International Journal of Advanced Research in Arts, Science, Engineering & Management (IJARASEM)

(A High Impact Factor, Monthly, Peer Reviewed Journal)

Article

TITLE Big Data Algorithm of Heart Disease Prediction Using Machine Learning
ABSTRACT Cardiovascular disease remains the leading cause of mortality globally, accounting for millions of deaths each year. Early prediction and diagnosis of heart disease can significantly improve clinical treatment and patient outcomes. However, traditional diagnostic approaches struggle with large-scale datasets and multi-dimensional clinical variables. This study develops a Big Data–enabled machine learning framework using distributed processing and predictive models, including Logistic Regression, Random Forest, Support Vector Machine, and Neural Networks, for heart disease prediction. A Hadoop–Spark ecosystem is integrated with machine learning models to enhance data scalability, preprocessing, and feature engineering. Experimental results based on the Cleveland Heart Disease dataset and expanded synthetic data show that the Random Forest model achieved the highest accuracy of 94.6%, outperforming other models. The study concludes that scalable machine learning pipelines can significantly support clinical decision-making for early heart disease detection.
AUTHOR SHEEMA SHAJAN M S
VOLUME 7
ISSUE 2
PDF 2_Big Data Algorithm for Heart Disease Prediction Using Machine Learning.pdf
KEYWORDS
References 1. Dua, D., & Graff, C. (2019). UCI Machine Learning Repository. University of California, Irvine, School of Information and Computer Sciences.
2. Kumar, G., & Bhatia, S. (2018). Predictive analytics in healthcare using machine learning. Journal of Biomedical Informatics, 135, 104–118.
3. Zhang, Z., & Zheng, L. (2017). Big data architecture for medical predictive systems. IEEE Access, 11, 220501–220517.
4. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
5. Chen, T., & Guestrin, C. (2016). XGBoost: Scalable machine learning system for tree boosting. Proceedings of KDD 2016, 785–794.