Comparison of Various Supervised Machine Learning Algorithms for the Risk Assessment of Non-Alcoholic Fatty Liver Disease

The liver is the body's biggest gland and is responsible for digesting food, filtering unwanted chemicals, and combating infections. However, the liver may suffer from exposure to chemicals or viruses, resulting in liver disease. This condition, which includes any impairment to the liver's function, is a major health issue that requires immediate medical care. This study employs machine learning (ML) approaches to predict liver disease in its early stages. Various machine learning algorithms were assessed and compared using F-measure, recall, accuracy, and precision measures. A dataset comprising 579 samples was utilized for the detection of liver disease (FLD). Use various classification techniques to identify the disease, including support vector machine, naive Bayes, k-nearest neighbor (KNN), and logistic regression. The value is 0.76 and the f value in the logistic regression algorithm is 0.75.