Heart Disease with Risk Prediction using Machine Learning Algorithms
S. Kavitha1, K. R. Baskaran2, S. Sathyavathi3
1S. Kavitha, Assistant Professor, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
2K. R. Baskaran, Professor, Department of Computer Science and Engineering, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
3S. Sathyavathi, Assistant Professor, Department of Information Technology, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
Manuscript received on 13 December 2018 | Revised Manuscript received on 24 December 2018 | Manuscript Published on 09 January 2019 | PP: 314-317 | Volume-7 Issue-4S November 2018 | Retrieval Number: E1984017519/19©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: Nowadays health connected issues are terribly high, and it can’tbe simply foretold earlier to avoid complications. Wellness heart condition cardiopathycar diovascular disease} (HD) may be a common disease for the individuals more matured cluster thirty-five to fifty. the sector of information mining has concerned within the medical domain, With the historical knowledge, mining algorithms are able to predict and classify the abnormality in conjunction with its risk levels. The previous studies related to predict heart problems have used several features which has been collected from patients. The accuracy level of prediction and the number of features is very less in the previous systems. To improve the prediction accuracy the planned system, consider additional range of options and implements a Weighted Principle Analysis (WPCA) and changed Genetic Algorithm(GA) The planned technique helps the medical domain for predicting HD with its numerous co-morbid (types of heart diseases) conditions. The system has 2 main objectives, that are rising diagnosing accuracy and reducing classification delay. The WPCA represents with the effective cacophonous criteria that has been applied into the genetic Algorithm. The system effectively identifies the disease and its sub types, the sub type which is referred as the level of class such as normal and mild or extreme. Using combinatorial methods from data mining decision making has been simplified and the proposed work achieved 96.34% accuracy, which is higher than the known approaches in the literature.
Keywords: Data Mining, Classification, Weighted Principle Analysis (WPCA), Modified Genetic Algorithm (GA), Heart Disease.
Scope of the Article: Machine Learning