Distinguishing between central and obstructive sleep apnea
Apparatuses and methods for detecting sleep apnea and classifying the events as obstructive sleep apnea (OSA) and/or central sleep apnea (CSA) are disclosed herein. The apparatuses can include respiratory treatment devices that have an auto adjusting algorithm that is able to classify a sleep apnea as CSA or OSA so that an appropriate pressure can be applied to the patient depending on the type of sleep apnea detected. The apparatuses and methods can use characteristics of at least one breath preceding the apnea event in classifying the event.
1. A respiratory treatment apparatus comprising:
a blower;
a sensor for measuring a respiratory airflow rate or pressure; and
a control system configured to:
control the blower,
receive an output of the sensor,
detect the presence of an apnea event based on the output of the sensor,
measure one or more characteristics of at least one breath preceding the apnea event, and
classify the apnea event as central sleep apnea or obstructive sleep apnea based on at least one of the characteristics and upon a determination that the apnea has ended.
2. The respiratory treatment apparatus of claim 1 , wherein the control system is configured to increase the pressure if the apnea event is classified as obstructive sleep apnea.
3. The respiratory treatment apparatus of claim 1 , wherein the control system is configured to maintain or decrease the pressure if the apnea event is classified as central sleep apnea.
4. The respiratory treatment apparatus of claim 1 , wherein the control system is configured to increase the pressure if the apnea event is classified as central sleep apnea and a current pressure is below a central sleep apnea pressure limit.
5. The respiratory treatment apparatus of claim 1 , wherein the at least one of the characteristics is derived from an average of multiple breaths.
6. The respiratory treatment apparatus of claim 1 , wherein the control system is configured to normalize the at least one of the characteristics.
7. The respiratory treatment apparatus of claim 6 , wherein the control system is configured to normalize the at least one of the characteristics relative to a standard characteristic.
8. The respiratory treatment apparatus of claim 7 , wherein the standard characteristic is derived from empirically determined data.
9. The respiratory treatment apparatus of claim 1 , wherein the control system is configured to classify the apnea event by using a trained classifier.
10. The respiratory treatment apparatus of claim 9 , wherein the trained classifier is a simple logistics model.
11. The respiratory treatment apparatus of claim 9 , wherein the trained classifier is a logistics model.
12. The respiratory treatment apparatus of claim 9 , wherein the trained classifier is configured to use one or more of a neural network model, logistics model, multiple perceptron model or support vector machine.
13. The respiratory treatment apparatus of claim 9 , wherein the control system is configured to classify the apnea by determining a probability distribution and comparing the probability distribution to a threshold value.
14. The respiratory treatment apparatus of claim 1 , wherein the control system is configured to classify the apnea only after at least one post-apnea breath is sensed.
15. The respiratory treatment apparatus of claim 1 , wherein the characteristic is one or more of flow index, max inspiration amplitude, breath duration, inspiration duration, expiration duration, maximum expiration amplitude, time of maximum expiration amplitude, maximum expiration time to time of maximum inspiration, maximum inspiration amplitude to maximum expiration amplitude, maximum inspiration acceleration, time to maximum inspiration acceleration, inspiration volume, expiration volume, volume ratio, amplitude inspiration center of mass (CM) CM, time inspiration CM, amplitude expiration CM, time expiration CM, time expiration CM to time inspiration CM, amplitude expiration CM to amplitude inspiration CM, maximum flow rate, time, of maximum flow rate, time of maximum negative acceleration, time of the maximum positive acceleration, maximum negative acceleration, or maximum positive acceleration.
16. A method of determining if an apnea is an obstructive sleep apnea or a central sleep apnea, the method comprising:
detecting the presence of an apnea event using one or more hardware processors, the detection based on information indicative of gas flow within a respiratory assistance device;
measuring one or more characteristics of at least one breath preceding the apnea event using the one or more hardware processors; and
automatically classifying the apnea event as central sleep apnea or obstructive sleep apnea, using the one or more hardware processors, based on at least one of the characteristics and upon a determination that the apnea has ended.
17. The method of claim 16 , further comprising increasing a pressure to the patient if the apnea event is classified as obstructive sleep apnea.
18. The method of claim 16 , further comprising decreasing or maintaining a pressure to the patient if the apnea event is classified as central sleep apnea.
19. The method of claim 16 , further comprising increasing a pressure to the patient if the apnea event is classified as central sleep apnea and a current pressure to the patient is below a central sleep apnea pressure limit.