APPARATUS FOR PROCESSING PHYSIOLOGICAL SENSOR DATA USING A PHYSIOLOGICAL MODEL AND METHOD OF OPERATION THEREFOR

• US 20110301436A1
• Filed: 06/08/2010
• Published: 12/08/2011
• Est. Priority Date: 04/22/2009
• Status: Active Grant

• Current Assignee: Vital Metrix Inc.
• Original Assignee: Streamline Automation LLC
• Inventors: Teixeira, Rodrigo E.
• Granted Patent: US 9,060,722 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 5/14552 Details of sensors specially adapted therefor
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/7267 involving training the classification device

Abstract

A pulse oximeter system comprises a data processor configured to perform a method that combines a sigma point Kalman filter (SPKF) or sequential Monte Carlo (SMC) algorithm with Bayesian statistics and a mathematical model comprising a cardiovascular model and a plethysmography model to remove contaminating noise and artifacts from the pulse oximeter sensor output and measure blood oxygen saturation, heart rate, left-ventricular stroke volume, aortic pressure and systemic pressures.

Claims

1. An apparatus for generation of a physiological estimate of a physiological process of an individual from input data, comprising:

a biomedical monitoring device comprising a data processor configured to run a dual estimation algorithm, said biomedical monitoring device configured to produce the input data, wherein the input data comprises at least one of;

a photoplethysmogram; and

an electrocardiogram,

said dual estimation algorithm configured to use a dynamic state-space model to operate on the input data using both an iterative state estimator and an iterative model parameter estimator in generation of said physiological estimate, said dynamic state-space model configured to;

mathematically represent probabilities of physiological processes that generate said physiological estimate and mathematically represent probabilities of physical processes that affect collection of the input data.

2. The apparatus of claim 1, said state estimator configured to iteratively:

(1) operate on an initial input probability distribution function or a re-sampled probability distribution function using said dynamic state-space model to generate a second probability distribution function;

(2) apply Bayes rule to said second probability distribution function and the input data to form a third probability distribution function; and

(3) resample said third probability distribution function as said re-sampled probability distribution function.

3. The apparatus of claim 2, said dynamic state-space model configured to operate on said second probability distribution function via use of at least one of:

a sequential Monte Carlo algorithm; and

a sigma point Kalman filter algorithm.

4. The apparatus of claim 3, said dynamic state-space model configured to use:

a probabilistic cardiovascular system model as an input to a probabilistic light absorption and scattering probabilistic model; and

a light absorption and scattering probabilistic model.

5. The apparatus of claim 2, said model parameter estimator configured to generate said physiological estimate, said physiological estimate comprising:

a blood oxygen saturation, a heart rate, and at least one of;

a left-ventricular stroke volume;

an aortic blood pressure;

a systemic blood pressure; and

a total blood volume.

6. The apparatus of claim 5, said model parameter estimator configured to iteratively:

(1) provide an initial model parameter or an updated model parameter as an input to said dynamic state-space model to generate a current model parameter;

(2) use said third probability distribution function and the input data; and

(3) generate said updated model parameter using unsupervised machine learning.

7. The apparatus of claim 6, further comprising:

at least two of;

an aortic pressure input to said dynamic state-space model;

a systemic pressure input to said dynamic state-space model;

a red signal input to said dynamic state-space model; and

an infrared signal input to said dynamic state-space model; and

at least one of;

a vital sign input in generation of said expectation model;

an age input in generation of said expectation model;

a gender input in generation of said expectation model.

8. The apparatus of claim 6, wherein said expectation model comprises a confidence interval representing an accuracy probability of said current physiological estimate.

9. The apparatus of claim 1, wherein said input data comprises a fusion of both said plethysmogram and said electrocardiogram.

10. The apparatus of claim 2, further comprising accelerometer data as an input to said dynamic state-space model.

11. A method for generating a physiological estimate from input data, comprising the steps of:

generating input data using a biomedical monitoring device comprising a data processor configured to run a dual estimation algorithm, wherein the input data comprises at least one of;

a photoplethysmogram; and

an electrocardiogram,

processing said input data using said dual estimation algorithm, said dual estimation algorithm configured to use a dynamic state-space model to operate on the input data using both an iterative state estimator and an iterative model parameter estimator in generation of said physiological estimate, said dynamic state-space model configured to;

mathematically represent probabilities of physiological processes that generate said physiological estimate and mathematically represent probabilities of physical processes that affect collection of the input data.

12. The method of claim 11, further comprising the steps of said state estimator iteratively:

operating on an initial input probability distribution function or a re-sampled probability distribution function using said dynamic state-space model to generate a second probability distribution function;

applying Bayes rule to said second probability distribution function and the input data to form a third probability distribution function; and

re-sampling said third probability distribution function as said re-sampled probability distribution function.

13. The method of claim 12, further comprising the step of:

said dynamic state-space model processing said second probability distribution function using at least one of;

a sequential Monte Carlo algorithm; and

a Kalman filter algorithm.

14. The method of claim 13, further comprising the step of:

said dynamic state-space model using;

a probabilistic cardiovascular system model; and

a third light absorption and scattering probabilistic model.

15. The method of claim 12, further comprising the step of:

generating said physiological estimate using said model parameter estimator, said physiological estimate comprising;

a blood oxygen saturation and at least two of;

a left-ventricular stroke volume;

an aortic blood pressure;

a systemic blood pressure; and

a total blood volume.

16. The method of claim 13, further comprising the steps of said model parameter estimator iteratively:

providing an initial model parameter or providing an updated model parameter as an input to said dynamic state-space model to generate a current value for said physiological estimate;

using said third probability function and said current model parameter to form an expectation model; and

combining said expectation model with the input data using unsupervised machine learning to generate said updated model parameter.

17. The method of claim 16, further providing an age input and a gender input in generation of said expectation model.

18. The method of claim 16, wherein said expectation model comprises a confidence interval representing an accuracy probability of said current model parameter.

19. The method of claim 11, further comprising the step of:

combining into the input data at least two of;

said plethysmogram;

said electrocardiogram;

co-oximeter data; and

blood pressure monitor data.

20. The method of claim 11, further comprising using said physiological estimate in at least one of the steps of:

warning of a hemorrhage;

warning of hypoxia;

warning of arrhythmias;

determining hypovolemia;

estimating vasomotor tone;

estimating carotid artery radius; and

indicating carotid artery stenosis.