Loading

Heart Disease Prediction using Data Mining with Mapreduce Algorithm
T.Nagamani1, S.Logeswari2, B.Gomathy3

1T. Nagamani, Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Sathyamangalam (Tamil Nadu), India.
2Dr. S. Logeswari, Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Sathyamangalam (Tamil Nadu), India.
3Dr. B. Gomathy, Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Sathyamangalam (Tamil Nadu), India.
Manuscript received on 05 January 2019 | Revised Manuscript received on 13 January 2019 | Manuscript published on 30 January 2019 | PP: 137-140 | Volume-8 Issue-3, January 2019 | Retrieval Number: C2624018319/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The World Health Organization (WHO) estimated that cardiovascular diseases (CVD) are the major cause of mortality globally, as well as in India. They are caused by disorders of the heart and blood vessels, and includes coronary heart disease (heart attacks), Data mining acts as a major role in the construction of an intellectual prediction model for healthcare systems to detect Heart Disease (HD) using patient data sets, which support doctors in diminishing mortality rate due to heart disease. Several researches have been carried out for building model using individually or by combining the Data Mining with computational techniques involving Decision tree (DT), Naïve bayes (NB) along with Meta-heuristics approach, Trained Neural Network (NN), Machine intelligence or AI and unsupervised learningalgorithms like KNN and Support vector machine (SVM). In the proposed system, large set of medical instances are taken as input. From this medical dataset, it is aimed to extract the needed information from the record of heart patients using Mapreduce technique. The performance of the proposed Mapreduce Algorithm’s implementation in parallel and distributed systems was evaluated by using Cleveland dataset and compared with that of the predictable ANN method. The trial results verify that the projected method could achieve an average prediction accuracy of 98%, which is greater than the conventional recurrent fuzzy neural network. In addition, this Mapreduce technique also had better performance than previous methods that reported prediction accuracies in the range of 95– 98%. These findings suggest that the Mapreduce technique could be used to accurately predict HD risks in the clinic.
Keyword: Data Mining, Cardiovascular Diseases (CVD), Accuracy, Prediction, Heart Disease (HD), Recurrent Fuzzy Neural Network(RFNN), Mapreduce, World Health Organization (WHO).
Scope of the Article: Data Mining Methods