Machine learning is used extensively in medical diagnosis to predict the existence of diseases. Existing classification algorithms are frequently used for automatic detection of diseases. But most of the times, they do not give 100% accurate results. Boosting techniques are often used in Machine learning to get maximum classification accuracy. Though several boosting techniques are in place but the XGBoost algorithm is doing extremely well for some selected data sets. Building an XGBoost model is simple but improving the model by tuning the parameters is a challenging task. There are many parameters to the XGBoost algorithm and deciding what set of parameters to tune and the ideal values of these parameters is a cumbersome and time taking task. We, in this paper, tuned the XGBoost model for the first time for Liver disease prediction and got 99% accuracy by tuning some of the hyper parameters. It is observed that the model proposed by us exhibited highest classification accuracy compared to all other models built till now by machine learning researchers and some regularly used algorithms like Support Vector Machines (SVM), Naive Bayes (NB), C4.5 Decision tree, Random Belief Networks, Alternating Decision Trees (ADT) experimented by us.

 Abstract: Classification techniques are often used for predicting Liver diseases and assist doctors in early detection of liver diseases. As per studies in the past and our experiments, conventional classification algorithms are found to be less accurate in predicting liver diseases. Therefore, there is a need for sophisticated classifiers in this area. For many medical applications, including Liver Diseases, Deep Neural Networks (DNNs) are used but the accuracies are not satisfactory. Deep Neural Network training is a time taking procedure, particularly if the hidden layers and nodes are more. Most of the times it leads to over fitting and the classifier does not perform well on unseen data samples .We, in this paper, tuned a Multi Layer Feed Forward Deep Neural Network (MLFFDNN) by fitting appropriate number of hidden layer and nodes, dropout function after each hidden layer to avoid over fitting, loss functions, bias, learning rate and activation functions for more accurate liver disease predictions. We used a balanced data set containing 882 samples. The data is collected from north coastal districts of Andhra Pradesh hospitals, India. The training process is carried out for 400 epochs and finally It is .observed that our model exhibited 98% accuracy at epoch 363 which is more than the performance of Neural Network models tuned till now by machine learning researchers and also some regularly used classification algorithms like Support Vector Machines (SVM), Naive Bayes (NB), C4.5 Decision Tree, Random Belief Networks and Alternating Decision Trees (ADT) .