Automatic detection of end QRS notching or slurring

Area of Science:

• Cardiology
• Biomedical Engineering
• Signal Processing

Background:

• Electrocardiography (ECG) is crucial for diagnosing cardiac conditions.
• Subtle ECG waveform abnormalities, like QRS notching and slurring, can indicate underlying pathology.
• Accurate and automated detection of these findings is desirable for efficient clinical workflow.

Purpose of the Study:

• To establish criteria for the automated detection of end QRS notching and slurring.
• To assess the accuracy of an automated ECG analysis program for identifying these phenomena.

Main Methods:

• Developed automated detection criteria for end QRS notching and slurring.
• Utilized a training and testing dataset of 100 resting 12-lead ECGs from young adult men.
• Validated the automated method on independent Caucasian and Nigerian subject populations.

Main Results:

• The automated detection achieved high sensitivity (90.5-92.1%) and specificity (96.5-96.6%) in both training and test sets.
• Prevalence of notching/slurring (≥ 0.1 mV amplitude) was 23% in Caucasians and 29% in Nigerians.
• The automated method demonstrated consistent performance across different populations.

Conclusions:

• Automated detection of end QRS notching and slurring is feasible with high accuracy.
• This automated approach can aid in the efficient and reliable identification of ECG abnormalities.
• The findings support the integration of such algorithms into clinical ECG interpretation tools.