Real-Time PPG Signal Quality Assessment via Frequency Domain Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining the quality of photoplethysmograph (PPG) signals from wearable devices are inefficient due to high susceptibility to motion artifacts, requiring extensive training data and being limited to offline analysis, making them unsuitable for real-time and dynamic scenarios.

Innovation Solution

A system and method that employs filtering, differential evolutionary optimization to estimate optimal thresholds for real-time PPG signal quality assessment, utilizing heart and respiratory frequency components from edge computing scenarios, including wearable and medical devices, to classify signals as good or bad.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If supervised machine learning methods are used for PPG signal quality assessment, then classification accuracy can be improved, but the method requires huge amount of training data and is limited to offline scenarios

Engineering Contradiction:
Improvesignal quality classification accuracyVSAvoidtraining data requirement
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential frequency domain features (heart rate and respiratory rate components) from the PPG signal, rather than using comprehensive supervised learning features. This extraction approach enables quality assessment with minimal data requirements while maintaining accuracy, directly resolving the contradiction between accuracy and data quantity requirements

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the complex supervised machine learning system with a simpler frequency domain analysis system based on physiological knowledge. This substitution eliminates the need for large training datasets while preserving classification accuracy, as the method relies on fundamental physiological signal characteristics rather than learned patterns

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If supervised machine learning methods are used for PPG signal quality assessment, then classification accuracy can be improved, but the method is limited to offline scenarios and cannot be implemented in real-time

Engineering Contradiction:
Improvesignal quality classification accuracyVSAvoidreal-time processing capability
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent substitutes complex supervised learning algorithms with straightforward frequency domain analysis that can be computed in real-time. By using spectral analysis to identify heart rate and respiratory rate peaks, the system achieves both high accuracy and real-time processing capability, resolving the contradiction between accuracy and productivity

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Loss of information

If pulse level feature extraction is used for PPG signal classification, then some signal quality information can be obtained, but the method is not reliable when signal is highly contaminated with artifacts

Engineering Contradiction:
Improvesignal quality information retentionVSAvoidclassification reliability under noise
Core Design Contradiction:
Loss of informationVSReliability

Solution Approach 1:

The patent transitions from time-domain pulse level analysis to frequency-domain analysis. By examining the spectral characteristics of the PPG signal, the method can identify heart rate and respiratory rate components even when time-domain pulse morphology is severely degraded by motion artifacts, thereby maintaining reliability under noisy conditions

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP4147633B1A method and a system for determining quality of photoplethysmogram (PPG) signal
Publication Date: 2024.03.06 TATA CONSULTANCY SERVICES LTD
  • EP4147633B1 patent drawingFigure 1
  • EP4147633B1 patent drawingFigure 2
  • EP4147633B1 patent drawingFigure 3A

AI summary

This disclosure relates generally to a method and a system for determining quality of PPG signal. The PPG signals are extensively used for deducing health parameters of patients to infer the physiological conditions of heart, blood pressure, breathing patterns of the patients. However, analysis based on PPG signals is extremely challenging and is accurate only on high quality PPG signals. However, the existing techniques for determining quality of PPG signal (that are collected using wearable devices) require huge training or use complicated algorithms and cannot be used for real-time analysis. The disclosed methods and system for PPG quality assessment is based on the frequency domain analysis, wherein heart and respiratory components in the frequency spectrum are used effectively to derive the quality checker metric which is further used to estimate a plurality of optimal thresholds that is used for determining the quality of PPG signals at real-time.