Efficient Detection of Congestive Heart Failure through Machine Learning

  • Shreya B. Yadav, Prof. M. S. Takalikar

Abstract

 Heart health is very much important for the survival of humans as the heart is one of the most important organs of body. The incidence of Heart failure and its prevalence has been increasing day by day. This has been attributed to the complicated mechanisms of heart failure and its diagnosis. Heart failure is a complex phenomenon that is caused due to various different attributes. Therefore, the detection of heart failure has been performed manually by the doctors which takes a lot of time and effort. There has been plenty of research efforts that has been performed to make heart failure detection but most of them could not satisfy their goals. Therefore, this dissertation applies machine learning approaches on a dataset containing heart parameters such as RR intervals, PR intervals, etc. to detect congestive heart failure. These parameters are easily calculated from electrocardiogram (ECG) analysis which is time saving with low cost. The proposed methodology utilizes K-means clustering and Linear Regression along with Artificial Neural Networks and a combination of Fuzzy and Decision tree techniques in order to enhance the reliability of detection. The experimental results are highly promising for this implementation in accurate Congestive Heart Failure detection.

Published
2020-12-01
How to Cite
Shreya B. Yadav, Prof. M. S. Takalikar. (2020). Efficient Detection of Congestive Heart Failure through Machine Learning. International Journal of Advanced Science and Technology, 29(04), 11221 - 11233. Retrieved from http://sersc.org/journals/index.php/IJAST/article/view/34446