Categorization of Non-Alcoholic Fatty Liver Disease Using XG-Boost

The liver holds immense importance within the human body, and liver diseases are increasingly seen as significant health concerns in India. Non-alcoholic fatty liver disease (NAFLD) stands out as one of the most prevalent chronic conditions affecting the liver, and it can affect individuals of any age. Early diagnosis and timely treatment are crucial. Unfortunately, when diagnosing Fatty Liver Disease (FLD), doctors commonly rely on liver biopsy and abdominal ultrasound as the primary methods. The primary goal of this project is to identify non-alcoholic fatty liver disease and provide support to medical professionals in the diagnosis, prognosis, and staging of NAFLD. The disease progresses through four stages: Non-Alcoholic Steatohepatitis (NASH), Fibrosis, Cirrhosis, and Simple Fatty Liver Disease. Various machine learning algorithms, widely used in medical data analysis, are employed in this research. Liver function tests serve as predictive tools for liver disease by inputting patient details and data into different classifier algorithms such as Logistic Regression, XG-Boost, Gradient Boosting, Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machines (SVM). The accuracy score and confusion matrix are used to compare the performance of these classification algorithms.