PPG Signal Quality Assessment Using ECG-Guided Heartbeat Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Photoplethysmography (PPG) signal measurement is hindered by inherent noise, particularly motion artifacts, and the lack of methods to evaluate signal quality, making it difficult to interpret waveform magnitudes and calculate clinical parameters accurately.

Innovation Solution

A system that concurrently records unfiltered PPG and ECG signals to segment heartbeats, extract features such as waveform amplitudes and pulse transition times, and classify each heartbeat as clean or noisy, allowing for the automatic identification and rejection of noisy segments, thereby improving signal quality evaluation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If signal processing techniques and compensation strategies are used to overcome noise issues, then signal quality is improved, but device complexity increases

Engineering Contradiction:
Improvesignal qualityVSAvoidprocessing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the continuous PPG signal into individual heartbeat cycles using ECG R-wave detection. Each heartbeat segment is independently analyzed for quality metrics, allowing noise contamination in specific segments to be identified and excluded without affecting the entire signal. This segmentation approach improves reliability by enabling selective use of clean segments while maintaining manageable processing complexity through localized analysis.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces ECG signal as an intermediary to guide PPG signal analysis. The ECG R-waves serve as precise markers to segment PPG heartbeats, and the correlation between ECG and PPG timing provides a reference framework for identifying motion artifacts. This intermediary approach improves signal quality assessment while avoiding the need for complex direct noise filtering of the PPG signal alone.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If PPG devices output filtered signal for visualization, then ease of operation is improved, but measurement precision deteriorates

Engineering Contradiction:
Improvevisualization easeVSAvoidsignal magnitude accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent performs quality assessment and segment selection before final parameter calculation and presentation. By pre-identifying clean heartbeat segments using multiple quality metrics (amplitude, morphology, timing correlation with ECG), the system ensures that subsequent filtered signals used for visualization are derived from validated clean data. This preliminary quality gatekeeping maintains measurement precision while preserving visualization ease.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces reliance on visual inspection of raw PPG waveforms with an automated computational quality assessment system. Instead of requiring operators to manually evaluate signal quality by looking at waveform magnitudes and shapes, the system automatically computes multiple quality metrics and selects clean segments algorithmically. This substitution maintains measurement precision through objective criteria while improving ease of operation by eliminating manual evaluation.

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

3Ease of manufacture

If motion artifacts are present in PPG signal, then signal acquisition is simplified, but measurement precision deteriorates

Engineering Contradiction:
Improvesignal acquisition simplicityVSAvoidwaveform accuracy
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent converts the presence of motion artifacts from a harmful factor into a useful indicator. By establishing baseline quality metrics for clean PPG segments and comparing actual segments against these benchmarks, the system identifies motion-contaminated segments through their deviations. The very presence of artifacts creates detectable anomalies in amplitude, morphology, and timing that the system exploits to automatically identify and exclude contaminated data, thereby maintaining measurement precision without complicating signal acquisition.

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables reliable measurement of blood oxygenation levels and estimation of other vital signs by automatically detecting clean PPG signal segments, enhancing clinical decision support and reducing errors in PPG waveform analysis.

Implementation Method 1

PPG uses the change in absorption of light by tissues to measure the difference in oxygenation levels and infer the changes in blood volume

Methodology Applied
Scientific EffectLight absorption: Absorption (EM radiation)

Implementation Method 2

The heart activity is detected by monitoring the patient's EKG waveform, and the blood flow is detected by a non-invasive pulse oximeter. The occurrence of the R wave portion of the EKG signal is detected

Methodology Applied
Scientific EffectElectrical signal detection: Electrical Resistance

Data Source

PatentEP3379997B1Method to quantify photoplethysmogram (PPG) signal quality
Publication Date: 2024.01.10 KONINKLIJKE PHILIPS NV
  • EP3379997B1 patent drawingFigure 1
  • EP3379997B1 patent drawingFigure 2
  • EP3379997B1 patent drawingFigure 3

AI summary

When evaluating the quality of photoplethysmography (PPG) signal (52) measured from a patient monitor (e.g., a finger sensor or the like), multiple features of the PPG signal are extracted and analyzed to facilitate assigning a score to the PPG signal or portions (e.g., heartbeats) thereof. Heartbeats in the PPG signal are segmented out using concurrently captured electrocardiograph (ECG) signal (50), and for each heartbeat, a plurality of extracted features are analyzed. If all extracted features satisfy one or more predetermined criteria for each feature, then the heartbeat waveform is compared to a predefined heartbeat template. If the waveform matches the template (e.g., within a predetermined match percentage or the like), then the heartbeat is classified as "clean." If the heartbeat does not patch the template, or if one or more of the extracted features fails to satisfy its one or more predetermined criteria, the heartbeat is classified as "noisy."