Prediction of Patient Survival after Liver Transplant Using Artificial Neural Network Techniques

Excessive alcohol consumption, inhalation of poisonous gases, and ingestion of tainted food, drinks, and medications are all contributing to an increase in the number of persons suffering from liver disease. The liver is responsible for a wide range of important functions, and liver illnesses pose a slew of medical care delivery difficulties. A liver transplant is a demanding treatment with a high rate of post-operative complications. The success of the transplant is highly contingent on choosing the correct donor and recipient. The post-transplant death rate might be greatly lowered if a large patient and donor database could be used to accurately match a donor recipient pair. Classification algorithms are widely used in several automated medical diagnostic technologies Artificial neural networks (ANNs), which are extremely strong technology, can help in pattern identification. They work in a variety of sectors, from medicine to the arts. Artificial Neural Networks, Radial Basis Function, and ARTMAP were evaluated and examined Using the Indian Liver Patient Dataset (ILPD) from the UCI machine learning library. These approaches were used to compare results measured by accuracy, mean absolute error (MAE), root MAE (root MAE), MAE (root MAE), MAE (root MAE), MAE (root MAE), and MAE (root MAE) (root MAE). After employing the 10-fold cross validation technique, the best approach was revealed to be a multilayer perceptron (MLP) artificial neural network, which had a success rate of 98.9708 percent. In India, little research has been done on this topic, although other countries, such as the United States, have. MLP was found tobe the best even when compared to other US dataset studies. Finally, the technique utilised to diagnose Chronic Liver Disease is described. The usage of artificial neural networks (ANN) has been created to predict patient survival following long-term treatment. The goal of this study is to propose a practical method for predicting patient survival after liver transplantation using neural networks such as artificial neural networks (ANN). The accuracy of calculations based on the different models for ANN was assessed to be 99 percent based on the analysis of the degree of accuracy among the various three models referred to in this research.