Method and apparatus for treatment of sleep disorder breathing employing artificial neural network

• US 5,953,713 A
• Filed: 09/12/1997
• Issued: 09/14/1999
• Est. Priority Date: 10/26/1995
• Status: Expired due to Term

• Current Assignee: Board of Regents of the University of Texas System (University of Texas System)
• Original Assignee: Board of Regents of the University of Texas System (University of Texas System)
• Inventors: Lopez, Francisco J., Behbehani, Khosrow, Burk, John R., Lucas, Edgar A.
• Primary Examiner(s): Hafiz, Tariq R.
• Assistant Examiner(s): STARKS, WILBERT L
• Application Number:
  US08/928,791
• Time in Patent Office: 732 Days
• Field of Search: 706/15, 706/62, 607/2
• US Class Current: 706/16
• CPC Class Codes: A61M 16/0066 Blowers or centrifugal pumps
• CPC Class Codes: A61M 16/0069 the speed thereof being controlled by respiratory parameters, e.g. by inhalation
• 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 2016/0021 with a proportional output signal, e.g. from a thermistor

Abstract

A method and apparatus for treating sleep disorder breathing is disclosed having improved ability to accurately detect pharyngeal wall vibration or other apneic events. An interface or mask is placed over a patient'"'"'s airway. The interface is coupled to a source of pressurized gas. A respiration-related variable, namely the total pressure in the interface, is measured or sampled. The respiration-related variable is input into an artificial neural network trained to recognize patterns characterizing sleep disorder breathing. Responsive to recognition by the artificial neural network of sleep disorder breathing, pressurized gas is supplied to the patient'"'"'s airways through the interface.

Claims

1. A method of treating sleep disorder breathing, the method comprising the steps of:

placing an interface over a patient'"'"'s airway, the interface coupled to a source of pressurized gas;

measuring a respiration-related variable in the interface;

inputting frequency data from the respiration-related variables into an artificial neural network trained to recognize patterns characterizing sleep disorder breathing;

responsive to recognition by the artificial neural network of sleep disorder breathing, supplying pressurized gas to the patient'"'"'s airway through the interface.

2. The method according to claim 1 wherein the step of measuring respiration-related variables includes the step of obtaining a frequency spectrum from the measured respiration-related variables.

3. The method according to claim 1 further comprising the step of:

comparing a number of outputs of the artificial neural network over a selected interval to a selected threshold value and indicating sleep disorder breathing only if the number of outputs of the artificial neural network indicative of sleep disorder breathing exceeds the selected threshold value.

4. The method according to claim 1 further comprising the step of normalizing the measured respiration-related variable prior to inputting them into the artificial neural network.

5. The method according to claim 1 wherein the respiration-related variable is the pressure in the interface.

6. A method of treating sleep disorder breathing, the method comprising the steps of:

placing an interface over a patient'"'"'s airway, the interface coupled to a source of pressurized gas;

measuring respiration-related variables in the interface;

obtaining a frequency spectrum from the measured respiration-related variables, the frequency spectrum including at least one frequency component;

inputting the frequency component of the frequency spectrum into an artificial neural network trained to recognize patterns characteristic of sleep disorder breathing;

responsive to output from the artificial neural network indicative of sleep disorder breathing, supplying pressurized gas to the patient'"'"'s airway through the interface.

7. The method according to claim 6 wherein the step of obtaining a frequency spectrum from the measured respiration-related variables comprises performing a fast Fourier transform on a selected group of sample of measured respiration-related variables.

8. The method according to claim 6 further comprising the step of:

comparing a number of outputs of the artificial neural network over a selected interval to a selected threshold value and indicating sleep disorder breathing only if the number of outputs of the artificial neural network indicative of sleep disorder breathing exceeds the selected threshold value.

9. The method according to claim 6 further comprising the step of:

normalizing the components of the frequency spectrum prior to inputting them into the artificial neural network.

10. The method according to claim 6 wherein the respiration-related variables are the pressure in the interface.

11. A method of treating sleep disorder breathing, the method comprising the steps of:

placing an interface over a patient'"'"'s airway, the interface coupled to a source of pressurized gas;

periodically sampling pressure in the interface;

periodically inputting frequency data from the sample of pressure in the interface into an artificial neural network trained to recognize patterns characterizing sleep disorder breathing, the artificial neural network producing an output for each sample of pressure input;

comparing the number of outputs indicating sleep disorder breathing to a selected threshold value, sleep disorder breathing being indicated if the number of outputs exceeds the threshold value; and

responsive indicated sleep disorder breathing, supplying pressurized gas to the patient'"'"'s airway through the interface.

12. The method according to claim 11 further including the step of obtaining a frequency spectrum from the measured respiration-related variables.

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

normalizing the components of the frequency spectrum prior to inputting them into the artificial neural network.

14. An apparatus for treatment of sleep disorder breathing comprising:

an interface for placement over a patient'"'"'s airway, the interface coupled to a source of pressurized gas;

means for measuring respiration-related variables in the interface;

means for inputting frequency data from the respiration-related variables into an artificial neural network trained to recognize patterns characterizing sleep disorder breathing;

means for supplying pressurized gas to the patient'"'"'s airway through the interface responsive to recognition by the artificial neural network of sleep disorder breathing.

15. The apparatus according to claim 14 further comprising:

means for obtaining a frequency spectrum from the measured respiration-related variables.

16. The apparatus according to claim 14 further comprising:

means for comparing a number of outputs of the artificial neural network over a selected interval to a selected threshold value and indicating sleep disorder breathing only if the number of outputs of the artificial neural network indicative of sleep disorder breathing exceeds the selected threshold value.

17. The apparatus according to claim 14 further comprising:

means for normalizing the measured respiration-related variables prior to inputting them into the artificial neural network.