Convolutional Neural Network's Stacking Classifier on Cardiovascular Disease

Chuhong Zhou

2024

Abstract

Cardiovascular disease is the leading cause of death worldwide. To diagnose cardiovascular disease, multiple risk indicators need to be combined, which is a challenge for limited medical resources. To reduce misdiagnosis, machine learning is being used to predict cardiovascular disease. Due to the inherent defect of algorithms, the results of a single model will produce certain errors. To improve prediction accuracy, Ensemble Learning combines several machine learning algorithms. However, Convolutional Neural Network (CNN), as an algorithm of machine learning, is not sufficiently applied in predicting problems of cardiovascular disease. Part of the data collected by the Centers for Disease Control and Prevention (CDC) in 2022 was used in this experiment, and pre-processing operations such as feature selection, Undersampling, and Synthetic Minority Over-sampling Technique (SMOTE) were performed. This experiment tested the accuracy of using a CNN as the base learner and meta-learner for the stacking model and compared it with traditional algorithms. The results show that the accuracy of the ensemble learning model that integrates CNN is 91.13, which is higher than the traditional algorithm compared to it.

Paper Citation

in Harvard Style

Zhou C. (2024). Convolutional Neural Network's Stacking Classifier on Cardiovascular Disease. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 116-121. DOI: 10.5220/0012827800004547

in Bibtex Style

@conference{icdse24,
author={Chuhong Zhou},
title={Convolutional Neural Network's Stacking Classifier on Cardiovascular Disease},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={116-121},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012827800004547},
isbn={978-989-758-690-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Convolutional Neural Network's Stacking Classifier on Cardiovascular Disease
SN - 978-989-758-690-3
AU - Zhou C.
PY - 2024
SP - 116
EP - 121
DO - 10.5220/0012827800004547
PB - SciTePress