Continuous Heart Rate Estimation Under PPG Motion Artifacts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for continuous heart rate measurement using photoplethysmography (PPG) are highly sensitive to motion artifacts, leading to unreliable heart rate estimates and a lack of confidence measures, especially in scenarios with vigorous user motion.
Innovation Solution
A system that combines pulsatility and motion data from wearable devices to generate continuous heart rate measurements with associated confidence scores, utilizing preprocessing, frequency transformation, and neural networks to distinguish cardiac cycles from motion artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If PPG signals are used to measure heart rate continuously, then heart rate monitoring capability is improved, but measurement reliability deteriorates due to motion artifacts
Solution Approach 1:
The patent introduces motion sensors as an intermediary component that captures motion data separately from the PPG signal. This motion data then serves as a mediator to identify and remove motion artifact components from the PPG signal during processing, allowing continuous monitoring while maintaining reliability even during vigorous activity
Solution Approach 2:
The patent extracts motion artifact components from the composite PPG signal by comparing it with motion sensor data. By separating and removing the motion-related components, the system isolates the true cardiac signal, thereby maintaining measurement reliability during continuous monitoring
2Duration of action of moving object
If motion artifacts are present in PPG signals, then measurement precision deteriorates, but continuous monitoring capability is maintained
Solution Approach 1:
The patent implements continuous signal processing that operates without interruption during motion events. The processing pipeline continuously receives PPG and motion data, dynamically identifies motion artifacts in real-time, and maintains continuous heart rate estimation even during vigorous activity, ensuring uninterrupted monitoring
Solution Approach 2:
Motion sensor data serves as an intermediary reference that enables the system to distinguish between true cardiac variations and motion-induced artifacts. This mediator allows the system to maintain precision by selectively filtering out artifact components while preserving genuine physiological signals during continuous monitoring
3Device complexity
If conventional PPG processing is used, then device complexity is minimized, but confidence assessment capability is lost
Solution Approach 1:
The patent implements a feedback mechanism where the processed heart rate estimate and its associated confidence score are fed back to the user interface. This feedback loop provides transparent information about measurement quality, allowing users to understand when readings are reliable without requiring complex additional hardware
Solution Approach 2:
The processing pipeline acts as an intermediary that not only computes heart rate but also generates confidence scores by analyzing the relationship between PPG signal quality and corresponding motion levels. This intermediary processing layer extracts confidence information without requiring significantly increased device complexity
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
The system provides robust heart rate measurements even in the presence of motion artifacts, offering confidence scores that reflect the reliability of the estimates, enabling reliable continuous monitoring across various anatomical locations.
Implementation Method 1
Photoplethysmography (PPG) is frequently used in wearable devices to measure blood volume changes at different parts of the body
Data Source
AI summary
A technique of estimating a continuous heart rate of a subject includes acquiring pulsatility data indicative of a cardiac cycle of the subject and motion data indicative of a motion of the subject. Frequency transformations are performed on the pulsatility and motion data over discrete windows of temporal length T to generate a set of windowed spectra. The discrete windows are temporally overlapping and each temporally offset from one another. Heart rate values, each corresponding to one of the windowed spectra, are output using a processing pipeline including one or more neural networks trained to collectively output one of the heart rate values for each windowed spectra. The continuous heart rate is estimated based upon a set of the heart rate values from the discrete windows that are temporally overlapping.