Home / Current Issue / Paper 1701742
Deployment of Heart Disease Prediction Model in Cloud Environment
Subject area: Science,Engineering and Technology · Area of research: Cloud Environment
Abstract
The main reason for heart failure is Cardiovascular Diseases (CVDs). The dataset used in this paper contains 9 attributes that can be used to predict death or mortality by heart failure. In this paper, a prediction modelin cloud environment is built to display the prediction outcome of the heart failure. The cloud service automatically generated the effective heart disease prediction model using pipeline-based approach. In this proposed work, Snap Random Forest Classifier is selected as the effective heart disease prediction model among other 7 prediction models with classification accuracy of 87.3%. The primary objective of this effective heart disease prediction model is to determine whether a patient should be diagnosed with heart disease or not, which is a binary outcome either 0 or 1. The outcome of binary value 1 implies that the patient will be diagnosed with heart disease and outcome of binary value 0 implies that the patient will not be diagnosed with heart disease.
How to cite this paper
@article{1701742,
author = {I. Bhuvaneshwarri},
title = {Deployment of Heart Disease Prediction Model in Cloud Environment},
journal = {Iconic Research And Engineering Journals},
year = {2019},
volume = {3},
number = {5},
pages = {177-180},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1701742.pdf},
abstract = {The main reason for heart failure is Cardiovascular Diseases (CVDs). The dataset used in this paper contains 9 attributes that can be used to predict death or mortality by heart failure. In this paper, a prediction modelin cloud environment is built to display the prediction outcome of the heart failure. The cloud service automatically generated the effective heart disease prediction model using pipeline-based approach. In this proposed work, Snap Random Forest Classifier is selected as the effective heart disease prediction model among other 7 prediction models with classification accuracy of 87.3%. The primary objective of this effective heart disease prediction model is to determine whether a patient should be diagnosed with heart disease or not, which is a binary outcome either 0 or 1. The outcome of binary value 1 implies that the patient will be diagnosed with heart disease and outcome of binary value 0 implies that the patient will not be diagnosed with heart disease.},
month = {November},
}