A Hybrid Machine Learning Approach for Heart Disease Prediction with Ecg & Echo Analysis and Explainable Ai
Abstract
Cardiovascular diseases remain one of the leading causes of mortality worldwide, underscoring the urgent need for early detection and accessible diagnostic solutions. This paper presents a hybrid machine learning and deep learning framework that integrates electrocardiogram (ECG) and echocardiography (ECHO) analysis with explainable AI techniques to enhance heart disease prediction. The developed application incorporates five core features: individualized patient prediction, batch prediction via CSV input, model transparency through algorithmic explanations, ECG-based arrhythmia and myocardial irregularity detection, and an extended framework for ECHO evaluation, personalized recommendations, hospital locator integration, and automated report summarization. By combining multiple machine learning and deep learning algorithms with explainable AI methodologies, the system not only improves predictive accuracy but also ensures interpretability and user trust. Furthermore, the model highlights critical risk factors such as cholesterol and blood pressure, bridging the gap between predictive analytics and practical healthcare applications.References
Soni, J., Ansari, U., Sharma, D., & Soni, S. (2011). Predictive data mining for medical diagnosis: An overview of heart disease prediction. International Journal of Computer Applications, 17(8), 43–48.
Jindal, H., Agrawal, S., Khera, R., Jain, R., & Nagrath, P. (2021). Heart disease prediction using machine learning algorithms. IOP Conference Series: Materials Science and Engineering, 1022(1), Article 012072. https://doi.org/10.1088/1757-899X/1022/1/012072
Saxena, K., & Sharma, R. (2016). Efficient heart disease prediction system. Procedia Computer Science, 85, 962–969. https://doi.org/10.1016/j.procs.2016.05.316
Marimuthu, M., Abinaya, M., Hariesh, K. S., Madhankumar, K., & Pavithra, V. (2018). A review on heart disease prediction using machine learning and data analytics approach. International Journal of Computer Applications, 181(18), 20–25.
Bhatla, N., & Jyoti, K. (2012). An analysis of heart disease prediction using different data mining techniques. International Journal of Engineering, 1(8), 1–4.
De Bacquer, D., De Backer, G., Kornitzer, M., & Blackburn, H. (1998). Prognostic value of ECG findings for total, cardiovascular disease, and coronary heart disease death in men and women. Heart, 80(6), 570–577. https://doi.org/10.1136/hrt.80.6.570
Golande, A. L., & Pavankumar, T. (2023). Optical electrocardiogram based heart disease prediction using hybrid deep learning. Journal of Big Data, 10(1), 139. https://doi.org/10.1186/s40537-023-00862-6
Dhandapani, S., Somasundaram, H., & Angamuthu, T. (2025). Hybrid deep learning framework for heart disease prediction using ECG signal images. Scientific Reports, 15(1), 33922. https://doi.org/10.1038/s41598-025-95066-6
Picano, E., Ciampi, Q., Citro, R., D’Andrea, A., Scali, M. C., Cortigiani, L., ... & Colonna, P. (2017). Stress Echo 2020: The international stress echo study in ischemic and non-ischemic heart disease. Cardiovascular Ultrasound, 15(1), Article 3. https://doi.org/10.1186/s12947-016-0092-1
Fedesoriano. (2020). Heart failure prediction dataset [Data set]. Kaggle. https://www.kaggle.com/datasets/fedesoriano/heart-failure-prediction
Evil Spirit05. (2024). ECG images dataset of cardiac patients [Data set]. Kaggle. https://www.kaggle.com/datasets/evilspirit05/ecg-analysis
Stanford AIMI. (2020). EchoNet-Dynamic [Data set]. https://stanfordaimi.azurewebsites.net/datasets/834e1cd1-92f7-4268-9daa-d359198b310a
