Prediction of Chronic Graft vs. Host Disease Using Machine Learning

This paper attempts to predict the onset of chronic Graft vs. Host Disease (GVHD) in children with blood cancers who have received a bone marrow or stem cell transplant using machine learning models. It analyzes and compares results three different models terms how accurate they each are predicting GVHD. These Logistic Regression, J48 algorithm decision trees, Multilayer Perceptron. The formed dataset containing 36 attributes, excluding GVHD itself. Through data preprocessing analysis Weka, these attributes narrowed down for model figure out which combination leads best predictive accuracy. study uses 10-fold cross validation Receiver Operating Characteristic (ROC) Area as measure accuracy model. found that Perceptron is predictor In comparison, Regression was worst used least number make its prediction.