Diagnosis of Disease from Clinical Big Data using Neural Network

Big Data is info whose assortment, intricacy and scale need novel procedures, analytics, methods and design to cope with it and mine value and hidden information from it. Big Data requires different approaches with an intention to resolve novel snags or existing hitches in an enhanced way. The greatest challenges is to deal with large dataset with high amount of dimensionality, together in terms of the number of features the data has, as well the number of rows of data that user is dealing with. Neural Networks is a machine learning tool that is capable of performing these tasks. This paper presents an integrative approach to predict the diabetic disease from clinical big data. The clinical database is generally redundant, incomplete, vague and unpredictable. The main objective of integrating is to experiment with different strategies of training neural networks in order to increase the prediction accuracy.