Hyperparameter-Tuned Machine Learning Model for Accurate Prediction of Heart Disease
DOI:
https://doi.org/10.63682/jns.v14i31S.7080Keywords:
Cardiovascular Disease, Hyper parameters, Machine learning algorithms, Cleveland dataset, Grid Search, Random Search, Halving Grid Search, and Halving Random SearchAbstract
Cardiovascular disease (CVD) continues to be a major global health concern, contributing significantly to morbidity and mortality rates. Early and accurate diagnosis of heart disease is crucial for timely intervention and improved patient outcomes. In this study, we present a robust machine learning framework enhanced through systematic hyperparameter tuning for the identification of heart disease. The well-known Cleveland Heart Disease dataset from the UCI Machine Learning Repository is employed as the primary dataset for model development and evaluation. The proposed methodology begins with the preprocessing of the dataset, followed by the extraction of relevant features essential for classification. These features are then supplied to multiple machine learning classifiers, where the performance of each model is refined using advanced hyperparameter tuning techniques. Specifically, four prominent tuning strategies are explored: Grid Search, Random Search, Halving Grid Search, and Halving Random Search. These techniques are applied to optimize the hyperparameters of various classifiers, with the objective of maximizing prediction accuracy.
Through extensive experimentation, the Random Forest classifier optimized via Random Search emerged as the most effective model, achieving an impressive accuracy of 92.45% in detecting heart disease. This significant result highlights the impact of appropriate hyperparameter tuning on the performance of machine learning algorithms, particularly in medical data classification tasks. The findings of this study demonstrate that incorporating systematic hyperparameter optimization into the machine learning pipeline not only enhances diagnostic accuracy but also improves the generalizability and reliability of predictive models in healthcare. The proposed framework shows promise as a decision-support tool that can aid medical professionals in the early and accurate detection of cardiovascular diseases
Downloads
Metrics
References
World Health Organization. (2021). Noncommunicable diseases. Retrieved from https://www.who.int/news-room/fact-sheets/detail/noncommunicable-diseases
Giri, R., & Shukla, A. (2020). Heart disease prediction using machine learning techniques: A survey. International Journal of Computer Applications, 175(21), 7–11.
Haq, A. U., et al. (2018). Hybrid machine learning model for heart disease prediction using data mining techniques. International Journal of Engineering & Technology, 7(2.8), 290-293.
Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(Feb), 281-305.
Johnson, A. E. W., et al. (2016). Machine learning and decision support in critical care. Proceedings of the IEEE, 104(2), 444–466.
Snoek, J., Larochelle, H., & Adams, R. P. (2012). Practical Bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems, 1(1), 2951–2959.
Li, L., Jamieson, K. G., Rostamizadeh, A., Gonina, E., Hardt, M., Recht, B., & Talwalkar, A. (2020). A system for massively parallel hyperparameter tuning. Communications of the ACM, 63(5), 90-99.
Jinny, S., Vinila, S., & Mate, Y. V. (2021). Early prediction model for coronary heart disease using genetic algorithms, hyper-parameter optimization and machine learning techniques. Health and Technology, 11(1), 63–73.
Asif, M., Islam, M. T., Hossain, M. S., & Hossain, M. A. (2021). Performance evaluation and comparative analysis of different machine learning algorithms in predicting cardiovascular disease. Engineering Letters, 29(2).
Hashi, E. K., & Zaman, M. S. U. (2020). Developing a hyperparameter tuning based machine learning approach of heart disease prediction. Journal of Applied Science & Process Engineering, 7(2), 631–647.
Hashi, E. K., & Zaman, M. S. U. (2020). Developing a hyperparameter tuning based machine learning approach of heart disease prediction. Journal of Applied Science & Process Engineering, 7(2), 631–647.
Firdaus, F. F., Nugroho, H. A., & Soesanti, I. (2021). Deep neural network with hyperparameter tuning for detection of heart disease. In 2021 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob) (pp. 1–6). IEEE.
Sonth, M. V., Padma, M. C., & Reddy, K. R. (2020). Optimization of random forest algorithm with ensemble and hyper parameter tuning techniques for multiple heart diseases. Solid State Technology, 63(5), 3961–3972.
Valarmathi, R., & Sheela, T. (2021). Heart disease prediction using hyper parameter optimization (HPO) tuning. Biomedical Signal Processing and Control, 70, 103033.
El-Shafiey, M. G., Mohamed, A. W., Ahmed, A. Y., & El-Metwally, S. E. D. (2022). A hybrid GA and PSO optimized approach for heart-disease prediction based on random forest. Multimedia Tools and Applications, 81(13), 18155–18179.
Bergstra, J., Yamins, D., & Cox, D. D. (2013). Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In Proceedings of the 30th International Conference on Machine Learning (pp. 1–9).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
