OF LIVER DISEASE USING MACHINE LEARNING ALGORITHMS

The escalating prevalence of liver diseases globally underscores the need for effective diagnostic tools and predictive models. This research addresses the increasing incidence of liver diseases by leveraging machine learning algorithms to predict the risk of liver disease based on various factors such as blood test results, alcohol consumption, and dietary habits. Using Python programming language and the Scikit-learn library, a predictive model is developed employing classification algorithms including Logistic Regression and K-Nearest Neighbors. The system prompts users to input their blood test details, and the model, trained on a diverse dataset, provides a risk assessment for liver disease. The study compares the performance of these algorithms to identify the most accurate model for risk prediction. The developed system holds promise for early detection and intervention in individuals at risk of liver diseases, contributing to improved public health outcomes.