Citation :

G. Amalorpavam, N. Rajkumar, "Improved Adaptive Kernel-Based SVM Ensemble for Enhanced Heart Disease Diagnosis: A Feature Optimization Approach," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 2, pp. 245-265, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I2P118

Abstract

Since cardiovascular disease continues to be the world’s leading cause of death, precise, data-driven diagnostic systems must be developed. By combining multi-phase feature selection, adaptive model training, and sophisticated preprocessing, this study suggests an intelligent classification framework for the diagnosis of heart disease. Using a novel hybrid kernel function for dynamic feature space adaptation, the Improved Adaptive Support Vector Machine (IASVM) is an improved version of the Random Forest (RF), Neural Network (NN), and Support Vector Machine (SVM) classifiers. The dataset is first normalized for consistency and cleaned using outlier detection (Isolation Forest). A comprehensive method that combines correlation analysis, ANOVA F-test, Random Forest Importance (RFI), and SHAP value analysis is used to select features. These complementary methods reduce dimensional complexity while identifying a small, highly impactful subset of features that maintain diagnostic significance. To assess how feature reduction affects performance, all four models are trained on both the full feature set and the optimized subset for classification. The IASVM uses an adaptive kernel function that dynamically scales according to the geometric properties of the dataset, integrating the Manhattan and Euclidean distances. Because of this, it can more effectively differentiate between overlapping classes in nonlinear spaces, especially in clinical settings where feature distributions are unbalanced or skewed. To fine-tune classification boundaries, grid search and cross-validation are used in the IASVM’s hyperparameter tuning process. A real-world dataset of heart disease is used for experimental evaluations, and metrics like accuracy, precision, recall, F1-score, and AUC are used to compare the models. The findings highlight the IASVM’s capacity to generalise in high-dimensional and noisy domains by showing that, even though traditional models function well, it invariably performs better than the others, particularly when using the chosen feature set. Additionally, to improve clinical interpretability and usability, a graphical user interface (GUI) is created to display feature selection results, classification metrics, and accuracy comparisons. This study demonstrates how well feature optimisation and adaptive kernel-based classification work together, offering a scalable and understandable method for improving cardiovascular healthcare decision support.

Keywords

Heart Disease Diagnosis, Random Forest, Neural Network, Support Vector Machine, Adaptive Support Vector Machine, Grid search, Feature Selection, SHAP, Ensemble Learning, Medical Classification, ROC Curve.

References

[1] World Health Organization, Cardiovascular Diseases (CVDs), WHO, 2021. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)

[2] P.K. Anooj, “Clinical Decision Support System: Risk Level Prediction of Heart Disease using Weighted Fuzzy Rules,” Journal of King Saud University - Computer and Information Sciences, vol. 24, no. 1, pp. 27-40, 2012.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Santhana Krishnan J. and Geetha S., “Prediction of Heart Disease Using Machine Learning Algorithms,” 2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT), Chennai, India, pp. 1-5, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[4] S. Madeh Piryonesi, and Tamer E. El-Diraby, “Data Analytics in Asset Management: Cost-Effective Prediction of the Pavement Condition Index,” Journal of Infrastructure Systems, vol. 26, no. 1, pp. 1-25, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Isabelle Guyon et al., “Gene Selection for Cancer Classification using Support Vector Machines,” Machine Learning, vol. 46, no. 1-3, pp. 389-422, 2002.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Debabrata Swain et al., “An Efficient Heart Disease Prediction System Using Machine Learning,” Machine Learning and Information Processing, Advances in Intelligent Systems and Computing, vol. 1101, Singapore, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Scott M Lundberg, and Su-In Lee, “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems (NeurIPS), vol. 30, pp. 1-10, 2017.
[Google Scholar] [Publisher Link]

[8] Raniya R. Sarra et al., “Enhanced Heart Disease Prediction based on Machine Learning and χ² Statistical Optimal Feature Selection Model,” Designs, vol. 6, no. 5, pp. 1-12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Mohsen Dorraki et al., “Improving Cardiovascular Disease Prediction with Machine Learning using Mental Health Data: A Prospective UK Biobank Study,” JACC: Advances, vol. 3, no. 9, pp. 1-9, 2024.
[Google Scholar] [Publisher Link]

[10] Narendra Kumar Sharma et al., “Enhancing Heart Disease Diagnosis: Leveraging Classification and Ensemble Machine Learning Techniques in Healthcare Decision-Making,” Journal of Integrated Science and Technology, vol. 13, no. 1, pp. 1-8, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Ahmad Hammoud et al., “Coronary Heart Disease Prediction: A Comparative Study of Machine Learning Algorithms,” Journal of Advances in Information Technology, vol. 15, no. 1, pp. 27-32, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Govardhan Logabiraman et al., “Heart Disease Prediction using Machine Learning Algorithms,” MATEC Web of Conferences, vol. 392, pp. 1-9, 2024.
[CrossRef] [Publisher Link]

[13] Neeraja Joshi, and Tejal Dave, “Improved Accuracy for Heart Disease Diagnosis using Machine Learning Techniques,” Journal of Informatics and Web Engineering, vol. 4, no. 1, pp. 42-52, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Vankamamidi S. Naresh, and Sivaranjani Reddi, “Exploring the Future of Privacy-Preserving Heart Disease Prediction: A Fully Homomorphic Encryption-Driven Logistic Regression Approach,” Journal of Big Data, vol. 12, no. 1, pp. 1-27, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Rasool Reddy Kamireddy, and Nagadevi Darapureddy, “A Machine Learning-Based Approach for the Prediction of Cardiovascular Diseases,” Engineering Proceedings, vol. 56, no. 1, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Arvind Pandey et al., “Mitigating Class Imbalance in Heart Disease Detection with Machine Learning,” Multimedia Tools and Applications, vol. 84, no. 30, pp. 36497-36522, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Bandla Ramesh, and Kuruva Lakshmanna, “A Novel Early Detection and Prevention of Coronary Heart Disease Framework using Hybrid Deep Learning Model and Neural Fuzzy Inference System,” IEEE Access, vol. 12, pp. 26683-26695, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] S. Kanimozhi, and N. Sivanandan, “RETRACTED: Machine Learning based Heart Disease Prediction System,” E3S Web of Conferences, vol. 491, 2024.
[CrossRef] [Publisher Link]

[19] Songze Li, “Heart Disease Prediction based on Machine Learning,” Applied and Computational Engineering, vol. 120, no. 1, pp. 127-132, 2024.
[CrossRef] [Publisher Link]

[20] Atul Garg et al., “A Machine Learning Approach to Cardiovascular Disease Prevention in Smart Healthcare,” Lecture Notes in Networks and Systems, pp. 169-178, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[21] N. Venkata MahaLakshmi, and Ranjeet Kumar Rout, “An Intelligence Method for Heart Disease Prediction using Integrated Filter-Evolutionary Search based Feature Selection and Optimized Ensemble Classifier,” Multimedia Tools and Applications, vol. 83, no. 13, pp. 39841-39865, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[22] María Teresa García-Ordás et al., “Heart Disease Risk Prediction using Deep Learning Techniques with Feature Augmentation,” Multimedia Tools and Applications, vol. 82, no. 20, pp. 31759-31773, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[23] S.N. Netra, N.N. Srinidhi, and E. Naresh, “Adaptive Deep SVM for Detecting Early Heart Disease among Cardiac Patients,” Scientific Reports, vol. 15, no. 1, pp. 1-23, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Ahmed Essaa Abed Alowaidi, and Mesut Cevik, “Adaptive Volcano Support Vector Machine (AVSVM) for Efficient Classification,” Applied Sciences, vol. 15, no. 24, pp. 1-29, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Ji-Yeong Jang et al., Explainable AI-Based Clinical Signal Analysis for Myocardial Infarction Classification and Risk Factor Interpretation,” Signals, vol. 6, no. 4, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Saeedeh Heydarian, Classification of Coronary Artery Disease, 2023. [Online]. Available: https://www.kaggle.com/datasets/saeedeheydarian/classification-of-coronary-artery-disease