ITERATIVE PROBABILISTIC PARAMETER ESTIMATION APPARATUS AND METHOD OF USE THEREFOR

• US 20120022336A1
• Filed: 07/12/2011
• Published: 01/26/2012
• Est. Priority Date: 07/21/2010
• Status: Abandoned Application

• Current Assignee: Vital Metrix Inc.
• Original Assignee: Streamline Automation LLC
• Inventors: Teixeira, Rodrigo
• Application Number:
  US13/181,247
• Publication Number:
  US 20120022336A1
• Time in Patent Office: Days
• US Class Current: 600/300
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7214 using signal cancellation, e.g. based on input of two identical physiological sensors spaced apart, or based on two signals derived from the same sensor, for different optical wavelengths
• CPC Class Codes: A61B 5/7242 using integration
• CPC Class Codes: A61B 5/725 using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00

Abstract

A probabilistic digital signal processor using data from multiple instruments is described. In one example, a digital signal processor is integrated into a biomedical device. The processor is configured to: use a dynamic state-space model configured with a physiological model of a body system to provide a prior probability distribution function; receive sensor data input from at least two data sources; and iteratively use a probabilistic updater to integrate the sensor data as a fused data set and generate a posterior probability distribution function using all of: (1) the fused data set; (2) an application of Bayesian probability; and (3) the prior probability distribution function. The processor further generates an output of a biomedical state using the posterior probability function.

Claims

1. An apparatus for estimation of a biomedical state of a body, comprising:

a digital signal processor integrated into a biomedical device, said processor configured to;

use a dynamic state-space model configured with a physiological model of a body system to provide a prior probability distribution function;

receive sensor data input from at least two data sources;

iteratively use a probabilistic updater to integrate the sensor data as a fused data set and generate a posterior probability distribution function using all of;

(1) the fused data set;

(2) an application of Bayesian probability; and

(3) said prior probability distribution function; and

generate an output of a biomedical state using said posterior probability function.

2. The apparatus of claim 1, wherein said posterior probability distribution function comprises a set of discretized probability particles, wherein each member of said set represents a probability density of a segment of said posterior probability distribution function.

3. The apparatus of claim 1, wherein said physiological model comprises a probabilistic model of an organ of the body.

4. The apparatus of claim 1, wherein the sensor data from said at least two data sources comprises:

output of a first biomedical device configured to determine a first parameter having a first unit of measure; and

output of a second biomedical device configured to determine a second parameter having a second unit of measure, said first unit of measure distinct from said second unit of measure,

wherein neither said first unit of measure nor said second unit of measure comprise a temperature or a time.

5. The apparatus of claim 4, wherein said output of a biomedical state comprises at least one of:

an indirect parameter having a third unit of measure distinct from both said first unit of measure and said second unit of measure; and

a signal-to-noise ratio enhanced measure of the first parameter.

6. The apparatus of claim 5, wherein said indirect parameter comprises at least one of:

a stroke volume of a heart;

a filling rate of the heart; and

a measure of contractility of the heart.

7. The apparatus of claim 4, wherein said physiological model comprises:

a first model configured to model a physical system associated with a first of said at least two data sources; and

a second model configured to model a physical system associated with a second of said at least two data sources.

8. The apparatus of claim 4, said dynamic state-space model further comprising an observation model, said observation model configured to describe at least one of:

state of said first biomedical device;

state of said second biomedical device; and

movement of the body.

9. The apparatus of claim 1, wherein said two sources each comprise one of:

a Doppler system;

an electrocardiogram device;

an electroencephalogram device;

a pulse oximeter;

a photoplethysmographic device;

an ultrasound device;

a carbon dioxide meter;

a heart catheter;

an impedance cardiography device;

a mixed venous oxygen saturation catheter;

a transcutaneous blood gas sensing meter; and

a pressure cuff yielding a pressure waveform.

10. The apparatus of claim 1, wherein said output comprises a prognosis of a heart condition.

11. The apparatus of claim 1, said physiological model configured with an equation variable for at least one of:

a cardiac output;

a stroke volume;

a heart chamber filling rate;

a radial blood pressure;

a distance between an optical source and an optical detector; and

a blood flow rate.

12. The apparatus of claim 1, said physiological model configured with an equation variable for at least one of:

a transmembrane potential;

a duration of a heart action potential;

a cycle length of a heart;

a permittivity;

a heart rate variability; and

an autonomic nervous system tone.

13. A method for estimating a biomedical state of a body, comprising the steps of:

providing a digital signal processor integrated into a biomedical device, said processor configured with a dynamic state-space model, wherein said dynamic state-space model comprises a physiological sub-model of a body system;

generating a prior probability distribution function through use of said physiological sub-model;

receiving sensor data input from at least two data sources;

iteratively integrating the sensor data as fused data using a probabilistic updater;

generating a posterior probability distribution function using all of;

(1) the fused data;

(2) an application of Bayesian probability; and

(3) said prior probability distribution function; and

outputting a biomedical state using said posterior probability function.

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

using an observation sub-model of said dynamic state-space model to identify motion artifact outlier data within a first data set associated with a first of the two data sources; and

removing outlier data from a second data set associated with a second of the two data sources using said motion artifact data,

wherein a first unit of measure associated with the first data set is different than a second unit of measure associated with the second data set.

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

using a process sub-model of said dynamic state-space model to model at least one of;

a hemodynamic system, wherein said hemodynamic system includes a first parameter related to heart movement;

an electrodynamic system, wherein said electrodynamic system includes a second parameter related to heart movement.

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

sharing information between said observation sub-model and said process sub-model.

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

representing probability density of segments of said posterior probability distribution function with a set of discretized probability particles.

18. The method of claim 14, wherein said physiological model comprises a probabilistic model of an organ of the body.

19. The method of claim 14, wherein the sensor data from said at least two data sources comprises:

output of a first biomedical device configured to determine a first parameter having a first unit of measure; and

output of a second biomedical device configured to determine a second parameter having a second unit of measure, the first unit of measure distinct from the second unit of measure,

wherein said output of a biomedical state comprises an indirect parameter having a third unit of measure distinct from both the first unit of measure and the second unit of measure, and

wherein none of the first unit of measure, the second unit of measure, and said indirect parameter comprise a temperature or a time.

20. The method of claim 14, wherein said output comprises a prognosis of a heart attack.