Physiological Signal Quality Assessment Using Shape-Based Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for evaluating the quality of periodic or quasi-periodic physiological signals, such as PPG, ECG, ICG, and BCG signals, are inadequate as they fail to accurately discriminate between high-quality and low-quality signal portions, especially in ambulatory setups where motion artifacts and environmental changes occur.
Innovation Solution
A method that segments physiological signals into temporal segments, determines a shape difference distance between each segment and offset segments, and calculates a quality index based on these distances, allowing for continuous adaptation to environmental and activity-level changes without the need for calibration or individualized measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional quality evaluation methods are used for physiological signals, then the system is simple to implement, but the measurement precision and reliability of signal quality assessment deteriorate in ambulatory setups with motion artifacts
Solution Approach 1:
The physiological signal is divided into multiple temporal segments, allowing quality assessment to be performed on individual segments rather than the entire signal. This enables precise identification of high-quality vs. low-quality portions (e.g., those affected by motion artifacts) while maintaining computational efficiency through localized analysis.
Solution Approach 2:
The quality evaluation transitions from static conventional methods to a dynamic approach where quality indices are computed for each temporal segment independently. This dynamic segmentation allows the system to adapt to changing signal conditions (e.g., motion artifacts occurring at specific times) and provides time-varying quality assessment.
2Reliability
If existing quality index methods are applied, then the computational process is fast, but the reliability of physiological parameter determination deteriorates due to inclusion of noisy segments
Solution Approach 1:
Different quality assessments are applied to different temporal segments of the physiological signal. Each segment receives an individual quality index reflecting its local characteristics, allowing the system to weight or select segments based on their specific quality rather than applying a uniform assessment to the entire signal.
Solution Approach 2:
Low-quality segments (e.g., those contaminated by motion artifacts) are extracted and excluded from physiological parameter computation. The method identifies and separates problematic segments from high-quality segments, ensuring that only reliable data contributes to the final physiological parameter determination.
3Adaptability or versatility
If fixed predetermined values are used for quality assessment, then the method is easy to implement, but the adaptability to environmental and activity-level changes deteriorates
Solution Approach 1:
The quality evaluation method transitions from using fixed predetermined thresholds to dynamic, data-driven quality indices computed for each temporal segment. This allows the system to automatically adapt to changing environmental conditions and activity levels without requiring manual recalibration or individualized measurements, as each segment is assessed based on its own characteristics and local context.
Data Source
AI summary
A method, intended for the evaluation of the quality of at least one periodic or quasi-periodic physiological signal, which includes the steps of: segmenting the physiological signal temporally into a plurality of signal segments; for each given signal segment, determining a distance representative of a shape difference between the given signal segment and at least one signal segment temporally offset relative to the given signal segment; and determining a quality index of the given signal segment according to the distance determined for the given signal segment.