AI-Driven Real-Time Classification of ECG Signals for Cardiac Monitoring Using i-AlexNet Architecture.

Area of Science:

• Biomedical Engineering
• Artificial Intelligence in Healthcare
• Computational Medicine

Background:

• The healthcare industry is increasingly leveraging artificial intelligence (AI) for advanced data analysis.
• AI offers potential for improved diagnostics, personalized treatments, and operational efficiency in medical settings.
• Analyzing electrocardiogram (ECG) signals is crucial for diagnosing various cardiac conditions.

Purpose of the Study:

• To develop and evaluate an AI-based method for accurate classification of normal and anomalous ECG signals.
• To enhance the diagnostic capabilities for cardiac abnormalities using advanced machine learning techniques.
• To improve the accuracy and efficiency of ECG interpretation in clinical practice.

Main Methods:

• ECG signals undergo preprocessing for noise reduction and heartbeat segmentation.
• Multi-feature extraction is performed, followed by an optimization technique for feature selection.
• An improved AlexNet model, termed i-AlexNet, is utilized for classifying ECG signals.
• The proposed method is validated using the PTB and MIT-BIH public ECG databases.

Main Results:

• The developed AI approach demonstrates high performance in classifying ECG signals.
• The i-AlexNet classifier achieves a superior accuracy of 98.8% on the tested databases.
• The proposed method outperforms existing techniques in the literature for ECG analysis.

Conclusions:

• The AI-driven method provides a robust and accurate solution for detecting abnormal ECG signals.
• This research highlights the significant potential of AI in revolutionizing cardiac diagnostics.
• The high accuracy achieved suggests clinical applicability for improved patient outcomes.