Processing of the electroencephalogram in cardiac surgery.

Area of Science:

• Biomedical Engineering
• Neuroscience
• Cardiology

Background:

• Cardiac surgery poses risks of neurological complications.
• Monitoring brain activity via electroencephalogram (EEG) is crucial during these procedures.
• Automated detection of abnormal EEG patterns can enhance patient safety.

Purpose of the Study:

• To develop an automated method for detecting abnormal EEG patterns during cardiac surgery.
• To evaluate the effectiveness of pattern recognition techniques for EEG analysis in this context.
• To identify key EEG features for accurate classification of normal and abnormal brain activity.

Main Methods:

• Analysis of EEG data using various signal processing techniques.
• Application of pattern recognition algorithms for classification.
• Feature extraction and selection from EEG signals.

Main Results:

• A high degree of accuracy was achieved in classifying EEG patterns as normal or abnormal.
• The classification performance was significantly enhanced by utilizing only two specific EEG features.
• The developed method demonstrated potential for real-time application.

Conclusions:

• Automated EEG analysis using limited features is effective for monitoring during cardiac surgery.
• The findings support the integration of this method into computer-based monitoring systems.
• This approach can improve intraoperative neurological safety for cardiac surgery patients.