Identification of Predictive Capability of Classifiers for Early Heart Disease Detection Using Machine Learning

Authors

  • Aquila Peeran Department Computer Science Engineering, Dayananda Sagar College of Engineering, Bengaluru, India
  • U. Brinda Kumar Department Computer Science Engineering, Dayananda Sagar College of Engineering, Bengaluru, India
  • N. Neha Department Computer Science Engineering, Dayananda Sagar College of Engineering, Bengaluru, India
  • Nikita Ravi Department Computer Science Engineering, Dayananda Sagar College of Engineering, Bengaluru, India

Keywords:

Cardiovascular, Deep Learning, Prediction system, Data Mining

Abstract

Heart and cardiovascular diseases are the leading cause of death in today’s world. In this era, even the younger generations are affected due to unbalanced and fast paced lifestyles. While most people can afford diagnostic tests, families with lower income cannot afford the cost of these expensive tests. This prediction system aims to aid such individuals in addition to issues such as lack of physicians in rural areas and places with low healthcare quality. By providing a prediction model for heart diseases at an early stage, this project helps reduce the cost of medical tests and the errors associated with it are also considerably reduced compared to manual testing. Since the model helps in predicting the diseases at an early stage, the dire consequences can be controlled and lifestyle changes can be made to reduce the further risks associated with a heart disease. The added feature of instant diagnosis can be very useful in case of an emergency. We check the capability of Deep Learning classifiers for cardiovascular disease identification and prediction in this paper along with a rigorous process of data mining to remove noisy data for a better decision making system with an extremely effective accuracy.

 

Downloads

Published

2021-02-26

How to Cite

[1]
A. Peeran, U. Brinda Kumar, N. Neha, and N. Ravi, “Identification of Predictive Capability of Classifiers for Early Heart Disease Detection Using Machine Learning”, IJRAMT, vol. 2, no. 2, pp. 27–28, Feb. 2021.

Issue

Section

Articles