Method and Apparatus for Predicting Work of Breathing

• US 20070232951A1
• Filed: 06/05/2007
• Published: 10/04/2007
• Est. Priority Date: 08/30/2002
• Status: Active Grant

• Current Assignee: Michael Banner, Neil Euliano, Paul Blanch, Victor Brennan
• Original Assignee: Michael Banner, Neil Euliano, Paul Blanch, Victor Brennan
• Inventors: Banner, Michael, Euliano, Neil, Blanch, Paul, Brennan, Victor
• Granted Patent: US 7,588,543 B2
• Time in Patent Office: Days
• US Class Current: 600/538
• CPC Class Codes: A61B 5/037 Measuring oesophageal pressure
• CPC Class Codes: A61B 5/08 Detecting, measuring or recording devices for evaluating the respiratory organs A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/082 Evaluation by breath analysis, e.g. determination of the chemical composition of exhaled breath A61B5/083, A61B5/091 take precedence
• CPC Class Codes: A61B 5/083 Measuring rate of metabolism by using breath test, e.g. measuring rate of oxygen consumption
• CPC Class Codes: A61B 5/085 Measuring impedance of respiratory organs or lung elasticity
• CPC Class Codes: A61B 5/087 Measuring breath flow
• CPC Class Codes: A61M 16/026 specially adapted for predicting, e.g. for determining an information representative of a flow limitation during a ventilation cycle by using a root square technique or a regression analysis
• CPC Class Codes: A61M 2016/0036 in the breathing tube and used in both inspiratory and expiratory phase

Abstract

A method of creating a non-invasive predictor of both physiologic and imposed patient effort from airway pressure and flow sensors attached to the patient using an adaptive mathematical model. The patient effort is commonly measured via work of breathing, power of breathing, or pressure-time product of esophageal pressure and is important for properly adjusting ventilatory support for spontaneously breathing patients. The method of calculating this non-invasive predictor is based on linear or non-linear calculations using multiple parameters derived from the above-mentioned sensors.

Claims

1. A method for estimating effort of breathing of a patient, comprising:

receiving respiratory parameters of the patient;

calculating respiratory data from the respiratory parameters;

inputting the respiratory data into a mathematical model created using clinical data;

providing at least one output variable from the mathematical model corresponding to effort of breathing.

2. The method of claim 1 wherein effort of breathing represents a physiologic work of breathing and an imposed work of breathing.

3. The method of claim 1 wherein the respiratory parameters comprise one or more of airway pressure, airway flow, airway volume, carbon dioxide flow, and pulse oximeter plethysmogram.

4. The method of claim 1, wherein the mathematical model is selected from the group consisting of a neural network model, a fuzzy logic model, a mixture of experts model, or a polynomial model.

5. The method of claim 1, wherein the respiratory data comprises one or more of tidal volume, breathing frequency, peak inspiratory pressure, inspiratory time, occlusion pressure at 0.1 seconds after breath initiation trigger time, trigger depth, respiratory resistance, respiratory compliance, end-tidal carbon dioxide, variations in the pulse oximeter plethysmogram, and concavity/convexity of a pressure waveform.

6. The method of claim 5, wherein the respiratory resistance is derived from an initial airway pressure rise at a beginning portion of an inspiratory phase.

7. The method of claim 6, wherein the beginning portion of the inspiratory phase is selected in the range of 0.0 seconds to 0.05 seconds from a start of the inspiratory phase.

8. The method of claim 1, further comprising providing said at least one output variable from the mathematical model to a ventilator to adjust a ventilator setting.

9. The method of claim 1, further comprising providing the output variable from the mathematical model corresponding to effort of breathing to a display.

10. The method of claim 1, wherein the output variable comprises one or more of a physiologic work of breathing variable, an imposed work of breathing variable, a power of breathing variable, and a pressure time product variable, each representing the effort exerted by the patient to breathe.

11. The method of claim 1, wherein the mathematical model is a neural network trained to provide said at least one output variable, wherein the training of the neural network comprises clinical testing of a test population of patients using esophageal pressure as clinical data input to the neural network.

12. The method of claim 11, wherein a drop in esophageal pressure is plotted on a pressure-volume plot and a loop is created and integrated with chest wall compliance line to calculate inspiratory work of breathing as one of said output variables.

13. The method of claim 12, wherein the approximation of 0.1 L/cm H20 is used for chest wall compliance.

14. The method of claim 12, further comprising calculating power of breathing as a per-minute average of work of breathing as one of said output variables.

15. The method of claim 12 further comprising calculating Pressure Time Product (PTP) as one of said output variables.

16. The method of claim 1, further comprising:

classifying the patient; and

selecting a mathematical model based on a classification of the patient.

17. The method of claim 16, wherein the patient is classified according to pathophisiology and physiologic parameters related to the patient.

18. The method of claim 17, wherein the physiologic parameters comprise lung resistance and compliance.

19. A method for estimating effort of breathing of a patient, comprising:

receiving respiratory parameters of a patient, wherein the respiratory parameters comprise one or more of airway pressure, airway flow, airway volume, carbon dioxide flow, and pulse oximeter plethysmogram;

calculating respiratory data from the respiratory parameters, wherein the respiratory data comprises one or more of tidal volume, breathing frequency, peak inspiratory pressure, inspiratory time, occlusion pressure at 0.1 seconds after breath initiation trigger time, trigger depth, respiratory resistance, respiratory compliance, end-tidal carbon dioxide, variations in the pulse oximeter plethysmogram, and concavity/convexity of a pressure waveform;

inputting the respiratory data into a mathematical model configured from clinical data to predict effort of breathing; and

providing at least one output variable from the mathematical model corresponding to effort of breathing.

20. The method of claim 19, wherein the mathematical model is a neural network trained to provide said at least one output variable, wherein the training of the neural network comprises clinical testing of a test population of patients using esophageal pressure as clinical data input to the neural network.

21. The method of claim 19, wherein the output variable comprises one or more of a physiologic work of breathing variable, an imposed work of breathing variable, a power of breathing variable, and a pressure time product variable, each representing the effort exerted by the patient to breathe.

22. An apparatus for estimating effort of breathing of a patient, comprising:

processing device for calculating respiratory data from respiratory parameters of the patient, wherein the respiratory parameters comprise one or more of airway pressure, airway flow, airway volume, carbon dioxide flow, and pulse oximeter plethysmogram, and wherein the respiratory data comprises one or more of tidal volume, breathing frequency, peak inspiratory pressure, inspiratory time, occlusion pressure at 0.1 seconds after breath initiation trigger time, trigger depth, respiratory resistance, respiratory compliance, end-tidal carbon dioxide, variations in the pulse oximeter plethysmogram, and concavity/convexity of a pressure waveform;

a mathematical modeling device created using clinical data to receive the respiratory data and predict effort of breathing; and

an output signal that provides at least one output variable from the mathematical model corresponding to effort of breathing.

23. The apparatus of claim 22, wherein the mathematical modeling device is a neural network trained to provide said at least one output variable, wherein the training of the neural network comprises clinical testing of a test population of patients using esophageal pressure as clinical data input to the neural network.

24. The apparatus of claim 22, wherein the output variable comprises one or more of a physiologic work of breathing variable, an imposed work of breathing variable, a power of breathing variable, and a pressure time product variable, each representing the effort exerted by the patient to breathe.

25. A system for estimating effort of breathing of a patient, comprising:

means for measuring respiratory parameters of the patient, wherein the respiratory parameters comprise one or more of airway pressure, airway flow, airway volume, carbon dioxide flow, and pulse oximeter plethysmogram;

means for calculating respiratory data from the respiratory parameters, wherein the respiratory data comprises one or more of tidal volume, breathing frequency, peak inspiratory pressure, inspiratory time, occlusion pressure at 0.1 seconds after breath initiation trigger time, trigger depth, respiratory resistance, respiratory compliance, end-tidal carbon dioxide, variations in the pulse oximeter plethysmogram, and concavity/convexity of a pressure waveform;

means for predicting effort of breathing using a mathematical model created using clinical data that receives the respiratory data; and

means for providing at least one output variable from the mathematical model corresponding to effort of breathing.

26. The system of claim 25, wherein the mathematical model is a neural network trained to provide said at least one output variable, wherein the training of the neural network comprises clinical testing of a test population of patients using esophageal pressure as clinical data input to the neural network.

27. The system of claim 25, wherein the output variable comprises one or more of a physiologic work of breathing variable, an imposed work of breathing variable, a power of breathing variable, and a pressure time product variable, each representing the effort exerted by the patient to breathe.

28. A computer readable medium for estimating effort of breathing of a patient, comprising:

code devices for receiving measured respiratory parameters of the patient, wherein the respiratory parameters comprise one or more of airway pressure, airway flow, airway volume, carbon dioxide flow, and pulse oximeter plethysmogram;

code devices for calculating respiratory data from the respiratory parameters, wherein the respiratory data comprises one or more of tidal volume, breathing frequency, peak inspiratory pressure, inspiratory time, occlusion pressure at 0.1 seconds after breath initiation trigger time, trigger depth, respiratory resistance, respiratory compliance, end-tidal carbon dioxide, variations in the pulse oximeter plethysmogram, and concavity/convexity of a pressure waveform;

code devices for predicting effort of breathing using a mathematical model created using clinical data that receives the respiratory data; and

code devices for providing at least one output variable from the mathematical model corresponding to effort of breathing.

29. The computer readable medium of claim 28, wherein the mathematical model is a neural network trained to provide said at least one output variable, wherein the training of the neural network comprises clinical testing of a test population of patients using esophageal pressure as clinical data input to the neural network.

30. The computer readable medium of claim 28, wherein the output variable comprises one or more of a physiologic work of breathing variable, an imposed work of breathing variable, a power of breathing variable, and a pressure time product variable, each representing the effort exerted by the patient to breathe.

31. A method of modeling work of breathing for a ventilator patient comprising:

monitoring a plurality of parameters related to a plurality of sample patient'"'"'s inspiratory effort while connected to respective ventilators;

collecting information related to the parameters for a desired period of time;

creating a mathematical model of patient inspiratory effort from the information collected for the plurality of patients over the desired period of time; and

applying an input indicative of the ventilator patient'"'"'s current inspiratory effort to the mathematical model; and

providing an actual breathing effort variable based on the input.

32. The method of claim 31, wherein the mathematical model is a neural network.

33. The method of claim 32, further comprising:

providing the information related to the parameters as primary teaching inputs to the neural network; and

training the neural network to provide an actual breathing effort variable based on the primary teaching inputs.

34. A system for predicting breathing effort of a patient connected to a ventilator comprising:

a signal processor for collecting data corresponding to the patient'"'"'s inspiratory effort;

a parameter extraction module for deriving desired parameters from the data corresponding to the patient'"'"'s inspiratory effort; and

an adaptive processor for modeling the patient'"'"'s inspiratory effort from the desired parameters and providing a control variable responsive to at least one input indicative of the patient'"'"'s current inspiratory effort.

35. The system of claim 34, further comprising a controller for providing the control variable to the ventilator.