Real-time estimation of human core body temperature based on non-invasive physiological measurements
Inventors
Reifman, Jaques • Laxminarayan, Srinivas • Rakesh, Vineet • Ramakrishnan, Sridhar • Liu, Jianbo
Assignees
United States Department of the Army
Publication Number
US-11540723-B2
Publication Date
2023-01-03
Expiration Date
2037-08-18
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
A method of estimating a body temperature of an individual based on physiological data including a heart rate received from at least one sensor 510 and received environmental data. The physiological data and the environmental data are inputted into a model present on a processor 520. The model generates an estimated body temperature and an estimated physiological condition based on the inputs. The processor 520 compares the estimated physiological condition to a measured physiological condition in the physiological data. A controller 530 modifies at least one parameter in the model when the difference between the estimated physiological condition and the measured physiological condition is above a threshold.
Core Innovation
The invention provides a system, method, and computer program product for real-time estimation of human core body temperature based on non-invasive physiological measurements. It receives physiological data, including heart rate and activity data, from at least one sensor worn by the individual, and environmental data such as ambient temperature and humidity. These data are input into a physiological model combined with a Kalman filter. The model generates an estimated core body temperature and an estimated physiological condition. The system compares the estimated physiological condition with the measured physiological condition and modifies one or more parameters in the model when there is a significant difference, thereby individualizing the model for more accurate real-time core body temperature estimation.
The physiological model comprises three coupled equations relating physical activity to heart rate, heart rate to core body temperature, and core body temperature to skin temperature. The model accounts for thermoregulatory processes, including heat gain from metabolic activity and heat loss via convective and evaporative mechanisms. The Kalman filter uses the error between estimated and measured physiological conditions to adjust seven key parameters automatically, which include rate constants and gains related to heart rate and heat exchange, to personalize the model continually. The system can also predict future core body temperatures based on current and past estimations to allow intervention before heat injury occurs.
The problem addressed by this invention is the lack of practical real-time solutions to alert individuals, such as U.S. Armed Forces personnel, about impending heat injury, especially in hot and humid environments. Existing methods like ingestible thermometer pills are invasive and impractical for continuous monitoring of multiple individuals. Data-driven algorithms lack the ability to individualize physiological responses or rely on single sensor data. This invention overcomes these limitations by using non-invasive multi-sensor physiological data, environmental inputs, and adaptive modeling to provide individualized, accurate, and continuous core temperature monitoring and prediction.
Claims Coverage
The patent includes three independent claims defining a method, a system, and a computer program product for estimating an individual's body temperature using non-invasive physiological data and a physiological model with a Kalman filter that adjusts model parameters based on measurement errors.
Real-time core body temperature estimation using a physiological model and Kalman filter
Receiving physiological data including heart rate and activity data, inputting them into a physiological model with multiple parameters combined with a Kalman filter, generating an estimated physiological condition, modifying at least one model parameter via the Kalman filter based on the error between estimated and measured physiological conditions, and estimating core body temperature using the adjusted parameters.
Incorporation of activity data and heart rate for individualized modeling
Use of activity data including exertion level, activity score, or 3-D body acceleration mapped into Metabolic Equivalent units to estimate heart rate and inform the physiological model, enhancing personalization and accuracy.
Integration of environmental data to enhance core temperature estimation
Receiving environmental data such as ambient temperature and humidity from sensors and/or online sources (queried with GPS location), which are input into the model to better account for external thermoregulatory influences.
Automatic parameter adjustment for individualized physiological modeling
Using the Kalman filter to compare measured heart rate with estimated heart rate and to adjust model parameters including rate constants and gains related to heart rate, heat gain, and heat loss, thereby producing an individualized physiological model.
Prediction of future core body temperature
Utilizing an autoregressive model to predict future core body temperature values based on current and past estimated temperatures after model adaptation.
System architecture combining sensors, processor, model, and controller
A system comprising at least one non-temperature physiological sensor to collect data, a processor executing the physiological model with Kalman filter, and a controller that modifies model parameters based on measurement errors, configured to produce individualized core temperature estimates.
Computer program product for implementing the estimation method
A computer program product with stored instructions causing a device to receive physiological and environmental data, execute the physiological model with Kalman filter to estimate and compare physiological conditions, modify model parameters based on differences, and generate estimated core body temperature.
The independent claims collectively cover a method, system, and computer program product for non-invasive, individualized, and adaptive real-time estimation of human core body temperature using physiological and environmental data, a physiological mathematical model, and a Kalman filter algorithm to adjust model parameters based on measurement discrepancies.
Stated Advantages
Provides non-invasive continuous monitoring of core body temperature, avoiding impracticalities of invasive methods like ingestible pills.
Individualizes temperature estimation by adapting to an individual's physiological response and environmental conditions.
Combines multiple physiological measurements, reducing reliance on any single sensor and increasing robustness.
Enables real-time and predictive estimation of core body temperature to allow timely intervention before heat injury occurs.
Documented Applications
Real-time monitoring of core body temperature for U.S. Armed Forces personnel during deployments in hot and humid climates to prevent heat injury.
Use in fitness-tracking devices such as wrist-worn accelerometers or chest straps to monitor physiological data for temperature estimation.
Integration with mobile computing platforms like smartphones or tablets to process data and provide personalized temperature estimates.
Development of heat-injury warning systems by predicting core body temperature increases ahead of time.
Interested in licensing this patent?