Enhancing Heart Attack Forecasting Using Machine Learning Models

DOI

10.2991/978-94-6463-884-4_73How to use a DOI?

Keywords

Cardiovascular Disease; XGBoost; Machine Learning; Heart Attack; Framingham database

Abstract

Heart attacks, or cardiac arrests, are a major global health concern, accounting for nearly 31% of deaths worldwide due to cardiovascular diseases (CVDs). These conditions result from chronic processes influenced by modifiable and non-modifiable risk factors. Many cases are preventable through lifestyle changes such as maintaining a healthy diet, engaging in regular physical activity, and avoiding tobacco use. Studies suggest that consuming more than five glasses of water daily and undergoing routine health evaluations focusing on blood pressure, cholesterol levels, and heart rate, along with stress management practices like meditation, can significantly reduce risks. Machine learning (ML) has become a pivotal tool in healthcare, enabling the development of predictive models for conditions like heart attacks. This study utilizes supervised ML classifiers, including XGBoost, Decision Tree, Random Forest, and Logistic Regression, to develop a model predicting myocardial infarction. Using data from the Framingham database and the UCI Heart repository, a machine-learning pipeline was established, incorporating unoptimized and feature-transformed methods to improve prediction accuracy. The results show that the XGBoost classifier achieved the highest accuracy, generating binary predictions where 1 indicates a heart attack risk and 0 suggests no risk. Chest pain type was the most significant predictive factor, with typical angina having the greatest impact, while asymptomatic chest pain was the least. Other important factors included cholesterol levels above 200 mg/dl, elevated heart rate, and thalassemia. The study emphasizes that 80% of premature heart attacks are preventable through proactive lifestyle interventions and consistent health monitoring. By leveraging advanced ML techniques and addressing modifiable risk factors, this research highlights the transformative role of technology in early detection, prevention, and improved management of cardiovascular diseases.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sohan Rana Apurbo
AU  - Israt Jahan Santa
AU  - Sharmin Akter
AU  - Md. Forhad Ali
PY  - 2025
DA  - 2025/11/18
TI  - Enhancing Heart Attack Forecasting Using Machine Learning Models
BT  - Proceedings of the 8th International Conference on Engineering Research, Innovation, and Education 2025 (ICERIE 2025)
PB  - Atlantis Press
SP  - 607
EP  - 613
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-884-4_73
DO  - 10.2991/978-94-6463-884-4_73
ID  - Apurbo2025
ER  -