Machine Learning Techniques: Performance Analysis for Prevalence of Heart Disease Prediction
Sachin Kamley1, R.S. Thakur2
1Sachin Kamley, Department. of Computer Applications, S.A.T.I,. Vidisha (M.P.), India.
2R.S. Thakur, Department of Computer Applications, M.A.N.I.T., Bhopal (M.P.), India.
Manuscript received on 18 April 2019 | Revised Manuscript received on 25 April 2019 | Manuscript published on 30 April 2019 | PP: 188-191 | Volume-8 Issue-4, April 2019 | Retrieval Number: C5880028319/19©BEIESP
Open Access | Ethics and 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: In these days, heart disease has become most dominating problem for medical professionals as well in India and abroad. However, heart disease is a major factor for behind the most of the people deaths today. An efficient and effective machine learning technique is required in order to reduce large scale of deaths due to this problem. In this direction, data mining and machine learning techniques play prominent role for pre-stage detection from heart disease problem. This study focuses on three most important machine learning techniques Support Vector Machine (SVM), Naive Bays (NB) and K-Nearest Neighbor (K-NN) for heart disease prediction. The machine learning tool Statistica is used for result generation purpose. Finally, experimental results stated that SVM method has excellent accuracy (86.12%) over other methods.
Keywords: Data Mining, Heart Disease, Machine Learning, Naïve Bays, Support Vector Machine, Prediction, Statistica.
Scope of the Article: Machine Learning