On globally heart disease is one of the major causes of death and also early detection of heart disease plays a crucial role in reducing mortality rates. In the Traditional diagnostic methods depends largely on manual analysis, Limited statistical tools and clinical experience which is delayed and incorrect diagnosis. With the huge growth of healthcare data and machine learning techniques offers a effective solutions in early stage and accurate prediction of heart disease. In this project I proposed an advanced machine learning based system for predicting the “Heart Disease” using patient’s medical attributes like age, cholesterol level, Heart rate, blood pressure and also other medical parameters. In This system employs multiple Machine Learning algorithms such as Random Forest, Support Vector machine (SVM), Gradient Boosting and Artificial Neural Network (ANN) to improve the accuracy of predicted data. Data pre-processing, feature selection and modern evaluation techniques are applied to enhanced System Performance. This system provides addition to disease prediction, The proposed system provides a personalized prediction, Recommendations and suggest suitable doctors and also patients condition. The results demonstrate that the proposed approach achieves higher accuracy and also reliability as compared to previous traditional methods. This system can serve as an effective decision-support tool for healthcare professionals and also can be further extended for real-time and large-scale healthcare applications.

This research effectively developed an advanced machine learning-based analytical system for the early prediction of a heart disease. Integrating outdated clinical parameters with sophisticated computational models this study addresses the limitations of a manual diagnostic methods and also which are often prone to human error and delays. The implementation of a difficult preprocessing pipeline—incorporating SMOTE for class balancing and IQR for an outlier mitigation it ensured high data integrity. Furthermore, the hybrid feature selection strategy is optimized the model by identifying critical predictors such as age, chest pain type, and cholesterol levels. Among the evaluated algorithms, the ensemble approach and Artificial Neural Networks (ANN) demonstrated superior performance in capturing complex, non-linear relationships compared to baseline models, achieving the higher accuracy and reliability. Beyond the mere binary classification, the system’s ability to provide a personalized recommendations and the risk social stratification transforms it into a feasible scientific decision support tool. This research bridges the gap between massive healthcare datasets and also actionable medical insights, particularly for the remote or underserved areas. Future enhancements will focus on the integrating real-time data from wearable sensors and implementing the Federated Learning to ensure patient privacy and ultimately facilitating for a large-scale transition toward proactive and personalized cardiovascular care.

1. A. Alghamdi, M. Alghamdi, and S. Alghamdi, “Heart Disease Prediction Using ML,” Journal of Imaging, vol. 11, no. 10, p. 124, Oct. 2025. [Online]. Available: https://www.mdpi.com/2673-4591/107/1/124. 2. M. Benhar, A. O. Boudhir, and A. Haqiq, “A systematic review of machine learning in heart disease prediction,” Frontiers in Artificial Intelligence, vol. 7, 2025. [Online]. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC12614364/ 3. S. Shah, D. Patel, and R. Shah, “A comprehensive review of machine learning for heart disease prediction,” Frontiers in Artificial Intelligence, vol. 8, p. 1583459, 2025. [Online]. Available: https://www.frontiersin.org/journals/artificialintelligence/ articles/ 10.3389/frai.2025.1583459/full 4. M. A. Alghamdi, M. Alghamdi, and S. Alghamdi, “A proposed technique for predicting heart disease using machine learning algorithms,” Scientific Reports, vol. 14, p. 74656, Oct. 2024. [Online].https://www.nature.com/articles/s41598-024-74656-2 5. R. Krishna, S. Kumar, and A. Reddy, “Accurate Heart Disease Prediction using Machine Learning Techniques on Clinical Data,” International Journal of Computer Applications, vol. 187, no. 65, Dec. 2025. [Online]. Available: https://ijcaonline.org/archives/volume187/number65/accurateheart- diseaseprediction-using-machine-learning-techniques-on-clinicaldata/

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close