ECG QRS Detection Using Wavelet Bands and Phase Transitions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ECG signal processing systems face challenges in accurately detecting QRS complexes due to artifacts caused by muscle movement or electrical interference, which can lead to misdiagnosis of cardiac arrhythmia.
Innovation Solution
A system utilizing analytic wavelet banks and quarter-phase object transforms to decompose ECG signals into frequency-limited bands, detect fractional phase transitions, and apply peak detection rules to identify QRS complexes, enhancing robustness against artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional ECG signal processing methods are used, then the system is simpler to implement, but the detection accuracy of QRS complexes deteriorates due to artifacts from muscle movement or electrical interference
Solution Approach 1:
The ECG signal is decomposed into multiple frequency bands using wavelet transform, separating the QRS complex detection task into multiple frequency-specific sub-tasks. This segmentation allows the system to focus on detecting QRS complexes in specific frequency ranges while filtering out artifacts from other frequency bands, thereby improving detection accuracy without requiring a completely complex system redesign
Solution Approach 2:
Wavelet transform coefficients serve as an intermediary representation between the raw ECG signal and the final QRS complex detection. This intermediary transforms the signal into a time-frequency domain where QRS complexes and artifacts can be more easily distinguished, allowing accurate detection while maintaining reasonable system complexity through the use of established wavelet transform algorithms
2Reliability
If artifact rejection techniques are applied to improve detection accuracy, then the reliability of heartbeat detection improves, but the computational load increases
Solution Approach 1:
The system applies different processing strategies to different frequency bands and signal components. By identifying which frequency bands contain QRS complexes versus which contain artifacts, the system applies artifact rejection techniques selectively only where needed, rather than processing the entire signal uniformly. This local approach improves reliability while minimizing unnecessary computational expenditure on clean signal portions
Solution Approach 2:
The wavelet transform parameters (such as decomposition level and wavelet type) are optimized to match the characteristic frequency ranges of QRS complexes. By tuning these parameters, the system achieves high artifact rejection capability while maintaining computational efficiency, as the transform naturally concentrates QRS energy in specific coefficient bands that can be processed with simpler operations
Data Source
AI summary
In one aspect, a computer-implemented method includes receiving a signal corresponding to electrical activity of a patient's heart; separating the signal into component signals; detecting fractional phase transitions for each of the component signals; generating, at each of the detected fractional phase transitions for each of the component signals, a data object containing a time value and an amplitude value; for a set of consecutive data objects associated with a first component signal of the component signals, detecting a peak amplitude; for a set of consecutive data objects associated with a second component signal of the component signals, detecting a peak amplitude; determining that the peak amplitudes satisfy a first time; calculating a consolidated peak amplitude and a consolidated peak time; and in response to determining that the consolidated peak amplitude satisfies both an amplitude criterion and a second time criterion, providing an indication of a detected heartbeat.