Wearable health monitors and methods of monitoring health
Inventors
Matichuk, Bruce • Duguay, Randy • Parker, William • Moore, Mathew • Antoniuk, Tim
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11848102-B2
Publication Date
2023-12-19
Expiration Date
Abstract
Wearable technologies, such as wearable health monitors, and methods of use are provided. In some embodiments, the wearable technology can be worn at the wrist of an individual and can use an accelerometer, pulse oximeter, and electrocardiogram to measure heart rate, oxygen saturation, blood pressure, pulse wave velocity, and activity. This information can then be provided to the individual. The individual can alter their behaviors and relationships with their own health by using features such as notifications and auto-tagging to better understand their own stress, diet, sleep, and exercise levels over various time periods and subsequently make appropriate behavioral changes.
Core Innovation
The invention relates to a wrist-worn wearable cardiovascular monitor that uses an accelerometer, electrocardiogram (ECG) sensing, and photoplethysmography (PPG) sensing with a pulse oximeter. The pulse oximeter uses an LED and a light sensor with dual-wavelength light to sense PPG data, including oxygen saturation. The monitor measures heart rate, oxygen saturation, pulse wave velocity (pulse transit time), and estimates blood pressure.
The monitor estimates blood pressure by using machine learning with sensed ECG data and sensed PPG data as inputs. The machine learning includes a neural network and one or any combination of a support vector machine and a polynomial regression analysis, with documented use of supervised learning. The determined amount of oxygen in the blood, derived from comparing absorbed amounts of oxygenated blood and deoxygenated blood, is used as one of the inputs for the machine learning.
The wearable is implemented as hardware with a strap, circuit board, sensors, and a pulse oximeter having an LED emitting a first type of light and a second type of light. The first and second types of light pass through openings in the strap prior to being sensed by the light sensor. The described system provides user feedback via display/notifications, supports health trajectories and predictive analysis using historical health data, and includes automatic tagging of behaviors/events and event-state categories such as stress, diet, sleep, and exercise.
Claims Coverage
The document provides three independent claims, each covering a strap-worn apparatus with sensors for ECG and PPG and a computing system that predicts a health metric using machine learning, with differences in the machine-learning component set and whether historical health data is included.
Strap-mounted ECG and PPG sensor apparatus with health metric prediction using machine learning
A strap with a circuit board attached and comprising a plurality of sensors that sense electrocardiogram (ECG) data and photoplethysmography (PPG) data, and a computing system communicatively coupled to the circuit board and configured to predict a health metric of the user by using machine learning and using the sensed ECG data and the sensed PPG data as inputs for the machine learning.
Pulse oximeter using first and second light types with strap openings
The circuit board comprises a light emitting diode (LED) and a light sensor, where the LED emits a first type of light and a second type of light having wavelengths within first and second ranges, the strap comprises openings, and the first type of light and the second type of light (or corresponding derivatives) pass through the openings prior to being sensed by the light sensor.
Oxygen amount determination from comparison of oxygenated and deoxygenated blood absorption
The pulse oximeter computing component compares a first reading sensed by the light sensor corresponding to an amount of the first type of light absorbed by blood of the user under skin (corresponding to oxygenated blood) and a second reading corresponding to an amount of the second type of light absorbed by the blood (corresponding to deoxygenated blood), determines an amount of oxygen in the blood based on the comparison, and uses the determined amount of oxygen in the blood as one of the inputs for the machine learning.
Neural network based machine learning with optional support vector machine and polynomial regression analysis
The machine learning comprises a neural network and further comprises one or any combination of a support vector machine and a polynomial regression analysis.
Polynomial regression analysis with support vector machine and/or neural network
The machine learning comprises a polynomial regression analysis and further comprises one or any combination of a support vector machine and a neural network.
Machine learning using sensed ECG, sensed PPG, and historical health data
The computing system is configured to predict a health metric by using machine learning and using the sensed ECG data, the sensed PPG data, and historical health data of the user as inputs for the machine learning.
Support vector machine with optional polynomial regression analysis and neural network
The machine learning comprises a support vector machine and further comprises one or any combination of a polynomial regression analysis and a neural network.
Across all independent claims, the inventive structure combines strap-mounted ECG and PPG sensing with a pulse oximeter that emits first and second light types through strap openings, determines oxygen in blood by comparing absorbed light readings, and feeds the determined oxygen amount into machine learning to predict a health metric from sensed ECG and PPG data. The independent claims differ in the specified machine-learning components and in whether historical health data is included.
Stated Advantages
Predicts a health metric of the user using machine learning based on sensed ECG data and sensed PPG data.
Estimates blood pressure by using the determined amount of oxygen in the blood as one of the inputs for the machine learning.
Measures heart rate, oxygen saturation, pulse wave velocity/pulse transit time.
Provides user feedback via display/notifications.
Supports health trajectories and predictive analysis using historical health data.
Includes automatic tagging of behaviors/events and event-state categories.
Documented Applications
Wrist-worn cardiovascular monitoring for measuring heart rate, oxygen saturation, and pulse wave velocity/pulse transit time, and estimating blood pressure.
User feedback via display/notifications as part of wearable monitoring.
Health trajectory and predictive analysis using historical health data.
Automatic tagging of user behaviors/events including stress, diet, sleep, and exercise.
Interested in licensing this patent?