Physiological Signal Processing Apparatus for Arrhythmia Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining vital signs from physiological signals, especially in non-stationary conditions or with arrhythmias, face challenges such as signal distortions, noise, and overlapping spectra, leading to inaccurate peak detection and quality assessment, particularly when using unobtrusive sensors like accelerometers.
Innovation Solution
A processing apparatus that determines an average waveform from physiological signals to create a model signal, which is invariant to timing and amplitude variations, allowing for accurate quality metric calculation and vital sign determination without prior knowledge of waveform shapes, and enables processing of non-stationary signals by comparing the model signal with the original signal to assess signal quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional spectral analysis or pattern matching methods are used to determine vital signs from physiological signals, then the processing can be performed with standard algorithms, but the accuracy deteriorates in non-stationary conditions or with arrhythmias due to signal distortions, noise, and overlapping spectra
Solution Approach 1:
The patent applies dynamics by making the reference waveform adaptive rather than fixed. The reference waveform is dynamically updated based on previously detected waveforms, allowing it to adapt to changing signal characteristics in non-stationary conditions. This enables the system to maintain high detection accuracy even when signal properties change over time or when arrhythmias are present.
Solution Approach 2:
The system uses self-service by automatically generating its own reference waveform from the measured signals themselves. Instead of requiring external template data or manual calibration, the system extracts reference waveforms directly from the physiological signals being analyzed, making the detection process self-calibrating and automatically adaptive to the specific subject and conditions.
2Measurement precision
If filtering techniques are used to suppress drifts, noise and artifacts in the physiological signal, then signal quality improves, but the shape or morphology information of the signal is lost
Solution Approach 1:
The patent applies taking out by extracting only the essential morphological features needed for detection while removing distracting elements. Instead of applying broad filtering that removes all variations, the system extracts the characteristic waveform shape and uses it as a reference for detection, thereby preserving the essential morphology information while suppressing noise and artifacts through the matching process.
3Ease of operation
If unobtrusive sensors like accelerometers are used to measure physiological signals, then patient comfort and compliance improve, but the signals contain more noise and overlapping physiological contributions
Solution Approach 1:
The patent applies intermediary by introducing a reference waveform as an intermediate representation that mediates between the noisy raw signal and the vital sign extraction. The reference waveform serves as a template that captures the essential signal characteristics while filtering out noise and artifacts through the correlation or matching process, enabling accurate detection despite the poor quality of signals from unobtrusive sensors.
Data Source
Figure 1~3
Figure 4~5
Figure 6~7
AI summary
A processing apparatus for processing a physiological signal is presented. The processing apparatus is configured to perform the steps of: obtaining the physiological signal (6) containing at least two wave cycles originating from a physiological process (6b), obtaining a feature signal (12) descriptive of occurrences of a feature (P) in the physiological signal (6), determining an average waveform of the physiological signal (6) around said occurrences of the feature (P) in the physiological signal (6), and determining a model signal (18) comprising amplitude-scaled instances of the average waveform of the physiological signal (6) placed at the occurrences of the feature (P) in the physiological signal (6). Furthermore, a corresponding processing method, a system (1) for determining a vital sign of a subject comprising said processing apparatus and a computer program are presented.