System and method for determining sleep stage based on sleep cycle

Patent metadata

Field	Value
Publication number	US-2016296164-A1
Application number	US-201415101008-A
Country	US
Kind code	A1
Filing date	Dec 3, 2014
Priority date	Dec 16, 2013
Publication date	Oct 13, 2016
Grant date	—

Abstract

The present disclosure pertains to a system and method for determining sleep stages during individual sleep cycles based on algorithms and/or parameters that correspond to the individual sleep cycles. The system enables more accurate real-time sleep stage determinations compared to prior art systems. Sleep cycles are detected in real-time based on an electroencephalogram (EEG), and/or by other methods. At the end of a sleep cycle, the system is configured such that the specific algorithms and/or parameters used for the previous sleep cycle to determine sleep stages are replaced by new ones which are specifically adapted for the next sleep cycle.

First claim

1 . A system configured to determine sleep stages of a subject during individual sleep cycles of a sleep session, the system comprising:
one or more sensors configured to generate output signals conveying information related to brain activity of the subject; and one or more physical computer processors configured by computer-readable instructions to:
detect individual sleep cycles during the sleep session based on the output signals, the individual sleep cycles including a first sleep cycle and a second sleep cycle;
obtain predetermined sleep stage detection algorithms and/or parameters that correspond to different detected sleep cycles, the sleep stage algorithms and/or parameters including first algorithms and/or parameters that correspond to the first sleep cycle and second algorithms and/or parameters that correspond to the second sleep cycle; and
determine sleep stages during different detected sleep cycles based on the output signals and the obtained sleep stage detection algorithms and/or parameters for the corresponding sleep cycles such that, during the first sleep cycle, sleep stages are determined based on the output signals and the first algorithms and/or parameters, and, during the second sleep cycle, sleep stages are determined based on the output signals and the second algorithms and/or parameters.

2 . The system of claim 1 , wherein the one or more physical computer processors detect the individual sleep cycles based on power in a beta band and power in a delta band of an electroencephalogram.

3 . The system of claim 1 , wherein the one or more physical computer processors are further configured such that the predetermined sleep stage detection algorithms and/or parameters include a vector quantization algorithm, wherein individual sleep stages are characterized by one or more of a representative vector or a representative centroid, and wherein a decision on which sleep stage a given current sleep stage vector belongs to is taken based on a representative centroid that is closest to the given current sleep stage vector.

4 . The system of claim 1 , wherein the one or more physical computer processors are configured such that the predetermined algorithms and/or parameters are stored electronically and indexed based on the individual sleep cycles.

5 . The system of claim 1 , wherein the one or more physical computer processors are configured such that the predetermined algorithms and/or parameters are based on one or more of a previous sleep session of the subject or information from sleep sessions of an age match population of subjects.

6 . A method for determining sleep stages of a subject during individual sleep cycles of a sleep session with a sleep stage determination system, the system comprising one or more sensors and one or more physical computer processors, the method comprising:
generating, with the one or more sensors, output signals conveying information related to brain activity of the subject; detecting, with the one or more physical computer processors, individual sleep cycles during the sleep session based on the output signals, the individual sleep cycles including a first sleep cycle and a second sleep cycle; obtaining, with the one or more physical computer processors, predetermined sleep stage detection algorithms and/or parameters that correspond to different detected sleep cycles, the sleep stage algorithms and/or parameters including first algorithms and/or parameters that correspond to the first sleep cycle and second algorithms and/or parameters that correspond to the second sleep cycle; and determining, with the one or more physical computer processors, sleep stages during different detected sleep cycles based on the output signals and the obtained sleep stage detection algorithms and/or parameters for the corresponding sleep cycles such that, during the first sleep cycle, sleep stages are determined based on the output signals and the first algorithms and/or parameters, and, during the second sleep cycle, sleep stages are determined based on the output signals and the second algorithms and/or parameters.

7 . The method of claim 6 , wherein the individual sleep cycles are detected based on power in a beta band and power in a delta band of an electroencephalogram.

8 . The method of claim 6 , wherein the predetermined sleep stage detection algorithms and/or parameters include a vector quantization algorithm, wherein individual sleep stages are characterized by one or more of a representative vector or a representative centroid, and wherein a decision on which sleep stage a given current sleep stage vector belongs to is taken based on a representative centroid that is closest to the given current sleep stage vector.

9 . The method of claim 6 , wherein the predetermined algorithms and/or parameters are stored electronically and indexed based on the individual sleep cycles.

10 . The method of claim 6 , wherein the predetermined algorithms and/or parameters are based on one or more of a previous sleep session of the subject or information from sleep sessions of an age match population of subjects.

11 . A system configured to determine sleep stages of a subject during individual sleep cycles of a sleep session, the system comprising:
means for generating output signals conveying information related to brain activity of the subject; means for detecting individual sleep cycles during the sleep session based on the output signals, the individual sleep cycles including a first sleep cycle and a second sleep cycle; means for obtaining sleep stage detection algorithms and/or parameters that correspond to different detected sleep cycles, the sleep stage algorithms and/or parameters including first algorithms and/or parameters that correspond to the first sleep cycle and second algorithms and/or parameters that correspond to the second sleep cycle; and means for determining sleep stages during different detected sleep cycles based on the output signals and the obtained sleep stage detection algorithms and/or parameters for the corresponding sleep cycles such that, during the first sleep cycle, sleep stages are determined based on the output signals and the first algorithms and/or parameters, and, during the second sleep cycle, sleep stages are determined based on the output signals and the second algorithms and/or parameters.

12 . The system of claim 11 , wherein the means for detecting detects the individual sleep cycles based on power in a beta band and power in a delta band of an electroencephalogram.

13 . The system of claim 11 , wherein the means for obtaining is configured such that the predetermined sleep stage detection algorithms and/or parameters include a vector quantization algorithm, wherein individual sleep stages are characterized by one or more of a representative vector or a representative centroid, and wherein a decision on which sleep stage a given current sleep stage vector belongs to is taken based on a representative centroid that is closest to the given current sleep stage vector.

14 . The system of claim 11 , wherein the means for obtaining is configured such that the predetermined algorithms and/or parameters are stored electronically and indexed based on the individual sleep cycles.

15 . The system of claim 11 , wherein the means for obtaining is configured such that the predetermined algorithms and/or parameters are based on one or more of a previous sleep session of the subject or information from sleep sessions of an age match population of subjects.

Assignees

• Koninklijke Philips Nv

Inventors

• Garcia Molina Gary

Classifications

• A61B5/7282

  Event detection, e.g. detecting unique waveforms indicative of a medical condition (cough events A61B5/0823; seizures A61B5/4094; sleep apnoea A61B5/4818) · CPC title

• A61B5/4812 Primary

  Detecting sleep stages or cycles · CPC title

• A61B5/7278

  Artificial waveform generation or derivation, e.g. synthesizing signals from measured signals · CPC title

• A61B5/0476

  Human Necessities · mapped topic

• A61B5/369

  Electroencephalography [EEG] · CPC title