A comparative analysis of predicting heart disease using machine learning algorithms
Heart disease remains a significant public health challenge. Predicting its circumstance at an early stage is crucial as it is a serious health condition. Machine learning has been widely applied to precisely identify the risk of heart disease depending on clinical data. The purpose of this study is...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
Springer Science and Business Media Deutschland GmbH
2026
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/47066/1/A%20comparative%20analysis%20of%20predicting%20heart%20disease.pdf https://umpir.ump.edu.my/id/eprint/47066/ https://doi.org/10.1007/978-981-96-7749-8_23 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Heart disease remains a significant public health challenge. Predicting its circumstance at an early stage is crucial as it is a serious health condition. Machine learning has been widely applied to precisely identify the risk of heart disease depending on clinical data. The purpose of this study is to investigate the potential of machine learning algorithms in forecasting heart disease and compare the performance of each algorithm. This study applies six machine learning algorithms, including K-nearest neighbors, logistic regression, Bayesian classifier, decision tree, random forest, and support vector machine. The study systematically makes use of the existing dataset from Kaggle. This research classifies their performance using different evaluation metrics comparatively accuracy, precision, recall, and F1-score. By examining the effectiveness of multiple algorithms, the study attempts to determine the greatest promising approach for prediction for heart disease. The findings of this study show that K-nearest neighbors exhibited the highest accuracy score achieving 90% compared to other classifiers. These results highlight the possibility of machine learning approaches for enhancing heart disease prognosis and enabling earlier diagnosis and treatment. |
|---|