There are few steps in analysis of ECG signals. The steps are namely noise elimination, cardiac cycle detection, extraction of features from ECG points, formulation of characteristic feature set, and finally classification of the ECG. Currently, we are using machine learning techniques only. The interpretation of the ECG data can be done more efficiently, accurately, and fast using deep learning techniques.

Chapter Contents:

• 11.1 Introduction
• 11.2 History
• 11.3 Overview
• 11.4 Interpreting the ECG: a six-step approach
• 11.4.1 Interpret ECG using rate and rhythm
• 11.4.1.1 Methods for calculating heart rate
• 11.4.1.2 Methods for identifying the rhythm
• 11.4.2 Axis determination in axial reference system (methods for determining the QRS axis)
• 11.4.3 Methods for determining the interval
• 11.4.4 Morphology
• 11.4.5 STE-mimics
• 11.4.6 Ischemia, injury and infarct
• 11.5 Computer-assisted ECG interpretation
• 11.5.1 Detection of limb lead misplacements
• 11.5.2 Pre-processing of ECG
• 11.5.2.1 Resample the ECG data
• 11.5.2.2 Remove noise from ECG data
• 11.5.2.3 Detection of QRS complex
• 11.5.3 Feature extraction
• 11.5.3.1 Estimation methods
• 11.5.3.2 Features to be extracted
• 11.5.4 Classification
• 11.5.5 Deep learning
• 11.6 Conclusion
• Acknowledgment
• References

Inspec keywords: noise; medical signal processing; learning (artificial intelligence); electrocardiography; feature extraction; signal classification

Other keywords: deep learning techniques; cardiac cycle detection; ECG signal processing; machine learning techniques; characteristic feature set; noise elimination; ECG points feature extraction; electrocardiography

Subjects: Bioelectric signals; Electrodiagnostics and other electrical measurement techniques; Neural computing techniques; Electrical activity in neurophysiological processes; Knowledge engineering techniques; Biology and medical computing; Digital signal processing; Signal processing and detection