ECG Noise Discrimination via Power Spectral Density Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cardiac monitoring devices face a high frequency of false detections of life-threatening arrhythmias due to noise in electrocardiogram (ECG) signals, leading to unnecessary treatments and alarm fatigue.
Innovation Solution
The implementation of a cardiac monitoring device that utilizes power spectral density (PSD) analysis and machine learning to distinguish between cardiac events and noise in ECG signals, by extracting features such as dominant frequency, in-band entropy, first-band entropy, and variance, and comparing these to predetermined threshold scores to accurately determine the presence of arrhythmias.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional signal processing techniques are used to detect arrhythmias, then detection sensitivity is maintained, but false detection frequency increases due to noise
Solution Approach 1:
The patent transforms the ECG signal from time-domain to frequency-domain using power spectral density analysis. This dimensional transformation allows the system to analyze signal characteristics in the frequency dimension, where arrhythmias exhibit distinct spectral patterns different from noise, enabling more accurate discrimination between true arrhythmias and noisy signals
Solution Approach 2:
The system changes the analysis parameters by computing power spectral density features (dominant frequency, in-band entropy, first-band entropy, variance) instead of relying on traditional time-domain signal processing. These spectral parameters provide new discriminative features that improve the ability to distinguish arrhythmias from noise, reducing false detections while maintaining detection sensitivity
2Measurement precision
If multiple signal processing routines are implemented to reduce false detections, then detection accuracy improves, but device complexity increases
Solution Approach 1:
The patent divides the signal processing system into two distinct modules: a first module that detects potential arrhythmia events using traditional signal processing, and a second module that evaluates these events using power spectral density analysis. This segmentation allows each module to specialize in its function, with the second module acting as a filter to reduce false detections without requiring complete redesign of the entire system
Solution Approach 2:
The power spectral density analysis acts as an intermediary evaluation layer between initial arrhythmia detection and final treatment decision. The second module computes spectral features and compares them against thresholds to determine whether a detected event represents a true arrhythmia or noise, providing a systematic intermediary assessment that reduces false positives
Data Source
AI summary
A system includes an ambulatory medical device and a server. The ambulatory medical device comprises: a digital signal processing module configured to: detect an abnormal rhythm from an electrocardiogram (ECG) signal of a patient using a first signal processing routine; and generate a first flag indicating an abnormal rhythm is detected; and a noise detector module configured to: receive the ECG signal from the digital signal processing module; execute a second signal processing routine to classify the abnormal rhythm as one of an arrhythmia event and a noise event; and, if the abnormal rhythm is classified as a noise event, initiate a preconfirmation period during which the noise detector module continues to evaluate the abnormal rhythm and classify the abnormal rhythm as one of an arrhythmia event and a noise event using the second signal processing routine; and generate a second flag indicating the start of the preconfirmation period; and a server configured to: receive the ECG signal, the first flag indicating the abnormal rhythm, and the second flag indicating the start of the preconfirmation period; and provide a visual indication of the preconfirmation period.