Artificial Intelligence for Cardiac Diseases Diagnosis and Prediction Using ECG Images on Embedded Systems.

Area of Science:

• Biomedical Engineering
• Artificial Intelligence in Healthcare
• Cardiology

Background:

• Electrocardiogram (ECG) analysis is crucial for detecting cardiac conditions.
• Advancements in signal processing, particularly deep learning, offer new avenues for ECG analysis.
• Rising healthcare costs necessitate cost-effective diagnostic tools.

Purpose of the Study:

• To develop and optimize algorithmic models for predicting cardiovascular diseases using ECG data.
• To evaluate the performance of deep learning models (MobileNetV2, VGG16) for ECG analysis.
• To enable accessible, real-time cardiovascular health monitoring via mobile devices.

Main Methods:

• Implementation of deep learning algorithms, specifically MobileNetV2 and VGG16.
• Optimization of deep learning parameters through extensive experimentation.
• Deployment and testing of models on a Raspberry Pi for real-world performance evaluation.

Main Results:

• Both MobileNetV2 and VGG16 achieved a validation accuracy of approximately 0.95.
• Post-Raspberry Pi implementation, accuracies were 0.94 for MobileNetV2 and 0.90 for VGG16.
• The study demonstrates the feasibility of using deep learning for accurate ECG analysis on resource-constrained devices.

Conclusions:

• Deep learning models show significant potential for accurate cardiovascular disease prediction from ECGs.
• Mobile implementation offers a cost-effective solution for real-time health monitoring.
• This approach can improve patient outcomes and reduce healthcare expenses through early detection.