CardioAI: A Multi-Modal Stacking Ensemble Platform for Cardiovascular Disease Prediction and 12-Lead ECG Classification with Explainable AI
Heart disease is one of the leading causes of death worldwide, and early prediction plays a crucial role in reducing mortality and improving patient outcomes. This paper presents a comparative study of machine learning and deep learning approaches for heart disease prediction using different types of medical data, including clinical records, ECG signals, and echocardiography images. Traditional machine learning models such as Logistic Regression, Support Vector Machine, and Random Forest are effective for structured clinical data, while deep learning models such as Convolutional Neural Networks (CNNs) are used for processing ECG signals and medical imaging data. In addition, multimodal approaches combining multiple data sources are also explored to improve prediction performance. To support the comparative analysis, three modules were implemented: Echo, ECG, and Clinical. The Clinical stacking model achieved the highest accuracy of 94.54%, followed by the ECG CNN-based model with 82.08%, and the Echo MobileNetV2 model with 80.7%. The results show that structured clinical data provides more reliable predictions, while signal and imaging data require larger datasets and more complex models. Despite improvements in prediction accuracy, challenges such as small dataset sizes, lack of interpretability, and high computational cost still exist. This study highlights the importance of integrating multiple data sources and suggests the need for efficient, explainable, and scalable models for realworld healthcare applications. Keywords—Heart Disease Prediction, Machine Learning, Deep Learning, ECG Signals, Medical Imaging, Multimodal Learning, Classification, Healthcare Analytics.
Authors
- Suraj Narayan Devamane
- Mrs. Manjusha Kulkarni
- Kalavathi V A
- Kartik G Golabhanvi
- Pruthvi N K
Publication Details
- Journal
- International Journal of Creative and Open Research in Engineering and Management
- Published
- 2026-11-21
- DOI
- https://doi.org/10.55041/ijcope.v2i11.096
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00