Sleep stage prediction and intervention preparation based thereon

Patent metadata

Field	Value
Publication number	US-2019192069-A1
Application number	US-201816209522-A
Country	US
Kind code	A1
Filing date	Dec 4, 2018
Priority date	Dec 21, 2017
Publication date	Jun 27, 2019
Grant date	—

Abstract

The present disclosure pertains to a system configured to facilitate prediction of a sleep stage and intervention preparation in advance of the sleep stage's occurrence. The system comprises sensors configured to be placed on a subject and to generate output signals conveying information related to brain activity of the subject; and processors configured to: determine a sample representing the output signals with respect to a first time period of a sleep session; provide the sample to a prediction model at a first time of the sleep session to predict a sleep stage of the subject occurring around a second time; determine intervention information based on the prediction of the sleep stage, the intervention information indicating one or more stimulator parameters related to periheral stimulation; and cause one or more stimulators to provide the intervention to the subject around the second time of the sleep session.

First claim

What is claimed is:

1 . A wearable device configured to facilitate prediction of a sleep stage and intervention preparation in advance of the sleep stage's occurrence, the wearable device comprising:
one or more sensors configured to be placed on a subject and to generate output signals conveying information related to brain activity of the subject; and one or more physical processors configured by computer-readable instructions to:
determine a sample representing the output signals with respect a first time period of a sleep session;
provide, during the sleep session, the sample to a prediction model at a first time of the sleep session to predict a sleep stage of the subject occurring around a second time of the sleep session;
determine, prior to the second time, intervention information based on the prediction of the sleep stage, the intervention information indicating one or more stimulator parameters related to peripheral stimulation; and
cause, based on the intervention information, one or more stimulators to provide the intervention to the subject around the second time of the sleep session.

2 . The wearable device of claim 1 , wherein the one or more physical processors are configured to obtain the prediction of the sleep stage from the prediction model.

3 . The wearable device of claim 1 , wherein the one or more physical processors are configured to:
obtain, from the prediction model, a probability of the sleep stage occurring around the second time and one or more other probabilities of one or more other sleep stages occurring around the second time; and selecting, based on the probability and the one or more other probabilities, the sleep stage to obtain the prediction of the sleep stage.

4 . The monitoring device of claim 1 , wherein the second time is at least ten seconds after the first time.

5 . The wearable device of claim 1 , further comprising:
the one or more stimulators configured to provide the intervention to the subject, wherein the one or more physical processors are further configured to:
determine a sleep disturbance risk of providing the intervention around the second time to the subject;
determine that the sleep disturbance risk does not satisfy a predetermined risk criteria; and
cause the one or more stimulators to provide the intervention to the subject around the second time of the sleep session based on (i) the intervention information and (ii) the determination that the sleep disturbance risk does not satisfy the predetermined risk criteria.

6 . The wearable device of claim 1 , wherein the one or more processors are further configured to:
continuously determine, during at least a part of the sleep session, other samples representing the output signals with respect one or more other time periods of the sleep session; continuously provide, during at least a part of the sleep session, the other samples to the prediction model to predict sleep stages of the subject occurring around other times that are subsequent to the other samples being respectively provided to the prediction model; and continuously determine, during at least a part of the sleep session, further intervention information based on the predictions of the sleep stages.

7 . The wearable device of claim 1 , wherein the one or more processors are further configured to:
obtain historical information related to one or more previous sleep sessions or biographical information related to the subject; and provide the historical data to the prediction model to cause the prediction model to generate one or more outputs related to the prediction of the sleep stage based on the historical data or the biographical information.

8 . The wearable device of claim 1 , wherein the intervention comprises magnetic stimulation, auditory stimulation, light stimulation, electrical stimulation, haptic stimulation, or olfactory stimulation.

9 . A method for facilitating prediction of a sleep stage and intervention preparation in advance of the sleep stage's occurrence, the method comprising:
generating, with one or more sensors, output signals conveying information related to brain activity of a subject; determining, the one or more physical processors, a sample representing the output signals with respect a first time period of a sleep session; providing, with the one or more physical processors, during the sleep session, the sample to a prediction model at a first time of the sleep session to predict a sleep stage of the subject occurring around a second time of the sleep session; determining, with the one or more physical processors, prior to the second time, intervention information based on the prediction of the sleep stage, the intervention information indicating one or more stimulator parameters related to peripheral stimulation; and causing, with the one or more physical processors, based on the intervention information, one or more stimulators to provide the intervention to the subject around the second time of the sleep session.

10 . The method of claim 9 , further comprising obtaining the prediction of the sleep stage from the prediction model.

11 . The method of claim 9 , further comprising:
obtaining, with the one or more physical processors, from the prediction model, a probability of the sleep stage occurring around the second time and one or more other probabilities of one or more other sleep stages occurring around the second time; and selecting, with the one or more physical processors, based on the probability and the one or more other probabilities, the sleep stage to obtain the prediction of the sleep stage.

12 . The method of claim 9 , wherein the second time is at least ten seconds after the first time.

13 . The method of claim 9 , further comprising:
providing, with one or more stimulators, the intervention to the subject, determining, with the one or more physical processors, a sleep disturbance risk of providing the intervention around the second time to the subject; determining, with the one or more physical processors, that the sleep disturbance risk does not satisfy a predetermined risk criteria; and causing, with the one or more physical processors, the one or more stimulators to provide the intervention to the subject around the second time of the sleep session based on (i) the intervention information and (ii) the determination that the sleep disturbance risk does not satisfy the predetermined risk criteria.

14 . The method of claim 9 , further comprising:
continuously determining, with the one or more physical processors, during at least a part of the sleep session, other samples representing the output signals with respect one or more other time periods of the sleep session; continuously providing, with the one or more physical processors, during at least a part of the sleep session, the other samples to the prediction model to predict sleep stages of the subject occurring around other times that are subsequent to the other samples being respectively provided to the prediction model; and continuously determining, with the one or more physical processors, during at least a part of the sleep session, further intervention information based on the predictions of the sleep stages.

15 . The method of claim 9 , further comprising:
obtaining, with the one or more physical processors, historical information related to one or more previous sleep sessions or biographical information related to the subject; and providing, with the one or more physical processors, the historical data to the prediction model to cause the prediction model to generate one

Assignees

• Koninklijke Philips Nv

Inventors

• Garcia Molina Gary Nelson
• Bresch Erik
• Grossekathöfer Ulf
• Heinrich Adrienne
• Pastoor Sander Theodoor

Classifications

• A61B5/7275

  Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor · CPC title

• A61M2021/0016

  by the smell sense · CPC title

• A61M2230/63

  Motion, e.g. physical activity · CPC title

• A61B5/4815

  Sleep quality · CPC title

• A61M2205/3592

  using telemetric means, e.g. radio or optical transmission · CPC title