RF Pulse Wave Training Data for Non-Invasive Blood Pressure Monitoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for monitoring blood glucose levels are invasive, costly, and lack practical implementation of non-invasive technologies, particularly in wearable devices like smartwatches, despite the feasibility of using millimeter range radio waves for non-invasive monitoring.

Innovation Solution

A method involving transmitting millimeter range radio waves in the 122-126 GHz frequency range to penetrate shallowly into the skin, utilizing a two-dimensional array of receive antennas for beamforming and Doppler effect processing to isolate signals from blood vessels, reducing signal processing complexity and improving signal quality for blood glucose monitoring.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If millimeter range radio waves are transmitted to penetrate into the skin for non-invasive monitoring, then non-invasive monitoring capability is improved, but signal processing complexity increases

Engineering Contradiction:
Improvenon-invasive monitoring capabilityVSAvoidsignal processing complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent segments the received radio frequency signals into multiple frequency bins through Fourier transformation, allowing selective processing of specific frequency ranges that contain the pulse wave information while filtering out other frequencies. This segmentation reduces the complexity of processing the entire signal spectrum.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts the pulse wave signal from the complex radio frequency scanning data by identifying and isolating the specific frequency components that correspond to the pulse wave. This extraction process separates the useful signal from the background noise and other irrelevant frequency components, simplifying subsequent analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If a two-dimensional array of receive antennas is used for beamforming and Doppler effect processing, then signal quality is improved, but device complexity increases

Engineering Contradiction:
Improvesignal qualityVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines beamforming and Doppler effect processing in a unified signal processing framework. By merging these two techniques, the system achieves high signal quality through enhanced spatial selectivity and motion detection while avoiding the need for separate complex processing chains, thus reducing overall device complexity.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The two-dimensional array of receive antennas serves multiple functions simultaneously: it performs beamforming for spatial signal selection, Doppler effect processing for motion detection, and pulse wave signal extraction. This multi-functionality reduces the need for additional dedicated components, thereby managing device complexity while maintaining high signal quality.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Ease of operation

If radio frequency scanning is used to generate pulse wave signals, then non-invasive monitoring is enabled, but power consumption increases

Engineering Contradiction:
Improvenon-invasive monitoring capabilityVSAvoidpower consumption
Core Design Contradiction:
Ease of operationVSUse of energy by moving object

Solution Approach 1:

The patent employs periodic radio frequency scanning at optimized intervals to generate pulse wave signals. By using periodic rather than continuous scanning, the system maintains the ability to capture pulse wave information while significantly reducing power consumption compared to continuous operation. The scanning frequency is optimized to balance signal quality requirements with power consumption constraints.

Inventive Principle:
Principle #19Periodic action

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

This approach enables non-invasive, high-resolution monitoring of blood glucose levels with reduced antenna size and power consumption, potentially integrating into wearable devices like smartwatches without the need for invasive techniques, offering improved accuracy and reliability.

Implementation Method 1

utilizing a two-dimensional array of receive antennas for beamforming and Doppler effect processing to isolate signals from blood vessels

Methodology Applied
Scientific EffectDoppler effect: Doppler Effect

Implementation Method 2

receiving a pulse wave signal that is generated from radio frequency scanning data that corresponds to radio waves that have reflected from below the skin surface of a person

Methodology Applied
Scientific EffectElectromagnetic wave reflection: Reflection

Data Source

PatentUS11832919B2Method for generating training data for use in monitoring the blood pressure of a person that utilizes a pulse wave signal generated from radio frequency scanning
Publication Date: 2023.12.05 MOVANO INC
  • US11832919B2 patent drawing
  • US11832919B2 patent drawing
  • US11832919B2 patent drawing

AI summary

Embodiments of the present technology may include a method for generating training data for use in monitoring a health parameter of a person, the method including receiving a pulse wave signal that is generated from radio frequency scanning data that corresponds to radio waves that have reflected from below the skin surface of a person. In some embodiments, the radio frequency scanning data is collected through a two-dimensional array of receive antennas over a range of radio frequencies. Embodiments may also include extracting features from at least one of the pulse wave signal and a mathematical model generated in response to the pulse wave signal. Embodiments may also include labeling the extracted features with a corresponding blood pressure to generate training data.