Performance Assessment of Ensemble Learning Model for Prediction of Cardiac Disease Among Smokers Based on HRV Features

Performance Assessment of Ensemble Learning Model for Prediction of Cardiac Disease Among Smokers Based on HRV Features

S. R. Rathod, C. Y. Patil
Copyright: © 2021 |Pages: 16
DOI: 10.4018/IJBCE.2021010102
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Smoking impacts the pattern of heart rate variability (HRV); HRV therefore acts as a predictor of cardiac diseases (CD). In this study, to predict CD non-invasively among smokers, ensemble machine learning methods have been used. A single model is created based on ensemble voting classifier with a combined boosting technique to improve the accuracy of predictive model. The final ensemble model shows an accuracy of 95.20%, precision of 97.27%, sensitivity of 92.35%, specificity of 98.07%, F1 score of 0.95, AUC of 0.961, MCE of 0.0479, kappa statistics value of 0.9041, and MSE of 0.2189. The obtained accuracy by using the proposed method is the highest value achieved so far for the prediction of CD among smokers using HRV data.
Article Preview
Top

2. Methods

The dataset was received from MITU Skillogies Pune India, data science research group. The dataset comprises of 1569 samples with 818 samples of cardiac disease-prone smokers and 751 non-smokers without cardiac disease sample. The data are synthetically generated using the formulas of HRV, based on the literature survey for research purpose only. We have observed the RR interval range in normal subject and cardiac disease prone smokers subject. Based on HRV formulae we have synthetically generated Time domain, Frequency domain and Nonlinear features. Hence all the feature of HRV are helpful for prediction of CD in smokers.

Complete Article List

Search this Journal:
Reset
Volume 12: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 11: 2 Issues (2022): 1 Released, 1 Forthcoming
Volume 10: 2 Issues (2021)
Volume 9: 2 Issues (2020)
Volume 8: 2 Issues (2019)
Volume 7: 2 Issues (2018)
Volume 6: 2 Issues (2017)
Volume 5: 2 Issues (2016)
Volume 4: 2 Issues (2015)
Volume 3: 2 Issues (2014)
Volume 2: 2 Issues (2013)
Volume 1: 2 Issues (2012)
View Complete Journal Contents Listing