ECG Feature-Based Classification of Heart Disease Using Hybrid Ensemble Models

DOI

10.2991/978-94-6463-866-0_78How to use a DOI?

Keywords

Heart Disease Prediction; Ensemble Machine Learning; Soft Voting Classifier; ECG Metadata Analysis; Random Forest; XGBoost; CatBoost; Diagnostic Accuracy; Medical Decision Support

Abstract

Heart disease continues to be the primary cause of death globally. It highlights the importance of reliable and efficient diagnostic methods to reduce its impact. This paper presents a state-of-the-art ensemble-based machine learning architecture for predicting heart disease, aiming to enhance diagnostic accuracy. The proposed model learns ECG image-derived metadata, with a focus on ST elevation, T-wave inversion, and abnormal QRS complexes, as these are the most significant indicators of heart disease. To achieve exceptional prediction accuracy, the proposed work combines Random Forest (89%), XGBoost (89%), and CatBoost (90%) into a Soft Voting Classifier (91%), ensuring reliability by harnessing the distinct advantages of each model. The methodology includes various data manipulation techniques, label encoding, dataset splitting, and data cleaning to ensure strong performance across datasets. The soft voting classifier not only expedites diagnosis but also provides valuable insights, empowering patients to take proactive steps and enhance their heart health. The machine learning ensemble, featuring a Soft Voting Classifier with 91% accuracy, facilitates quicker and more precise heart disease diagnosis by promoting dependable, scalable medical decision-making.

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  - M. Sam Navin
AU  - P. V. K. Ravi
AU  - C. Bhavitha
AU  - S. Sanath
PY  - 2025
DA  - 2025/10/31
TI  - ECG Feature-Based Classification of Heart Disease Using Hybrid Ensemble Models
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 967
EP  - 979
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_78
DO  - 10.2991/978-94-6463-866-0_78
ID  - Navin2025
ER  -