Application of Logistics Regression to Artificial Neural Network on Hepatitis B
Keywords:
Logistic Regression, Artificial Neural Network, Hepatitis B, Acute-on-Chronic Liver Failure, Multilayer PerceptronsAbstract
"Hepatitis B is a vaccine-preventable disease caused by the hepatitis B virus (HBV) that can lead to potentially fatal liver damage. It has infected approximately 2 billion people worldwide, representing one-third of the global population. HBV is a leading cause of acute-on-chronic liver failure (ACLF), characterized by rapid deterioration of liver function and high short-term mortality. A study aimed to compare the performance of Multilayer Perceptrons (MLP) and Radial Basis Function Neural Networks (RBFNN) with conventional Logistic Regression (LR) algorithms in predicting hepatitis B. The results indicated that age (p = .051), gender (p = .042), and country (p = .052) significantly contributed to the prediction model. Males were found to be twice as likely to have hepatitis B compared to females, and increasing age was associated with a higher likelihood of the disease. The output layer of artificial neural networks is responsible for producing the final results, and its structure varies depending on the classification problem. Transfer functions like sigmoid or hyperbolic tangent are used for signal transformation. The process involves multiple layers of processing elements, resulting in a final output value or vector. The study used a deep neural network-based transfer learning model, and the classification accuracy was compared with a non-transfer learning model across multiple source datasets."