Chronic Kidney Disease Using Fuzzy C-Means Clustering Analysis

Chronic Kidney Disease Using Fuzzy C-Means Clustering Analysis

Vineeta Kunwar (Amity University Uttar Pradesh, Noida, India), A. Sai Sabitha (Amity University Uttar Pradesh, Noida, India), Tanupriya Choudhury (Informatics Department, School of CS, University of Petroleum and Energy Studies, Dehradun, India) and Archit Aggarwal (Amity University Uttar Pradesh, Noida, India)
Copyright: © 2019 |Pages: 22
DOI: 10.4018/IJBAN.2019070104

Abstract

Medical industries are encountered with challenges like providing quality services to patients, correct diagnosis and effective treatments at reasonable cost. Data mining has become a necessity and provides solutions to many important and critical health related concerns. It is the process to mine knowledgeable information from voluminous medical data sets. It plays an essential role in improving medical decision making and helps to investigate trends in patient conditions which can be used by doctors for disease diagnosis. Clustering is an unsupervised learning technique that groups object with high similarity together. Chronic kidney disease (CKD) causes renal failure and kidney dysfunction. It has become an important health issue with the number of cases on the rise every year. This article presents analysis and detection of Chronic Kidney Disease using Fuzzy C Means (FCM) clustering which is effective in mining complex data having fuzzy relationships among members. FCM will investigate and group together the patients having CKD and Not CKD. The simulation and coding are done in MATLAB.
Article Preview
Top

Literature Survey

Data Mining and Heath Care

Data Mining is an interesting and motivating area of research which has become popular in the medical field. It plays a vital role to uncover latest trends in the medical industry. It aims to find out useful information from massive data sets. In present times, there is a requirement of methodology like data mining that detects and analyzes important information in health data. Health industries generate voluminous complex data. The massive medical database maintains information like patient history, images, medical claims and treatment, reports on radiology and pathology. Health data may be dynamic, high dimensional, inconsistent, noisy, imprecise and voluminous having missing values. The use of data mining to a great extent can enhance decision making and effectiveness of treatments in medical field. By converting voluminous healthcare data into knowledge, cost can be controlled, and quality of patient care can be improved. There has been a wide use of data mining techniques for finding newer patterns in medical data. Some of its uses in medical field involve grouping and finding the relationship between genes, discovering patterns between brain images, developing prediction models of lung cancer and breast cancer, detecting diabetes, finding new drugs etc. (Ting et al., 2009).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 7: 4 Issues (2020): 2 Released, 2 Forthcoming
Volume 6: 4 Issues (2019)
Volume 5: 4 Issues (2018)
Volume 4: 4 Issues (2017)
Volume 3: 4 Issues (2016)
Volume 2: 4 Issues (2015)
Volume 1: 4 Issues (2014)
View Complete Journal Contents Listing