A wavelet transform coupled with a fuzzy neural network for prediction of significant st segmental changes in the ecg

Area of Science:

• Biomedical Engineering
• Cardiology
• Artificial Intelligence

Background:

• Heart disease is the leading cause of death for individuals aged 65 and older in the US.
• Myocardial infarction can cause ST segment abnormalities on an Electrocardiogram (ECG), indicating critical cardiac events.
• Early detection of ST segment changes is crucial for timely treatment and improved patient outcomes.

Purpose of the Study:

• To develop a pattern recognition model for detecting critical ST segment abnormalities in ECGs.
• To enhance the early detection capabilities for cardiac events, particularly in pre-hospital settings.
• To provide a foundation for developing treatment protocols that can save lives.

Main Methods:

• Utilizing Wavelet analysis for feature extraction from ECG signals.
• Employing a Fuzzy Neural Network for classification of ECG abnormalities.
• Implementing and simulating the model using MatLab software.
• Validating the model with ECG samples from the MIT-BIH database.

Main Results:

• The developed pattern recognition model demonstrates capability in detecting critical ST segment changes.
• Simulations confirm the model's effectiveness in identifying abnormalities in representative ECG samples.
• The approach combines advanced signal processing and machine learning for robust ECG analysis.

Conclusions:

• The developed model shows promise for early detection of critical ST changes in ECGs.
• Implementation in pre-hospital devices could significantly improve cardiac event management.
• Accurate detection facilitates the establishment of effective treatment guidelines, potentially saving lives.