A Patient-Oriented Environment for Biomedical Engineering Applications using Big-Data and C means Clustering

Abstract: Massive amounts of data and machine learning have recently altered medical care research. Information derived from Electronic Health Records and the many other clinical sources that can be used to the assist different patients. It is also possible to predict the outcomes or effects of pharmaceutical, as well as the risk of infection on the human body, by using Big Data Analytics (BDA) on medical data. To investigate medical care data, a few AI algorithms, such as bunching and categorization, are used. In this paper, a structure for Biomedical Engineering applications is proposed using C-implies Clustering. The structure can also be used benefit professionals and patients. For example, a Clinician can use this paradigm to decide whether or not to provide suitable medication to a certain patient. The information for this structure was taken from the UCI AI repository. The data was subsequently analysed using Hadoop, a well-known large-scale data processing technology.

Keywords: Big Data, Hadoop, Machine Learning, , C-Implies, ID3, MapReduce