Electrocardiogram Delineation Using Deep Neural Networks.

Area of Science:

• Computational biology
• Medical informatics
• Artificial intelligence in healthcare

Background:

• Deep neural networks (DNNs) are increasingly explored for electrocardiogram (ECG) analysis.
• Accurate ECG wave delineation is crucial for diagnosing cardiac conditions.

Purpose of the Study:

• To investigate various DNN architectures for ECG delineation.
• To evaluate the performance of DNNs in classifying ECG waves.
• To assess the computational efficiency of DNN models.

Main Methods:

• A 5-fold cross-validation approach was employed to test multiple DNN architectures.
• Performance metrics included sensitivity and positive predictive value for ECG wave identification.

Main Results:

• The top-performing DNN achieved 100% sensitivity for all ECG waves.
• The best network demonstrated a positive predictive value exceeding 97% for all ECG waves.
• The developed DNN approach offers comparable classification performance to existing methods.

Conclusions:

• DNNs can effectively delineate ECG waves with high accuracy.
• The proposed DNN model achieves high performance at a reduced computational cost.
• This research contributes to efficient AI-driven ECG analysis.