International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | XAI Based Heart Disease Prediction System with Feature Importance Visualization: A Survey |
|---|---|
| ABSTRACT | Heart disease remains the leading global cause of mortality, which makes reliable and actionable prediction systems a clinical priority. Conventional machine learning (ML) models can achieve strong discriminative performance on structured clinical data or biosignals such as ECG, but they often behave as opaque black boxes—limiting clinical adoption where trust, accountability, and auditability are essential. Explainable Artificial Intelligence (XAI) provides a principled set of tools to expose model behavior, attribute contributions, and reduce the risk of spurious associations. This survey synthesizes recent research on XAI-driven heart disease prediction across two major data modalities—clinical tabular features and ECG signals. We review representative studies that apply SHAP-based post-hoc explainability on tree ensembles and gradient boosting, as well as signal-processing pipelines using DWT/EWT feature extraction for ECG followed by interpretable classifiers. We organize the literature by data source, modeling approach, and explanation technique, highlight a practical design that combines clinical and ECG pathways with SHAP-based global and local interpretability, and discuss open challenges in validation, uncertainty communication, and deployment. |
| AUTHOR | SANKET S. GAJARE, PROF. DR. S. A. ITKAR Department of Computer Engineering, P.E.S. Modern College of Engineering, Pune, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405101 |
| pdf/101_XAI Based Heart Disease Prediction System with Feature Importance Visualization.pdf | |
| KEYWORDS | |
| References | [1] B. Majhi and A. Kashyap, "Explainable AI-driven machine learning for heart disease detection using ECG signal," Applied Soft Computing, vol. 167, 2024. [2] A. K. Mandal, S. Dehuri, and P. K. D. Sarma, "Analysis of machine learning approaches for predictive modeling in heart disease detection systems," Biomedical Signal Processing and Control, vol. 106, 2025. [3] U. Daharwal, I. Singh, and G. Khekare, "Comparison of Machine Learning Algorithms for Heart Disease Prediction," Procedia Computer Science, vol. 260, pp. 12-21, 2025. [4] S. H. Murad, N. B. Tayfor, N. H. Mahmood, and L. Arman, "Hybrid genetic algorithms-driven optimization of machine learning models for heart disease prediction," MethodsX, vol. 15, 103510, 2025. [5] M. A. Bouqentar, O. Terrada, S. Hamida, et al., "Early heart disease prediction using feature engineering and machine learning algorithms," Heliyon, vol. 10, e38731, 2024. [6] A. Li, Y. Wang, and H. Chen, "AI driven cardiovascular risk prediction using NLP and Large Language Models for personalized medicine in athletes," SLAS Technology, vol. 32, 100286, 2025. |
