Enhancing Cardiovascular Disease Prediction with Machine Learning: A Comparative Study Using the UCI Heart Disease Dataset

Hanwen Li

2024

Abstract

At present, cardiovascular diseases (CVDs) remain the principal cause of death at large global scale, so early detection is essential for improving patient outcomes. In this study, machine learning (ML) techniques are introduced in an effort to oppress heart disease prediction work, using the University of California, Irvine (UCI) Heart Disease Archive Database as the facility for model evaluation. Thesis want to talk about the performance of a number of ML models: Logistic Regression, K-Nearest Neighbors (KNN), Decision Trees, Artificial Neural Networks (ANN) and Deep Neural Networks (DNN). The research involves data preprocessing steps including normalization and imputation steps of the dataset, followed by training and testing models to evaluate accuracy and precision. The data source consists of 303 instances with 14 angles. Logistic Regression achieves the highest accuracy at 93.40 percent. ANNs and DNNs show strong capabilities for pattern recognition but also encounter overfitting problems. Decision Trees provide valuable interpretation but have only moderate generalization power. Performance is precisely sensitive to data characteristics. These findings illustrate the potential of ML techniques as a means to amplify heart disease prediction (providing clinicians with even more accurate tools for early diagnosis and personalized treatments) not only their strength but also conclusion on real-time where direct benefits will certainly be received by patients ourselves within health care settings.

Paper Citation

in Harvard Style

Li H. (2024). Enhancing Cardiovascular Disease Prediction with Machine Learning: A Comparative Study Using the UCI Heart Disease Dataset. In Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-754-2, SciTePress, pages 295-300. DOI: 10.5220/0013516000004619

in Bibtex Style

@conference{daml24,
author={Hanwen Li},
title={Enhancing Cardiovascular Disease Prediction with Machine Learning: A Comparative Study Using the UCI Heart Disease Dataset},
booktitle={Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2024},
pages={295-300},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013516000004619},
isbn={978-989-758-754-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Enhancing Cardiovascular Disease Prediction with Machine Learning: A Comparative Study Using the UCI Heart Disease Dataset
SN - 978-989-758-754-2
AU - Li H.
PY - 2024
SP - 295
EP - 300
DO - 10.5220/0013516000004619
PB - SciTePress