Liver Cirrhosis Prediction Using Machine Learning Classification Techniques

Machine learning is the process of automating and analyzing patterns within data and using these identified patterns to make predictions. Supervised learning focuses on scenarios where a labeled dataset is used to train and test the machine and help it to analyze and make predictions. The dataset used in this paper is the “Cirrhosis Prediction Dataset” taken from Kaggle. This data has been collected from 424 patients across ten years at the Mayo Clinic. In the process of experimentation, the algorithms used were Multilayer Perceptron, Decision Tree, XGBoost, AdaBoost Random Forest, and LightGB algorithms. After analysis, it was found that the algorithms have good accuracy after the selection of features appropriately.