A Survey on Disease Prediction from Healthcare Communities Over Big Data

Abstract

Data mining is the process of extracting hidden interesting patterns from massive database.  Medical domain contains heterogeneous data in the form of text, numbers and images that can be mined properly to provide variety of useful information for the physicians. The patterns obtained from the medical data can be useful for the physicians to detect diseases, predict the survivability of the patients after disease, severity of diseases etc.  The main aim of this paper is to analyse the application of data mining in medical domain and some of the techniques used in disease prediction.Medical datasets are often categorized by huge amount of disease measurements and comparatively small amount of patient records. These measurements (feature selection) are not relevant, where this irrelevant and redundancy features are difficult to evaluate. On the other hand, the large number of features may cause the problem of memory storage in order to represent the data set. Different kinds of machine learning algorithms can convenient with imprecision and uncertainty in data analysis and can effectively remove impurities and failure information.