Sleep state detection for apnea-hypopnea index calculation

Abstract

Disclosed are devices, systems, and methods that detect one or more parameters related to a user's movements, the user's cardiac activity, audio associated with the user, or a combination thereof during a user's sleep session, process the one or more parameters to determine the user's sleep state, which is at least one of wakefulness, sleep, or a sleep stage, and calculate an apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of and priority to U.S. Provisional Patent Application No. 63 / 002,585, entitled "SLEEP STATUS DETECTION FOR APNEA-RESPIRATION INDEX CALCULATION," filed March 31, 2020, and U.S. Provisional Patent Application No. 62 / 968,775, entitled "SLEEP STATUS DETECTION FOR APNEA-RESPIRATION INDEX CALCULATION," filed January 31, 2020, the contents of which are incorporated herein by reference in their entireties.

[0002] Technology field The present technology relates to devices, systems, and methods for detecting sleep states and determining an apnea-hypopnea index (AHI) that takes sleep states into account. [Background technology]

[0003] A user's state of sleep can be considered whether they are asleep or awake. Once asleep, sleep can be characterized by four distinct sleep stages that change throughout the night. It is common for users, especially healthy users, to cycle through the sleep stages several times during their sleep. Sleep stages include N1, N2, and N3, which are also referred to as non-REM and REM stages.

[0004] Stage N1 is the lightest sleep stage and is characterized by the appearance of several low-amplitude waves at multiple frequencies interspersed with alpha waves for more than 50% of the epoch. There may also be sharp peaks, several slow eye movements on the electrooculography (EOG) signal, and / or an overall decrease in frequency on the electroencephalogram (EEG) signal.

[0005] Stage N2 is a slightly deeper sleep stage and is characterized by the appearance of sleep spindles and K-complexes on a background of mixed-frequency signals. Sleep spindles are bursts of higher frequency activity (e.g., above 12 Hz). K-complexes are distinct, isolated dipolar waves lasting approximately 1-2 seconds.

[0006] Stage N3 is the deepest sleep stage and is characterized by the appearance of slow waves (e.g., 1-2 Hz frequency) for at least 20% of the epochs.

[0007] The REM stage is rapid eye movement sleep and is evident by the presence of distinct activity in the EOG signal. The recorded EEG signal typically closely resembles stage N1 and may even be wakeful.

[0008] The term sleep-disordered breathing (SDB) can refer to a condition in which apneas (e.g., cessation of airflow for 10 seconds or more) and hypopneas (e.g., a reduction in airflow of 30% or more for 10 seconds or more with associated oxygen desaturation or arousals) are present during sleep.

[0009] Respiratory instability is an indicator of wakefulness or REM sleep, while respiratory stability is an indicator of non-REM (e.g., N1, N2, N3) sleep. However, respiratory instability alone is insufficient to accurately infer sleep stages. For example, respiratory instability is a manifestation of wakefulness or REM sleep, and can also occur as a result of frequent respiratory events, such as apneas, hypopneas, and respiratory effort-related arousals (RERAs), that occur during sleep. Therefore, it is useful to distinguish periods of respiratory instability, most of which are induced by respiratory events, from periods of true wakefulness.

[0010] Positive airway pressure devices can be configured to detect sleep-disordered breathing (SDB) events, such as apneas and hypopneas, in real time, but often falsely detect SDB events based on the user not being asleep or being in the incorrect sleep stage. For example, analysis of flow can lead to a determination as to whether the user is asleep and even what sleep stage they are in. However, such flow-based sleep stage determination has limitations. It can be difficult to accurately distinguish between awake and asleep states using a flow-based signal. Flow-based signals can be fragmented, missing information at the beginning, middle (when going to the bathroom or getting out of bed in the middle of the night), and end.

[0011] It is interesting to know when a user falls asleep, when they wake up, and which sleep stages they went through during that time. A complete representation of the various sleep stages a user went through during a sleep session is called a sleepgram. One use of a sleepgram is to calculate an index of SDB severity called the apnea-hypopnea index (AHI). The AHI is typically calculated by dividing the total number of apneas and hypopneas by the length of the sleep session and is widely used as a screening, diagnostic, and monitoring tool for SDB. However, such calculations tend to underestimate the AHI because the user may not have been asleep for a significant period during the session. As a result, traditional AHI calculations can lead users to be overly optimistic about the effectiveness of therapy. In particular, flow-based sleep stage determinations are biased toward sleep, resulting in SDB events occurring during wakefulness being incorrectly counted in the AHI. Conversely, if SDB events are incorrectly detected when the user is awake and moving, the AHI may be overestimated. Overestimation and / or underestimation may mean, for example, that the automatic setting algorithm of the breathing device adapts the therapy in a way that negatively impacts sleep quality and / or the effectiveness of the therapy.

[0012] A more accurate way to calculate the AHI is to divide the number of apneas and hypopneas by the number of hours the user was asleep during the session. Calculating the AHI in this way requires knowledge of when the user was asleep, knowledge that can be obtained from a sleep diagram. However, inferring sleep stages purely from respiratory flow has proven to be a difficult task, which ultimately affects the accuracy of the AHI calculation and, in turn, AHI-based user monitoring for respiratory therapy (e.g., continuous positive airway pressure (CPAP) therapy).

[0013] Therefore, there is a need to develop improved devices, systems, and methods for inferring the sleep states and stages of respiratory therapy users, so that the user's illness and the effectiveness of the applied therapy can be more accurately assessed, thereby improving the sleep architecture by treating SDB. Summary of the Invention

[0014] According to some aspects of the present disclosure, devices, systems, and methods are disclosed for distinguishing between arousals and respiratory event sleep based on sleep state.

[0015] According to some aspects of the present disclosure, devices, systems, and methods are disclosed for detecting sleep and providing feedback to a user regarding a sleep state.

[0016] According to one embodiment of the present disclosure, a method for detecting a sleep state of a user is disclosed. The method includes detecting one or more parameters related to the user's movements during a sleep session. The method further includes processing the one or more parameters to determine the user's sleep state. The sleep state is at least one of wakefulness, sleep, or a sleep stage. The method further includes calculating an apnea-hypopnea index of the user during the sleep session based at least in part on the sleep state.

[0017] According to some aspects of this implementation, the sleep stage may be a manifestation of non-REM sleep, N1 sleep, N2 sleep, N3 sleep, or REM sleep. According to some aspects of this implementation, one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state was determined to be awake during the one or more events. Furthermore, the one or more events are one or more apneas, one or more hypopneas, or a combination thereof. According to some aspects of this implementation, the one or more parameters relate to duration, frequency, intensity, type of user movement, or a combination thereof. According to some aspects of this implementation, the one or more parameters are measured based on one or more sensors located on the user, near the user, or a combination thereof. Pressurized air can be applied to the user's airway through a tube and a mask connected to the breathing device. At least one of the one or more sensors may be located on or within the tube, the mask, or a combination thereof. The at least one sensor may include an inertial measurement unit on or within the tube, the mask, or a combination thereof. At least one sensor of the one or more sensors may include an inertial measurement unit in a smart device coupled to the user. The smart device may be one or more of: (1) a smart watch, a smartphone, an activity tracker, a smart mask, smart clothing, a smart mattress, a smart pillow, a smart sheet, a smart ring, or a health monitor, each in contact with the user; (2) a smart speaker or a smart TV, each in proximity to the user; or (3) a combination thereof. According to some aspects of this implementation, processing the one or more parameters includes processing a signal representative of at least one of the one or more parameters over time.

[0018] According to another implementation of the present disclosure, a method for detecting a sleep state of a user is disclosed. The method includes detecting one or more parameters related to a user's cardiac activity during a sleep session, which may include applying pressurized air to the user's airway. The method further includes processing the one or more parameters to determine a sleep state of the user. The sleep state is at least one of wakefulness, sleep, or a sleep stage. The method further includes calculating an apnea-hypopnea index of the user during the sleep session based at least in part on the sleep state.

[0019] According to some aspects of this implementation, one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state during the one or more events is determined to be awake. The one or more events may be one or more apneas, one or more hypopneas, or a combination thereof. According to some aspects of this implementation, the one or more parameters relate to the user's heart rate, heart rate variability, cardiac output, or a combination thereof. Heart rate variability may be calculated over 1 minute, 5 minutes, 10 minutes, 30 minutes, 1 hour, 2 hours, 3 hours, or 4 hours. According to some aspects of this implementation, pressurized air may be applied to the user's airway through a tube and a mask connected to the respiratory device, and at least one sensor for the one or more parameters may be located on or within the tube, the mask, or a combination thereof. In one or more implementations, the at least one sensor may be a microphone. Detecting the one or more parameters may be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more audio signals, or a combination thereof.

[0020] According to one embodiment of the present disclosure, a method for detecting a sleep state of a user is disclosed. The method includes detecting one or more parameters related to speech associated with a user during a sleep session, which may include applying pressurized air to the user's airway. The method further includes processing the one or more parameters to determine a sleep state of the user. The sleep state is at least one of wakefulness, sleep, or a sleep stage. The method further includes calculating an apnea-hypopnea index of the user during the sleep session based at least in part on the sleep state.

[0021] According to some aspects of this implementation, one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state during the one or more events is determined to be awake. The one or more events may be one or more apneas, one or more hypopneas, or a combination thereof. According to some aspects of this implementation, the sound is associated with (1) one or more movements of the user, (2) one or more movements of a tube, a mask, or a combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof. Detecting one or more parameters related to the sound associated with one or more movements of the tube, the mask, or a combination thereof may be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more audio signals, or a combination thereof. According to some aspects of this implementation, the sound may be detected based on one or more microphones in a tube, a mask, or a device connected to the tube, the device providing pressurized air to the user's airway.

[0022] According to one embodiment of the present disclosure, a method for detecting a user's sleep state is disclosed. The method includes detecting a plurality of parameters associated with an individual during a sleep session or a user during a session of applying pressurized air to the user's airway, each parameter of the plurality of parameters being associated with at least one modality, and the plurality of parameters encompassing multiple modalities. The method further includes processing the plurality of parameters to determine the user's sleep state, the sleep state being at least one of wake, sleep, or a sleep stage. The method further includes calculating an apnea-hypopnea index for the user during the session based at least in part on the sleep state. Furthermore, multiple modalities can be combined, in which case one or more modalities associated with or determined from the respiratory therapy system 120 are not used. For example, the sleep state and / or stage can be determined in combination with an AHI obtained from a modality related to cardiac activity. One or more other parameters related to movement but not cardiac activity can then be used to confirm the sleep state and / or stage based on cardiac activity. As a further example, the AHI (not necessarily the sleep state and / or stage) can be determined from blood oxygen level or some other parameter(s) that do not capture sleep stage and / or stage, and then other parameters related to different modalities, such as movement or cardiac activity, can be used to confirm the sleep state and / or stage.

[0023] According to some aspects of this implementation, the modalities include two or more of user movement, pressurized air flow, user cardiac activity, and audio associated with the user. According to some aspects of this implementation, one or more events affecting the calculation of the user's apnea-hypopnea index are ignored in response to a sleep state being determined to be awake during the one or more events. The one or more events include one or more apneas, one or more hypopneas, or a combination thereof. According to some aspects of this implementation, processing the plurality of parameters further includes determining that the user's sleep state cannot be determined based on one or more parameters of a plurality of parameters associated with a first modality of the two or more modalities. Processing the plurality of parameters further includes processing one or more parameters of a plurality of parameters associated with a second modality of the two or more modalities to determine the user's sleep state. According to some aspects of this implementation, determining that the user's sleep state cannot be determined is based on satisfying a threshold decision metric. The threshold decision metric may be based on two or more parameters of a plurality of parameters competing for a sleep state, a sleep state, or a combination thereof. The two or more competing parameters are derived from the two or more modalities. Conflicts between the two or more competing parameters are resolved by disregarding parameters derived based on lower quality data and / or giving increased weight to parameters extracted from higher quality data. The threshold decision metric may be based on multiple previous parameters associated with the user during one or more previous sessions of applying pressurized air to the user's airway. According to some aspects of this implementation, the processing is performed by a sleep stage classifier based on one or more of supervised machine learning, deep learning, a convolutional neural network, or a recurrent neural network. According to some aspects, the processing of the multiple parameters is based on a subset of multiple parameters derived from selected two or more of the multiple modalities.The two or more selected modalities may be selected according to a weighting based on data quality.

[0024] According to one or more implementations, one or more systems are disclosed that may include one or more sensors configured to detect one or more parameters disclosed herein, a respiratory device having a tube and a mask connected to a user, a memory that stores machine-readable instructions, and a control system including one or more processors configured to execute the machine-readable instructions to perform the methods disclosed herein.

[0025] Some versions of the technology may include a computer processor-readable memory storage device having encoded processor-executable instructions that, when executed by a processor, cause the processor to perform any one or more of the methods disclosed herein.

[0026] According to one implementation of the present disclosure, a method for calculating an apnea-hypopnea index of a user is disclosed. The method includes detecting one or more parameters related to a user's movement during a sleep session, which may include applying pressurized air to the user's airway. The method further includes processing the one or more parameters to determine a sleep state of the user. The sleep state may be at least one of wakefulness, sleep, or a sleep stage. The method further includes calculating the user's apnea-hypopnea index during the sleep session based at least in part on the sleep state. The method further includes initiating an action based at least in part on the apnea-hypopnea index, the sleep state, or a combination thereof.

[0027] According to some aspects of this implementation, the action includes one or more of: (1) saving a record of the apnea-hypopnea index; (b) communicating the apnea-hypopnea index to an external device; or (c) adjusting an operational setting of the device. The device may be a respiratory device that delivers pressurized air to the user's airway. According to some aspects of this implementation, one or more events that affect the calculation of the user's apnea-hypopnea index are ignored in response to the sleep state being determined to be awake during the one or more events. The one or more events may be one or more apneas, one or more hypopneas, one or more periodic limb movements, or a combination thereof. According to some aspects of this implementation, the one or more parameters may relate to duration, duration, rate, frequency, intensity, type of user movement, or a combination thereof. According to some aspects of this implementation, the one or more parameters may be measured based on one or more sensors located on or near the user, or a combination thereof. Pressurized air can be applied to the user's airway through a tube and a mask connected to the breathing device, and at least one sensor of the one or more sensors is located on or in the tube, on or in the mask, or a combination thereof. The at least one sensor may include a body motion sensor on or in the tube, on or in the mask, or a combination thereof. According to some aspects of this implementation, the at least one sensor of the one or more sensors includes a body motion sensor in a smart device. The smart device may be one or more of: (1) a smart watch, a smartphone, an activity tracker, a smart mask, smart clothing, a smart mattress, a smart pillow, a smart sheet, a smart ring, or a health monitor, each of which is in contact with the user; (2) a smart speaker or a smart TV, each of which is located near the user; or (3) a combination thereof. According to some aspects of this implementation, processing the one or more parameters includes processing a signal representing at least one of the one or more parameters over time.According to some aspects of this implementation, the user's movements can be associated with the user's cardiac or respiratory activity. The at least one sensor can be a microphone. Detecting the one or more parameters can be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more audio signals, or a combination thereof. According to some implementations, detecting the one or more parameters can be related to audio associated with the user during a session. The audio can be associated with (1) one or more movements of the user, (2) one or more movements of a tube, a mask, or a combination thereof connected to a respiratory device configured to apply pressurized air to the user, or (3) a combination thereof. Detecting the one or more parameters related to the audio can be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more audio signals, or a combination thereof. The audio can be detected based on one or more microphones in a tube, a mask, or a device connected to the tube, which provides pressurized air to the user's airway. According to some implementations, each parameter of the one or more plurality of parameters can be associated with at least one modality, and a plurality of the one or more parameters encompass multiple modalities. These modalities may include a user's movement, a flow rate of pressurized air, a user's cardiac activity, and a voice associated with the user. Processing the plurality of parameters may further include determining that the user's sleep state cannot be determined based on one or more parameters of the plurality of parameters associated with a first modality of the two or more modalities, and processing one or more parameters of the plurality of parameters associated with a second modality of the two or more modalities to determine the user's sleep state. According to some aspects of this implementation, determining that the user's sleep state cannot be determined may be based on satisfying a threshold decision metric.The threshold determination metric may be based on two or more parameters of a plurality of conflicting parameters for the determined sleep state, sleep stage, or a combination thereof. The two or more conflicting parameters originate from the two or more modalities. Conflicts between two or more conflicting parameters may be resolved by ignoring parameters derived based on lower quality data and / or increasing the weight given to parameters extracted from higher quality data. According to some aspects of this implementation, the threshold determination metric may be based on multiple previous parameters associated with the user during one or more previous sessions of applying pressurized air to the user's airway. According to some aspects of this implementation, this processing may be performed by a sleep stage classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks.

[0028] According to one embodiment of the present disclosure, a system for calculating a user's apnea-hypopnea index is disclosed. The system includes one or more sensors configured to detect one or more parameters related to a user's movements during a sleep session, which may include a session in which pressurized air is applied to the user's airway. The system further includes a memory storing machine-readable instructions and a control system. The control system includes one or more processors configured to execute the machine-readable instructions to process the one or more parameters to determine the user's sleep state, which may be at least one of wakefulness, sleep, or a sleep stage; calculate the user's apnea-hypopnea index during the sleep session based at least in part on the sleep state; and initiate an action based at least in part on the apnea-hypopnea index, the sleep state, or a combination thereof.

[0029] According to some aspects of this implementation, the actions include one or more of: (1) saving a record of the apnea-hypopnea index; (b) communicating the apnea-hypopnea index to an external device; or (c) adjusting an operational setting of the device. The device is a respiratory device that delivers pressurized air to the user's airway. According to some aspects of this implementation, one or more events that affect the calculation of the user's apnea-hypopnea index are ignored in response to the sleep state being determined to be awake during the one or more events. The one or more events are one or more apneas, one or more hypopneas, one or more periodic limb movements, or a combination thereof. According to some aspects of this implementation, the one or more parameters relate to duration, period, rate, frequency, intensity, type of user movement, or a combination thereof. According to some aspects of this implementation, the one or more sensors are located on the user, near the user, or a combination thereof. According to some aspects of this implementation, the system further includes a respiratory device having a tube and a mask connected to the user. Pressurized air can be applied to the user's airway through a tube and a mask, and at least one sensor of the one or more sensors is located on or within the tube, the mask, or a combination thereof. The one or more sensors may include a body motion sensor on or within the tube, the mask, or a combination thereof. According to some aspects of this implementation, at least one sensor of the one or more sensors may include a body motion sensor in a smart device. The smart device may be one or more of: (1) a smart watch, a smartphone, an activity tracker, a smart mask, smart clothing, a smart mattress, a smart pillow, a smart sheet, a smart ring, or a health monitor, each of which is in contact with the user; (2) a smart speaker or a smart TV, each of which is located near the user; or (3) a combination thereof. According to some aspects of this implementation, processing the one or more parameters may include processing a signal representing at least one of the one or more parameters over time.According to some aspects of this implementation, the user's movements can be associated with the user's cardiac or respiratory activity. The at least one sensor can be a microphone. The detection of the one or more parameters can be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more audio signals, or a combination thereof detected by the microphone. According to some aspects of this implementation, the detection of the one or more parameters can be related to audio associated with the user during a sleep session. According to some aspects of this implementation, the audio can be associated with (1) one or more movements of the user, (2) one or more movements of a tube, a mask, or a combination thereof connected to a respiratory device configured to apply pressurized air to the user, or (3) a combination thereof. According to some aspects of this implementation, the detection of the one or more parameters related to the audio can be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more audio signals, or a combination thereof. According to some aspects of this implementation, the sound can be detected based on one or more microphones in a tube, a mask, or a device connected to the tube, and the device provides pressurized air to the user's airway. According to some aspects of this implementation, each parameter of the one or more parameters is associated with at least one modality, and the one or more parameters cover multiple modalities. These modalities may include user movement, a flow rate of the pressurized air, cardiac activity of the user, and sound associated with the user. The control system can be configured to execute the machine-readable instructions to determine that the user's sleep state cannot be determined based on one or more parameters of the plurality of parameters associated with a first modality of the two or more modalities, and to process one or more parameters of the plurality of parameters associated with a second modality of the two or more modalities to determine the user's sleep state.According to some aspects of this implementation, the determination that the user's sleep state cannot be determined is based on satisfying a threshold decision metric. The threshold decision metric may be based on two or more parameters of a plurality of conflicting parameters for the determined sleep state, sleep stage, or a combination thereof. The two or more conflicting parameters may originate from two or more modalities. According to some aspects of this implementation, the conflict between two or more conflicting parameters may be resolved by ignoring parameters derived based on lower-quality data and / or giving increased weight to parameters extracted from higher-quality data. According to some aspects of this implementation, the threshold decision metric may be based on multiple previous parameters associated with the user during one or more previous sessions of applying pressurized air to the user's airway. According to some aspects of this implementation, this processing may be performed by a sleep stage classifier based on one or more of supervised machine learning, deep learning, a convolutional neural network, or a recurrent neural network. According to some aspects of this implementation, each parameter of the one or more parameters may be associated with at least one modality, and the one or more parameters encompass multiple modalities. The processing of the plurality of parameters may be based on a subset of the plurality of parameters derived from two or more selected modalities of the plurality of modalities. The two or more selected modalities may be selected according to a weighting based on data quality. According to some aspects of this implementation, the sleep stage may be a manifestation of non-REM sleep or REM sleep. According to some aspects of this implementation, the sleep stage may be a manifestation of N1 sleep, N2 sleep, N3 sleep, or REM sleep.

[0030] According to one implementation of the present disclosure, a system is disclosed that includes a control system having one or more processors, the system comprising a memory having machine-readable instructions stored therein, the control system being coupled to the memory, and any one or more of the methods described above being implemented when the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system.

[0031] According to one implementation of the present disclosure, a system is disclosed that includes a control system configured to perform any one or more of the methods disclosed above.

[0032] According to one implementation of the present disclosure, a computer program product is disclosed that includes instructions that, when executed by a computer, cause the computer to perform any one or more of the methods disclosed above. In one or more implementations, the computer program product is a non-transitory computer-readable medium.

[0033] Parts of the above aspects may form sub-aspects of the present technology. Other features of the present technology will become apparent in light of the information contained in the following detailed description, abstract, drawings, and claims. In addition, various sub-aspects and / or aspects may be combined in various ways to form further aspects or sub-aspects of the present technology. The above summary is not intended to describe every implementation or aspect of the present disclosure. Further features and benefits of the present disclosure will be apparent from the following detailed description and drawings. [Brief explanation of the drawings]

[0034] [Figure 1] FIG. 1 is a functional block diagram of a system according to some implementations of the present disclosure. [Figure 2] 2 is a perspective view of at least a portion of the system of FIG. 1, a user wearing a full face mask, and a bed companion, according to some implementations of the present disclosure. [Figure 3]FIG. 2 is another perspective view of at least another portion of the system of FIG. 1, a user wearing a full face mask, and a bed companion, according to some implementations of the present disclosure. [Figure 4] FIG. 1 is a flow diagram of a process for detecting a user's sleep state based on the user's movements, according to various aspects of the present disclosure. [Figure 5] FIG. 1 is a flow diagram of a process for detecting a user's sleep state based on cardiac activity, according to various aspects of the disclosure. [Figure 6] FIG. 1 is a flow diagram of a process for detecting a sleep state of a user based on audio parameters associated with the user, according to various aspects of the present disclosure. [Figure 7] FIG. 1 is a flow diagram of a process for detecting a user's sleep state based on multiple different modalities, according to various aspects of the present disclosure. [Figure 8] FIG. 1 is a hypnogram according to various aspects of the present disclosure.

[0035] While the present disclosure is susceptible to various modifications and alternative forms, specific implementations and embodiments thereof have been shown by way of example in the drawings and are described in detail herein. It is to be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but rather that the disclosure is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims. DETAILED DESCRIPTION OF THE INVENTION

[0036] The disclosed devices, systems, and methods solve the above-mentioned problems by determining sleep state (e.g., sleep state and / or sleep stage) based on parameters associated with modalities other than flow rate, or based on parameters associated with other modalities in combination with flow-based parameters. The disclosed devices, systems, and methods further solve or ameliorate the above-mentioned problems by determining the AHI after ignoring false SDB events that occur when the user is not asleep. As such, false SDB events detected when the user is awake do not erroneously affect the AHI.

[0037] As described above, flow-based sleep stage determination involves calculating flow-related parameters, including respiration rate, respiration rate variability (over long and short time scales), and normalized respiration rate variability. To address the shortcomings of flow-based sleep stage determination, the devices, systems, and methods of the present disclosure may include additional processing based at least in part on parameters generated and / or calculated by a respiratory device or other device in the user's environment. For example, the respiratory device and / or another smart device in the environment may detect the user's cardiogenic oscillations to estimate heart rate and heart rate variability. For example, parameters indicative of rapid fluctuations in signal quality of cardiogenic oscillation signal parameters may be used, alone or in combination with changes in general flow signal parameters, to infer user movement. Thus, heart rate variability (short-term heart rate variability and long-term trend analysis over the night) may be an additional input parameter for determining sleep state.

[0038] Additionally or alternatively, these devices, systems, and methods can provide multimodal functionality that combines audio and flow parameters representative of a user's sleep state. In one or more implementations, these devices, systems, and methods use a microphone in the breathing device, interface, or tubing, alone or in combination with a flow signal, to determine sleep state. The microphone can detect parameters associated with the user's movement events. These parameters can indicate the duration, frequency, and intensity of the movement events to assist in determining sleep state.

[0039] In one or more specific implementations, these movements alter the echoic reflections of sound within the tube, which can then be detected. Like heart rate, breathing rate is more stable when a user is asleep and is lower during sleep than during wakefulness, and even lower during deep sleep. Adding motion detection assists in determining sleep state because the flow rate resulting from breathing rate is more irregular and motion is present, indicating a high likelihood that the user is awake. However, during REM sleep, even though there is less motion than during wakefulness, the flow signal may still be irregular. Adding motion detection further assists in detecting sleep state, thereby focusing the AHI calculation on actual SDB events when the user is asleep and avoiding counting spurious SDB events that may appear to be AHI events but in which the user is actually awake.

[0040] In one or more implementations, the AHI can be calculated at a finer granularity than a single AHI. For example, in one or more implementations, the AHI can be calculated over multiple sleep sessions, a single sleep session, an hour during a sleep session, or smaller time increments. Thus, a user can have a single AHI value stored, reported, and / or used to control a respiratory device, or can have multiple AHI values ​​stored, reported, and / or used to control a respiratory device, among various other potential actions.

[0041] In one or more implementations, a user can have an AHI determined at a finer level of granularity for sleep stages. For example, the detected sleep stages can be REM and non-REM. In that case, an AHI can be calculated for REM and a separate AHI can be calculated for non-REM. This calculation can be performed in addition to or without calculating an overall AHI. In one or more implementations, an AHI can be calculated for each sleep stage, for example, N1, N2, N3, and / or REM. This can provide a user with insight into the best sleep stage in terms of achieving quality sleep without SDB events. Alternatively, an AHI can be calculated only for N3 and REM, or only for N2, N3, and REM.

[0042] 1, a functional block diagram of a system 100 for inferring sleep states and stages is shown, in accordance with various aspects of the present disclosure. System 100 includes a control system 110, a memory device 114, an electronic interface 119, a respiratory therapy system 120, one or more sensors 130, and one or more user devices 170. In some implementations, system 100 optionally further includes a blood pressure device 182, an activity tracker 190, or any combination thereof.

[0043] During use, respiratory therapy system 120 may detect and count SDB events (e.g., apnea or hypopnea events) during a sleep session in which respiratory therapy system 120 attempts to maintain a medically prescribed air pressure. Respiratory therapy system 120 can estimate an AHI from these SDB events. The AHI can be used to stratify SDB risk and monitor severity across sessions. However, as noted above, respiratory therapy system 120 can detect conditions that appear to be apnea or hypopnea events but in fact result in the user being awake or in a light sleep stage (e.g., N1). In such cases, it may be desirable to not consider events detected during an "awake" state that appear to be apnea or hypopnea events when calculating the AHI. Alternatively, respiratory therapy system 120 may detect the effects of periodic limb movements (PLM) and erroneously assume the user is awake. In such cases, respiratory therapy system 120 may miss SDB events that should be considered in the AHI. For example, the individual may still be asleep during PLM, but their sleep quality may have deteriorated. Respiratory therapy system 120 is configured to more accurately determine a user's (e.g., user 210 of FIG. 2 ) sleep state (e.g., awake or asleep) during a session of applying pressurized air, as well as more accurately determine the user's sleep stage (e.g., N1, N2, N3, REM). More accurate sleep state and sleep stage determinations may enable respiratory therapy system 120 to more accurately determine the AHI, which may be particularly beneficial in providing better future sessions to prevent airway narrowing or collapse.

[0044] The control system 110 includes one or more processors 112 (hereinafter processors 112). The control system 110 is generally used to control various components of the system 100 and / or analyze data acquired and / or generated by the components of the system 100. The processor 112 may be a general-purpose or special-purpose processor or microprocessor. Although one processor 112 is shown in FIG. 1 , the control system 110 may include any suitable number of processors (e.g., one processor, two processors, five processors, ten processors, etc.), which may reside in a single housing or may be located remotely from one another. The control system 110 may be coupled to and / or located within, for example, the housing of the user device 170, the activity tracker 190, and / or one or more of the sensors 130. The control system 110 may be centralized (within one such housing) or distributed (within two or more such housings that are physically separate). In such implementations that include two or more housings that house the control system 110, such housings can be located proximate to one another and / or remotely.

[0045] The control system 110 can perform the methods disclosed herein for determining sleep states / stages and calculating the AHI in "real time" or as post-processing, i.e., after the completion of a sleep session. In post-processing implementations, the data used in the methods can be stored on the memory device 114 as a time series of samples at a predetermined sampling rate.

[0046] The memory device 114 stores machine-readable instructions executable by the processor 112 of the control system 110 and specific to determining a user's sleep state / stage, along with other methods disclosed herein. The memory device 114 may be any suitable computer-readable storage device or medium, such as, for example, a random or serial access memory device, a hard drive, a solid-state drive, a flash memory device, etc. Although one memory device 114 is shown in FIG. 1 , the system 100 may include any suitable number of memory devices 114 (e.g., one memory device, two memory devices, five memory devices, ten memory devices, etc.). The memory device 114 may be coupled to and / or located within the housing of the respiratory device 122, the housing of the user device 170, the housing of the activity tracker 190, the housing of one or more of the sensors 130, or any combination thereof. Like the control system 110, the memory device 114 may be centralized (within one such housing) or distributed (within two or more such physically distinct housings).

[0047] In one or more implementations, memory device 114 may include stored processor control instructions for signal processing, such as audio signal processing, motion signal processing, etc. Such specific signal processing may include measurement filtering, Fourier transforms, logarithms, position determination, degree determination, difference determination, etc. In one or more implementations, processor control instructions and data for controlling the disclosed methods may be contained within memory device 114 as software used by control system 110, which may be considered an application-specific processor, according to any of the methods described herein.

[0048] In some implementations, the memory device 114 stores a user profile associated with the user, which can be implemented as parameters for inferring conditions and stages. The user profile may include, for example, demographic information associated with the user, biometric information associated with the user, medical information associated with the user, self-reported user feedback, sleep parameters associated with the user (e.g., sleep-related parameters recorded from one or more sleep sessions), or any combination thereof. Demographic information may include, for example, information indicative of the user's age, the user's gender, the user's race, the user's ethnicity, the user's geographic location, the user's travel history, relationship status, whether the user has one or more pets, whether the user has a family, a family history of health illnesses, the user's employment status, the user's education status, the user's socioeconomic status, or any combination thereof. Medical information may include, for example, information indicative of one or more medical conditions associated with the user, medication use by the user, or both. The medical information data may further include results or scores of a Multiple Sleep Latency Test (MSLT) and / or scores or values ​​of a Pittsburgh Sleep Quality Index (PSQI). The medical information data may include results obtained from one or more of a polysomnography (PSG) test, CPAP titration, or home sleep testing (HST), respiratory therapy system settings obtained from one or more sleep sessions, sleep-related respiratory events obtained from one or more sleep sessions, or any combination thereof. The self-reported user feedback may include information indicating a self-reported subjective therapy score (poor, fair, good, etc.), a self-reported user's subjective stress level, a self-reported user's subjective fatigue level, a self-reported user's subjective health status, recent life events experienced by the user, or any combination thereof. The user profile information may be updated at any time, such as daily (e.g., between sleep sessions), weekly, monthly, or yearly.In some implementations, memory device 114 stores media content that can be displayed on display device 128 and / or display device 172 described below.

[0049] The electronic interface 119 is configured to receive data (e.g., physiological data, flow data, pressure data, motion data, and / or acoustic data, etc.) from one or more sensors 130, which may be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. The received data, such as physiological data, flow data, pressure data, motion data, acoustic data, etc., may be used to determine and / or calculate parameters for inferring sleep states and stages. The electronic interface 119 may communicate with the one or more sensors 130 using a wired or wireless connection (e.g., using an RF communication protocol, a Wi-Fi communication protocol, a Bluetooth communication protocol, an IR communication protocol, a cellular network, or any other optical communication protocol, etc.). The electronic interface 119 may include an antenna, a receiver (e.g., an RF receiver), a transmitter (e.g., an RF transmitter), a transceiver (e.g., an RF transmitter), or any combination thereof. The electronic interface 119 may also include another processor and / or another memory device that is the same as or similar to the processor 112 and memory device 114 described herein. In some implementations, the electronic interface 119 is coupled to or integrated with the user device 170. In other implementations, the electronic interface 119 is coupled to or integrated with the control system 110 and / or the memory device 114 within the housing.

[0050] Respiratory therapy system 120 may include a respiratory pressure therapy (RPT) device 122 (referred to herein as respiratory device 122), a user interface 124, a conduit 126 (also referred to as tubing or air circuit), a display device 128, a humidification tank 129, a receptacle 180, or a combination thereof. In some implementations, control system 110, memory device 114, display device 128, one or more of sensors 130, and humidification tank 129 are part of respiratory device 122.

[0051] Respiratory pressure therapy refers to the application of an air supply to the entrance of a user's airway at a controlled target pressure that is nominally positive relative to atmosphere throughout the user's respiratory cycle (as opposed to negative pressure therapies such as, for example, tank ventilators or positive-negative pressure extracorporeal ventilators (cuirass)). Respiratory therapy systems 120 are typically used to treat individuals suffering from one or more sleep-related breathing disorders (e.g., obstructive sleep apnea, central sleep apnea, or mixed sleep apnea).

[0052] The respiratory device 122 is generally used to generate pressurized air delivered to a user (e.g., using one or more motors driving one or more compressors). In some implementations, the respiratory device 122 generates a continuous, constant air pressure delivered to the user. In other implementations, the respiratory device 122 generates two or more predetermined pressures (e.g., a first predetermined air pressure and a second predetermined air pressure). In still other implementations, the respiratory device 122 is configured to generate a variety of different air pressures within a predetermined range. For example, the respiratory device 122 can deliver at least about 6 cmH2O, at least about 10 cmH2O, at least about 20 cmH2O, about 6 cmH2O to about 10 cmH2O, about 7 cmH2O to about 12 cmH2O, etc. The respiratory device 122 can also deliver pressurized air at a predetermined flow rate, for example, between about -20 L / min and about 150 L / min, while maintaining a positive pressure (relative to ambient pressure).

[0053] The user interface 124 engages a portion of the user's face and delivers pressurized air from the breathing device 122 to the user's airway to help prevent the airway from narrowing and / or obstructing during sleep. This may also increase the user's oxygen intake while sleeping. The user interface 124 typically engages the user's face so that the pressurized air is delivered to the user's airway through the user's mouth, the user's nose, or both the user's mouth and nose. The breathing device 122, the user interface 124, and the conduit 126 together form an airway that is fluidly connected to the user's airway.

[0054] Depending on the therapy being applied, the user interface 124 may form a seal with, for example, an area or portion of the user's face, thereby facilitating delivery of gas at a pressure sufficiently different from ambient pressure to provide the therapeutic effect, such as a positive pressure of about 10 cmH2O relative to ambient pressure. In other forms of therapy, such as oxygen delivery, the user interface may not include a sufficient seal to facilitate delivery of a gas supply to the airways at a positive pressure of about 10 cmH2O.

[0055] As shown in FIG. 2 , in some implementations, the user interface 124 is or includes a face mask (e.g., a full-face mask) that covers the user's nose and mouth. Alternatively, in some implementations, the user interface 124 is a nasal mask that provides air to the user's nose or a nasal pillow mask that delivers air directly to the user's nostrils. The user interface 124 may include multiple straps (e.g., including hook-and-loop fasteners) for positioning and / or stabilizing the interface on a portion of the user (e.g., the face) and a conformable cushion (e.g., silicone, plastic, foam, etc.) that helps provide an airtight seal between the user interface 124 and the user. The user interface 124 may also include one or more vents to allow carbon dioxide and other gases exhaled by the user 210 to escape. In other implementations, the user interface 124 includes a mouthpiece (e.g., a night guard mouthpiece shaped to fit the user's teeth, a mandible repositioning device, etc.).

[0056] A conduit 126 (also referred to as an air circuit or tubing) allows air to flow between two components of the respiratory therapy system 120, such as the respiratory device 122 and the user interface 124. In some implementations, there may be separate branches of this conduit for inhalation and exhalation. In other implementations, a single-branch conduit is used for both inhalation and exhalation.

[0057] One or more of the respiratory device 122, the user interface 124, the conduit 126, the display device 128, and the humidification tank 129 may include one or more sensors (e.g., a pressure sensor, a flow sensor, a humidity sensor, a temperature sensor, or more generally, any of the sensors 130 described herein) that can be used, for example, to measure the air pressure and / or flow rate of the pressurized air supplied by the respiratory device 122.

[0058] The display device 128 is generally used to display image(s), including still images, video, or both, and / or information about the respiratory device 122. For example, the display device 128 can provide information about the status of the respiratory device 122 (e.g., whether the respiratory device 122 is on or off, the pressure of the air being delivered by the respiratory device 122, the temperature of the air being delivered by the respiratory device 122, etc.) and / or other information (e.g., a sleep score and / or therapy score (also referred to as a myAir™ score as described in WO 2016 / 061629, which is incorporated herein by reference in its entirety), the current date / time, personal information of the user 210, etc. In some implementations, the display device 128 serves as a human-machine interface (HMI) that includes a graphic user interface (GUI) configured to display image(s) as an input interface. The display device 128 can be an LED display, an OLED display, a liquid crystal display, etc. The input interface may be, for example, a touch screen or touch-sensitive board, a mouse, a keyboard, or any sensor system configured to sense inputs made by a human user interacting with the breathing device 122.

[0059] The humidification tank 129 is coupled to or integrated with the respiratory device 122. The humidification tank 129 includes a water reservoir that can be used to humidify the pressurized air delivered from the respiratory device 122. The respiratory device 122 may include a heater that heats water in the humidification tank 129 to humidify the pressurized air provided to the user. Additionally, in some implementations, the conduit 126 may also include a heating element (e.g., coupled to and / or embedded in the conduit 126) that heats the pressurized air delivered to the user. The humidification tank 129 may be fluidly coupled to a water vapor inlet of the air path and deliver water vapor into the air path via the water vapor inlet, or may be formed in-line with the air path as part of the air path itself. In other implementations, the respiratory device 122 or the conduit 126 may include a waterless humidifier. The waterless humidifier may incorporate a sensor that interfaces with other sensors positioned elsewhere in the system 100.

[0060] In some implementations, system 100 can be used to deliver at least a portion of a substance from receptacle 180 to a user's air path based at least in part on physiological data, sleep-related parameters, other data or information, or any combination thereof. Generally, modifying the delivery of the portion of the substance to the air path can include (i) starting the delivery of the substance to the air path, (ii) terminating the delivery of the portion of the substance to the air path, (iii) changing the amount of the substance delivered to the air path, (iv) changing a temporal characteristic of the delivery of the portion of the substance to the air path, (v) changing a quantitative characteristic of the delivery of the portion of the substance to the air path, (vi) changing any parameter associated with the delivery of the substance to the air path, or (vii) any combination of (i)-(vi).

[0061] Varying the temporal characteristics of the delivery of the portion of the substance into the air pathway can include changing the rate at which the substance is delivered, starting and / or ending at different times, continuing for different periods of time, changing the time distribution or characteristics of the delivery, changing the amount distribution independent of the time distribution, etc. Independent time and amount variations ensure that the amount of substance released each time can be varied separately from changing the frequency of release of the substance. In this way, several different combinations of release frequency and release amount can be achieved (e.g., high frequency but low amount release, high frequency and high amount, low frequency and high amount, low frequency and low amount, etc.). Other modifications to the delivery of the portion of the substance into the air pathway can also be utilized.

[0062] The respiratory therapy system 120 can be used as a ventilator or a positive airway pressure (PAP) system, such as a continuous positive airway pressure (CPAP) system, an automatic positive airway pressure (APAP), a bilevel or variable positive airway pressure system (BPAP or VPAP), or any combination thereof. A CPAP system delivers a predetermined air pressure (e.g., determined by a sleep physician) to a user. An APAP system automatically varies the air pressure delivered to a user based, for example, on respiratory data associated with the user. A BPAP or VPAP system is configured to deliver a first predetermined pressure (e.g., inspiratory positive airway pressure or IPAP) and a second predetermined pressure (e.g., expiratory positive airway pressure or EPAP) that is lower than the first predetermined pressure.

[0063] Referring to Figure 2, a portion of the system 100 (Figure 1) according to some implementations is depicted. A user 210 and a bed partner 220 of the respiratory therapy system 120 are in bed 230, lying on a mattress 232. Although a motion sensor 138, a blood pressure device 182, and an activity tracker 190 are shown, any one or more sensors 130 may be used to generate parameters for determining the sleep state and stage of the user 210 during the user's therapy, sleep, and / or rest sessions.

[0064] The user interface 124 is a face mask (e.g., a full-face mask) that covers the nose and mouth of the user 210. Alternatively, the user interface 124 may be a nasal mask that provides air to the nose of the user 210 or a nasal pillows mask that delivers air directly to the nostrils of the user 210. The user interface 124 may include multiple straps (e.g., including hook-and-loop fasteners) for positioning and / or stabilizing the interface on a portion (e.g., the face) of the user 210 and a conformable cushion (e.g., silicone, plastic, foam, etc.) that helps provide an airtight seal between the user interface 124 and the user 210. The user interface 124 may also include one or more vents to allow carbon dioxide and other gases exhaled by the user 210 to escape. In other implementations, the user interface 124 is a mouthpiece (e.g., a night guard mouthpiece shaped to fit the user's teeth, a mandible repositioning device, etc.) for directing pressurized air into the mouth of the user 210.

[0065] The user interface 124 is fluidly coupled and / or connected to the respiratory device 122 via the conduit 126. The respiratory device 122 delivers pressurized air to the user 210 via the conduit 126 and the user interface 124 to increase air pressure in the user's 210 throat and help prevent the airway from becoming blocked and / or narrowed while sleeping. The respiratory device 122 can be positioned on a nightstand 240 immediately adjacent to the bed 230, as shown in FIG. 2, or more generally on any surface or structure generally adjacent to the bed 230 and / or user 210.

[0066] Generally, users prescribed the use of respiratory therapy system 120 tend to experience improved sleep quality and reduced daytime fatigue after using respiratory therapy system 120 while sleeping compared to not using respiratory therapy system 120 (especially when the user suffers from sleep apnea or other sleep-related disorders). For example, user 210 may suffer from obstructive sleep apnea and rely on user interface 124 (e.g., a full-face mask) to deliver pressurized air from respiratory device 122 via conduit 126. Respiratory device 122 may be a continuous positive airway pressure (CPAP) machine used to increase air pressure in the user's 210 throat to prevent the airway from closing and / or narrowing during sleep. People with sleep apnea may experience sleep disruption due to narrowing or collapse of the airway during sleep, reducing oxygen intake, causing awakenings, and other disturbances. The respiratory device 122 prevents the airway from narrowing or collapsing, thereby minimizing the occurrence of reduced oxygen intake waking or otherwise disturbing the user 210.

[0067] 1 , the one or more sensors 130 of the system 100 include a pressure sensor 132, a flow sensor 134, a temperature sensor 136, a motion sensor 138, a microphone 140, a speaker 142, an RF receiver 146, an RF transmitter 148, a camera 150, an infrared sensor 152, a photoelectric (PPG) sensor 154, an electrocardiogram (ECG) sensor 156, an electroencephalogram (EEG) sensor 158, a capacitance sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyogram (EMG) sensor 166, an oxygen sensor 168, an analyte sensor 174, a moisture sensor 176, and a light detection and ranging (LiDAR) sensor 178. In one or more implementations, the one or more sensors 130 may include various other sensors, such as an electrodermal sensor, an accelerometer, an electrooculogram (EOG) sensor, a light sensor, a humidity sensor, an air quality sensor, or any combination thereof. Generally, each of the one or more sensors 130 is configured to output sensor data received and stored in memory device 114 or one or more other memory devices for at least partially implementing the methods disclosed herein.

[0068] One or more sensors 130 are used to detect parameters associated with the user. These parameters may be associated with the flow rate of pressurized air to the user. These parameters may be associated with various user motions, such as body motion, breathing, and cardiac motion. These parameters may be associated with cardiac motion (e.g., heart rate) or motion specific to other cardiac functions. These parameters may be associated with audio parameters to indicate overall body motion, cardiac motion (e.g., heart rate), motion related to components of the respiratory device 122, characteristics of the user interface 124 and / or conduits 126 of the respiratory therapy system 120, etc. As described further below, in one or more implementations, the sensors 130 may be part of the respiratory therapy system 120, may be in communication with one or more external devices to receive one or more parameters from the one or more sensors 130 of the external devices, or a combination of both situations.

[0069] Although the one or more sensors 130 are illustrated and described as including each of a pressure sensor 132, a flow sensor 134, a temperature sensor 136, a motion sensor 138, a microphone 140, a speaker 142, an RF receiver 146, an RF transmitter 148, a camera 150, an infrared sensor 152, a photoelectric (PPG) sensor 154, an electrocardiogram (ECG) sensor 156, an electroencephalogram (EEG) sensor 158, a capacitance sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyogram (EMG) sensor 166, an oxygen sensor 168, an analyte sensor 174, a moisture sensor 176, and a light detection and ranging (LiDAR) sensor 178, it is more general that the one or more sensors 130 may include any combination and any number of each of the sensors described and / or illustrated herein.

[0070] Data from one or more sensors 130 that are indoor environmental sensors can be used as parameters described herein, such as temperature throughout a sleep session (e.g., too warm, too cold), humidity (e.g., too high, too low), pollution levels (e.g., amount and / or concentration of CO and / or particles below or above a threshold), light levels (e.g., too bright, no blinds used, too much blue light before falling asleep), and sound levels (e.g., above a threshold, type of sound source, associated with sleep interruptions, bedmate snoring). These can be captured by one or more sensors 130 on the respiratory device 122, on a user device 170 such as a smartphone (e.g., connected via Bluetooth or the Internet), or on other devices / systems connected to or part of a home automation system. Air quality sensors can also detect indoor pollution other than allergy-causing types, such as pollution from pets or dust mites, and the room may benefit from air filtration to improve user comfort.

[0071] Parameters derived from the user's health (physical and / or mental) illnesses can also be incorporated. For example, parameters may also be health-related (such as changes due to the onset or resolution of illnesses, such as respiratory symptoms, and / or changes in underlying illnesses, such as coexisting chronic illnesses).

[0072] For example, PPG data from a PPG sensor 154 (worn on a mask, on headgear, as a patch, as a wristwatch, as a ring, or in the ear, etc.) can be used to estimate heart rate, blood pressure, and SpO2. Blood oxygen levels can be referenced during PAP therapy to ensure there are no unexpected drops and to monitor residual breathing (e.g., apnea) events when / if therapy is paused (e.g., mask removed). These PPG data can be used to estimate likely daytime headaches and / or suggest modifications to PAP therapy, such as addressing flow limitation in addition to purely obstructive events. These PPG data can also be used to check for the presence or absence of an inflammatory response. Headaches may be caused by a pressure setting that is too high and may benefit from reduced pressure or a change in the EPR setting.

[0073] 1 , as described herein, system 100 generally can be used to generate data (e.g., physiological data, flow data, pressure data, motion data, acoustic data, etc.) associated with a user of respiratory therapy system 120 (user 210 of FIG. 2 ) during a sleep session. The generated data can be analyzed to generate one or more sleep-related parameters, which can include any data, readings, measurements, etc. associated with the user during a sleep session. The one or more sleep-related parameters that can be determined for user 210 during a sleep session include, for example, an AHI score, a sleep score, a flow signal, a respiratory signal, a respiratory rate, an inspiratory amplitude, an expiratory amplitude, an inspiratory-to-expiratory ratio, events per hour, an event pattern, a stage, a pressure setting of respiratory device 122, a heart rate, a heart rate variability, movement of user 210, a temperature, an EEG activity, an EMG activity, arousals, snoring, choking, coughing, wheezing, wheezing, or any combination thereof.

[0074] The one or more sensors 130 can be used to generate, for example, physiological data, flow data, pressure data, motion data, acoustic data, etc. In some implementations, data generated by one or more of the sensors 130 can be used by the control system 110 to determine the duration and quality of sleep of the user 210. This data is a parameter, such as a sleep-wake signal and one or more sleep-related parameters associated with the user 210 during a sleep session. The sleep-wake signal can indicate one or more sleep states including sleep, wakefulness, relaxed wakefulness, micro-arousal, or distinct sleep stages, such as a rapid eye movement (REM) stage, a first non-REM stage (often referred to as “N1”), a second non-REM stage (often referred to as “N2”), a third non-REM stage (often referred to as “N3”), or any combination thereof. Methods for determining sleep states and / or sleep stages from physiological data generated by one or more sensors, such as sensor 130, are described, for example, in International Publication No. WO 2014 / 047110, U.S. Patent Application Publication No. 2014 / 0088373, International Publication No. WO 2017 / 132726, International Publication No. WO 2019 / 122413, and International Publication No. WO 2019 / 122414, all of which are incorporated by reference in their entireties.

[0075] The sleep-wake signal may also be time-stamped to determine when the user went to bed, when the user woke up, when the user attempted to fall asleep, etc. The sleep-wake signal may be measured by one or more sensors 130 at a predetermined sampling rate during the sleep session, such as one sample per second, one sample per 30 seconds, one sample per minute, etc. In some implementations, the sleep-wake signal may also indicate a respiratory signal, a respiratory rate, an inspiratory amplitude, an expiratory amplitude, an inspiratory-to-expiratory ratio, a number of events per hour, an event pattern, a pressure setting of the respiratory device 122, or any combination thereof during the sleep session.

[0076] The event(s) may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, mouth leak, mask leak (e.g., from the user interface 124), restless legs, sleep disturbances, choking, increased heart rate, heart rate variability, dyspnea, asthma attack, epileptic episode, seizure, fever, coughing, sneezing, snoring, shortness of breath, presence of illness such as a cold or flu, or any combination thereof. In some implementations, the mouth leak may include a continuous mouth leak or a valve-like mouth leak (i.e., fluctuating over the duration of a breath), where the user's lips typically flap open during exhalation using a nasal / nasal pillows mask. Mouth leak can lead to dry mouth, bad breath, and is sometimes colloquially referred to as a "sandpaper mouth."

[0077] One or more sleep-related parameters that can be determined for a user during a sleep session based on the sleep-wake signal may include, for example, sleep quality metrics such as total time in bed, total sleep time, sleep onset latency, wake-up parameters after sleep onset, sleep efficiency, fragmentation index, or any combination thereof.

[0078] Data generated by one or more sensors 130 (e.g., physiological data, flow data, pressure data, motion data, acoustic data, etc.) can also be used to determine a respiratory signal associated with the user during a sleep session. The respiratory signal generally indicates the user's breathing or breathing during a sleep session. The respiratory signal may indicate, for example, respiratory rate, respiratory rate variability, inspiratory amplitude, expiratory amplitude, inspiratory-to-expiratory ratio, number of events per hour, event pattern, pressure setting of the respiratory device 122, or any combination thereof. The event(s) may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, mouth leak, mask leak (e.g., from the user interface 124), restless legs, sleep disorder, choking, increased heart rate, dyspnea, asthma attack, epileptic episode, seizure, or any combination thereof.

[0079] Generally, a sleep session includes any time after the user 210 lies or sits in bed 230 (or another area or object used for sleeping) and / or turns on the breathing device 122 and / or puts on the user interface 124. As such, a sleep session may include (i) a period of time during which the user 210 is using the CPAP system but before attempting to fall asleep (e.g., the user 210 is lying in bed 230 reading a book), (ii) a period of time during which the user 210 is trying to fall asleep but is still awake, (iii) a period of time during which the user 210 is in light sleep (also referred to as stages 1 and 2 of non-rapid eye movement (NREM) sleep), (iv) a period of time during which the user 210 is in deep sleep (also referred to as slow wave sleep, SWS, or stage 3 of NREM sleep), (v) a period of time during which the user 210 is in rapid eye movement (REM) sleep, (vi) a period of time during which the user 210 is waking periodically between light sleep, deep sleep, or REM sleep, or (vii) a period of time during which the user 210 is awake and does not fall asleep again.

[0080] A sleep session is typically defined to end when the user 210 removes the user interface 124, turns off the breathing device 122, and / or gets out of bed 230. In some implementations, a sleep session may include additional periods of time or may be limited to only some of the periods disclosed above. For example, a sleep session may be defined to begin when the breathing device 122 begins to supply pressurized air to the airway or user 210 and end when the breathing device 122 stops supplying pressurized air to the airway of the user 210, encompassing some or all of the time in between when the user 210 is asleep or awake.

[0081] Pressure sensor 132 outputs pressure data that can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. In some implementations, pressure sensor 132 is an air pressure sensor (e.g., an atmospheric pressure sensor) that generates sensor data indicative of a user's breathing (e.g., inhalation and / or exhalation) and / or ambient pressure of the respiratory therapy system 120. In such implementations, pressure sensor 132 can be coupled to or integrated with respiratory device 122, user interface 124, or conduit 126. Pressure sensor 132 can be used to determine air pressure within respiratory device 122, conduit 126, user interface 124, or any combination thereof. Pressure sensor 132 can be, for example, a capacitive sensor, an electromagnetic sensor, an inductive sensor, a resistive sensor, a piezoelectric sensor, a strain gauge sensor, an optical sensor, a potentiometric sensor, or any combination thereof. In one example, pressure sensor 132 can be used to determine a user's blood pressure.

[0082] The flow sensor 134 outputs flow data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some implementations, the flow sensor 134 is used to determine the airflow rate from the respiratory device 122, the airflow rate through the conduit 126, the airflow rate through the user interface 124, or any combination thereof. In such implementations, the flow sensor 134 can be coupled to or integrated with the respiratory device 122, the user interface 124, or the conduit 126. The flow sensor 134 can be, for example, a mass flow sensor such as a rotary flow meter (e.g., a Hall effect flow meter), a turbine flow meter, an orifice flow meter, an ultrasonic flow meter, a hot wire sensor, a vortex sensor, a membrane sensor, or any combination thereof.

[0083] The flow sensor 134 can be used to generate flow data associated with a user 210 ( FIG. 2 ) of the breathing device 122 during a sleep session. Examples of flow sensors (e.g., flow velocity sensor 134) are described in International Publication No. WO 2012 / 012835, which is incorporated by reference herein in its entirety. In some implementations, the flow sensor 134 is configured to measure exhaust flow (e.g., intentional “leak”), unintentional leak (e.g., mouth leak and / or mask leak), patient flow (e.g., air into and / or out of the lungs), or any combination thereof. In some implementations, this flow data can be analyzed to determine the user's cardiogenic oscillations.

[0084] The temperature sensor 136 outputs temperature data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some implementations, the temperature sensor 136 generates temperature data indicative of the core body temperature of the user 210 ( FIG. 2 ), the skin temperature of the user 210, the temperature of the air flowing from the respiratory device 122 and / or through the conduit 126, the temperature of the air within the user interface 124, the ambient temperature, or any combination thereof. The temperature sensor 136 may be, for example, a thermocouple sensor, a thermistor sensor, a silicon bandgap temperature sensor or semiconductor-based sensor, a resistance temperature detector, or any combination thereof.

[0085] The motion sensor 138 outputs motion data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. The motion sensor 138 can be used to detect movement of the user 210 during a sleep session and / or to detect movement of any of the components of the respiratory therapy system 120, such as the respiratory device 122, the user interface 124, or the conduit 126. The motion sensor 138 can include one or more inertial sensors, such as an accelerometer, a gyroscope, and a magnetometer. In some implementations, the motion sensor 138 alternatively or additionally generates one or more signals representative of the user's body movements, from which a signal representative of the user's sleep state or sleep stage can be obtained, for example, via the user's respiratory movements. In some implementations, the motion data from the motion sensor 138 can be used in conjunction with additional data from another sensor 130 to determine the user's sleep state or sleep stage. In some implementations, this motion data can be used to determine the user's location, body position, and / or changes in body position.

[0086] The motion sensor 138 can detect movement of the user. In some implementations, the motion sensor 138 works in conjunction with the camera 150 (e.g., an infrared camera) to determine changes and / or displacements in body temperature relative to the ambient temperature to determine whether the user is moving. In some implementations, the motion sensor 138 uses electromagnetic sensing at infrared wavelengths to detect movement. Using an IR sensor, a slight drop in body temperature can be used as an indicator that the user is asleep. When the body temperature rises above a certain level based on infrared sensing, the motion sensor 138 can determine that the user is awake and / or moving. This temperature change can also be obtained from a temperature sensor attached to the mask of the breathing system so as to contact the user's skin during use of the mask. Other examples of the motion sensor 138 include passive infrared sensors, sensors that emit acoustic signals (as described above and below) and determine whether received detection of reflected acoustic signals indicates a change in pattern, inertial measurement units (IMUs), gyroscopes and accelerometers, passive microphones, radio frequency (RF)-based sensors, ultra-wideband sensors, etc.

[0087] The microphone 140 outputs sound data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. The microphone 140 can be used to record sound(s) (e.g., sounds from the user 210) during a sleep session to determine (e.g., using the control system 110) one or more sleep-related parameters, which may include one or more events (e.g., respiratory events), as described in further detail herein. The microphone 140 can be coupled to or integrated with the respiratory device 122, the user interface 124, the conduit 126, or the user device 170. In some implementations, the system 100 includes multiple microphones (e.g., two or more microphones and / or an array of microphones with beamforming capabilities), such that sound data generated by each of the multiple microphones can be used to distinguish sound data generated by another of the multiple microphones.

[0088] The speaker 142 outputs sound waves. In one or more implementations, these sound waves may be audible to a user of the system 100 (e.g., user 210 of FIG. 2 ) or may be inaudible to a user of the system (e.g., ultrasound). The speaker 142 may be used, for example, as an alarm clock or to play alerts or messages to the user 210 (e.g., in response to identified body positions and / or body position changes). In some implementations, the speaker 142 may be used to communicate audio data generated by the microphone 140 to the user. The speaker 142 may be coupled to or integrated with the respiratory device 122, the user interface 124, the conduit 126, or the user device 170.

[0089] The microphone 140 and the speaker 142 can be used as separate devices. In some implementations, the microphone 140 and the speaker 142 can be incorporated into an acoustic sensor 141 (e.g., a sonar sensor), for example, as described in International Publication Nos. WO 2018 / 050913 and WO 2020 / 104465, each of which is incorporated by reference in its entirety. In such implementations, the speaker 142 generates or emits sound waves at predetermined intervals and / or frequencies, and the microphone 140 detects reflections of the sound waves emitted from the speaker 142. In one or more implementations, the sound waves generated or emitted by the speaker 142 can have a frequency inaudible to the human ear (e.g., below 20 Hz or above about 18 kHz) so as not to disturb the sleep of the user 210 or bedmate 220 ( FIG. 2 ). Based at least in part on data from microphone 140 and / or speaker 142, control system 110 can determine the location of user 210 (FIG. 2) and / or one or more of the sleep-related parameters (e.g., identified body positions and / or body position changes) described herein, such as, for example, a respiratory signal, a respiratory rate, an inhalation amplitude, an exhalation amplitude, an inhalation-to-exhalation ratio, a number of events per hour, an event pattern, a sleep state, a sleep stage, a pressure setting of respiratory device 122, or any combination thereof. In this context, a sonar sensor may be understood to involve active acoustic sensing, such as by generating / transmitting ultrasonic or low-frequency ultrasonic sensing signals (e.g., within a frequency range of approximately 17-23 kHz, 18-22 kHz, or 17-18 kHz) in the air. Such systems may be discussed in light of the above-referenced International Publication Nos. WO 2018 / 050913 and WO 2020 / 104465.

[0090] In some implementations, the sensor 130 includes (i) a first microphone that is identical to or similar to the microphone 140 and is integrated into the acoustic sensor 141, and (ii) a second microphone that is identical to or similar to the microphone 140 but is separate and distinct from the first microphone that is integrated into the acoustic sensor 141.

[0091] The RF transmitter 148 generates and / or emits radio waves having a predetermined frequency and / or a predetermined amplitude (e.g., within a high frequency band, within a low frequency band, a long wave signal, a short wave signal, etc.). The RF receiver 146 detects reflections of the radio waves emitted from the RF transmitter 148, and this data can be analyzed by the control system 110 to determine the location and / or posture of the user 210 ( FIG. 2 ) and / or one or more of the sleep-related parameters described herein. The RF receiver (either the RF receiver 146 and the RF transmitter 148, or another RF pair) may also be used for wireless communication between the control system 110, the respiratory device 122, one or more sensors 130, the user device 170, or any combination thereof. While the RF receiver 146 and the RF transmitter 148 are shown as separate and distinct elements in FIG. 1 , in some implementations the RF receiver 146 and the RF transmitter 148 are combined as part of an RF sensor 147 (e.g., a RADAR sensor). In some such implementations, the RF sensor 147 includes the control circuitry. The particular form of RF communication may be Wi-Fi, Bluetooth, or the like.

[0092] In some implementations, the RF sensor 147 is part of a mesh system. One example of a mesh system is a Wi-Fi mesh system, which may include mesh nodes, mesh router(s), and mesh gateway(s), each of which may be mobile / movable or fixed. In such implementations, the Wi-Fi mesh system includes a Wi-Fi router and / or a Wi-Fi controller and one or more satellites (e.g., access points), each of which includes an RF sensor that is the same as or similar to the RF sensor 147. The Wi-Fi router and satellites constantly communicate with each other using Wi-Fi signals. The Wi-Fi mesh system can be used to generate motion data based on changes in the Wi-Fi signal (e.g., differences in received signal strength) between the router and satellite(s) caused by objects or people moving and partially obstructing the signal. This motion data may indicate motion, breathing, heart rate, walking, falls, behavior, etc., or any combination thereof.

[0093] The camera 150 outputs image data that can be reproduced as one or more images (e.g., still images, video, thermal images, or any combination thereof) that can be stored in the memory device 114. The image data from the camera 150 can be used by the control system 110 to determine one or more of the sleep-related parameters described herein. The control system 110 can use the image data from the camera 150 to determine one or more of the sleep-related parameters described herein, such as, for example, one or more events (e.g., periodic limb movement or restless legs syndrome), a respiratory signal, a respiratory rate, an inhalation amplitude, an exhalation amplitude, an inhalation-to-exhalation ratio, a number of events per hour, an event pattern, a sleep state, a sleep stage, or any combination thereof. Furthermore, the image data from the camera 150 can be used to identify the location and / or position of the user, determine the chest movement of the user 210, determine the airflow at the mouth and / or nose of the user 210, determine when the user 210 entered the bed 230, and determine when the user 210 left the bed 230. The camera 150 may also be used to track eye movement, pupil dilation (when one or both of the user's 210 eyes are open), blink rate, or any changes during REM sleep.

[0094] The infrared (IR) sensor 152 outputs infrared image data that can be reproduced as one or more infrared images (e.g., still images, video, or both) that can be stored in the memory device 114. The infrared data from the IR sensor 152 can be used to determine one or more sleep-related parameters during a sleep session, including the temperature of the user 210 and / or the movement of the user 210. The IR sensor 152 can also be used in combination with the camera 150 in measuring the presence, location, and / or movement of the user 210. The IR sensor 152 can detect infrared light having a wavelength between about 700 nm and about 1 mm, for example, while the camera 150 can detect visible light having a wavelength between about 180 nm and about 740 nm.

[0095] The PPG sensor 154 outputs physiological data associated with the user 210 ( FIG. 2 ) that can be used to determine one or more sleep-related parameters, such as, for example, heart rate, heart rate pattern, heart rate variability, cardiac cycle, respiratory rate, inspiration amplitude, expiration amplitude, inspiration-to-expiration ratio, estimated blood pressure parameter(s), or any combination thereof. The PPG sensor 154 can be worn by the user 210, embedded in clothing and / or fabric worn by the user 210, embedded in and / or coupled to the user interface 124 and / or its associated headgear (e.g., straps, etc.), etc.

[0096] The ECG sensor 156 outputs physiological data associated with the electrical activity of the heart of the user 210. In some implementations, the ECG sensor 156 includes one or more electrodes positioned on or around a portion of the user 210 during a sleep session. The physiological data from the ECG sensor 156 can be used, for example, to determine one or more of the sleep-related parameters described herein.

[0097] The EEG sensor 158 outputs physiological data associated with electrical activity of the user's 210 brain. In some implementations, the EEG sensor 158 includes one or more electrodes positioned on or around the user's 210 scalp during a sleep session. The physiological data from the EEG sensor 158 can be used, for example, to determine the user's 210 sleep state or sleep stage at any given time during a sleep session. In some implementations, the EEG sensor 158 can be integrated into the user interface 124 and / or its associated headgear (e.g., straps, etc.).

[0098] The capacitance sensor 160, the force sensor 162, and the strain gauge sensor 164 output data that can be stored in the memory device 114 and that the control system 110 can use to determine one or more of the sleep-related parameters described herein. The EMG sensor 166 outputs physiological data associated with electrical activity produced by one or more muscles. The oxygen sensor 168 outputs oxygen data indicative of the oxygen concentration of gas (e.g., in the conduit 126 or at the user interface 124). The oxygen sensor 168 can be, for example, an ultrasonic oxygen sensor, an electrical oxygen sensor, a chemical oxygen sensor, an optical oxygen sensor, or any combination thereof. In some implementations, the one or more sensors 130 also include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a sphygmomanometer sensor, an oximetry sensor, or any combination thereof.

[0099] The analyte sensor 174 can be used to detect the presence of an analyte in the exhaled breath of the user 210. Data output by the analyte sensor 174 can be stored in the memory device 114 and can be used by the control system 110 to determine the identity and concentration of any analytes in the breath of the user 210. In some implementations, the analyte sensor 174 is positioned near the mouth of the user 210 to detect analytes in breath exhaled from the mouth of the user 210. For example, if the user interface 124 is a face mask that covers the nose and mouth of the user 210, the analyte sensor 174 can be positioned within the face mask to monitor the mouth breathing of the user 210. In other implementations, such as when the user interface 124 is a nasal mask or nasal pillows mask, the analyte sensor 174 can be positioned near the nose of the user 210 to detect analytes in breath exhaled through the user's nose. In yet other implementations, the analyte sensor 174 may be positioned near the mouth of the user 210 when the user interface 124 is a nasal mask or nasal pillows mask. In some implementations, the analyte sensor 174 can be used to detect whether air is inadvertently leaking from the mouth of the user 210. In some implementations, the analyte sensor 174 is a volatile organic compound (VOC) sensor that can be used to detect carbon-based chemicals or compounds. In some implementations, the analyte sensor 174 can also be used to detect whether the user 210 is breathing through the nose or mouth. For example, if the presence of an analyte is detected by data output by the analyte sensor 174 positioned near the mouth of the user 210 or in the face mask (in implementations where the user interface 124 is a face mask), the control system 110 can use this data as an indicator that the user 210 is breathing through their mouth.

[0100] The moisture sensor 176 outputs data that can be stored in the memory device 114 and used by the control system 110. The moisture sensor 176 can be used to detect moisture in various areas surrounding the user (e.g., inside the conduit 126 or the user interface 124, near the face of the user 210, near the connection between the conduit 126 and the user interface 124, near the connection between the conduit 126 and the respiratory device 122, etc.). Thus, in some implementations, the moisture sensor 176 can be positioned on the user interface 124 or the conduit 126 to monitor the humidity of the pressurized air from the respiratory device 122. In other implementations, the moisture sensor 176 is located near any area where humidity levels need to be monitored. The moisture sensor 176 can also be used to monitor the humidity of the ambient environment surrounding the user 210, such as the air in the user's 210 bedroom. The moisture sensor 176 can also be used to track the user's 210 biological responses to environmental changes.

[0101] One or more light detection and ranging (LiDAR) sensors 178 can be used for depth sensing. This type of optical sensor (e.g., a laser sensor) can be used to detect objects and create a three-dimensional (3D) map of a surrounding environment, such as a living space. LiDAR typically uses a pulsed laser to measure time of flight. LiDAR is also referred to as 3D laser scanning. In one use case of such a sensor, a fixed or mobile device (such as a smartphone) with a LiDAR sensor 178 can measure and map an area more than five meters away from the sensor. LiDAR data can be fused with point cloud data estimated, for example, by an electromagnetic RADAR sensor. The LiDAR sensor(s) 178 can also automatically create geofences for a RADAR system by using artificial intelligence (AI) to detect and classify features in a space that may pose a problem for the RADAR system, such as glass windows (which may be highly reflective to the RADAR). LiDAR can also be used to estimate a person's height, as well as changes in height that occur when a person sits down, falls, etc. LiDAR can be used to create a 3D mesh representation of the environment. In a further application, LiDAR can reflect off solid surfaces through which radio waves pass (e.g., radio-transparent materials), allowing classification of different types of obstacles.

[0102] In some implementations, the one or more sensors 130 also include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a blood pressure sensor, an oximetry sensor, a sonar sensor, a RADAR sensor, a blood glucose sensor, a color sensor, a pH sensor, an air quality sensor, a tilt sensor, a direction sensor, a rain sensor, a soil moisture sensor, a water flow sensor, an alcohol sensor, or any combination thereof.

[0103] 1 and 2 , any combination of one or more sensors 130 may be integrated with and / or coupled to any one or more of the components of system 100, including breathing device 122, user interface 124, conduit 126, humidification tank 129, control system 110, user device 170, or any combination thereof. For example, acoustic sensor 141 and / or RF sensor 147 may be integrated with and / or coupled to user device 170. In such implementations, user device 170 may be considered a secondary device that generates additional or secondary data for use by system 100 (e.g., control system 110) according to some aspects of the present disclosure. In some implementations, at least one of the one or more sensors 130 is not physically and / or communicatively coupled to the breathing device 122, the control system 110, or the user device 170, but is positioned generally adjacent to the user 210 during a sleep session (e.g., positioned on or in contact with a portion of the user 210, worn by the user 210, coupled or positioned on a nightstand, coupled to a mattress, coupled to a ceiling, etc.).

[0104] Data from one or more sensors 130 can be analyzed to determine one or more sleep-related parameters, which may include a respiratory signal, a respiratory rate, a respiratory pattern, an inspiratory amplitude, an expiratory amplitude, an inspiratory-to-expiratory ratio, the occurrence of one or more events, the number of events per hour, an event pattern, a sleep state, a sleep stage, an apnea-hypopnea index (AHI), or any combination thereof. The one or more events may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, an intentional mask leak, an unintentional mask leak, a mouth leak, coughing, restless legs, a sleep disorder, choking, an increased heart rate, dyspnea, an asthma attack, an epileptic episode, a seizure, an elevated blood pressure, or any combination thereof. While many of these sleep-related parameters are physiological, some of these sleep-related parameters can be considered non-physiological. Non-physiological parameters may also include operating parameters of the respiratory therapy system, including pressurized air flow rate, pressure, humidity, motor speed, etc. Other types of physiological and non-physiological parameters may be determined either from data from one or more sensors 130 or from other types of data.

[0105] The user device 170 includes a display device 172. The user device 170 may be a mobile device, such as a smartphone, tablet, game console, smartwatch, laptop, or the like. Alternatively, the user device 170 may be an external sensing system, a television (e.g., a smart TV), or another smart home device (e.g., smart speaker(s), such as Google Home, Amazon Echo, Alexa, etc.). In some implementations, the user device is a wearable device (e.g., a smart watch). The display device 172 is generally used to display image(s), including still images, video, or both. In some implementations, the display device 172 serves as a human-machine interface (HMI), including a graphical user interface (GUI) configured to display image(s) and an input interface. The display device 172 may be an LED display, an OLED display, a liquid crystal display, or the like. The input interface may be, for example, a touchscreen or touch-sensitive substrate, a mouse, a keyboard, or any sensor system configured to sense inputs made by a human user interacting with user device 170. In some implementations, one or more user devices may be used by and / or included in system 100.

[0106] The blood pressure device 182 is typically used to assist in generating physiological data for determining one or more blood pressure measurements associated with a user. The blood pressure device 182 may include, for example, at least one of the one or more sensors 130 for measuring a systolic blood pressure component and / or a diastolic blood pressure component.

[0107] In some implementations, the blood pressure device 182 is a blood pressure monitor that includes an inflatable cuff that can be worn by the user and a pressure sensor (e.g., the pressure sensor 132 described herein). For example, as shown in the example of FIG. 2, the blood pressure device 182 can be worn on the upper arm of the user 210. In such implementations in which the blood pressure device 182 is a blood pressure monitor, the blood pressure device 182 also includes a pump (e.g., a manually operated valve) for inflating the cuff. In some implementations, the blood pressure device 182 is coupled to the respiratory device 122 of the respiratory therapy system 120, which delivers pressurized air to inflate the cuff. More typically, the blood pressure device 182 can be communicatively coupled to and / or physically integrated (e.g., within a housing) with the control system 110, the memory device 114, the respiratory therapy system 120, the user device 170, and / or the activity tracker 190.

[0108] The activity tracker 190 is typically used to assist in generating physiological data for determining activity metrics associated with a user. The activity metrics may include, for example, number of steps, distance traveled, number of steps climbed, duration of physical activity, type of physical activity, intensity of physical activity, time spent standing, respiration rate, average respiration rate, resting respiration rate, maximum respiration rate, respiration rate variability, heart rate, average heart rate, resting heart rate, maximum heart rate, heart rate variability, number of calories burned, blood oxygen saturation (SpO2), electrodermal activity (also referred to as skin conductance or galvanic skin response), user position, user posture, or any combination thereof. The activity tracker 190 includes one or more of the sensors 130 described herein, such as, for example, a motion sensor 138 (e.g., one or more accelerometers and / or gyroscope), a PPG sensor 154, and / or an ECG sensor 156.

[0109] In some implementations, the activity tracker 190 is a wearable device that can be worn by a user, such as a smartwatch, wristband, ring, or patch. For example, referring to FIG. 2 , the activity tracker 190 is worn on the wrist of the user 210. The activity tracker 190 can also be coupled to or integrated with clothing or apparel worn by the user. As a further alternative, the activity tracker 190 can be coupled to or integrated with the user device 170 (e.g., within the same housing). More typically, the activity tracker 190 can be communicatively coupled to or physically integrated (e.g., within the housing) with the control system 110, the memory device 114, the respiratory therapy system 120, and / or the user device 170, and / or the blood pressure device 182.

[0110] 1 as separate and distinct components of system 100, in some implementations control system 110 and / or memory device 114 are integrated into user device 170 and / or respiratory device 122. Alternatively, in some implementations control system 110 or a portion thereof (e.g., processor 112) may be located in the cloud (e.g., integrated into a server, integrated into an Internet of Things (IoT) device, connected to the cloud, subject to edge cloud processing, etc.), may be located on one or more servers (e.g., remote servers, local servers, etc., or any combination thereof).

[0111] Although system 100 is shown as including all of the above components, according to various implementations of the present disclosure, a system can include more or fewer components to analyze data associated with a user's use of respiratory therapy system 120. For example, a first alternative system includes control system 110, memory device 114, and at least one of one or more sensors 130. As another example, a second alternative system includes control system 110, memory device 114, at least one of one or more sensors 130, user device 170, and blood pressure device 182 and / or activity tracker 190. As another example, a third alternative system includes control system 110, memory device 114, respiratory therapy system 120, at least one of one or more sensors 130, activity tracker 190, and user device 170. As another example, a fourth alternative system includes control system 110, memory device 114, respiratory therapy system 120, at least one of one or more sensors 130, user device 170, blood pressure device 182, and / or activity tracker 190. As such, any portion or portions of the components shown and described herein can be used and / or combined with one or more other components to form a variety of systems.

[0112] Referring again to FIG. 2 , system 100 includes several optional components (i.e., multiple sensors, cameras, etc.) that are not necessarily required for system 100 operation. Any of these sensors capable of detecting one of the modalities described below is typically sufficient for the system to operate as described herein. Having more than one sensor in the system allows for parallel and / or independent estimation of sleep state, thereby increasing the accuracy of the computations. The system uses one or more of the identified sensors to determine sleep state, which may include sleep stage (e.g., N1, N2, N3, REM) if asleep, as well as whether awake or asleep. This determination may be based on modalities other than flow, but may also be based on flow in combination with one or more other modalities, such as movement, speech, or cardiac. For ease of explanation, the singular form is used, where applicable, for all components identified in FIG. 3 . However, the use of the singular form does not limit the description to only one of each such component.

[0113] As noted above, in one or more implementations, the respiratory system 100 may further include or be associated with a user device 170. The user device 170 may have the same functionality as the respiratory device 122 in terms of having a control system 172. Furthermore, the user device 170 may be a variety of devices, such as a smart home device, a smartphone, a smart watch, a smart speaker, a television, a smart mask, a smart ring, a fitness tracker, a computing device (e.g., a personal computer, laptop, tablet, etc.), a smart pendant, smart clothing, or any other device that is capable of communicating with one or more of the sensors 130 described herein and that also has smart functionality by having at least a control system 172, even if one or more sensors 130 are not integrated into the user device 170. A smart device is an electronic device that can connect to other devices or networks and typically has some processing power that allows it to generally operate, at least to some extent, interactively and autonomously. The user device 170 is widely associated with a user because it is used to measure the user's parameters. In some cases, user device 170 may be coupled to a user. Such coupling may be in mechanical contact with the user, either directly, such as by contact with the user's skin, or indirectly, such as through clothing. Coupled smart devices may include smart watches, smartphones, activity trackers, smart masks, smart clothing, smart mattresses, smart pillows, smart sheets, smart rings, or wearable health monitors. Contactless (untethered) smart devices may include smart TVs, smart speakers, smart cars, entertainment systems (including in-car entertainment systems), etc.

[0114] The user device 170 may also include and / or communicate with one or more remote servers (relative to the user and the local smart device). These servers may be configured to process and store, or simply store, data associated with the user. In some cases, these servers, typically capable of more complex and / or intensive computational tasks, may be configured to receive data from the local smart device and perform more computationally intensive tasks. The server(s) may then store and / or return results to the local smart device.

[0115] In one or more implementations, the control system 110 can perform the methods disclosed herein to determine a user's sleep state, i.e., based on respiratory flow data acquired by the device flow sensors. The control system 110 can be further configured to collect data from any additional disclosed sensors. Alternatively, the methods disclosed herein for determining a user's sleep state can be implemented by a control system 172 of a user device 170 configured to communicate with the respiratory device 122. In such an embodiment, the respiratory device 122 can transmit one or more signals to the user device 170 representing information collected and / or generated by the respiratory device 122 and used by the user device 170 to perform the methods.

[0116] In one or more alternative implementations, the methods disclosed herein for determining a user's sleep state may be implemented in part by control system 110 and in part by control system 172 of user device 170. For example, control system 110 may process information to determine the user's sleep state based on one or more flow parameters. In addition, user device 170 may process information using one or more additional sensors to determine the user's sleep state based on one or more other parameters, such as parameters related to the user's body movements, the user's cardiac data, etc. One of respiratory device 122 and user device 170 may transmit the determined user's sleep state to the other of respiratory device 122 and user device 170 for subsequent determination of the user's final sleep state and for further processing, such as determining the AHI.

[0117] 3, another example arrangement of components of system 100 in an environment is shown, according to some embodiments of the present disclosure. The environment is again a bedroom environment including a user 210 and a bed companion 220. User 210 is wearing a user interface 124 connected to a respiratory device 122 via a conduit 126. Respiratory device 122 includes a flow sensor that can facilitate measuring the respiratory flow of user 210. Statistical analysis of the respiratory flow can then be used to calculate sleep parameters that indicate whether the user 210 is awake or asleep and what sleep stage the user 210 is in at different times, as disclosed, for example, in International Patent Application Publication No. 2014 / 047110 (PCT / US2013 / 060652), entitled "SYSTEM AND METHOD FOR DETERMINING SLEEP STAGE," and International Patent Application Publication No. 2015 / 006164 (PCT / US2014 / 045814), entitled "METHOD AND SYSTEM FOR SLEEP MANAGEMENT," the contents of both of which are incorporated herein by reference in their entireties.

[0118] As described in International Patent Application Publication No. WO 2014 / 047110, it is possible to determine whether a person is asleep or awake without further determining sleep stages or first determining a specific sleep stage. In other words, the present disclosure contemplates determining whether a user 210 is awake or asleep, i.e., a sleep state, independently of, or at least without, determining a sleep stage.

[0119] In one or more implementations, one or more features can be generated from various data associated with the user 210 regarding use of the respiratory device and / or the user's 210 environment. These features can be used to determine whether the user 210 is awake or asleep. For example, flow data, including (but not limited to or requiring) flow and voice or other acoustic signals, can be processed while the user 210 is using the respiratory device to generate respiratory features. These respiratory features can be associated with the user 210 being awake or asleep. Based on the respiratory features input into the classifier, the classifier can analyze the respiratory features to determine whether the user 210 is awake or asleep.

[0120] In one or more implementations, a classifier can be trained to further determine sleep states by inputting previous respiratory or cardiac features (or other features generally associated with sleep) associated with known sleep states of wakefulness or sleep. After training, the classifier can be used to determine the sleep state of the user 210. The classifier can be, for example, a linear or quadrant discriminant analysis classifier, a decision tree, a support vector machine, or a neural network performing two-state classification, to name just a few such classifiers that can be trained to output a sleep state (e.g., wakefulness / sleep determination) based on the input features. As a further example, the classifier can be a rule-based processing system that classifies the input features. In some cases, the classifier can include input information from a function library for detecting sleep states. The library can provide signal processing on one or more sensed signals to estimate movement, activity counts, and respiration rate per epoch, such as time, frequency, or time vs. frequency, using wavelet or non-wavelet-based processing.

[0121] In one or more particular implementations, features associated with the user 210 can be input to a classifier. The classifier can then combine the features to generate a number used to estimate a sleep state of awake or asleep. For example, a number can be generated by the classifier, and the number can be a discriminant value. In some implementations, the combination of values ​​in the classifier can be done in a linear manner. For example, the discriminant value can be a linearly weighted combination of features. The classifier can then generate an appropriate sleep state label (e.g., asleep, awake, or present / absent) from the discriminant value. The sleep state classifier thus processes input features (e.g., wavelet features, respiratory features, etc.) to detect sleep states.

[0122] Various locations of the components of system 100 are contemplated. For example, one or more cameras can be mounted on the ceiling of the room. Non-contact sensing can also be achieved using non-contact sensors, such as cameras, motion sensors, radar sensors, sonar sensors, and / or microphones, located at locations 350, 352, 354, 356, and 358. One or more microphones, a combination of a microphone and speaker for sonar, or a transmitter and receiver for radar can be mounted on the bed 230 and / or on the walls of the room. In some implementations, having multiple cameras or microphones at different locations in the room allows for multiple video angles and stereo sound, which may enable the user 210 to directly distinguish and reject noise from bedmates 220. In some implementations, contact sensors, such as PPG sensors, GSR sensors, ECG sensors, and actigraphy sensors, can be placed on the user 210 at locations 360, 362, 364, and 366.

[0123] Although the present disclosure has been described primarily in the context of detecting a user's sleep state and / or stage while the user is using a respiratory therapy device, the methods of the present disclosure may be applied to any SDB device. For example, the methods of the present disclosure may be applied to a mandibular repositioning device. Furthermore, the methods of the present disclosure may be applied to any individual who desires more information about their sleep, not necessarily to individuals suffering from some form of sleep-disordered breathing. As such, these methods that do not require a respiratory therapy system may be applied to any individual having the other components of system 100 described above that can determine the user's sleep state and / or stage. In such cases, for example, respiratory therapy system 120 may be omitted from system 100, and sleep state and / or sleep stage determination may be achieved by other components of system 100.

[0124] 4 illustrates an example process 400 for detecting a sleep state based on a user's movements, according to various aspects of the present disclosure. For convenience, the following description will refer to process 400 as being performed by respiratory therapy system 120. However, process 400 may be performed by respiratory therapy system 120 and / or by a remote external sensor and / or computing device, such as any one of the sensors / devices included (locally or otherwise) in the system of FIG. 1.

[0125] In step 402, the respiratory therapy system 120 detects one or more parameters related to the user's movements during a sleep session. In one or more implementations, the sleep session may optionally include a session in which pressurized air is applied to the user's airway. In one or more implementations, the one or more parameters may relate to the duration, speed, frequency (or duration), intensity, or type of the user's movements, and combinations thereof. In one or more implementations, the one or more parameters may be measured based on one or more sensors located on the user, near the user, or a combination thereof. These sensors capture at least one parameter representative of the user's movements, such as the user's whole body movements, movements of one or more of the user's limbs, etc. In one or more implementations, the movements include any movements not related to respiratory or cardiac function. Examples of such general body movements are referred to throughout this specification as body movements and include, for example, rolling over, twitching, postural adjustments, limb movements, etc. These movement-indicative parameters may be provided by radio frequency bio-motion sensors, but may also be acquired by one or more actigraphy-based or pressure sensors, bio-impedance measurement systems, ultrasonic sensors, or optical sensors embedded in a sensor film or sensor mattress, etc.

[0126] In one or more implementations, this motion may include any one or more of respiratory motion, cardiac motion, and whole-body motion. With regard to respiratory motion, these motion parameters can be calculated based on flow information or other motion sensors collected by the respiratory device, either contact (respiratory belt or other wearable inertial measurement sensor) or non-contact (RF or acoustic) sensors. These respiratory parameters may include respiratory amplitude, relative respiratory amplitude, respiratory rate, and respiratory rate variability.

[0127] In one or more embodiments, pressurized air is applied to the user's airway through a tube and / or mask connected to the breathing device, and at least one of the one or more sensors may be located on or within the tube, the mask, or a combination thereof. In one or more embodiments, the at least one sensor may include an inertial measurement unit on or within the tube, the mask, or a combination thereof. In one or more embodiments, the at least one sensor of the one or more sensors may include an inertial measurement unit in a smart device coupled to the user. For example, the smart device may include a smartwatch, a smartphone, an activity tracker, a smart mask worn by the user during therapy, or a health monitor.

[0128] In one or more implementations, parameters associated with body and / or respiratory movements can be acquired through non-invasive sensors, such as a pressure-sensitive mattress or a radio frequency (RF) motion sensor. RF motion sensors are contactless sensors because they do not require the user to make mechanical contact with the sensor. The RF motion sensor can be configured to be sensitive to movements within a distance of, for example, 1.2 meters and to avoid detecting movements from objects further away. This can prevent or limit interference from, for example, a second user in bed or nearby moving objects, such as a fan. One or more specific examples of such sensors can be found in International Patent Application Publication No. 2007 / 143535 (PCT / US2007 / 070196), entitled "APPARATUS, SYSTEM, AND METHOD FOR MONITORING PHYSIOLOGICAL SIGNS," the contents of which are incorporated herein by reference in their entirety, and in the above-mentioned International Patent Application Publication No. 2015 / 006164 (PCT / US2014 / 045814).

[0129] It is understood that in some versions of the present technology, other sensors, such as those further described herein, may be used in addition or instead to generate movement (breathing signals) for detecting sleep stages.

[0130] In step 404, respiratory therapy system 120 processes one or more parameters to determine the user's sleep state, whether the user is awake, asleep, or in a particular sleep stage. In one or more implementations, some specific parameters that may be estimated and analyzed relate to the frequency, amplitude, and bursts of high-frequency (fast) movements that occur when the user transitions from an awake state to the twilight phase of sleep stage N1. The combined properties of the movement pattern, breathing rate value, and waveform shape may be used to classify the sleep state.

[0131] In one or more implementations, the respiratory therapy system 120 can use a classifier to determine the user's sleep state. The classifier can be derived from any one or more of supervised machine learning, deep learning, convolutional neural networks, and recurrent neural networks. The classifier can receive the parameters detected in step 402 as input information and process the parameters to determine the sleep state. In one or more implementations, the classifier can be a full sleep stage classifier using a one-dimensional convolutional neural network. In this approach, a set of feature decoders is trained directly from the raw or preprocessed flow signal.

[0132] In one or more implementations, processing the one or more parameters includes processing a signal representing at least one of the one or more parameters over time, so that respiratory therapy system 120 can adapt to and learn subject-specific data over time (e.g., typical baseline breathing rates and subject movement, i.e., the amount of tossing / fidgeting in bed as the user falls asleep) and use it in the estimation process to improve the accuracy of this classification.

[0133] In step 406, respiratory therapy system 120 calculates the user's AHI during the session based at least in part on the user's movement-based sleep state. The AHI is calculated such that one or more events that would affect the calculation of the user's apnea-hypopnea index are ignored due to the sleep state being determined to be awake during the one or more events. The one or more events may be one or more apneas, one or more hypopneas, or a combination thereof. Thus, if one or more SBD events occur but the sleep state indicates the user is awake, the SBD events are ignored so that the AHI is not affected by the false events.

[0134] 5 depicts an embodiment somewhat similar to that of FIG. 4, but in which a process 500 for detecting a sleep state is based on cardiac activity, according to various aspects of the present disclosure. For convenience, the following description will refer to process 500 as performed by respiratory therapy system 120. However, process 500 may also be performed by respiratory therapy system 120 in conjunction with any one or more of the sensors and devices (local or otherwise) included in the system of FIG. 1.

[0135] In step 502, respiratory therapy system 120 detects one or more parameters related to the user's cardiac activity during a sleep session. In one or more implementations, the sleep session may optionally include a session in which pressurized air is applied to the user's airway. In one or more implementations, the pressurized air is applied to the user's airway through a tube and a mask connected to a breathing device. At least one sensor for the one or more parameters may be on or in the tube, the mask, or a combination thereof.

[0136] In one or more implementations, cardiac signals can be extracted from respiratory flow signals (collected by a respiratory device flow sensor or from additional contact or non-contact sensors) or based on pressure waves produced at the body surface, called ballistocardiograms. In some cases, a combination of positioning, body type, and distance from the sensor provides a signal in which individual pulses are clearly visible through movement. In such cases, thresholding techniques are used to determine heartbeats. For example, pulses are associated with points where the signal crosses a threshold. In more complex but typical cases, ballistocardiograms exhibit more complex but highly reproducible pulse shapes. Therefore, the acquired cardiac signal can be correlated with a pulse shape template, and locations of high correlation are used as the locations of heartbeats. Pulses can then be measured using a motion sensor, such as the RF sensor described above.

[0137] More specifically, similar to the implementations described above with respect to movement, in one or more implementations, the sensor can be a radio frequency sensor separate from or integrated with the respiratory device. The sensor can transmit a radio frequency signal toward the user. The reflected signal is then received, amplified, and mixed with a portion of the original signal. The output of this mixer can be low-pass filtered. The resulting signal contains information about the user's cardiac activity and is typically superimposed on a respiratory signal collected from the user. In an alternative implementation, the sensor can also use quadrature transmission, in which two carrier signals are used that are 90 degrees out of phase. Within the limit of very short pulse durations, such a system can be characterized as an ultra-wideband (UWB) radio frequency sensor.

[0138] In one or more implementations, the one or more parameters may be related to the user's heart rate, heart rate variability, cardiac output, or a combination thereof. In one or more implementations, heart rate variability may be calculated over 1 minute, 5 minutes, 10 minutes, 30 minutes, 1 hour, 2 hours, 3 hours, or 4 hours.

[0139] In step 504, the respiratory therapy system 120 processes the one or more parameters to determine the user's sleep state, which may be at least one of wakefulness, sleep, or a sleep stage. As above, in one or more implementations, the respiratory system may use a classifier to determine the user's sleep state. The classifier may be derived from any one or more of supervised machine learning, deep learning, convolutional neural networks, and recurrent neural networks. The classifier may receive the parameters from step 502 as input and process the parameters to determine the sleep state. In one or more implementations, the classifier may be a full sleep stage classifier using a one-dimensional convolutional neural network. In this approach, a set of feature decoders is trained directly from the raw or preprocessed flow signal.

[0140] In step 506, the respiratory therapy system 120 calculates the user's apnea-hypopnea index during the session based at least in part on the sleep state. The AHI is typically calculated based on respiratory data collected from a flow sensor in the respiratory device, as described above. Knowledge of the user's sleep state allows the AHI index to be calculated such that one or more events that would affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state during the one or more events was determined to be awake. The one or more events may be one or more apneas, one or more hypopneas, or a combination thereof. Thus, if one or more SBD events occur but the sleep state determined for that time indicates the user is awake, the SBD events are ignored so that the AHI is not affected by the erroneously scored events.

[0141] 6 illustrates an example process 600 for detecting a sleep state based on audio parameters associated with a user, according to various aspects of the present disclosure. For convenience, the following description refers to process 600 as being performed by respiratory therapy system 120. However, process 600 may be performed by respiratory therapy system 120 in cooperation with additional sensors and computing devices, such as any one of the sensors / devices (local or otherwise) shown in system 100 of FIG. 1.

[0142] In step 602, the respiratory therapy system 120 detects one or more parameters related to sound associated with the user during a sleep session using an internal (within the respiratory system) or external microphone. In one or more implementations, the sleep session may optionally include a session in which pressurized air is applied to the user's airway. The sound parameters may relate to sounds passively heard by a microphone positioned proximate to the user, for example. For example, sounds may be generated by a tube scraping across an object such as a sheet or passing along a side panel.

[0143] Alternatively, the sound parameters may relate to sounds emitted and received via echoes at a microphone positioned in the vicinity of the user. These sounds may be emitted by a device specifically configured to emit sound, such as a speaker, or by a device that emits sound indirectly, such as a blower in a breathing device.

[0144] In one or more specific implementations, the sound can be associated with (1) one or more movements of the user, (2) one or more movements of a tube, a mask, or a combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof. For example, the user can move, and the movement can produce a sound that is picked up by a microphone. Alternatively, the user can move equipment that makes up the breathing system, such as a tube, and the sound of the tube can be picked up by a microphone. The movement of the tube can indicate the user's activity. Alternatively, loud snoring can indicate that the user has fallen asleep quickly.

[0145] In one or more implementations, detecting the one or more parameters related to the sound associated with one or more movements of the tube, the mask, or a combination thereof is based on cepstral analysis, spectral analysis, a fast Fourier transform, or a combination thereof of one or more sound signals. The sound can be detected based on one or more microphones in the tube, the mask, or a device connected to the tube, which provides pressurized air to the user's airway.

[0146] More specifically, the tube can be a waveguide. Changes in the tube's properties as it moves as a waveguide cause reflections (e.g., echoes) within the tube to change location. Mathematical processing of the changes in reflections, such as by cepstrum processing, wavelet analysis, squared signals, or root mean square, can detect and match the changes to the user's movements. Further details of the mathematical processing can be found in International Patent Application Publication No. 2010 / 091362 (PCT / AU2010 / 000140), entitled "ACOUSTIC DETECTION FOR RESPIRATORY TREATMENT APPARATUS," the contents of which are incorporated herein by reference in their entirety. Further acoustic sensors are disclosed in International Patent Application Publication No. 2018 / 050913 (PCT / EP2017 / 073613), entitled "Apparatus, System, and Method for Detecting Physiological Movement from Audio and Multimodal Signals," International Patent Application Publication No. 2019 / 122412 (PCT / EP2018 / 086762), entitled "Apparatus, System, and Method for Health and Medical Sensing," and International Patent Application Publication No. 2019 / 122412 (PCT / EP2018 / 086762), entitled "Apparatus, System, and Method for Motion Detection." and International Patent Application Publication No. 2019 / 122413 (PCT / EP2018 / 086764) entitled "Apparatus, System, and Method for Motion Sensing," and International Patent Application Publication No. 2019 / 122414 (PCT / EP2018 / 086765) entitled "Apparatus, System, and Method for Physical Sensing in Vehicles," the contents of which are incorporated herein by reference in their entireties.

[0147] In step 604, respiratory therapy system 120 processes the one or more parameters to determine the user's sleep state, which may be at least one of wakefulness, sleep, or a sleep stage. As described above, in one or more implementations, respiratory therapy system 120 can use a classifier to determine the user's sleep state. The classifier can be derived from any one or more of supervised machine learning, deep learning, convolutional neural networks, and recurrent neural networks. The classifier can receive the parameters detected in step 602 as input and process those parameters to determine the sleep state. In one or more implementations, the classifier can be a full sleep stage classifier using a one-dimensional convolutional neural network. In this approach, a set of feature decoders is trained directly from the raw or preprocessed flow signal.

[0148] In step 606, respiratory therapy system 120 calculates the user's apnea-hypopnea index during the session based at least in part on the sleep state. The AHI is calculated such that one or more events that would affect the calculation of the user's apnea-hypopnea index are ignored in response to the sleep state being determined to be awake during the one or more events. The one or more events may be one or more apneas, one or more hypopneas, or a combination thereof. Thus, if one or more SBD events occur but the sleep state indicates that the user is awake, the SBD events are ignored so that the AHI is not affected by the false events.

[0149] 7 illustrates an example process 700 for detecting a user's sleep state based on multiple different modalities, according to various aspects of the present disclosure. For convenience, the following description will refer to process 700 as being performed by respiratory therapy system 120. However, process 700 may be performed by respiratory therapy system 120 in cooperation with any other sensors or devices (local or otherwise) included in FIG. 1 .

[0150] In step 702, respiratory therapy system 120 detects a plurality of parameters associated with a user during a session of applying pressurized air to the user's airway. Each parameter of the plurality of parameters is associated with at least one modality, such as user movement, pressurized air flow rate, user cardiac activity, or audio associated with the user. The detection is multimodal, with the plurality of parameters encompassing at least two of the modalities. For example, the parameters may include body movement and respiratory flow rate, cardiac movement and respiratory flow rate, audio and respiratory flow rate, etc.

[0151] In step 704, the respiratory therapy system 120 processes the plurality of parameters to determine the user's sleep state, which may be at least one of wakefulness, sleep, or a sleep stage. As described above, in one or more implementations, the respiratory therapy system 120 can use a classifier to determine the user's sleep state. The classifier can be derived from any one or more of supervised machine learning, deep learning, convolutional neural networks, and recurrent neural networks. The classifier can receive the parameters from step 702 as input and process the parameters to determine the sleep state. In one or more implementations, the classifier can be a full sleep stage classifier using a one-dimensional convolutional neural network. In this approach, a set of feature decoders is trained directly from the raw or preprocessed flow signal.

[0152] In one or more implementations, parameters of three different modalities are divided into time epochs, and statistical features are generated for each epoch. For example, these features may be signal variance, spectral content, or peak values, which are grouped into vectors Xr, Xn, and Xc. These vectors can then form a single vector of features X. These features are combined to determine the likelihood that the epoch corresponds to a particular sleep state (e.g., the user is asleep, the user is awake). Classifications from an epoch can be further combined with classifications from other epochs to form higher-level determinations, such as the user's sleep stage.

[0153] In one or more implementations using RF sensors for detecting body motion, respiratory activity, and cardiac activity, body motion can be identified using a zero-crossing or energy envelope detection algorithm (or a more complex algorithm) and used to form a "motion on" or "motion off" indicator. Respiratory activity is typically in the range of 0.1 to 0.8 Hz and can be derived by filtering the raw sensor signal with a bandpass filter whose passband is within that range. Cardiac activity can be detected as a high-frequency signal (i.e., in a respiratory flow signal collected by a respiratory device or other contact or non-contact sensor) that can be accessed by filtering with a bandpass filter having a passband such as 1 to 10 Hz.

[0154] In one or more implementations, the system first tests which modality provides the best signal. One or more of these are then used in further measurements. In further implementations, the system may start with two or more predetermined modalities. However, in some cases, this processing may determine that the user's sleep state cannot be determined based on one or more parameters of the plurality of parameters associated with one of the two or more predetermined modalities. For example, one of the predetermined modalities may be respiratory flow. Regarding the above-mentioned deficiencies related to flow, if the respiratory device determines that the sleep state cannot be determined based on flow alone, the processing of one or more parameters of the plurality of parameters may then be associated with a second of the two predetermined modalities, or the second modality plus a (third) modality. For example, the second or third modality may be one of the user's body movement, the user's cardiac activity, audio associated with the user, etc.

[0155] In one or more implementations, a determination that a user's sleep state cannot be determined may be based on meeting a threshold decision metric. The threshold decision metric may be based on two or more parameters of a plurality of conflicting parameters for a sleep state, a sleep state, or a combination thereof. In one or more implementations, the two or more conflicting parameters may be derived from two or more different modalities. In one or more implementations, a conflict between two or more conflicting parameters is resolved by ignoring parameters derived based on lower-quality data and / or increasing weighting for parameters extracted from higher-quality data. Thus, each modality and / or parameter may be weighted according to data quality. A sleep state (e.g., a sleep state and a sleep stage) may be determined from a modality and / or parameter with a higher weighting, for example, based on the modality and / or parameter being conventionally more accurate. Thus, in one or more implementations, processing of the plurality of parameters may be based on a subset of the plurality of parameters from two or more selected modalities of the plurality of modalities. The selected two or more modalities may be selected according to a weighting based on data quality.

[0156] The threshold determination metric may be based on multiple prior parameters associated with the user during one or more prior sessions of applying pressurized air to the user's airway. The prior parameters may be verified from the prior sessions as accurately reflecting the user's sleep state. A classifier may then be used based on this learned information to provide a threshold determination. This process is performed by a sleep stage classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks.

[0157] For example, Table 1 lists user characteristics, specifically physiological responses, that are used by the respiratory system in determining sleep stages. [Table 1]

[0158] In Table 1, the sleep stages listed are non-REM sleep and REM sleep within the context of the sleep state of being asleep. The sleep states listed are wake and sleep. The user's physiological responses are respiratory rate, activity, tidal volume, heart rate, airway resistance, obstructive apnea, central apnea, snoring (non-apneic), and snoring (apneic). Each of these features can be determined based on the flow signal from the respiratory device and then potentially used to determine the sleep stage. However, the determination is likelihood-based, such as likely, unlikely, and variable. Nevertheless, combining additional modalities with the flow modality to determine the sleep state and sleep stage increases the accuracy of the determined state / stage. Increased accuracy leads to improved determinations and outcomes, such as a more accurate AHI.

[0159] In step 706, respiratory therapy system 120 calculates the user's apnea-hypopnea index during the session based at least in part on the sleep state. The AHI is calculated such that one or more events that would affect the calculation of the user's apnea-hypopnea index are ignored in response to the sleep state being determined to be awake during the one or more events. The one or more events may be one or more apneas, one or more hypopneas, or a combination thereof. Thus, if one or more SBD events occur but the sleep state indicates that the user is awake, the SBD events are ignored so that the AHI is not affected by the false events.

[0160] FIG. 8 illustrates several graphs associated with a user's sleep session. These graphs include a pneumotachogram 804 and a respiration rate (beats per minute) graph 806. Parameters associated with these graphs are processed to determine a sleep graph plot 806 illustrating the user's sleep state (i.e., awake or not) and, if not awake, their sleep stages (i.e., N1+N2, N3, and REM). The respiration rate graph 806 may be based on data received from the pneumotachogram 804. Many respiratory therapy devices plot the pneumotachogram 804 and calculate the AHI based on data obtained using a flow sensor in the respiratory device. However, pneumotachogram data may also be obtained by independent measurements, such as with additional contact or non-contact sensors, as described earlier in this document. Thus, the AHI calculation may also be performed based on data obtained by these alternative sensors. Furthermore, such additional sensor(s) may provide information directed to other modalities, such as the user's cardiac or body movement, as well as any audible signals generated by the user during the sleep session. By processing data associated with more than one modality, an accurate hypnogram plot 806 can be generated that accurately reflects the user's sleep state during sessions in which pressurized air is provided using the respiratory device, which may result in improved accuracy in calculating the user's AHI.

[0161] In one or more implementations, after determining the sleep state, the AHI, or both in any one or more of the processes described above with respect to FIGS. 4-7 , an action may be initiated based at least in part on the sleep state, the AHI, or a combination thereof. In one or more implementations, the action may include one or more of: (1) storing a record of the apnea-hypopnea index; (b) communicating the apnea-hypopnea index to an external device and displaying the information on a screen; or (c) adjusting an operational setting of the device. For example, one or more settings of the respiratory device 122 may be adjusted based on the detected sleep state, sleep stage, and / or AHI. In one example, a more accurately detected AHI may indicate an improvement in the user's sleep-disordered breathing, and the respiratory pressure setting of the respiratory device 122 may be automatically reduced. This may increase user comfort without necessarily compromising the therapeutic benefits of using the respiratory device 122, and may potentially improve user compliance with prescribed treatment. If the device detecting the sleep state and / or AHI is not the respiratory device 122, such as the user device 170, the sleep state, sleep stage, and / or AHI can be transmitted to the respiratory device 122 or the respiratory therapy system 120. As such, one or more measures can be implemented to improve therapy compliance, for example, by providing the user with richer feedback regarding sleep quality (e.g., more accurate AHI and / or sleep state). Providing more information to the user with more accurate sleep staging can improve engagement by providing consumer features and can also improve patient adherence by providing the user with feedback that quantifies the benefit of therapy.

[0162] While the present disclosure has been described with reference to one or more particular implementations or implementations, those skilled in the art will recognize that numerous modifications may be made without departing from the spirit and scope of the present disclosure. Each of these implementations and obvious variations thereof is contemplated as falling within the spirit and scope of the present disclosure. And it is also contemplated that further implementations according to various aspects of the present disclosure may combine any number of features from any of the implementations described herein. The following are appendices to the present disclosure. (Additional note 1) Detecting one or more parameters related to a user's movements during a sleep session of the user; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the one or more parameters; and calculating an apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state. (Additional note 2) 2. The method of claim 1, wherein the sleep session includes a session in which pressurized air is applied to the user's airway. (Additional note 3) 3. The method of claim 1 or 2, wherein the sleep stages include manifestations of non-REM, N1 sleep, N2 sleep, N3 sleep, or REM sleep. (Additional note 4) 4. The method of any one of claims 1 to 3, wherein one or more events that affect the calculation of the apnea-hypopnea index of the user are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 5) 5. The method of claim 4, wherein the one or more events are one or more apneas, one or more hypopneas, or a combination thereof. (Additional note 6) 6. The method of any one of clauses 1 to 5, wherein the one or more parameters relate to duration, period, speed, frequency, intensity, type of movement of the user, or a combination thereof. (Additional note 7) 7. The method of any one of clauses 1 to 6, wherein the one or more parameters are measured based on one or more sensors located on the user, located in the vicinity of the user, or a combination thereof. (Additional note 8) 8. The method of claim 7, wherein pressurized air is applied to the user's airway through a tube and a mask connected to a breathing device, and at least one sensor of the one or more sensors is located on or in the tube, on or in the mask, or a combination thereof. (Additional note 9) 9. The method of claim 8, wherein the at least one sensor includes a motion sensor located on or within the tube, on or within the mask, or a combination thereof. (Additional note 10) 10. The method of any one of clauses 7 to 9, wherein at least one sensor of the one or more sensors includes a motion sensor in a smart device. (Additional note 11) 11. The method of claim 10, wherein the smart device is one or more of: (1) a smart watch, smartphone, activity tracker, smart mask, smart clothing, smart mattress, smart pillow, smart sheet, smart ring, or health monitor, each of which is in contact with the user; (2) a smartphone, smart speaker, smart TV, radar-based sensor, sonar-based sensor, LiDAR-based sensor, or other non-contact motion sensor, each of which is in proximity to the user; (3) or a combination thereof. (Additional note 12) 12. The method of any one of clauses 1 to 11, wherein the processing of the one or more parameters comprises processing a signal representative of at least one of the one or more parameters over time. (Additional note 13) Detecting one or more parameters related to cardiac activity of a user during a sleep session of the user; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the one or more parameters; and calculating an apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state. (Additional note 14) The method described in Appendix 13, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 15) 15. The method of claim 14, wherein the one or more events are one or more apneas, one or more hypopneas, or a combination thereof. (Additional note 16) 16. The method of any one of clauses 13 to 15, wherein the one or more parameters relate to the user's heart rate, heart rate variability, cardiac output, or a combination thereof. (Additional note 17) 17. The method of claim 16, wherein the heart rate variability is calculated over 1 minute, 5 minutes, 10 minutes, 30 minutes, 1 hour, 2 hours, 3 hours, or 4 hours. (Additional note 18) 18. The method of any one of clauses 13 to 17, wherein pressurized air is applied to the user's airways through a tube and a mask connected to a breathing device, and at least one sensor of the one or more parameters is located on or within the tube, the mask, or a combination thereof. (Additional note 19) 19. The method of any one of clauses 13 to 18, wherein the sleep session includes a session in which pressurized air is applied to the user's airway. (Additional note 20) 20. The method of any one of clauses 13 to 19, wherein the detecting of the one or more parameters is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more audio signals, or a combination thereof. (Additional note 21) Detecting one or more parameters related to audio associated with a user during a sleep session of the user; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the one or more parameters; and calculating an apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state. (Additional note 22) The method described in Appendix 21, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 23) The one or more events include one or more apneas, one or more hypopneas, or a combination thereof. 23. The method according to claim 22, wherein the method is a combination of (Additional note 24) 24. The method of any one of clauses 21 to 23, wherein the audio is associated with (1) one or more movements of the user, (2) one or more movements of a tube, a mask, or a combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof. (Additional note 25) 25. The method of claim 24, wherein detecting the one or more parameters related to the audio associated with the one or more movements of the tube, the mask, or a combination thereof is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more audio signals, or a combination thereof. (Additional note 26) 26. The method of any one of clauses 21 to 25, wherein the sound is detected based on one or more microphones in a tube, a mask, or a device connected to the tube, and the device provides pressurized air to the user's airway. (Additional note 27) detecting a plurality of parameters associated with a user during a session of applying pressurized air to the user's airway, each parameter of the plurality of parameters being associated with at least one modality, the plurality of parameters encompassing a plurality of modalities; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the plurality of parameters; and calculating an apnea-hypopnea index for the user during the session based at least in part on the sleep state. (Additional note 28) 28. The method of claim 27, wherein the modalities include movement of the user, flow rate of the pressurized air, cardiac activity of the user, and audio associated with the user. (Additional note 29) 29. The method of claim 27 or 28, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 30) 30. The method of claim 29, wherein the one or more events include one or more apneas, one or more hypopneas, or a combination thereof. (Additional note 31) said processing of said plurality of parameters comprising: determining that the sleep state of the user cannot be determined based on one or more parameters of the plurality of parameters associated with a first modality of the two or more modalities; 31. The method of any one of clauses 27 to 30, further comprising: processing one or more parameters of the plurality of parameters associated with a second modality of the two or more modalities to determine the sleep state of the user. (Additional note 32) 32. The method of claim 31, wherein the determination that the sleep state of the user cannot be determined is based on satisfying a threshold decision metric. (Additional note 33) 33. The method of claim 32, wherein the threshold determination metric is based on two or more parameters of the plurality of competing parameters for sleep state, sleep stage, or a combination thereof. (Additional note 34) 34. The method of claim 33, wherein the two or more competing parameters are derived from the two or more modalities. (Additional note 35) 35. The method of any one of clauses 27 to 34, wherein conflicts between two or more competing parameters are resolved by ignoring parameters derived based on lower quality data and / or increasing the weight given to parameters extracted from higher quality data. (Additional note 36) 36. The method of claim 35, wherein the threshold determination metric is based on a plurality of previous parameters associated with the user during one or more previous sessions of applying the pressurized air to the user's airway. (Additional note 37) 37. The method of any one of clauses 27 to 36, wherein the processing is performed by a sleep stage classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks. (Additional note 38) 38. The method of any one of clauses 27 to 37, wherein the processing of the plurality of parameters is based on a subset of the plurality of parameters derived from two or more selected modalities of the plurality of modalities, the two or more selected modalities being selected according to a weighting based on data quality. (Additional note 39) one or more sensors configured to detect one or more parameters related to the user's movements during the user's sleep session; a memory storing machine-readable instructions; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the one or more parameters; Calculating an apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state. and a control system including one or more processors configured to execute the machine-readable instructions to: (Additional note 40) The system described in Appendix 39, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 41) The system of claim 40, wherein the one or more events are one or more apneas, one or more hypopneas, or a combination thereof. (Additional note 42) 42. The system of any one of clauses 39 to 41, wherein the one or more parameters relate to duration, period, speed, frequency, intensity, type of movement of the user, or a combination thereof. (Additional note 43) 43. The system of claim 42, wherein the at least one sensor is located on the user, located near the user, or a combination thereof. (Additional note 44) a breathing device having a tube and a mask connected to the user; 44. The system of claim 43, wherein pressurized air is applied to the user's airway through the tube and the mask, and at least one of the one or more sensors is located on or within the tube, on or within the mask, or a combination thereof. (Additional note 45) 45. The system of any one of clauses 39 to 44, wherein the one or more sensors include a motion sensor located on or within the tube, on or within the mask, or a combination thereof. (Additional note 46) 46. ​​The system of any one of clauses 39 to 45, wherein at least one of the one or more sensors includes a motion sensor within a smart device. (Additional note 47) 47. The system of claim 46, wherein the smart device is one or more of: (1) a smart watch, smartphone, activity tracker, smart mask, smart clothing, smart mattress, smart pillow, smart sheet, smart ring, or health monitor, each of which is in contact with the user; (2) a smart speaker or smart TV, each of which is located in proximity to the user; or (3) a combination thereof. (Additional note 48) 48. The system of any one of clauses 39 to 47, wherein the processing of the one or more parameters comprises processing a signal representing at least one of the one or more parameters over time. (Additional note 49) at least one sensor configured to detect one or more parameters related to cardiac activity of the user during the user's sleep session; a memory storing machine-readable instructions; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the one or more parameters; Calculating an apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state. and a control system including one or more processors configured to execute the machine-readable instructions to: (Additional note 50) The system described in Appendix 49, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 51) The system of claim 50, wherein the one or more events are one or more apneas, one or more hypopneas, or a combination thereof. (Additional note 52) 52. The system of any one of clauses 39 to 51, wherein the one or more parameters relate to the user's heart rate, heart rate variability, cardiac output, or a combination thereof. (Additional note 53) 53. The system of claim 52, wherein the heart rate variability is calculated over 1 minute, 5 minutes, 10 minutes, 30 minutes, 1 hour, 2 hours, 3 hours, or 4 hours. (Additional note 54) a breathing device having a tube and a mask connected to the user; 54. The system of any one of clauses 39 to 53, wherein pressurized air is applied to the user's airway through the tube and the mask, and at least one of the one or more sensors is located on or within the tube, the mask, or a combination thereof. (Additional note 55) 55. The system of claim 54, wherein the at least one sensor is a microphone. (Additional note 56) 56. The system of claim 55, wherein the detecting of the one or more parameters is based on cepstrum analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more audio signals, or a combination thereof, detected by the microphone. (Additional note 57) one or more sensors configured to detect one or more parameters related to audio associated with a user during the user's sleep session; a memory storing machine-readable instructions; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the one or more parameters; Calculating an apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state. and a control system including one or more processors configured to execute the machine-readable instructions to: (Additional note 58) The system described in Appendix 57, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 59) The system of claim 58, wherein the one or more events are one or more apneas, one or more hypopneas, or a combination thereof. (Additional note 60) a breathing device having a tube and a mask connected to the user; 60. The system of any one of clauses 57 to 59, wherein the audio is associated with (1) one or more movements of the user, (2) one or more movements of the tube, the mask, or a combination thereof connected to the breathing device configured to apply pressurized air to the user, or (3) a combination thereof. (Additional note 61) The system of claim 60, wherein detecting the one or more parameters related to the audio associated with the one or more movements of the tube, the mask, or a combination thereof is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more audio signals, or a combination thereof. (Additional note 62) a breathing device having a tube and a mask connected to the user; 62. The system of any one of clauses 57 to 61, wherein the one or more sensors are one or more microphones in a tube, a mask, or a device connected to the tube, and the device provides pressurized air to the user's airway. (Additional note 63) one or more sensors configured to detect a plurality of parameters associated with a user during a session of applying pressurized air to the user's airway, wherein each parameter of the plurality of parameters is associated with at least one modality, and the plurality of parameters spans a plurality of modalities; a memory storing machine-readable instructions; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the plurality of parameters; calculating an apnea-hypopnea index for the user during the session based at least in part on the sleep state; and a control system including one or more processors configured to execute the machine-readable instructions to: (Additional note 64) 64. The system of claim 63, wherein the modalities include the user's movement, the flow rate of the pressurized air, the user's cardiac activity, and audio associated with the user. (Additional note 65) The system described in appended clause 63 or 64, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 66) The system of claim 65, wherein the one or more events include one or more apneas, one or more hypopneas, or a combination thereof. (Additional note 67) the control system determining that the sleep state of the user cannot be determined based on one or more parameters of the plurality of parameters associated with a first modality of the two or more modalities; processing one or more parameters of the plurality of parameters associated with a second modality of the two or more modalities to determine the sleep state of the user; 67. The system of any one of clauses 63 to 66, further configured to execute the machine-readable instructions to further process the plurality of parameters. (Additional note 68) 68. The system of claim 67, wherein the determination that the user's sleep state cannot be determined is based on satisfying a threshold decision metric. (Additional note 69) 69. The system of claim 68, wherein the threshold determination metric is based on two or more parameters of the plurality of competing parameters relating to sleep state, sleep stage, or a combination thereof. (Additional note 70) The system of claim 69, wherein the two or more competing parameters are derived from the two or more modalities. (Additional note 71) 71. A system according to any one of clauses 63 to 70, wherein conflicts between two or more competing parameters are resolved by ignoring parameters derived based on lower quality data and / or giving increased weight to parameters extracted from higher quality data. (Additional note 72) The system of claim 71, wherein the threshold determination metric is based on a plurality of previous parameters associated with the user during one or more previous sessions of applying the pressurized air to the user's airway. (Additional note 73) 73. The system of any one of clauses 63 to 72, wherein the processing is performed by a sleep stage classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks. (Additional note 74) 74. The system of any one of clauses 63 to 73, wherein the sleep stages include manifestations of non-REM sleep or REM sleep. (Additional note 75) 75. The system of any one of clauses 63 to 74, wherein the sleep stages include manifestations of N1 sleep, N2 sleep, N3 sleep, or REM sleep. (Additional note 76) The control system processes the plurality of parameters to select one of the plurality of modalities. 76. The system of any one of clauses 63 to 75, further configured to execute the machine-readable instructions to determine the user's sleep state based on a subset of the plurality of parameters derived from two or more selected modalities, wherein the two or more selected modalities are selected according to a weighting based on data quality. (Additional note 77) 1. A method for calculating an apnea-hypopnea index of a user, comprising: Detecting one or more parameters related to a user's movements during a sleep session of the user; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the one or more parameters; calculating the apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state; and initiating an action based at least in part on the apnea-hypopnea index, the sleep state, or a combination thereof. (Additional note 78) 78. The method of claim 77, wherein the sleep session includes a session in which pressurized air is applied to the user's airway. (Additional note 79) 79. The method of claim 77 or claim 78, wherein the sleep stages include manifestations of N1 sleep, N2 sleep, N3 sleep, or REM sleep. (Additional note 80) The method of any one of clauses 77 to 79, wherein the action includes one or more of: (1) saving a record of the apnea-hypopnea index; (b) transmitting the apnea-hypopnea index to an external device; or (c) adjusting operating settings of a device. (Additional note 81) 81. The method of claim 80, wherein the device is a respiratory device that supplies the pressurized air to the user's airway. (Additional note 82) 82. The method of any one of clauses 77 to 81, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Additional note 83) 83. The method of claim 82, wherein the one or more events are one or more apneas, one or more hypopneas, one or more periodic limb movements, or a combination thereof. (Additional note 84) 84. The method of any one of clauses 77 to 83, wherein the one or more parameters relate to duration, period, speed, frequency, intensity, type of movement of the user, or a combination thereof. (Additional note 85) 85. The method of any one of clauses 77 to 84, wherein the one or more parameters are measured based on one or more sensors located on the user, located near the user, or a combination thereof. (Additional note 86) The method described in Appendix 85, wherein pressurized air is applied to the user's airway through a tube and mask connected to a breathing device, and at least one of the one or more sensors is located on or inside the tube, on or inside the mask, or a combination thereof. (Additional note 87) The at least one sensor may include a body motion sensor located on or in the tube, on or in the mask, or a combination thereof. 6. The method according to claim 6. (Additional note 88) 88. The method of any one of clauses 85 to 87, wherein at least one sensor of the one or more sensors includes a body movement sensor within a smart device. (Additional note 89) 89. The method of claim 88, wherein the smart device is one or more of: (1) a smart watch, smartphone, activity tracker, smart mask, smart clothing, smart mattress, smart pillow, smart sheet, smart ring, or health monitor, each of which is in contact with the user; (2) a smart speaker or smart TV, each of which is located in the vicinity of the user; or (3) a combination thereof. (Additional note 90) 90. The method of any one of clauses 77 to 89, wherein the processing of the one or more parameters comprises processing a signal representing at least one of the one or more parameters over time. (Additional note 91) 91. The method of any one of clauses 77 to 90, wherein the movement of the user is associated with cardiac or respiratory activity of the user. (Additional note 92) 92. The method of claim 91, wherein the at least one sensor is a microphone. (Additional note 93) 93. The method of claim 92, wherein the detecting of the one or more parameters is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more audio signals, or a combination thereof. (Additional note 94) 94. The method of any one of clauses 77 to 93, wherein the detection of the one or more parameters relates to audio associated with the user during the sleep session. (Additional note 95) The method described in Appendix 94, wherein the audio is associated with (1) one or more movements of the user, (2) one or more movements of a tube, a mask, or a combination thereof connected to a respiratory device configured to apply pressurized air to the user, or (3) a combination thereof. (Additional note 96) 96. The method of claim 94 or 95, wherein the detecting of the one or more parameters related to the voice is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more voice signals, or a combination thereof. (Additional note 97) 97. The method of any one of clauses 77 to 96, wherein the sound is detected based on one or more microphones in a tube, a mask, or a device connected to the tube, and the device provides pressurized air to the user's airway. (Additional note 98) Each parameter of the one or more parameters is associated with at least one modality, the one or more parameters encompass a plurality of modalities, the modalities including movement of the user, a flow rate of pressurized air, cardiac activity of the user, and audio associated with the user, and the processing of the plurality of parameters comprises: determining that the sleep state of the user cannot be determined based on one or more parameters of the plurality of parameters associated with a first modality of the two or more modalities; processing one or more parameters of the plurality of parameters associated with a second modality of the two or more modalities to determine the sleep state of the user; The method of any one of clauses 77 to 97, further comprising: (Additional note 99) 99. The method of claim 98, wherein the determination that the sleep state of the user cannot be determined is based on satisfying a threshold decision metric. (Additional note 100) 99. The method of claim 99, wherein the threshold determination metric is based on two or more parameters of the plurality of parameters that compete for the determined sleep state, sleep stage, or combination thereof. (Additional note 101) The method of claim 100, wherein the two or more competing parameters are derived from the two or more modalities. (Additional note 102) The method of claim 100 or 101, wherein conflicts between two or more competing parameters are resolved by ignoring parameters derived based on lower quality data and / or increasing the weight given to parameters extracted from higher quality data. (Additional note 103) 103. The method of any one of clauses 77 to 102, wherein the threshold determination metric is based on a plurality of previous parameters associated with the user during one or more previous sessions of applying pressurized air to the user's airway. (Additional note 104) 104. The method of any one of clauses 77 to 103, wherein each parameter of the one or more parameters is associated with at least one modality, the one or more parameters encompass multiple modalities, and the processing of the multiple parameters is based on a subset of the multiple parameters derived from two or more selected modalities of the multiple modalities, and the two or more selected modalities are selected according to a weighting based on data quality. (Additional note 105) 105. The method of any one of clauses 77 to 104, wherein the processing is performed by a sleep stage classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks. (Additional note 106) 1. A system for calculating an apnea-hypopnea index of a user, comprising: one or more sensors configured to detect one or more parameters related to the user's movements during the user's sleep session; a memory storing machine-readable instructions; determining a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage, by processing the one or more parameters; calculating the apnea-hypopnea index for the user during the sleep session based at least in part on the sleep state; Initiating an action based at least in part on the apnea-hypopnea index, the sleep state, or a combination thereof. and a control system including one or more processors configured to execute the machine-readable instructions to: (Additional note 107) The system described in Appendix 106, wherein the action includes one or more of: (1) saving a record of the apnea-hypopnea index; (b) transmitting the apnea-hypopnea index to an external device; or (c) adjusting operating settings of the device. (Additional note 108) The system described in clause 107, wherein the device is a respiratory device that supplies the pressurized air to the user's airway. (Additional note 109) The system of any one of clauses 106 to 108, wherein one or more events that affect the calculation of the user's apnea-hypopnea index are ignored because the sleep state is determined to be awake during the one or more events. (Supplementary Note 110) The system of claim 109, wherein the one or more events are one or more apneas, one or more hypopneas, one or more periodic limb movements, or a combination thereof. (Additional note 111) 111. The system of any one of clauses 106 to 110, wherein the one or more parameters relate to duration, period, speed, frequency, intensity, type of movement of the user, or a combination thereof. (Additional Note 112) 112. The system of any one of clauses 106 to 111, wherein the one or more sensors are located on the user, near the user, or a combination thereof. (Additional note 113) a breathing device having a tube and a mask connected to the user; The system of claim 112, wherein pressurized air is applied to the user's airway through the tube and the mask, and at least one of the one or more sensors is located on or within the tube, the mask, or a combination thereof. (Additional note 114) 114. The system of any one of clauses 106 to 113, wherein the one or more sensors include a body movement sensor on or within the tube, the mask, or a combination thereof. (Additional note 115) The system of any one of clauses 106 to 114, wherein at least one of the one or more sensors includes a body movement sensor within a smart device. (Additional note 116) The system of claim 115, wherein the smart device is one or more of: (1) a smart watch, smartphone, activity tracker, smart mask, smart clothing, smart mattress, smart pillow, smart sheet, smart ring, or health monitor, each of which is in contact with the user; (2) a smart speaker or smart TV, each of which is located in proximity to the user; or (3) a combination thereof. (Additional note 117) 117. The system of any one of clauses 106 to 116, wherein the processing of the one or more parameters includes processing a signal representing at least one of the one or more parameters over time. (Additional note 118) The system of any one of clauses 106 to 117, wherein the movement of the user is associated with cardiac or respiratory activity of the user. (Additional note 119) The system of claim 118, wherein the at least one sensor is a microphone. (Supplementary Note 120) The system of claim 119, wherein the detecting of the one or more parameters is based on cepstrum analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more audio signals, or a combination thereof, detected by the microphone. (Additional note 121) The detection of the one or more parameters is associated with the user during the sleep session. The system of any one of clauses 106 to 120, relating to recorded audio. (Additional note 122) The system described in Appendix 121, wherein the audio is associated with (1) one or more movements of the user, (2) one or more movements of a tube, a mask, or a combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof. (Additional note 123) The system of claim 121 or claim 122, wherein the detecting of the one or more parameters related to the voice is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more voice signals, or a combination thereof. (Additional note 124) The system of any one of clauses 106 to 123, wherein the sound is detected based on one or more microphones in a tube, a mask, or a device connected to the tube, and the device provides pressurized air to the user's airway. (Additional note 125) each parameter of the one or more parameters is associated with at least one modality, the one or more parameters encompassing a plurality of modalities, the modalities including movement of the user, a flow rate of pressurized air, cardiac activity of the user, and audio associated with the user; and the control system: determining that the sleep state of the user cannot be determined based on one or more parameters of the plurality of parameters associated with a first modality of the two or more modalities; processing one or more parameters of the plurality of parameters associated with a second modality of the two or more modalities to determine the sleep state of the user; The system of any one of clauses 106 to 124, configured to execute the machine-readable instructions to: (Additional note 126) The system of clause 125, wherein the determination that the user's sleep state cannot be determined is based on satisfying a threshold decision metric. (Additional note 127) The system of clause 126, wherein the threshold determination metric is based on two or more parameters of the plurality of parameters that compete for the determined sleep state, sleep stage, or combination thereof. (Additional note 128) The system of claim 127, wherein the two or more competing parameters are derived from the two or more modalities. (Additional note 129) A system as described in appendix 127 or 128, wherein conflicts between two or more competing parameters are resolved by ignoring parameters derived based on lower quality data and / or increasing the weight given to parameters extracted from higher quality data. (Supplementary Note 130) The system of any one of claims 126 to 129, wherein the threshold determination metric is based on a plurality of previous parameters associated with the user during one or more previous sessions of applying pressurized air to the user's airway. (Additional note 131) Each parameter of the one or more parameters is associated with at least one modality, the one or more parameters encompass multiple modalities, and the control system The system of any one of clauses 106 to 130, further configured to execute the machine-readable instructions to process the plurality of parameters and determine the user's sleep state based on a subset of the plurality of parameters derived from two or more selected modalities of the plurality of modalities, the two or more selected modalities being selected according to a weighting based on data quality. (Additional note 132) The system of any one of clauses 106 to 131, wherein the processing is performed by a sleep stage classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks. (Additional note 133) The system of any one of clauses 106 to 132, wherein the sleep stages include manifestations of non-REM sleep or REM sleep. (Additional note 134) 134. The system of claim 133, wherein the sleep stages include manifestations of N1 sleep, N2 sleep, N3 sleep, or REM sleep. (Additional note 135) a control system including one or more processors; a memory storing machine-readable instructions; A system, wherein the control system is coupled to the memory, and the method of any one of claims 1 to 38 and 77 to 105 is performed when the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system. (Additional note 136) A system comprising a control system configured to implement the method described in any one of clauses 1 to 38 and 77 to 105. (Additional note 137) A computer program product comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of clauses 1 to 38 and 77 to 105. (Additional note 138) The computer program product of clause 137, wherein the computer program product is a non-transitory computer-readable medium.

Claims

1. A method of operating a system, comprising: a processor detecting one or more parameters related to movement of the user, cardiac activity of the user, sound associated with the user, or a combination thereof during the user's sleep session; the processor processes the one or more parameters to determine the user's sleep state, which is at least one of wakefulness, sleep, or a sleep stage, during the sleep session; the processor detecting a sleep disordered breathing (SDB) event during the sleep session based on the one or more parameters; the processor calculating an apnea-hypopnea index for the user during the sleep session based on the SDB events detected during the sleep session; If the sleep state is determined to be arousal during detection of one or more of the SDB events, the one or more SDB events for which the sleep state was determined to be arousal are ignored when calculating the apnea-hypopnea index. How it works.

2. 2. The method of claim 1, wherein the one or more parameters relate to duration, period, speed, frequency, intensity, type of movement of the user, or a combination thereof, and the one or more parameters are measured based on one or more sensors located on the user, located near the user, or a combination thereof.

3. 3. The method of claim 2, wherein at least one sensor of the one or more sensors includes a motion sensor located on or in a tube, on or in a mask, or a combination thereof, and wherein the tube and the mask are connected to a breathing device configured to apply pressurized air to the user's airway.

4. The method of claim 2 , wherein at least one sensor of the one or more sensors includes a motion sensor in a smart device.

5. 5. A method according to any one of claims 1 to 4, wherein the one or more parameters relate to the user's cardiac activity, the one or more parameters relating to the user's heart rate, heart rate variability, cardiac output, or a combination thereof.

6. 6. The method of claim 1, wherein the detecting of the one or more parameters is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more audio signals, or a combination thereof.

7. 7. The method of claim 1, wherein the one or more parameters relate to audio associated with the user, and the audio is associated with (1) one or more movements of the user, (2) one or more movements of a tube, a mask, or a combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof.

8. 8. The method of claim 7, wherein detecting the one or more parameters related to the sound associated with the one or more movements of the tube, the mask, or a combination thereof is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more sound signals, or a combination thereof.

9. If the one or more parameters relate to a movement of the user, the processor initiating an action based at least in part on the apnea-hypopnea index, the sleep state, or a combination thereof; 9. The method of claim 1, wherein the actions include one or more of: (a) storing a record of the apnea-hypopnea index; (b) communicating the apnea-hypopnea index to an external device; (c) adjusting operational settings of a respiratory device to supply pressurized air to the user's airway; or (d) providing feedback to the user.

10. The method of claim 9 , wherein the processing of the one or more parameters comprises processing a signal representative of at least one of the one or more parameters over time.

11. each parameter of the one or more parameters is associated with at least one modality, the one or more parameters encompassing a plurality of modalities, the modalities including the movement of the user, the flow rate of pressurized air, the cardiac activity of the user, and the audio associated with the user, and the processing of a plurality of parameters comprises: determining, by the processor, that the sleep state of the user cannot be determined based on one or more parameters of the plurality of parameters associated with a first modality of the two or more modalities; 11. The method of claim 1, further comprising: the processor processing one or more parameters of the plurality of parameters associated with a second modality of the two or more modalities to determine the sleep state of the user.

12. The method of claim 11 , wherein the determination that the sleep state of the user cannot be determined is based on meeting a threshold decision metric.

13. The method of claim 12 , wherein the threshold decision metric is based on two or more parameters of the plurality of parameters that compete for the determined sleep state, sleep stage, or combination thereof.

14. During a sleep session of a user, detecting one or more parameters related to the user's movement, the user's cardiac activity, audio associated with the user, or a combination thereof. one or more sensors configured to a memory storing machine-readable instructions; processing the one or more parameters to determine a sleep state of the user, the sleep state being at least one of wakefulness, sleep, or a sleep stage during the sleep session; Detecting a sleep disordered breathing (SDB) event during the sleep session based on the one or more parameters; Calculating an apnea-hypopnea index for the user during the sleep session based on the SDB events detected during the sleep session. one or more processors configured to execute the machine-readable instructions for: If the sleep state is determined to be arousal during detection of one or more of the SDB events, the one or more SDB events for which the sleep state was determined to be arousal are ignored when calculating the apnea-hypopnea index. a control system.

15. 15. The system of claim 14, wherein the one or more parameters are related to user movement, the one or more parameters relating to duration, duration, speed, frequency, intensity, type of user movement, or a combination thereof, and the one or more parameters are measured based on one or more sensors located on the user, near the user, or a combination thereof.

16. 16. The system of claim 15, wherein at least one sensor of the one or more sensors includes a motion sensor located on or in a tube, on or in a mask, or a combination thereof, and wherein the tube and the mask are connected to a breathing device configured to apply pressurized air to the user's airway.

17. The system of claim 15 , wherein at least one sensor of the one or more sensors includes a motion sensor in a smart device.

18. 18. The system of claim 14, wherein the one or more parameters relate to the user's cardiac activity, and the one or more parameters relate to the user's heart rate, heart rate variability, cardiac output, or a combination thereof.

19. 19. The system of claim 14, wherein the detecting of the one or more parameters is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof, of one or more flow signals, one or more audio signals, or a combination thereof.

20. the one or more parameters relate to a voice associated with the user; 20. The system of claim 14, wherein the audio is associated with: (1) one or more movements of the user; (2) one or more movements of a tube, a mask, or a combination thereof connected to a breathing device configured to apply pressurized air to the user; or (3) a combination thereof.

21. 21. The system of claim 20, wherein detecting the one or more parameters related to the audio associated with the one or more movements of the tube, the mask, or a combination thereof is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more flow signals, one or more audio signals, or a combination thereof.

22. If the one or more parameters relate to a movement of the user, The control system further executes the machine-readable instructions to initiate an action based at least in part on the apnea-hypopnea index, the sleep state, or a combination thereof. configured to 22. The system of any one of claims 14 to 21, wherein the actions include one or more of: (a) storing a record of the apnea-hypopnea index; (b) communicating the apnea-hypopnea index to an external device; (c) adjusting operational settings of a respiratory device to supply pressurized air to the user's airway; or (d) providing feedback to the user.

23. 23. The system of claim 22, wherein the processing of the one or more parameters comprises processing a signal representative of at least one of the one or more parameters over time.

24. each parameter of the one or more parameters is associated with at least one modality, the one or more parameters encompassing a plurality of modalities, the modalities including the movement of the user, the flow rate of pressurized air, the cardiac activity of the user, and the audio associated with the user; said processing of a plurality of parameters by said control system executing said machine-readable instructions comprises: determining that the sleep state of the user cannot be determined based on one or more parameters of the plurality of parameters associated with a first modality of the two or more modalities; 24. The system of claim 14, further comprising: processing one or more parameters of the plurality of parameters associated with a second modality of the two or more modalities to determine the sleep state of the user.

25. 25. The system of claim 24, wherein the determination that the sleep state of the user cannot be determined is based on meeting a threshold decision metric.

26. 26. The system of claim 25, wherein the threshold decision metric is based on two or more parameters of the plurality of competing parameters for the determined sleep state, sleep stage, or combination thereof.

27. 2. The method of claim 1, wherein the sleep stage is one of a plurality of sleep stages, and the apnea-hypopnea index is calculated for only one of the plurality of sleep stages occurring during the sleep session.

28. 15. The system of claim 14, wherein the sleep stage is one of a plurality of sleep stages, and the apnea-hypopnea index is calculated for only one of the plurality of sleep stages occurring during the sleep session.

Images