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

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

CardioAI: A Multi-Modal Stacking Ensemble Platform for Cardiovascular Disease Prediction and 12-Lead ECG Classification with Explainable AI

Suraj Narayan Devamane, Mrs. Manjusha Kulkarni, Kalavathi V A, Kartik G Golabhanvi et al.
International Journal of Creative and Open Research in Engineering and Management
Artificial Intelligence in Healthcare
article

CardioAI: A Multi-Modal Stacking Ensemble Platform for Cardiovascular Disease Prediction and 12-Lead ECG Classification with Explainable AI

Suraj Narayan Devamane, Mrs. Manjusha Kulkarni, Kalavathi V A, Kartik G Golabhanvi, Pruthvi N K
article en

Abstract

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.

International Journal of Creative and Open Research in Engineering and ManagementVol. 02(11)
Artificial Intelligence in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon