Video-Based Heart Rate Variability Estimation via Frequency Ratio
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating heart rate variability (HRV) are prone to errors due to complex ECG signal morphology, ectopic beats, and environmental noise, limiting the accuracy of non-contact monitoring techniques.
Innovation Solution
A video-based system that extracts low and high frequency components from time-series signals generated from video images of a subject, computing their ratio to estimate HRV, which can be used for continuous monitoring with high accuracy in various settings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contact-based ECG methods are used to estimate HRV, then measurement precision can be achieved, but device complexity and ease of operation are reduced due to wires and probes
Solution Approach 1:
The patent replaces the mechanical contact-based ECG system with an optical video-based system. Instead of using wires and probes that physically contact the skin to detect electrical signals, the system uses a video camera to capture optical reflections from skin blood volume changes, thereby eliminating the mechanical complexity while maintaining HRV measurement capability
Solution Approach 2:
The patent introduces an intermediary approach by using optical reflections as a mediator between the heart's electrical activity and the measurement device. Rather than directly detecting electrical signals through contact, the system detects changes in skin blood volume through optical means, providing an indirect but non-invasive measurement path
2Measurement precision
If contact-based ECG methods are used to estimate HRV, then measurement precision can be achieved, but adaptability is reduced due to limited sensor placement options
Solution Approach 1:
The patent implements universality by making the video camera serve multiple functions: it not only captures video for HRV analysis but can also be used for general monitoring and documentation. The system can analyze HRV from various body regions (face, chest, other areas with visible blood vessels) using the same device, enhancing adaptability across different clinical scenarios
3Ease of operation
If non-contact video methods are used to estimate HRV, then ease of operation and adaptability are improved, but measurement precision deteriorates due to signal extraction challenges
Solution Approach 1:
The patent applies extraction by isolating and removing the photoplethysmographic signal from the complex video data stream. The system extracts the specific blood volume pulse signal component from the overall video signal, separating it from other movements and artifacts, thereby improving measurement precision from the non-contact method
Solution Approach 2:
The patent uses copying by creating a digital representation of the physiological signal through video capture. The optical reflections captured by the video camera serve as a copy of the underlying blood volume changes, which can then be processed and analyzed to extract HRV metrics without direct physical contact
4Measurement precision
If ECG signals are used to estimate HRV, then measurement precision can be achieved, but reliability is reduced due to ectopic beats and arrhythmic events
Solution Approach 1:
The patent converts the limitation of non-contact methods into a benefit by showing that the optical method is inherently more robust to certain artifacts. While ECG is sensitive to ectopic beats and arrhythmias, the photoplethysmographic signal from video captures peripheral blood volume changes that can be more reliably detected and filtered, turning the non-contact approach's initial disadvantage into a reliability advantage
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 video-based method provides accurate and continuous HRV monitoring without the need for contact sensors, suitable for emergency rooms, intensive care units, and telemedicine applications, offering improved flexibility and measurement precision.
Implementation Method 1
a video is received which captures a target area of a region of exposed skin of a subject of interest where photoplethysmograph (PPG) signals can be registered
Data Source
AI summary
What is disclosed is a video-based system and method for estimating heart rate variability from time-series signals generated from video images captured of a subject of interest being monitored for cardiac function. In a manner more fully disclosed herein, low frequency and high frequency components are extracted from a time-series signal obtained by processing a video of the subject being monitored. A ratio of the low and high frequency of the integrated power spectrum within these components is computed. Analysis of the dynamics of this ratio over time is used to estimate heart rate variability. The teachings hereof can be used in a continuous monitoring mode with a relatively high degree of measurement accuracy and find their uses in a variety of diverse applications such as, for instance, emergency rooms, cardiac intensive care units, neonatal intensive care units, and various telemedicine applications.