PROBABILISTIC PARAMETER ESTIMATION USING FUSED DATA APPARATUS AND METHOD OF USE THEREOF

• US 20170079596A1
• Filed: 08/30/2016
• Published: 03/23/2017
• Est. Priority Date: 04/22/2009
• Status: Active Grant

• Current Assignee: Rodrigo E. Teixeira
• Original Assignee: Rodrigo E. Teixeira
• Inventors: Teixeira, Rodrigo E.
• Granted Patent: US 10,460,843 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 2560/0252 using ambient temperature
• CPC Class Codes: A61B 2560/0257 using atmospheric pressure
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 2562/029 Humidity sensors
• 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 5/022 by applying pressure to close blood vessels, e.g. against the skin; Ophthalmodynamometers
• CPC Class Codes: A61B 5/027 using catheters
• CPC Class Codes: A61B 5/029 Measuring or recording blood output from the heart, e.g. minute volume A61B8/065 takes precedence
• CPC Class Codes: A61B 5/0836 Measuring rate of CO2 production
• 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 5/725 using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: A61B 8/065 to determine blood output from the heart in general A61B5/029
• CPC Class Codes: A61B 8/488 involving Doppler signals
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G06F 2218/00 Aspects of pattern recognition specially adapted for signal processing
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A probabilistic digital signal processor using data from multiple instruments is described. In one example, an analyzer is configured to: receive discrete first and second input data, related to a first and second sub-system of the system, from a first and second instrument, respectively. A system processor is used to fuse the first and second input data into fused data. The system processor optionally includes: (1) a probabilistic processor configured to convert the fused data into at least two probability distribution functions and (2) a dynamic state-space model, the dynamic state-space model including at least one probabilistic model configured to operate on the at least two probability distribution functions. The system processor iteratively circulates the at least two probability distribution functions in the dynamic state-space model in synchronization with receipt of updated input data, processes the probability distribution functions, and generates an output related to the state of the system.

Claims

1. A method for estimation of state of a biomedical system, comprising the steps of:

providing a cardiac stroke volume analyzer, said cardiac stroke volume analyzer comprising a system processor, said system processor comprising;

a probabilistic processor; and

a dynamic state-space model;

said cardiac stroke volume analyzer receiving discrete first cardiovascular input data, related to a first sub-system of the biomedical system, from a first blood pressure instrument;

said cardiac stroke volume analyzer receiving discrete second cardiovascular input data, related to a second sub-system of the biomedical system, from a second electrocardiogram instrument;

a system processor, of said cardiac stroke volume analyzer, fusing the first input data and the second input data into fused data, said system processor comprising;

said probabilistic processor converting the fused data into at least two probability distribution functions; and

at least one probabilistic model, of said dynamic state-space model, operating on said at least two probability distribution functions,

said system processor iteratively circulating at least two probability distribution functions in said dynamic state-space model in synchronization with receipt of at least one of;

updated first input data; and

updated second input data,

said system processor processing the probability distribution functions to generate an output related to the state of the biomedical system, said output comprising a left ventricle stroke volume of a heart of a patient.

2. The method of claim 1, wherein said output comprises an output probability distribution function, wherein said output probability distribution function comprises both:

(1) an output from a heart model of said dynamic state-space model and (2) an input to a vascular model of said dynamic state-space model.

3. The method of claim 1, further comprising the steps of said dynamic state-space model:

modeling physical aspects of the first sub-system using a first process model;

modeling physical aspects of the second sub-system using a probabilistic process model; and

modeling at least one data noise source related to the fused data using an observation model.

4. The method of claim 3, further comprising the steps of:

said dynamic state-space model using a fused process model to model aspects of both the first sub-system and the second sub-system; and

said dynamic state-space model using a probabilistic observation model to detect motion related artifacts of at least one sensor used to generate the first input data.

5. The method of claim 1, wherein said cardiac stroke volume analyzer comprises any of:

a mechanical analyzer; and

a physical medical analyzer.

6. The method of claim 1, further comprising the steps of:

providing a probabilistic physiological model, comprising a first heart model and a second vascular model; and

said probabilistic model, comprising said probabilistic physiological model, sharing information from the first heart model with the second vascular model.

7. The method of claim 1, said probabilistic model further comprising:

a first model of a hemodynamic system of a body; and

a second model of an electrodynamic system of a body that generates an electrical signal in the absence of a sample probe.

8. The method of claim 1, further comprising the step of:

said cardiac stroke volume analyzer receiving discrete cardiovascular data from a third instrument comprising at least one of;

a Doppler system; and

an ultrasound device.

9. The method of claim 1, further comprising the step of:

said cardiac stroke volume analyzer receiving discrete cardiovascular data from a third instrument comprising at least one of;

a carbon dioxide meter;

a heart catheter;

an impedance cardiography device; and

a pressure cuff yielding a pressure waveform.

10. The method of claim 1, further comprising the step of:

said cardiac stroke volume analyzer receiving discrete third input data, related to a local environment outside of the cardiac stroke volume analyzer, from a third instrument, wherein said fused data incorporates the third input data.

11. The method of claim 10, wherein the third input data comprises at least one of:

pressure; and

humidity.

12. The method of claim 1, further comprising the steps of:

said cardiac stroke volume analyzer receiving accelerometer data; and

said probabilistic processor using the accelerometer data for outlier determination in the fused data.

13. The method of claim 1, further comprising the step of:

said cardiac stroke volume analyzer generating a measure of a blood filling rate of a heart.

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

said cardiac stroke volume analyzer generating a measure of a contractility.