Sleep state detection for apnea-hypoapnea index calculation

Abstract

Devices, systems, and methods are disclosed. The devices, systems, and methods detect, during a sleep session of a user, one or more parameters related to movement of the user, heart activity of the user, audio associated with the user, or a combination thereof; process the one or more parameters to determine a sleep state of the user, the sleep state being at least one of awake, asleep, or a sleep stage; and calculate an apnea-hypopnea index of the user during the sleep session based at least in part on the sleep state.

Description

[0001] Cross-references to related applications

[0002] This application claims the following benefits and priorities: U.S. Provisional Patent Application No. 63 / 002,585, filed March 31, 2020, entitled "Sleep State Detection for Apnea-Hypopnea Index Calculation," and U.S. Provisional Patent Application No. 62 / 968,775, filed January 31, 2020, entitled "Sleep State Detection for Apnea-Hypopnea Index Calculation," the contents of which are incorporated herein by reference in their entirety. Technical Field

[0003] This technology relates to apparatus, systems, and methods for detecting sleep states and determining the apnea-hypopnea index (AHI) taking sleep states into account. Background Technology

[0004] Whether a user is asleep or awake can be considered a sleep state. After falling asleep, sleep can be characterized by four distinct sleep stages, which change throughout the night. Users, especially healthy users, typically move between sleep stages multiple times in sequence during sleep. Sleep stages include N1, N2, and N3, collectively known as the non-rapid eye movement (NREM) stage and the rapid eye movement (REM) stage.

[0005] Stage N1 is the lightest sleep stage, characterized by several low-amplitude waves of multiple frequencies interspersed with alpha waves in more than 50% of the epochs. Sharp vertex waves, some slow eye movements on the electrooculogram (EOG) signal, and / or an overall decrease in the frequency of the electroencephalogram (EEG) signal may also be present.

[0006] Stage N2 is a slightly deeper sleep stage and is characterized by the presence of sleep axes and K-complexes against a background of mixed signals. Sleep spindles are bursts of higher-frequency activity (e.g., greater than 12 Hz). K-complexes are distinct, isolated bipolar waves lasting approximately 1–2 seconds.

[0007] Stage N3 is the deepest sleep stage, characterized by slow waves (e.g., 1-2 Hz frequency) occurring in at least 20% of the period.

[0008] Stage REM sleep is rapid eye movement sleep and is distinguished by the presence of significant activity in the EOG signals. The recorded EEG signals are often very similar to stage N1 or even wakefulness.

[0009] The term sleep-disordered breathing (SDB) can refer to a condition in which there are apnea (e.g., airflow stops for ten seconds or more) and hypopnea (e.g., airflow is reduced by at least 30% for 10 seconds or more, accompanied by associated oxygen desaturation or awakening) during sleep.

[0010] Breathing instability is an indicator of wakefulness or REM sleep, while breathing stability is an indicator of non-REM (e.g., N1, N2, N3) sleep. However, breathing instability alone is insufficient to accurately infer sleep stages. For example, breathing instability is an indicator of wakefulness or REM sleep, but it can also occur as a result of frequent respiratory events, such as apnea, hypoventilation, and respiratory effort-related awakenings (RERA) that occur during sleep. Therefore, it is helpful to distinguish between periods of breathing instability primarily driven by respiratory events and true periods of wakefulness.

[0011] Although positive airway pressure (POP) breathing devices can be configured to detect sleep apnea (SDB) events, such as apnea and hypopnea, they often miss SDB events because the user is not asleep or is in an incorrect sleep stage. For example, flow-based analysis can lead to determining whether a user is asleep, or even what sleep stage they are in. However, this flow-based sleep stage analysis has limitations. Accurately distinguishing between awake and sleep states using flow-based signals can be difficult. Flow-based signals can be segmented, losing information at the beginning, middle (when going to the rest room or leaving in the middle of the night), and end.

[0012] It is of interest to know when a user falls asleep, when they wake up, and what sleep stages they pass through simultaneously. A complete representation of the various sleep stages a user passes through during a sleep period is called a sleep graph. An example application of the sleep graph is the calculation of the SDB severity index, known as the Apnea-Hypopnea Index (AHI). The AHI, typically calculated as the total number of apneas and hypopneas divided by the length of sleep duration, is a widely used tool for SDB screening, diagnosis, and monitoring. However, this calculation tends to underestimate the AHI because the user may not be asleep for a considerable period during the sleep period. As a result, if a traditional AHI calculation is used, the user tends to receive an overly optimistic picture of the user's treatment efficacy. This is particularly true for flow-based sleep stages, which are biased towards sleep, so SDB events occurring during wakefulness are incorrectly counted in the AHI. Conversely, if SDB events are incorrectly detected while the user is awake and moving, the AHI may be overestimated. Overestimation and / or underestimation can mean that, for example, automated settings algorithms for breathing devices may adapt to treatment in ways that adversely affect sleep quality and / or treatment efficacy.

[0013] A more accurate method for calculating AHI is to divide the number of apneas and hypopneas by the number of hours the user slept during the period. Calculating AHI in this way requires knowledge of when the user fell asleep, which can be obtained from sleep charts. However, inferring sleep stages purely from respiratory flow has proven to be a difficult task, impacting the accuracy of AHI calculations and thus affecting AHI-based monitoring of respiratory therapies such as continuous positive airway pressure (CPAP).

[0014] Therefore, there is a need to develop improved devices, systems, and methods for inferring the sleep state and stages of users of respiratory therapy in order to more accurately assess the user's condition and the efficacy of the applied treatment, which can improve sleep structure by treating SDB. Summary of the Invention

[0015] According to some aspects of the present invention, apparatus, systems and methods for distinguishing respiratory events from sleep and wakefulness based on sleep states are disclosed.

[0016] According to some aspects of the present invention, apparatus, systems and methods for detecting sleep and providing feedback to a user on sleep status are disclosed.

[0017] According to one implementation of the present invention, a method for detecting a user's sleep state is disclosed. The method includes detecting one or more parameters relating to the user's movement during a sleep period. The method further includes processing the one or more parameters to determine the user's sleep state. A sleep state is at least one of wakefulness, sleep, or a sleep stage. The method further includes calculating the user's apnea-hypopnea index during the sleep period, at least in part based on the sleep state.

[0018] According to some aspects of this implementation, the sleep stage can be an indication of non-REM sleep, N1 sleep, N2 sleep, N3 sleep, or REM sleep. According to some aspects of this implementation, in response to a sleep state being determined to be awake during one or more events affecting the calculation of the user's apnea-hypopnea index, the one or more events are ignored. 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, one or more parameters relate to duration, frequency, intensity, user movement type, or a combination thereof. According to some aspects of this implementation, the one or more parameters are measured based on one or more sensors placed on, near, or in combination with the user. Pressurized air can be applied to the user's airway through a tube and mask connected to the breathing apparatus. At least one of the one or more sensors can be on or within the tube, mask, or combination thereof. At least one sensor can include an inertial measurement unit on or within the tube, mask, or combination thereof. At least one of the one or more sensors can include an inertial measurement unit coupled to a smart device connected to the user. The smart device may be one or more of the following: (1) a smartwatch, smart phone, activity tracker, smart mask, smart clothing, smart mattress, smart pillow, smart sheet, smart ring, or health monitor, each in contact with the user; (2) a smart speaker or smart TV, each near the user; (3) or a combination thereof. According to some aspects of this implementation, processing the one or more parameters includes processing a signal representing a change in at least one of the one or more parameters over time.

[0019] According to another implementation of the invention, a method for detecting a user's sleep state is disclosed. The method includes detecting one or more parameters relating to the user's cardiac activity during a sleep period, which may include applying pressurized air to the user's airway. The method further includes processing one or more parameters to determine the user's sleep state. A sleep state is at least one of wakefulness, sleep, or a sleep stage. The method further includes calculating the user's apnea-hypopnea index during the sleep period, at least in part based on the sleep state.

[0020] According to some aspects of this implementation, in response to a sleep state being determined to be awake during one or more events affecting the calculation of the user's apnea-hypopnea index, the one or more events are ignored. The one or more events are one or more apneas, one or more hypopneas, or a combination thereof. According to some aspects of the implementation, the one or more parameters relate to the user's heart rate, heart rate variability, cardiac output, or a combination thereof. The heart rate variability can be calculated over time periods of one minute, five minutes, ten minutes, half an hour, one hour, two hours, three hours, or four hours. According to some aspects of the implementation, pressurized air can be applied to the user's airway through a tube and mask connected to the breathing apparatus, 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. In one or more implementations, at least one sensor can be a microphone. 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 stream signals, one or more audio signals, or a combination thereof.

[0021] According to one implementation of the present invention, a method for detecting a user's sleep state is disclosed. The method includes detecting one or more parameters relating to audio associated with the user during a sleep period, which may include applying pressurized air to the user's airway. The method further includes processing one or more parameters to determine the user's sleep state. A sleep state is at least one of wakefulness, sleep, or sleep stages. The method further includes calculating the user's apnea-hypopnea index during the sleep period, at least in part based on the sleep state.

[0022] According to some aspects of this implementation, in response to a sleep state being determined to be awake during one or more events affecting the calculation of the user's apnea-hypopnea index, the one or more events are ignored. 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 audio is associated with (1) one or more movements of the user, (2) one or more movements of a tube, mask, or combination thereof connected to a breathing apparatus configured to apply pressurized air to the user, or (3) a combination thereof. Detection of one or more parameters relating to the audio associated with one or more movements of the tube, mask, or combination thereof may be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more stream signals, one or more audio signals, or a combination thereof. According to some aspects of this implementation, the audio may be detected based on one or more microphones within the tube, mask, or apparatus connected to the tube and device and providing pressurized air to the user's airway.

[0023] According to one implementation of the invention, a method for detecting a user's sleep state is disclosed. The method includes detecting multiple parameters associated with an individual during a sleep period, or during the application of pressurized air to the user's airway, wherein each of the multiple parameters is associated with at least one modality, and the multiple parameters cover multiple modalities. The method further includes processing the multiple parameters to determine the user's sleep state, which is at least one of wakefulness, sleep, or sleep stage. The method further includes calculating the user's apnea-hypopnea index (AHI) during the period, at least partially based on the sleep state. Furthermore, multiple modalities can be combined, wherein one or more modalities associated with or determined from the respiratory therapy system 120 are not used. For example, the AHI from a modality associated with cardiac activity can be combined to determine the sleep state and / or stage. Subsequently, one or more other parameters related to movement and unrelated to cardiac activity can be used to confirm the sleep state and / or stage based on cardiac activity. As another example, the AHI (but not necessarily the sleep state and / or stage) can be determined from blood oxygen levels or some other parameters that do not capture the sleep stage and / or stage. Subsequently, another parameter related to different morphologies, such as movement and cardiac activity, can be used to confirm sleep state and / or stage.

[0024] According to some aspects of this implementation, the modality includes two or more of the following: user movement, pressurized air flow, user cardiac activity, and audio associated with the user. According to some aspects of this implementation, in response to a sleep state being determined to be awake during one or more events affecting the calculation of the user's apnea-hypopnea index, the one or more events are ignored. The one or more events include one or more apneas, one or more hypopneas, or combinations thereof. According to some aspects of this implementation, processing multiple parameters further includes determining that the user's sleep state cannot be determined based on one or more parameters associated with a first modality of two or more modalities. Processing multiple parameters further includes processing one or more parameters associated with a second modality of 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 a threshold determination metric being satisfied. The threshold determination metric may be based on two or more parameters that conflict with sleep state, sleep stage, or combinations thereof. The two or more conflicting parameters originate from two or more modalities. Conflicts between the two or more conflicting parameters are resolved by ignoring parameters derived from low-quality data and / or by giving increased weight to parameters extracted from higher-quality data. The threshold determination metric may be based on multiple prior parameters associated with the user during one or more prior periods of applying pressurized air to the user's airway. According to some aspects of this implementation, the processing is performed by a sleep segmentation classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks. According to some aspects, processing multiple parameters is based on a subset of multiple parameters from two or more selected modalities. The selected two or more modalities may be chosen based on a weighted average of data quality.

[0025] According to one or more implementations, one or more systems are disclosed, which may include: one or more sensors configured to detect one or more parameters disclosed herein, a breathing device having a tube and a mask coupled to a user; a memory storing 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.

[0026] Some versions of this technology may include a computer processor-readable storage device having processor-executable instructions encoded thereon, which, when executed by a processor, cause the processor to perform any one or more methods disclosed herein.

[0027] According to one implementation of the invention, a method for calculating a user's apnea-hypopnea index is disclosed. The method includes detecting one or more parameters relating to the user's movement during sleep, which may include applying pressurized air to the user's airway. The method further includes processing one or more parameters to determine the user's sleep state. The sleep state may be at least one of wakefulness, sleep, or sleep stages. The method further includes calculating the user's apnea-hypopnea index during the sleep period 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, sleep state, or a combination thereof.

[0028] According to some aspects of this implementation, the action includes one or more of the following: (1) saving a record of the apnea-hypopnea index, (b) transmitting the apnea-hypopnea index to an external device, or (c) adjusting the operating settings of the device. The device may be a breathing apparatus that supplies pressurized air to the user's airway. According to some aspects of this implementation, in response to a sleep state being determined to be awake during one or more events affecting the calculation of the user's apnea-hypopnea index, the one or more events are ignored. 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, period, rate, frequency, intensity, type of movement of the user, 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 placed on, near, or in combination with the user. Pressurized air may be applied to the user's airway through a tube and mask connected to the breathing apparatus, 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. At least one sensor may include a physical motion sensor, which may be on or inside a tube, on or inside a mask, or a combination thereof. According to some aspects of this implementation, at least one of the one or more sensors includes a physical motion sensor within a smart device. The smart device may be one or more of the following: (1) a smartwatch, smart phone, activity tracker, smart mask, smart clothing, smart mattress, smart pillow, smart sheet, smart ring, or health monitor, each in contact with the user; (2) a smart speaker or smart TV, each near the user; (3) a combination thereof. According to some aspects of this implementation, processing the one or more parameters includes processing a signal representing the change of at least one of the one or more parameters over time. According to some aspects of this implementation, the user's movement may be associated with the user's heart or respiratory activity. At least one sensor may be a microphone. Detection of the one or more parameters may be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more streaming signals, one or more audio signals, or a combination thereof. According to some implementations, detection of the one or more parameters may be related to audio associated with the user during a time period. The audio can be associated with (1) one or more movements of the user, (2) one or more movements of a tube, mask, or combination thereof connected to a breathing apparatus configured to apply pressurized air to the user, or (3) a combination thereof. Detection of one or more parameters relating to the audio can be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more streaming signals, one or more audio signals, or a combination thereof.Audio can be detected using one or more microphones within a tube, mask, or device connected to the tube and device and supplying pressurized air to the user's airway. According to some implementations, each of the one or more parameters can be associated with at least one modality, and multiple of the one or more parameters cover multiple modalities. Modalities can include the user's movement, the flow of pressurized air, the user's cardiac activity, and audio associated with the user. Processing multiple parameters can further include determining that the user's sleep state cannot be determined based on one or more of the multiple parameters associated with a first modality of two or more modalities; and processing one or more of the multiple 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 can be based on a threshold determination metric being satisfied. The threshold determination metric can be based on two or more parameters that conflict with the determined sleep state, sleep stage, or a combination thereof. The two or more conflicting parameters originate from two or more modalities. Conflicts between two or more conflicting parameters can be resolved by ignoring parameters derived from low-quality data and / or by giving increased weight to parameters extracted from higher-quality data. According to some aspects of this implementation, the threshold determination metric can be based on multiple prior parameters associated with the user during one or more prior periods of applying pressurized air to the user's airway. According to some aspects of this implementation, the process can be performed by a sleep segmentation classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks.

[0029] According to one implementation of the invention, 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 relating to the user's movement during a sleep period, which may include periods of pressurized air being 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 machine-readable instructions to: process one or more parameters to determine the user's sleep state, which is at least one of wakefulness, sleep, or sleep stages; calculate the user's apnea-hypopnea index during the sleep period 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.

[0030] According to some aspects of this implementation, the action includes one or more of the following: (1) saving a record of the apnea-hypopnea index, (b) transmitting the apnea-hypopnea index to an external device, or (c) adjusting the operating settings of the device. The device is a breathing device that supplies pressurized air to the user's airway. According to some aspects of this implementation, in response to a sleep state being determined to be awake during one or more events affecting the calculation of the user's apnea-hypopnea index, the one or more events are ignored. 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 movement of the user, or a combination thereof. According to some aspects of this implementation, the one or more sensors are placed on the user, near the user, or a combination thereof. According to some aspects of this implementation, the system further includes a breathing device having a tube and a mask connected to the user. Pressurized air can be applied to the user's airway through the tube and mask, and at least one of the one or more sensors is on or within the tube, mask, or combination thereof. The one or more sensors may include physical motion sensors on or within a tube, mask, or combination thereof. According to some aspects of this implementation, at least one of the one or more sensors may include a physical motion sensor within a smart device. The smart device may be one or more of the following: (1) a smartwatch, smart phone, activity tracker, smart mask, smart clothing, smart mattress, smart pillow, smart sheet, smart ring, or health monitor, each in contact with the user; (2) a smart speaker or smart TV, each near the user; (3) or a combination thereof. According to some aspects of this implementation, processing the one or more parameters may include processing a signal representing the change of at least one of the one or more parameters over time. According to some aspects of this implementation, the user's movement may be associated with the user's heart or respiratory activity. At least one sensor may be a microphone. Detection of the one or more parameters may be based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more stream signals, one or more audio signals, or combinations thereof detected by the microphone. According to some aspects of this implementation, detection of the one or more parameters may relate to audio associated with the user during sleep periods. 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, mask, or combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof.According to some aspects of this implementation, the detection of one or more parameters related to audio can be based on cepstral analysis, spectral analysis, fast Fourier transform, or combinations thereof of one or more streaming signals, one or more audio signals, or combinations thereof. According to some aspects of this implementation, audio can be detected based on one or more microphones within a tube, mask, or device connected to the tube and device and supplying pressurized air to the user's airway. According to some aspects of this implementation, each of the one or more parameters is associated with at least one modality, and the one or more parameters cover multiple modalities. Modalities may include the user's movement, the flow of pressurized air, the user's cardiac activity, and the audio associated with the user. The control system can be configured to execute machine-readable instructions to determine that the user's sleep state cannot be determined based on one or more of the multiple parameters associated with a first modality of two or more modalities; and to process one or more of the multiple 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 a threshold determination metric being satisfied. The threshold determination metric may be based on two or more of the multiple parameters that conflict with the determined sleep state, sleep stage, or combination thereof. Two or more conflicting parameters may originate from two or more modalities. According to some aspects of this implementation, conflicts between two or more conflicting parameters can be resolved by ignoring parameters derived from low-quality data and / or by giving increased weight to parameters extracted from higher-quality data. According to some aspects of this implementation, the threshold determination metric may be based on multiple prior parameters associated with the user during one or more prior periods of applying pressurized air to the user's airway. According to some aspects of this implementation, the processing may be performed by a sleep segmentation classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks. According to some aspects of this implementation, each of the one or more parameters may be associated with at least one modality, and the one or more parameters may cover multiple modalities. Processing multiple parameters may be based on a subset of multiple parameters from two or more modalities selected from multiple modalities. The selected two or more modalities may be chosen based on a weighting based on data quality. According to some aspects of this implementation, the sleep stage may be an indication of non-REM sleep or REM sleep. According to some aspects of this implementation, the sleep stage may be an indication of N1 sleep, N2 sleep, N3 sleep, or REM sleep.

[0031] According to one implementation of the present invention, a system comprising a control system having one or more processors is disclosed. The system further comprises: a memory storing machine-readable instructions; a control system coupled to the memory, and implementing any one or more of the methods described above when the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system.

[0032] According to one implementation of the present invention, a system is disclosed, the system comprising a control system configured to implement any one or more of the methods disclosed above.

[0033] According to one implementation of the present invention, a computer program product comprising instructions, which, when executed by a computer, cause the computer to perform any or more of the methods disclosed above. In one or more implementations, the computer program product is a non-transitory computer-readable medium.

[0034] The foregoing aspects may form sub-aspects of this technology. Other features of this technology will become apparent from the information contained in the following detailed description, abstract, drawings, and claims. Sub-aspects and / or aspects of the aspects may be combined in various ways and also constitute other aspects or sub-aspects of this technology. The above summary is not intended to represent every implementation or every aspect of the invention. Additional features and advantages of the invention will be apparent from the detailed description and drawings. Attached Figure Description

[0035] Figure 1 This is a functional block diagram of a system according to some implementations of the present invention.

[0036] Figure 2 This is according to some implementations of the present invention. Figure 1 A perspective view of at least a part of the system, the user wearing a full-face mask, and the bed partner.

[0037] Figure 3 This is according to some implementations of the present invention. Figure 1 Another perspective of at least another part of the system, the user wearing a full-face mask, and the bed partner.

[0038] Figure 4 This is a flowchart of a process for detecting a user's sleep state based on user movement, according to various aspects of the present invention.

[0039] Figure 5 This is a flowchart of a process for detecting a user's sleep state based on cardiac activity, according to an aspect of the present invention.

[0040] Figure 6This is a flowchart of a process for detecting a user's sleep state based on audio parameters associated with the user, according to various aspects of the present invention.

[0041] Figure 7 This is a flowchart of a process for detecting a user's sleep state based on multiple different modalities, according to various aspects of the present invention.

[0042] Figure 8 This is a schematic diagram of a sleep diagram according to some implementations of the present invention.

[0043] While the present invention is susceptible to various modifications and substitutions, specific implementations and embodiments thereof have been illustrated by way of example in the accompanying drawings and will be described in detail herein. However, it should be understood that this is not intended to limit the invention to the specific forms disclosed, but rather, the invention is intended to cover all modifications, equivalents, and substitutions falling within the spirit and scope of the invention as defined by the appended claims. Detailed Implementation

[0044] The devices, systems, and methods of the present invention address the aforementioned problems by determining sleep states (e.g., sleep states and / or sleep stages) based on parameters associated with modalities other than flow rate, or based on parameters associated with other modalities in combination with flow rate-based parameters. The devices, systems, and methods of the present invention further address or improve upon the aforementioned problems by determining the AHI after ignoring erroneous SDB events that occur when the user is awake. Therefore, spurious SDB events detected while the user is awake do not incorrectly affect the AHI.

[0045] As described above, flow-based sleep staging involves calculating flow-related parameters, including respiratory rate, respiratory rate variability (on both short and long time scales), and normalized respiratory rate variability. To overcome the limitations of flow-based sleep staging, the apparatus, systems, and methods of the present invention may include additional processing based at least in part on parameters generated and / or calculated by a breathing device or other devices within the user's environment. For example, a breathing device and / or another intelligent device in the environment may detect the user's cardiac oscillations to estimate heart rate and heart rate variability. Parameters indicating rapid fluctuations in signal quality, such as cardiac oscillation signal parameters, alone or in combination with changes in general flow signal parameters, may be used to infer the user's motion. Therefore, heart rate variability (short-term heart rate variability and long-term nocturnal trend analysis) may be further input parameters for determining sleep state.

[0046] Alternatively, the apparatus, system, and method may provide a multimodal capability to combine flow parameters with audio parameters representing a user's sleep state. In one or more implementations, the apparatus, system, and method use a microphone within the breathing device, in an interface, or in a conduit, either alone or in combination with the flow signal, for sleep state determination. The microphone may detect parameters associated with the user's motion events. These parameters may indicate the duration, frequency, and intensity of the motion events, aiding in sleep state determination.

[0047] In one or more specific implementations, motion alters the echo reflection of sound in the tube, which can then be detected. Similar to heart rate, the breathing rate is more stable and slower when a user is asleep than when awake. The rate is even lower during deep sleep. Adding motion detection helps determine sleep state because if the airflow generated by the breathing rate is more unstable and motion is present, the user is more likely to be awake. However, for REM sleep, the flow signal may still be less stable, although there may be less movement than during wakefulness. Adding motion detection will further aid in sleep state detection, which can focus the AHI calculation on actual SDB events when the user is asleep, rather than calculating spurious SDB events that might appear as AHI events but when the user is awake.

[0048] In one or more implementations, the AHI can be calculated at a more granular level than a single AHI. For example, in one or more implementations, the AHI can be calculated over multiple sleep periods, a single sleep period, or a time increment of one hour or less between sleep periods. Therefore, a user can have a single AHI value stored, reported, and / or used to control the ventilator, or a user can have multiple AHI values ​​stored, reported, and / or used to control the ventilator, as well as various other potential actions.

[0049] In one or more implementations, the user can determine the AHI at a more granular level relative to the sleep stage. For example, the detected sleep stage could be REM and non-REM. In this case, the AHI can be calculated for REM, and a separate AHI can be calculated for non-REM. This can occur outside of calculating the total AHI, or without calculating the total AHI. In one or more implementations, the AHI can be calculated for each sleep stage, such as N1, N2, N3, and / or REM. This can provide the user with an understanding of the optimal sleep stage for achieving quality sleep without SDB events occurring. Alternatively, the AHI can be calculated only for N3 and REM, or only for N2, N3, and REM.

[0050] refer to Figure 1The diagram illustrates a functional block diagram of a system 100 for inferring sleep states and stages according to various aspects of the present invention. 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 may further optionally include a blood pressure device 182, an activity tracker 190, or any combination thereof.

[0051] During use, the respiratory therapy system 120 can detect and count SDB events (e.g., apnea or hypopnea events) during periods when the system attempts to maintain medically prescribed air pressure during sleep. Based on these SDB events, the system can estimate the AHI. The AHI can be used to stratify SDB risk and monitor the severity of each period. However, as mentioned above, the respiratory therapy system 120 can detect conditions that manifest as apnea or hypopnea events, but the user may be awake or in a light sleep stage (e.g., N1). In this case, it may be desirable not to consider events detected during the “awake” state, which manifest as apnea or hypopnea events in the AHI calculation. Alternatively, the respiratory therapy system 120 may detect the effects of periodic limb movement (PLM) and not correctly estimate that the user is awake. In this case, the system may miss SDB events that should be considered in the AHI. For example, a person may still be asleep during PLM, but may have reduced sleep quality. The respiratory therapy system 120 is configured to more accurately identify the user (e.g., during the period of pressurized air application) Figure 2 The ability to determine the sleep state (e.g., awake or asleep) of the user (210) and the ability to more accurately determine the user's sleep stages (e.g., N1, N2, N3, REM). This ability to more accurately determine sleep state and sleep stage allows the respiratory therapy system 120 to more accurately determine the AHI, which can provide better future time to prevent airway narrowing or collapse, as well as other benefits.

[0052] The control system 110 includes one or more processors 112 (hereinafter, processor 112). The control system 110 is typically 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 a microprocessor. Although in Figure 1A processor 112 is shown, but the control system 110 may include any suitable number of processors (e.g., one processor, two processors, five processors, ten processors, etc.), which may be located in a single housing or positioned remotely from each other. 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 sensors 130. The control system 110 may be centralized (within one such housing) or distributed (within two or more physically different such housings). In this embodiment, which includes two or more housings containing the control system 110, such housings may be positioned close to and / or far from each other.

[0053] The control system 110 can execute the methods disclosed herein for determining sleep states / stages and calculating AHI "in real time" or as post-processing; that is, after the sleep period is completed. In the post-processing implementation, the data used in the method can be stored as a time series sampled at a predetermined sampling rate on the memory device 114.

[0054] Memory device 114 stores machine-readable instructions executable by processor 112 of control system 110, specifically for determining a user's sleep state / stage, and other methods disclosed herein. Memory device 114 can be any suitable computer-readable storage device or medium, such as random or serial access storage devices, hard disk drives, solid-state drives, flash memory devices, etc. Although Figure 1 A memory device 114 is shown, but 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 breathing apparatus 122, the housing of the user device 170, the housing of the activity tracker 190, the housing of one or more sensors 130, or any combination thereof. Similar to control system 110, the memory device 114 may be centralized (within one such housing) or distributed (within two or more physically different such housings).

[0055] In one or more implementations, memory device 114 may include stored processor control instructions for signal processing (e.g., sound signal processing, motion signal processing, etc.). Such specific signal processing may include measurement filtering, Fourier transform, logarithmic operations, position determination, range determination, difference determination, etc. In one or more implementations, processor control instructions and data for controlling the disclosed methods may be included in memory device 114 as software for use by control system 110, and may be considered a dedicated processor according to any method discussed herein.

[0056] In some implementations, memory device 114 stores a user profile associated with the user, which can be implemented as parameters for inferring state and stage. The user profile may include, for example, user-associated demographic information, user-associated biostatistical information, user-associated medical information, self-reported user feedback, user-associated sleep parameters (e.g., sleep-related parameters recorded from one or more sleep periods), or any combination thereof. Demographic information may include, for example, information indicating the user's age, user gender, user ethnicity, user geographic location, user travel history, relationship status, whether the user has one or more pets, whether the user has a family, family history of health conditions, user employment status, user education status, user socioeconomic status, or any combination thereof. Medical information may include, for example, information indicating one or more medical conditions associated with the user, user medication use, or both. Medical information data may further include Multisleep Latency Test (MSLT) results or scores and / or Pittsburgh Sleep Quality Index (PSQI) scores or values. Medical information data may include results from one or more of a polysomnography (PSG) test, CPAP titration, or home sleep test (HST), respiratory therapy system settings from one or more sleep periods, sleep-related breathing events from one or more sleep periods, or any combination thereof. Self-reported user feedback may include information indicating self-reported subjective treatment scores (e.g., poor, average, excellent), the user's self-reported subjective stress level, the user's self-reported subjective fatigue level, the user's self-reported subjective health status, recent life events experienced by the user, or any combination thereof. User profile information may be updated at any time, such as daily (e.g., between sleep periods), weekly, monthly, or yearly. In some embodiments, memory device 114 stores media content that may be displayed on display device 128 and / or display device 172, as discussed below.

[0057] Electronic interface 119 is configured to receive data (e.g., physiological data, flow data, pressure data, motion data, acoustic data, etc.) from one or more sensors 130, such that the data can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. The received data (e.g., physiological data, flow data, pressure data, motion data, acoustic data, etc.) can be used to determine and / or calculate parameters for inferring sleep states and stages. Electronic interface 119 can use wired or wireless connections (e.g., using RF communication protocols, Wi-Fi communication protocols, Bluetooth communication protocols, IR communication protocols, via cellular networks, via any other optical communication protocol, etc.). Electronic interface 119 may include an antenna, a receiver (e.g., an RF receiver), a transmitter (e.g., an RF transmitter), a transceiver (RF transceiver), or any combination thereof. Electronic interface 119 may also include one or more processors and / or one or more memory devices that are the same as or similar to processor 112 and memory device 114 described herein. In some implementations, electronic interface 119 is coupled to or integrated into user device 170. In other implementations, the electronic interface 119 is coupled to or integrated into the housing with the control system 110 and / or the memory device 114.

[0058] The respiratory therapy system 120 may include a respiratory pressure therapy device 122 (also referred to herein as a breathing device 122), a user interface 124, a conduit 126 (also referred to herein as a tube or air circuit), a display device 128, a humidifier 129, a receiver 180, or any combination thereof. In some implementations, a control system 110, a memory device 114, a display device 128, one or more sensors 130, and a humidifier 129 are part of the breathing device 122.

[0059] Respiratory pressure therapy refers to supplying air to the user's airway inlet at a controlled target pressure that is nominally positive relative to the atmosphere throughout the user's respiratory cycle (e.g., the opposite of negative pressure therapy with canister ventilators or tubing ventilators). 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).

[0060] Breathing device 122 is typically used to generate pressurized air to be delivered to a user (e.g., using one or more motors driving one or more compressors). In some implementations, breathing device 122 generates a continuous, constant air pressure that is delivered to the user. In other implementations, breathing 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, breathing device 122 is configured to generate a variety of different air pressures within a predetermined range. For example, breathing device 122 may deliver at least about 6 cm H2O, at least about 10 cm H2O, at least about 20 cm H2O, between about 6 cm H2O and about 10 cm H2O, between about 7 cm H2O and about 12 cm H2O, etc. Breathing device 122 may also deliver pressurized air at predetermined flow rates, for example, between about -20 L / min and about 150 L / min, while maintaining positive pressure (relative to ambient pressure).

[0061] User interface 124 engages with a portion of the user's face and delivers pressurized air from breathing apparatus 122 to the user's airway to help prevent airway narrowing and / or collapse during sleep. This can also increase the user's oxygen intake during sleep. Typically, user interface 124 engages with the user's face such that pressurized air is delivered to the user's airway via the user's mouth, the user's nose, or both the user's mouth and nose. Breathing apparatus 122, user interface 124, and conduit 126 together form an air passage fluidly connected to the user's airway.

[0062] Depending on the treatment to be applied, the user interface 124 may form a seal with, for example, an area or portion of the user's face, thereby facilitating the delivery of gas at a pressure sufficiently different from ambient pressure (e.g., a positive pressure of approximately 10 cm H2O relative to ambient pressure) to achieve the treatment. For other forms of treatment, such as oxygen delivery, the user interface may not include a seal sufficient to deliver gas at a positive pressure of approximately 10 cm H2O to the airway.

[0063] like Figure 2As shown, in some implementations, the user interface 124 is or includes a 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 supplies air to the user's nose or a nasal pillow mask that supplies 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 part of the user (e.g., the face) and conformal cushioning pads (e.g., silicone, plastic, foam, etc.) to help provide an airtight seal between the user interface 124 and the user. The user interface 124 may also include one or more vents for allowing 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-protective mouthpiece molded to conform to the user's teeth, a jaw repositioning device, etc.).

[0064] The conduit 126 (also referred to as an air circuit or tube) allows air to flow between two components of the respiratory therapy system 120, such as the breathing device 122 and the user interface 124. In some implementations, there may be separate branches for the inspiratory and expiratory conduits. In other implementations, a single-branch air conduit is used for both inspiratory and expiratory breathing.

[0065] One or more of the breathing apparatus 122, user interface 124, conduit 126, display device 128, and humidifier 129 may include one or more sensors (e.g., pressure sensor, flow sensor, humidity sensor, temperature sensor, or any sensor 130 described herein more generally). These one or more sensors may be used, for example, to measure the air pressure and / or flow rate of the pressurized air supplied by the breathing apparatus 122.

[0066] Display device 128 is typically used to display images including still images, video images, or both, and / or information about breathing apparatus 122. For example, display device 128 may provide information about the status of breathing apparatus 122 (e.g., whether breathing apparatus 122 is on / off, the pressure of the air delivered by breathing apparatus 122, the temperature of the air delivered by breathing apparatus 122, etc.) and / or other information (e.g., sleep score or treatment score (also known as myAir)). TMScores, such as those described in WO 2016 / 061629 (which are incorporated herein by reference in their entirety), current date / time, user 210's personal information, etc. In some implementations, the display device 128 acts as a human-machine interface (HMI) including a graphical user interface (GUI) configured to display images as input. The display device 128 may be an LED display, an OLED display, an LCD display, etc. The input interface may be, for example, a touchscreen or touch-sensitive substrate, a mouse, a keyboard, or any sensor system configured to sense input made by a human user interacting with the breathing device 122.

[0067] A humidifier canister 129 is coupled to or integrated into a breathing apparatus 122. The humidifier canister 129 includes a reservoir for humidifying pressurized air supplied from the breathing apparatus 122. The breathing apparatus 122 may include a heater to heat the water in the humidifier canister 129 to humidify the pressurized air supplied to the user. Additionally, in some implementations, the conduit 126 may include a heating element (e.g., coupled to and / or embedded in the conduit 126) that heats the pressurized air supplied to the user. The humidifier canister 129 may be fluidly coupled to a water vapor inlet of an air passage and deliver water vapor into the air passage via the water vapor inlet, or it may be formed in a straight line with the air passage as part of the air passage itself. In other implementations, the breathing apparatus 122 or the conduit 126 may include a waterless humidifier. The waterless humidifier may include a sensor that interfaces with other sensors located elsewhere in the system 100.

[0068] In some implementations, system 100 may be used to deliver at least a portion of a substance from container 180 to a user's air path, at least in part based on physiological data, sleep-related parameters, other data or information, or any combination thereof. Typically, modifying the delivery of a portion of the substance into the air path may include: (i) initiating the delivery of the substance into the air path, (ii) ending the delivery of a portion of the substance into the air path, (iii) modifying the amount of substance delivered into the air path, (iv) modifying the timing characteristics of the delivery of a portion of the substance into the air path, (v) modifying the quantitative characteristics of the delivery of a portion of the substance into the air path, (vi) modifying any parameters associated with the delivery of the substance into the air path, or (vii) any combination of (i) to (vi).

[0069] Altering the temporal characteristics of the delivery of a portion of a substance into the air channel can include changing the delivery rate, starting and / or ending at different times, lasting for different periods, changing the temporal distribution or characteristics of the delivery, and changing the quantity distribution independently of the time distribution. Independent temporal and quantity variations ensure that, in addition to changing the frequency of substance release, the amount of substance released each time can be altered. In this way, various combinations of release frequency and release quantity can be achieved (e.g., higher frequency but lower release quantity, higher frequency and higher release quantity, lower frequency and higher release quantity, lower frequency and lower release quantity, etc.). Other variations in the delivery of a portion of the substance into the air channel can also be utilized.

[0070] The respiratory therapy system 120 can be used as, for example, a ventilator or a positive airway pressure (PAP) system, such as a continuous positive airway pressure (CPAP) system, an automated positive airway pressure (APAP) system, a bilevel or variable positive airway pressure (BPAP or VPAP) system, or any combination thereof. A CPAP system delivers a predetermined pressure (e.g., determined by a sleep physician) to the user. An APAP system automatically changes the pressure delivered to the user based on, for example, breathing data relevant to 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 lower than the first predetermined pressure (e.g., expiratory positive airway pressure or EPAP).

[0071] Reference Figure 2 The system 100 is shown according to some implementation methods. Figure 1 As part of the respiratory therapy system 120, the user 210 and bed partner 220 are located in bed 230 and lying on mattress 232. Motion sensor 138, blood pressure device 182, and activity tracker 190 are shown, but any one or more sensors 130 can be used to generate parameters for determining the user 210's sleep state and stage during treatment, sleep, and / or rest periods.

[0072] User interface 124 is a mask (e.g., a full-face mask) that covers the nose and mouth of user 210. Alternatively, user interface 124 may be a nasal mask that supplies air to the nose of user 210 or a nasal pillow mask that supplies air directly to the nostrils of user 210. 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 user 210 (e.g., face) and conformal cushioning pads (e.g., silicone, plastic, foam, etc.) to help provide an airtight seal between user interface 124 and user 210. User interface 124 may also include one or more vents for allowing carbon dioxide and other gases exhaled by user 210 to escape. In other implementations, user interface 124 is a mouthpiece for directing pressurized air into the mouth of user 210 (e.g., a night-protective mouthpiece molded to conform to the user's teeth, a jaw repositioning device, etc.).

[0073] User interface 124 is fluidly connected and / or linked to breathing device 122 via conduit 126. Breathing device 122, in turn, delivers pressurized air to user 210 via conduit 126 and user interface 124 to increase air pressure in user 210's throat, thereby helping to prevent airway closure and / or narrowing during sleep. Breathing device 122 can be positioned such as Figure 2 The bedside table 240 shown is directly adjacent to the bed 230, or more generally, is positioned on any surface or structure that is typically adjacent to the bed 230 and / or the user 210.

[0074] Typically, compared to not using the respiratory therapy system 120 (especially when the user has sleep apnea or other sleep-related conditions), users designated to use the respiratory therapy system 120 will tend to experience higher quality sleep and less fatigue throughout the day following use of the respiratory therapy system 120. For example, user 210 may have obstructive sleep apnea and rely on user interface 124 (e.g., a full-face mask) to deliver pressurized air from breathing device 122 via catheter 126. Breathing device 122 may be a continuous positive airway pressure (CPAP) machine used to increase air pressure in user 210's throat to prevent airway closure and / or narrowing during sleep. For people with sleep apnea, their airways can narrow or collapse during sleep, reducing oxygen intake and forcing them to wake up and / or otherwise disrupting their sleep. Breathing device 122 prevents airway narrowing or collapse, thereby minimizing the likelihood of user 210 waking up or being disturbed due to reduced oxygen intake.

[0075] See again Figure 1The system 100 includes one or more sensors 130, such as 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 photoplethysmography (PPG) sensor 154, an electrocardiogram (ECG) sensor 156, an EEG sensor 158, a capacitance sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyography (EMG) sensor 166, an oxygen sensor 168, an analyte sensor 174, a humidity sensor 176, and a lidar (LiDAR) sensor 178. In one or more implementations, the one or more sensors 130 may include a variety of other sensors, such as a skin conductance sensor, an accelerometer, an electrooculography (EOG) sensor, a light sensor, a humidity sensor, an air quality sensor, or any combination thereof. Typically, each of one or more sensors 130 is configured to output sensor data received and stored in memory device 114 or one or more other storage devices thereon to implement at least in part the methods disclosed herein.

[0076] One or more sensors 130 are used to detect parameters associated with the user. These parameters may be associated with the flow of pressurized air to the user. These parameters may be associated with various movements of the user, such as body movements, breathing, cardiac movements, etc. These parameters may be associated with movements specific to cardiac movements (e.g., heartbeat) or movements specific to other cardiac functions. These parameters may be associated with audio parameters, such as those indicating general body movement, movement relative to the heart (e.g., heartbeat), movement relative to components of the breathing apparatus 122, characteristics of the user interface 124 and / or catheter 126 of the respiratory therapy system 120, etc. In one or more implementations, the sensor 130 may be part of the respiratory therapy system 120, or the respiratory therapy system 120 may alternatively communicate with one or more external devices to receive one or more parameters from one or more sensors 130 of the external devices, or a combination of both, as discussed further below.

[0077] Although one or more sensors 130 are shown and described as including each of the following: pressure sensor 132, flow sensor 134, temperature sensor 136, motion sensor 138, microphone 140, speaker 142, RF receiver 146, RF transmitter 148, camera 150, infrared sensor 152, photoplethysmography (PPG) sensor 154, electrocardiogram (ECG) sensor 156, EEG sensor 158, capacitance sensor 160, force sensor 162, strain gauge sensor 164, electromyography (EMG) sensor 166, oxygen sensor 168, analyte sensor 174, humidity sensor 176, and lidar (LiDAR) sensor 178, more generally, one or more sensors 130 may include any combination and any number of each of the sensors described and / or shown herein.

[0078] Data from one or more sensors 130, which function as indoor environment sensors, can be used as parameters as discussed herein, such as temperature throughout the sleep period (e.g., too warm, too cold), humidity (e.g., too high, too low), pollution levels (e.g., amount and / or concentration of CO2 and / or particulates below or above a threshold), light levels (e.g., too bright, not using blackout curtains before falling asleep, too much blue light), and sound levels (e.g., exceeding a threshold, source type, associated with sleep interruptions, partner snoring). These can be captured by one or more sensors 130 on a breathing device 122, a user device 170 such as a smartphone (e.g., connected via Bluetooth or the internet), or other devices / systems such as those connected to a home automation system or a portion thereof. Air quality sensors can also detect other types of pollution in the room besides those causing allergies, such as from pets, dust mites, etc., where the room can benefit from air filtration to increase user comfort.

[0079] Parameters derived from the user's health (physical and / or mental) status can also be incorporated. For example, parameters can also be related to health (e.g., changes due to the onset or relief of illnesses such as breathing problems, and / or changes due to underlying conditions such as comorbid chronic diseases).

[0080] For example, PPG data from the PPG sensor 154 (such as on a mask, headband, patch, watch, ring, or in the ear) can be used to estimate heart rate, blood pressure, and SpO2. Blood oxygenation levels can be referenced to PAP treatment to confirm that no unexpected drop has been observed, and also to whether / when treatment was turned off (e.g., removing the mask) to monitor for any residual breathing (e.g., apnea) events. This PPG data can be used to estimate possible daytime headaches and / or to suggest changes to PAP therapy, such as further treatment of flow restriction in addition to pure obstructive events. This PPG data can also be used to examine inflammatory responses. Headaches may also be due to excessively high pressure settings and may benefit from reduced pressure or a change to an EPR setting.

[0081] Return to reference Figure 1 As described herein, system 100 can typically be used to generate information related to the user of breathing therapy system 120 during sleep periods. Figure 2 Data associated with user 210 (e.g., physiological data, flow data, stress data, exercise data, acoustic data, etc.). The generated data can be analyzed to produce one or more sleep-related parameters, which may include any data, readings, measurements, etc., related to the user during the sleep period. One or more sleep-related parameters that can be determined for user 210 during the sleep period include, for example, AHI score, sleep score, flow signal, respiratory signal, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, number of events per hour, event pattern, stage, pressure setting of breathing device 122, heart rate, heart rate variability, user 210's movement, temperature, EEG activity, EMG activity, awakening, snoring, choking, coughing, whistling, wheezing, or any combination thereof.

[0082] 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, the control system 110 can use the data generated by one or more sensors 130 to determine the sleep duration and sleep quality of the user 210 as parameters. For example, sleep-wake signals and one or more sleep-related parameters associated with the user 210 during sleep periods. Sleep-wake signals can indicate one or more sleep states, including sleep, wakefulness, relaxed wakefulness, micro-wakefulness, or different sleep stages, such as the rapid eye movement (REM) stage, the first non-REM stage (commonly referred to as "N1"), the second non-REM stage (commonly referred to as "N2"), the third non-REM stage (commonly referred to as "N3"), or any combination thereof. Methods for determining sleep state and / or sleep stage based on physiological data generated by one or more sensors (e.g., sensor 130) are described in, for example, WO 2014 / 047110, US 2014 / 0088373, WO 2017 / 132726, WO2019 / 122413 and WO 2019 / 122414, each of which is incorporated herein by reference in its entirety.

[0083] The sleep-wake signal can also be timestamped to determine the time the user enters the bed, the time the user leaves the bed, the time the user attempts to fall asleep, etc. The sleep-wake signal can be measured by one or more sensors 130 during the sleep period at a predetermined sampling rate, such as one sample per second, one sample every 30 seconds, one sample per minute, etc. In some implementations, the sleep-wake signal can also indicate respiratory signals, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, number of events per hour, event pattern, pressure setting of breathing device 122, or any combination thereof.

[0084] Events can include snoring, sleep apnea, central sleep apnea, obstructive sleep apnea, mixed sleep apnea, mouth leakage, hypopnea, mask leakage (e.g., from user interface 124), restless legs, sleep disturbances, choking, increased heart rate, heart rate variability, difficulty breathing, asthma attacks, seizures, epilepsy, fever, cough, sneezing, wheezing, the presence of illnesses such as the common cold or influenza, and combinations thereof. In some implementations, mouth leakage can include continuous mouth leakage or valve-like mouth leakage (i.e., varying in breathing duration) where the user's lips (typically using a nose / nose pillow mask) suddenly open during exhalation. Mouth leakage can lead to dry mouth, halitosis, sometimes colloquially known as "sandpaper mouth."

[0085] One or more sleep-related parameters that can be determined for a user during sleep periods based on sleep-wake signals include, for example, sleep quality measures such as total time in bed, total sleep time, sleep onset wait time, wake-up parameters after sleep onset, sleep efficiency, segmentation index, or any combination thereof.

[0086] 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 respiratory signals associated with the user during sleep periods. Respiratory signals typically represent the user's breathing during sleep periods. Respiratory signals can indicate, for example, respiratory rate, respiratory rate variability, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, number of events per hour, event pattern, pressure setting of breathing device 122, or any combination thereof. Events can include snoring, sleep apnea, central sleep apnea, obstructive sleep apnea, mixed sleep apnea, hypopnea, mouth leak, mask leak (e.g., from user interface 124), restless legs, sleep disturbance, choking, increased heart rate, difficulty breathing, asthma attack, seizure, epilepsy, or any combination thereof.

[0087] Typically, a sleep period includes any point in time after the user 210 has already lay down or sat in bed 230 (or another area or object where they intend to sleep), and / or has turned on breathing apparatus 122 and / or put on user interface 124. A sleep period can therefore include time periods (i) when the user 210 is using the CPAP system, but before the user 210 attempts to fall asleep (e.g., when the user 210 is lying in bed 230 reading a book); (ii) when the user 210 begins to try to fall asleep but remains awake; (iii) when the user 210 is in light sleep (also known as stages 1 and 2 of non-rapid eye movement (NREM) sleep); (iv) when the user 210 is in deep sleep (also known as slow-wave sleep, SWS, or stage 3 of NREM sleep); (v) when the user 210 is in rapid eye movement (REM) sleep; (vi) when the user 210 periodically wakes between light sleep, deep sleep, or REM sleep; or (vii) when the user 210 wakes without falling back asleep.

[0088] A sleep period is typically defined as ending once user 210 removes user interface 124, shuts off breathing apparatus 122, and / or leaves bed 230. In some implementations, a sleep period may include additional time periods, or may be limited to only some of the aforementioned time periods. For example, a sleep period may be defined as a time period that begins when breathing apparatus 122 begins supplying pressurized air to the airway or user 210, ends when breathing apparatus 122 stops supplying pressurized air to the airway of user 210, and includes some or all of the time points between when user 210 is asleep or awake.

[0089] 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 indicating the breathing (e.g., inhalation and / or exhalation) and / or ambient pressure of the user of respiratory therapy system 120. In this implementation, pressure sensor 132 can be coupled to or integrated into respiratory device 122, user interface 124, or catheter 126. Pressure sensor 132 can be used to determine the air pressure in respiratory device 122, air pressure in catheter 126, air pressure in user interface 124, or any combination thereof. Pressure sensor 132 can be, for example, a capacitive sensor, electromagnetic sensor, inductive sensor, piezoelectric sensor, resistive sensor, strain gauge sensor, optical sensor, potentiometric sensor, or any combination thereof. In one example, pressure sensor 132 can be used to determine the user's blood pressure.

[0090] 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 from the breathing apparatus 122, the airflow through the duct 126, the airflow through the user interface 124, or any combination thereof. In this implementation, the flow sensor 134 can be coupled to or integrated into the breathing apparatus 122, the user interface 124, or the duct 126. The flow sensor 134 can be 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, an eddy current sensor, a membrane sensor, or any combination thereof.

[0091] Flow sensor 134 can be used to generate a flow rate during sleep in relation to user 210 of breathing device 122. Figure 2 The associated flow data. An example of a flow sensor (e.g., flow sensor 134) is described in WO2012 / 012835, which is incorporated herein by reference in its entirety. In some implementations, flow sensor 134 is configured to measure ventilation flow (e.g., intentional “leakage”), unintentional leakage (e.g., mouth leak and / or mask leak), patient flow (e.g., air entering and / or leaving the lungs), or any combination thereof. In some implementations, flow data can be analyzed to determine the user’s cardiogenic oscillations.

[0092] Temperature sensor 136 outputs temperature data that can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. In some implementations, temperature sensor 136 generates instructions for user 210 ( Figure 2Temperature data including core body temperature, user 210 skin temperature, temperature of air flowing from breathing apparatus 122 and / or through conduit 126, temperature of air in user interface 124, ambient temperature, or any combination thereof. Temperature sensor 136 may be, for example, a thermocouple sensor, a thermistor sensor, a silicon bandgap temperature sensor or a semiconductor-based sensor, a resistance temperature detector, or any combination thereof.

[0093] Motion sensor 138 outputs motion data that can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. Motion sensor 138 can be used to detect movement of user 210 during sleep, and / or to detect movement of any component of respiratory therapy system 120, such as breathing device 122, user interface 124, or catheter 126. Motion sensor 138 may include one or more inertial sensors, such as accelerometers, gyroscopes, and magnetometers. In some implementations, motion sensor 138 alternatively or additionally generates one or more signals representing the user's body movements, from which signals representing the user's sleep state or sleep stage can be obtained; for example, through the user's breathing movements. In some implementations, motion data from motion sensor 138 can be combined with additional data from another sensor 130 to determine the user's sleep state or sleep stage. In some implementations, motion data can be used to determine the user's position, body position, and / or changes in body position.

[0094] Motion sensor 138 can detect a user's movement. In some implementations, motion sensor 138 collaborates with camera 150 (e.g., an infrared camera) to determine changes and / or shifts in body temperature relative to ambient temperature, thereby determining whether the user is moving. In some implementations, motion sensor 138 utilizes electromagnetic sensing in infrared wavelengths to detect movement. The use of an IR sensor allows the determination of a slight drop in body temperature as an indication that the user is sleeping. When body temperature rises above a certain level based on infrared sensing, motion sensor 138 can determine that the user is waking up and / or moving. Temperature changes can also be obtained from a temperature sensor attached to a mask connected to a breathing system, thus coming into contact with the user's skin during mask use. Other examples of motion sensor 138 include passive infrared sensors, sensors that emit acoustic signals (as described above and below) and determine whether the reception of detected reflected acoustic signals indicates a changing pattern, inertial measurement units (IMUs), gyroscopes and accelerometers, passive microphones, radio frequency (RF) based sensors, ultra-wideband sensors, etc.

[0095] The microphone 140 output can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. Microphone 140 can be used to record sound (e.g., sound from user 210) during sleep periods to determine (e.g., using control system 110) one or more sleep-related parameters, which may include one or more events (e.g., breathing events), as further described herein. Microphone 140 can be coupled to or integrated into breathing device 122, user interface 124, catheter 126, or user device 170. In some implementations, system 100 includes multiple microphones (e.g., two or more microphones and / or a microphone array with beamforming), 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.

[0096] Speaker 142 outputs sound waves. In one or more implementations, the sound waves can be audible to the user of system 100 (e.g., Figure 2 The speaker 142 may be used as an alarm clock or to play alarms or messages to user 210 (e.g., in response to identified body position and / or changes in body position). In some implementations, the speaker 142 may be used to transmit audio data generated by microphone 140 to the user. The speaker 142 may be coupled to or integrated into breathing apparatus 122, user interface 124, catheter 126, or user device 170.

[0097] Microphone 140 and speaker 142 can be used as separate devices. In some implementations, microphone 140 and speaker 142 can be combined into acoustic sensor 141 (e.g., a sonar sensor), as described in, for example, WO2018 / 050913 and WO2020 / 104465, which are incorporated herein by reference in their entirety. In this implementation, speaker 142 generates or emits sound waves at predetermined intervals and / or frequencies, and microphone 140 detects reflections of the emitted sound waves from speaker 142. The sound waves generated or emitted by speaker 142 have frequencies inaudible to the human ear (e.g., below 20 Hz or above about 18 kHz) so as not to disturb the sleep of user 210 or bed partner 220. Figure 2 Based at least in part on data from microphone 140 and / or speaker 142, control system 110 can determine user 210 ( Figure 2The location of the breathing device 122 and / or one or more of the sleep-related parameters described herein (e.g., determined body posture and / or changes in body posture), such as respiratory signals, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, number of events per hour, event pattern, sleep state, sleep stage, pressure setting of breathing device 122, or any combination thereof. In this document, a sonar sensor can be understood to involve active acoustic sensing, such as by generating / transmitting ultrasonic or low-frequency ultrasonic sensing signals through the air (e.g., in a frequency range of, for example, about 17-23 kHz, 18-22 kHz, or 17-18 kHz). Such a system can be considered relative to WO 2018 / 050913 and WO 2020 / 104465 above.

[0098] In some embodiments, sensor 130 includes (i) a first microphone that is the same as or similar to microphone 140 and is integrated in acoustic sensor 141; and (ii) a second microphone that is the same as or similar to microphone 140, but is separate from and different from the first microphone integrated in acoustic sensor 141.

[0099] RF transmitter 148 generates and / or transmits radio waves with a predetermined frequency and / or predetermined amplitude (e.g., in the high-frequency band, in the low-frequency band, long-wave signal, short-wave signal, etc.). RF receiver 146 detects the reflection of the radio waves emitted from RF transmitter 148, and this data can be analyzed by control system 110 to determine the user 210 (…). Figure 2 The location and / or body position and / or one or more of the sleep-related parameters described herein. An RF receiver (RF receiver 146 and RF transmitter 148 or another RF pair) may also be used for wireless communication between the control system 110, the breathing device 122, one or more sensors 130, the user device 170, or any combination thereof. Although RF receiver 146 and RF transmitter 148 are in... Figure 1 While shown as separate and distinct components, in some implementations, the RF receiver 146 and RF transmitter 148 are combined as part of the RF sensor 147 (e.g., a radar sensor). In some such implementations, the RF sensor 147 includes control circuitry. The specific format of the RF communication can be Wi-Fi, Bluetooth, etc.

[0100] In some implementations, RF sensor 147 is part of a mesh system. An example of a mesh system is a Wi-Fi mesh system, which may include mesh nodes, mesh routers, and mesh gateways, each of which may be mobile / movable or fixed. In such an implementation, the Wi-Fi mesh system includes Wi-Fi routers and / or Wi-Fi controllers, and one or more satellites (e.g., access points), each satellite including the same or similar RF sensor as RF sensor 147. The Wi-Fi routers and satellites communicate continuously 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 signals between the routers and satellites (e.g., differences in received signal strength), caused by a moving object or person partially blocking the signal. The motion data may indicate movement, breathing, heart rate, gait, falls, behavior, etc., or any combination thereof.

[0101] Camera 150 outputs image data that can be reproduced as one or more images (e.g., still images, video images, thermal images, or any combination thereof) that can be stored in memory device 114. Image data from camera 150 can be used by control system 110 to determine one or more of the sleep-related parameters described herein. Image data from camera 150 can be used by control system 110 to determine one or more of the sleep-related parameters described herein, such as one or more events (e.g., periodic limb movements or restless legs syndrome), respiratory signals, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, number of events per hour, event pattern, sleep state, sleep stage, or any combination thereof. Furthermore, image data from camera 150 can be used to identify the user's position and / or body position, determine chest movement of user 210, determine airflow from user 210's mouth and / or nose, determine the time user 210 enters bed 230, and determine the time user 210 leaves bed 230. Camera 150 can also be used to track eye movements, pupil dilation (if one or both eyes of user 210 are open), blink rate, or any changes during REM sleep.

[0102] Infrared (IR) sensor 152 outputs infrared image data that can be reproduced as one or more infrared images (e.g., still images, video images, or both) that can be stored in memory device 114. The infrared data from IR sensor 152 can be used to determine one or more sleep-related parameters during a sleep period, including the user 210's temperature and / or the user 210's movement. IR sensor 152 can also be used in conjunction with camera 150 when measuring the presence, location, and / or movement of user 210. For example, IR sensor 152 can detect infrared light with wavelengths between about 700 nm and about 1 mm, while camera 150 can detect visible light with wavelengths between about 180 nm and about 740 nm.

[0103] PPG sensor 154 output and user 210 ( Figure 2 The associated physiological data can be used to determine one or more sleep-related parameters, such as heart rate, heart rate pattern, heart rate variability, cardiac cycle, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, estimated blood pressure parameters, 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 connected to the user interface 124 and / or its associated helmet (e.g., straps, etc.).

[0104] ECG sensor 156 outputs physiological data associated with the electrical activity of the heart of user 210. In some implementations, ECG sensor 156 includes one or more electrodes located above or around a portion of user 210 during sleep periods. Physiological data from ECG sensor 156 can be used, for example, to determine one or more of the sleep-related parameters described herein.

[0105] EEG sensor 158 outputs physiological data associated with the electrical activity of the user 210's brain. In some embodiments, EEG sensor 158 includes one or more electrodes positioned on or around the user 210's scalp during sleep. Physiological data from EEG sensor 158 can be used, for example, to determine the user 210's sleep state or sleep stage at any given time during a sleep period. In some implementations, EEG sensor 158 may be integrated into user interface 124 and / or an associated helmet (e.g., a strap, etc.).

[0106] The capacitive sensor 160, force sensor 162, and strain gauge sensor 164 output data that can be stored in memory device 114 and used by control system 110 to determine one or more of the sleep-related parameters described herein. EMG sensor 166 outputs physiological data related to electrical activity generated by one or more muscles. Oxygen sensor 168 outputs oxygen data indicating the oxygen concentration of a gas (e.g., in conduit 126 or at user interface 124). Oxygen sensor 168 can be, for example, an ultrasonic oxygen sensor, an electro-oxygen sensor, a chemical oxygen sensor, an optical oxygen sensor, or any combination thereof. In some embodiments, one or more sensors 130 further include a ground-skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a blood pressure sensor, a blood oxygen sensor, or any combination thereof.

[0107] Analyte sensor 174 can be used to detect the presence of analytes in the exhaled breath of user 210. Data output from analyte sensor 174 can be stored in memory device 114 and used by control system 110 to determine the characteristics and concentration of any analytes in the breath of user 210. In some embodiments, analyte sensor 174 is positioned near the mouth of user 210 to detect analytes in the breath exhaled from the mouth of user 210. For example, when user interface 124 is a mask covering the nose and mouth of user 210, analyte sensor 174 can be located inside the mask to monitor mouth breathing of user 210. In other implementations, such as when user interface 124 is a nasal mask or nasal pillow mask, analyte sensor 174 can be positioned near the nose of user 210 to detect analytes in the breath exhaled through the nose. In other implementations, when user interface 124 is a nasal mask or nasal pillow mask, analyte sensor 174 can be located near the mouth of user 210. In some implementations, the analyte sensor 174 can be used to detect whether any air is unintentionally leaking from the mouth of 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 embodiments, the analyte sensor 174 can also be used to detect whether user 210 is breathing through their nose or mouth. For example, if the presence of an analyte is detected by data output from the analyte sensor 174 located near the mouth of user 210 or inside a mask (in the implementation where user interface 124 is a mask), the control system 110 can use that data as an indication that user 210 is breathing through their mouth.

[0108] The humidity sensor 176 outputs data that can be stored in the storage device 114 and used by the control system 110. The humidity sensor 176 can be used to detect humidity in various areas surrounding the user (e.g., inside the conduit 126 or user interface 124, near the user 210's face, near the connection between the conduit 126 and user interface 124, near the connection between the conduit 126 and breathing apparatus 122, etc.). Therefore, in some implementations, the humidity sensor 176 may be positioned in the user interface 124 or the conduit 126 to monitor the humidity of pressurized air from the breathing apparatus 122. In other implementations, the humidity sensor 176 is placed near any area where the humidity level needs to be monitored. The humidity sensor 176 can also be used to monitor the humidity of the surrounding environment around the user 210, such as the air in the user 210's bedroom. The humidity sensor 176 can also be used to track the user 210's biometric response to environmental changes.

[0109] 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 construct a three-dimensional (3D) map of the surrounding environment (e.g., a living space). LiDAR typically utilizes pulsed lasers for time-of-flight measurements. LiDAR is also known as 3D laser scanning. In examples using this sensor, a fixed or mobile device (such as a smartphone) with LiDAR sensor 178 can measure and map an area extending 5 meters or more from the sensor. For example, LiDAR data can be fused with point cloud data estimated by an electromagnetic RADAR sensor. LiDAR sensor 178 can also use artificial intelligence (AI) to automatically geofence the RADAR system by detecting and classifying features in the space that may cause problems for the RADAR system, such as glass windows (which may be highly reflective to RADAR). For example, LiDAR can also be used to provide an estimate of a person's height, and how that height changes when the person sits down or falls. LiDAR can be used to form a 3D mesh representation of the environment. In further applications, lidar can reflect radio waves off solid surfaces (e.g., transmissive materials) to allow for the classification of different types of obstacles.

[0110] In some implementations, one or more sensors 130 may also include a skin conductance response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a blood pressure sensor, a pulse oximeter 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 orientation sensor, a rain sensor, a soil moisture sensor, a water flow sensor, an alcohol sensor, or any combination thereof.

[0111] Although Figure 1 and2 While shown separately, any combination of one or more sensors 130 may be integrated into and / or coupled to any one or more components of system 100, including breathing apparatus 122, user interface 124, conduit 126, humidifier 129, control system 110, user device 170, or any combination thereof. For example, acoustic sensor 141 and / or RF sensor 147 may be integrated into external device 170 and / or coupled to user device. In such implementations, user device 170 may be considered as an auxiliary device for generating additional or auxiliary data for use by system 100 (e.g., control system 110) according to some aspects of the invention. In some implementations, at least one of the one or more sensors 130 is not physically or communicatively coupled to breathing apparatus 122, control system 110, or user device 170, and is typically positioned near user 210 during sleep periods (e.g., positioned on or in contact with a portion of user 210, worn by user 210, coupled to or positioned on a bedside table, coupled to a mattress, coupled to a ceiling, etc.).

[0112] Data from one or more sensors 130 can be analyzed to determine one or more sleep-related parameters, which may include respiratory signals, respiratory rate, respiratory pattern, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, occurrence of one or more events, number of events per hour, event pattern, sleep state, sleep stage, apnea-hypopnea index (AHI), or any combination thereof. One or more events may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, intentional mask leakage, unintentional mask leakage, mouth leakage, coughing, restless legs, sleep disturbance, apnea, tachycardia, dyspnea, asthma attack, seizure, epilepsy, elevated blood pressure, or any combination thereof. Many of these sleep-related parameters are physiological parameters, although some may be considered non-physiological parameters. Non-physiological parameters may also include operating parameters of the respiratory therapy system, including flow rate, pressure, humidity of pressurized air, motor speed, etc. Other types of physiological and non-physiological parameters may also be determined based on data from one or more sensors 130 or based on other types of data.

[0113] User device 170 includes display device 172. User device 170 may be, for example, a mobile device such as a smartphone, tablet, game console, smartwatch, laptop, etc. Alternatively, user device 170 may be an external sensing system, a television (e.g., a smart TV), or another smart home device (e.g., a smart speaker such as Google Home, Amazon Echo, Alexa, etc.). In some implementations, the user device is a wearable device (e.g., a smartwatch). Display device 172 is typically used to display images including still images, video images, or both. In some implementations, display device 172 acts as a human-machine interface (HMI) including a graphical user interface (GUI) configured to display images and provide input. Display device 172 may be an LED display, OLED display, LCD display, etc. Input interface may be, for example, a touchscreen or touch-sensitive substrate, a mouse, a keyboard, or any sensor system configured to sense input made by a human user interacting with user device 170. In some implementations, system 100 may use and / or include one or more user devices.

[0114] Blood pressure device 182 is typically used to help generate physiological data for determining one or more blood pressure measurements associated with a user. Blood pressure device 182 may include at least one of one or more sensors 130 to measure, for example, systolic blood pressure components and / or diastolic blood pressure components.

[0115] In some implementations, the blood pressure device 182 is a blood pressure monitor that includes an inflatable cuff that can be worn by a user and a pressure sensor (e.g., pressure sensor 132 described herein). For example, as Figure 2 As shown in the example, the blood pressure device 182 can be worn on the upper arm of the user 210. In this implementation where the blood pressure device 182 is a blood pressure monitor, the blood pressure device 182 also includes a pump (e.g., a manually operated light bulb) for inflating the cuff. In some implementations, the blood pressure device 182 is coupled to the breathing device 122 of the breathing system 120, which in turn delivers pressurized air to inflate the cuff. More generally, the blood pressure device 182 can be communicatively coupled to and / or physically integrated into the control system 110, memory device 114, breathing therapy system 120, user device 170, and / or activity tracker 190 (e.g., within a housing).

[0116] Activity tracker 190 is typically used to help generate physiological data for determining activity measurements associated with a user. Activity measurements may include, for example, steps, distance traveled, steps climbed, duration of physical activity, type of physical activity, intensity of physical activity, time spent standing, respiratory rate, average respiratory rate, resting respiratory rate, maximum respiratory rate, respiratory rate variability, heart rate, average heart rate, resting heart rate, maximum heart rate, heart rate variability, calories burned, blood oxygen saturation (SpO2), electrical skin activity (also known as skin conductance or skin response), user location, user posture, or any combination thereof. Activity tracker 190 includes one or more sensors 130 described herein, such as motion sensors 138 (e.g., one or more accelerometers and / or gyroscopes), PPG sensors 154, and / or ECG sensors 156.

[0117] In some implementations, the activity tracker 190 is a wearable device that can be worn by the user, such as a smartwatch, wristband, ring, or patch. For example, see reference... Figure 2 The activity tracker 190 is worn on the wrist of the user 210. The activity tracker 190 can also be attached to or integrated into clothing or garments worn by the user. Alternatively, the activity tracker 190 can also be attached to an external device 170 or integrated into the user device (e.g., within the same housing). More generally, the activity tracker 190 can be communicatively attached to the control system 110, memory device 114, respiratory therapy system 120, user device 170, and / or blood pressure device 182, or physically integrated into the control system, memory device, respiratory therapy system, user device, and / or blood pressure device (e.g., within a housing).

[0118] Although the control system 110 and the memory device 114 are in Figure 1 While described and shown 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 breathing device 122. Alternatively, in some implementations, control system 110 or a portion thereof (e.g., processor 112) may reside in the cloud (e.g., integrated into a server, integrated into an Internet of Things (IoT) device, connected to the cloud, subjected to edge cloud processing, etc.), or in one or more servers (e.g., remote servers, local servers, etc., or any combination thereof).

[0119] Although system 100 is shown as including all the components described above, according to an implementation of the invention, the system may include more or fewer components for analyzing data related to a user's use of the respiratory therapy system 120. For example, a first alternative system includes a control system 110, a memory device 114, and at least one of one or more sensors 130. As another example, a second alternative system includes a control system 110, a memory device 114, at least one of one or more sensors 130, a user device 170, and a blood pressure device 182 and / or an activity tracker 190. As yet another example, a third alternative system includes a control system 110, a memory device 114, a respiratory therapy system 120, at least one of one or more sensors 130, an activity tracker 190, and a user device 170. As yet another example, a fourth alternative system includes a control system 110, a memory device 114, a respiratory therapy system 120, at least one of one or more sensors 130, a user device 170, and a blood pressure device 182 and / or an activity tracker 190. Therefore, various systems can be formed using any part or multiple parts of the components shown and described herein and / or combined with one or more other components.

[0120] Refer again Figure 2 System 100 includes multiple optional components (i.e., a large number of sensors, cameras, etc.) that are not necessarily required for the operation of system 100. Typically, any one of these sensors, if capable of detecting one of the modalities described below, will be sufficient to enable the system to operate as described herein. Having more than one sensor in the system allows for parallel and / or independent estimation of sleep states, which brings improved determinism to the computational results. Using one or more of the indicated sensors, the system determines the sleep state, which, in addition to sleep stages (e.g., N1, N2, N3, REM), can include a waking or sleeping sleep state. This determination can be based on modalities other than flow, but can also be based on flow in combination with another or more modalities such as motion, audio, cardiac, etc. For simplicity of discussion, where appropriate, for Figure 3 All components identified in the text will be in the singular form. However, the use of the singular does not limit the discussion to only one of each such component.

[0121] As described above, in one or more implementations, the respiratory system 100 may further include or be associated with a user device 170. With respect to the control system 172, the user device 170 may have the same functionality as the respiratory device 122. Furthermore, the user device 170 may be a variety of devices, such as smart home devices, smart phones, smartwatches, smart speakers, televisions, smart masks, smart rings, fitness trackers, computing devices (e.g., personal computers, laptops, tablets, etc.), smart pendants, smart clothing, or any other device that, if one or more sensors 130 are not integrated into the user device 170, possesses intelligent functionality in addition to having the ability to communicate with the one or more sensors 130 discussed herein, through at least the control system 172. A smart device is an electronic device capable of connecting to other devices or networks, which typically has certain processing capabilities that allow it to operate at least to some extent interactively and autonomously. Because the user device 170 is used to measure the user's parameters, it is widely associated with the user. In some cases, a communication device 170 may be connected to the user. Such connectors come into mechanical contact with the user, either directly, such as through skin, or indirectly, such as through clothing. Connected smart devices can include smartwatches, smartphones, activity trackers, smart masks, smart clothing, smart mattresses, smart pillows, smart sheets, smart rings, or wearable health monitors. Contactless (non-connected) smart devices can include smart TVs, smart speakers, smart cars, entertainment systems (including vehicle entertainment systems), etc.

[0122] User device 170 may also include one or more remote (relative to the user and local smart device) servers and / or communicate with one or more remote (relative to the user and local smart device) servers. These may be configured to process and store, or simply store, data associated with the user. In some cases, these servers, which are typically capable of performing more complex and / or computationally intensive tasks, may be configured to receive data from the local smart device and perform any tasks with higher computational requirements. The servers may then store and / or return the results to the local smart device.

[0123] In one or more implementations, the control system 110 may execute the methods disclosed herein to determine the user's sleep state, i.e., based on respiratory flow data obtained from the device's flow sensor. The control system 110 of the present invention may also be arranged to collect data from any additional disclosed sensors. Alternatively, the methods disclosed herein for determining the user's sleep state may be implemented by a control system 172 of a user device 170 configured to communicate with the breathing device 122. In this form, the breathing device 122 may send one or more signals to the user device 170 representing information collected and / or generated by the breathing device 122 and information used by the user device 170 to perform the method.

[0124] In one or more possible implementations, the method disclosed herein for determining a user's sleep state may be implemented partly by control system 110 and partly 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. Additionally, user device 170 may use one or more additional sensors to process information to determine the user's sleep state based on one or more other parameters, such as parameters related to the user's body movement, the user's cardiac data. One of breathing device 122 and user device 170 may transmit the determined user sleep state to the other for subsequent determination of the user's final sleep state and additional processing, such as determining AHI.

[0125] Reference Figure 3 This illustration shows another example of the arrangement of components of a system 100 according to some aspects of the invention in an environment. The environment is again a bedroom setting including a user 210 and a bed partner 220. The user 210 wears a user interface 124 connected via a conduit 126 to a breathing apparatus 122. The breathing apparatus 122 includes a flow sensor capable of facilitating the measurement of the user 210's respiratory flow. Statistical analysis of the respiratory flow can then be used to calculate sleep parameters indicating 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. WO 2014 / 047110 (PCT / US2013 / 060652) entitled "SYSTEM AND METHOD FOR DETERMINING SLEEP STAGE" and International Patent Application Publication No. WO2015 / 006164 (PCT / US2014 / 045814) entitled "METHOD AND SYSTEM FOR SLEEP MANAGEMENT," the contents of which are incorporated herein by reference in their entirety.

[0126] As described in International Patent Application Publication No. WO2014 / 047110, it is possible to determine whether a person is asleep or awake without further determining the sleep stage, or without first determining a specific sleep stage. In other words, the present invention considers determining whether user 210 is awake or asleep, i.e., in a sleep state, independently of or at least without determining the sleep stage.

[0127] In one or more implementations, one or more features can be generated from various data associated with user 210 regarding the use of the breathing device and / or the environment of user 210. These features can be used to determine whether user 210 is awake or asleep. For example, when user 210 is using the breathing device, flow data including (but not limited to) flow rate and audio or other acoustic signals can be processed to generate breathing features. These breathing features can be associated with whether user 210 is awake or asleep. Based on the breathing features input into a classifier, the classifier can analyze the breathing features to determine whether user 210 is awake or asleep.

[0128] In one or more implementations, a classifier can be trained for further sleep state determination by inputting previous respiratory or cardiac features (or other features generally associated with sleep) that are associated with a known sleep state of being awake or asleep. After training, the classifier can be used to determine the sleep state of 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 that performs two-state classification; to name just a few examples, it can be trained to output sleep state (e.g., wakefulness / sleep determination) based on the input features. As another example, such a classifier can be a rule-based processing system that classifies input features. In some cases, the classifier can include input from a function library for sleep state detection. This library can provide signal processing of one or more sensed signals to estimate motion, activity counts, and respiratory rates, for example, based on epochs; such as by using time, frequency, or time-frequency methods based on wavelet or non-wavelet processing.

[0129] In one or more specific implementations, features associated with user 210 can be input into a classifier. The classifier can then combine these features to produce a number, which is then used to estimate a sleep state of being awake or asleep. For example, the number can be generated by the classifier and can be a discriminant value. In some implementations, the combination of values ​​within the classifier can be done linearly. For example, the discriminant value can be a linearly weighted combination of features. The classifier can then generate an appropriate sleep state label from it (e.g., sleep, awake, or even presence / absence). The sleep state classifier thus processes the input features (e.g., wavelet features, breathing features, etc.) to detect sleep states.

[0130] Different locations of components in system 100 are considered. For example, one or more cameras may be mounted in 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) placed at locations 350, 352, 354, 356, and 358. One or more microphones, a microphone and speaker combination for sonar, or a transmitter and receiver for radar may be mounted on the bed 230 and / or the walls of the room, etc. In some implementations, multiple cameras or microphones at different locations in the room enable multiple video angles and stereo sound, which can allow direct differentiation and cancellation of noise from bed partner 220 relative to user 210. In some implementations, contact sensors such as PPG sensors, GSR sensors, ECG sensors, activity recording sensors, etc., may be placed at locations 360, 362, 364, and 366 of user 210.

[0131] Although the invention is described primarily in the context of detecting a user's sleep state and / or stage while the user is using a breathing therapy device, the method of the invention can be applied to any SDB device. For example, the method of the invention can be applied to a mandibular repositioning device. Furthermore, the method of the invention can be applied to any individual who wishes to obtain more information about his or her sleep, and not necessarily an individual suffering from some form of sleep-disordered breathing. Therefore, a method that does not require a breathing therapy system can be applied to any individual having the other components described above within system 100 that can determine the user's sleep stage and / or phase. In this case, for example, the breathing therapy system 120 can be omitted from system 100, and the determination of sleep state and / or sleep stage can be performed by other components of system 100.

[0132] Figure 4 An example of a process 400 for detecting sleep state based on user movement according to an aspect of the present invention is described below. For convenience, the following description will refer to the process 400 performed by the respiratory therapy system 120. However, the process 400 may be performed by the respiratory therapy system 120 and / or remote external sensors and / or computing devices, for example, including Figure 1 Any sensor / device in the system (local or other).

[0133] In step 402, the respiratory therapy system 120 detects one or more parameters relating to user movement during sleep. In one or more implementations, the sleep period may optionally include a period of pressurized air being applied to the user's airway. In one or more implementations, the one or more parameters may relate to the duration, rate, frequency (or period), intensity, or type of the user's movement, and combinations thereof. In one or more implementations, the one or more parameters may be measured based on one or more sensors placed on, near, or in combination thereof on the user. The sensors acquire at least one parameter representing user movement, such as the user's overall body movement, movement of one or more of the user's limbs, etc. In one or more implementations, the movement will include any movement unrelated to breathing or cardiac function. Examples of such general body movement, referred to throughout the specification as body or body movement, include, for example, rolling, twitching, adjusting position, limb movement, etc. Parameters indicating these movements may be provided by radiofrequency biomotion sensors, but may also be acquired by one or more activity-based sensors or pressure sensors embedded in a sensor membrane or sensor mattress, by a bioimpedance measurement system, an ultrasonic sensor, or an optical sensor, etc.

[0134] In one or more implementations, the movement may include any one or more of respiratory movement, cardiac movement, and overall body movement. Regarding respiratory movement, motion parameters may be calculated based on flow information collected by the breathing device or other motion sensors (contact (breathing belt or other wearable inertial measurement sensors) or non-contact (RF or acoustic) sensors). Respiratory parameters may include respiratory amplitude, relative respiratory amplitude, respiratory rate, and respiratory rate variability.

[0135] In one or more implementations, pressurized air is applied to the user's airway via a tube and / or mask connected to the breathing apparatus, and at least one of the one or more sensors may be on or within the tube, mask, or a combination thereof. In one or more implementations, at least one sensor may include an inertial measurement unit on or within the tube, mask, or a combination thereof. In one or more implementations, at least one of the one or more sensors may include an inertial measurement unit coupled to a smart device connected to the user. For example, the smart device may include a smartwatch, smartphone, activity tracker, smart mask worn by the user during treatment, or health monitor.

[0136] In one or more implementations, parameters associated with body movement and / or respiratory movement can be obtained using non-invasive sensors, such as pressure-sensitive mattresses or radio frequency (RF) motion sensors. RF motion sensors are non-contact sensors because the user does not need to have mechanical contact with the sensor. RF motion sensors can be configured to be sensitive to movement within, for example, a distance of 1.2 meters and avoid detecting movement from objects further away. This can prevent or limit interference from, for example, a second user in the bed or nearby moving objects (e.g., a fan). This information is found in International Patent Application Publication No. WO 2007 / 143535 (PCT / US2007 / 070196), entitled “APPARATUS, SYSTEM, AND METHOD FORMONITORING PHYSIOLOGICAL SIGNS”, the contents of which are incorporated herein by reference in their entirety, and in International Patent Application Publication No. WO 2015 / 006164 (PCT / US2014 / 045814), which is cited above.

[0137] It should be understood that in some versions of this technology, other sensors, such as those further described herein, may also be used, or alternatively, to generate motion (respiratory signals) for detecting sleep stages.

[0138] In step 404, the respiratory therapy system 120 processes one or more parameters to determine the user's sleep state, which is whether the user is awake, asleep, or in one of a specific sleep stages. In one or more implementations, some specific parameters that can be estimated and analyzed relate to the frequency, amplitude, and bursts of higher-frequency (faster) movements when the user moves from the waking stage to the drowsy stage of sleep stage N1. The combined properties of movement patterns and respiratory rate values, as well as waveform shape, can be used to classify sleep states.

[0139] 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 parameters from step 402 as input and process the parameters to determine the sleep state. In one or more implementations, the classifier can be a full sleep grading classifier using a one-dimensional convolutional neural network. In this method, a set of feature decoders is learned directly from the raw or preprocessed streaming signal.

[0140] In one or more implementations, processing the one or more parameters includes processing a signal representing the change of at least one of the one or more parameters over time. Thus, over time, the respiratory therapy system 120 can be adapted to object-specific data to increase the accuracy of the classification (e.g., the object's typical baseline respiratory rate and movement, i.e., how much the user moves / stirs in bed when asleep), which can be learned and adopted during the estimation process.

[0141] In step 406, the respiratory therapy system 120 calculates the user's Apnea-Hypopnea Index (AHI) during the period at least partially based on the sleep state, which is based on the user's movement. In response to the sleep state being determined to be awake during one or more events affecting the calculation of the user's apnea-hypopnea index, the AHI is calculated such that the one or more events are ignored. The one or more events can be one or more apneas, one or more hypopneas, or a combination thereof. Therefore, when 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 incorrect events.

[0142] Figure 5 A slightly similar embodiment of various aspects of the invention is shown. Figure 4 The example in the text, however, uses a process 500 for detecting sleep state based on cardiac activity. For convenience, the following description will refer to process 500 performed by the respiratory therapy system 120. However, process 500 can also be combined with the respiratory therapy system 120. Figure 1 The system includes any one or more sensors and devices (local or other) to perform this function.

[0143] In step 502, the respiratory therapy system 120 detects one or more parameters concerning the user's cardiac activity during sleep. In one or more implementations, the sleep period may optionally include a period of applying pressurized air to the user's airway. In one or more implementations, pressurized air is applied to the user's airway via a tube and mask connected to the breathing apparatus. At least one sensor for one or more parameters may be located on or within the tube, mask, or a combination thereof.

[0144] In one or more implementations, the cardiac signal can be extracted from respiratory flow signals (collected by a flow sensor on a breathing apparatus or from additional contact or non-contact sensors) or based on pressure waves generated at the body surface, known as a cardiac impactogram. In some cases, due to a combination of location, body type, and distance from the sensor, the cardiac signal will provide a signal in which individual pulses are clearly visible through motion. In this case, the heartbeat will be determined technically by a threshold. For example, the pulse is associated with the point where the signal exceeds the threshold. In more complex but typical cases, the cardiac impactogram will present a more complex but repeatable pulse shape. Therefore, a pulse shape template can be correlated with the acquired cardiac signal, and locations with high correlation will be used as the heartbeat locations. The pulse can then be measured using a motion sensor such as the RF sensor described above.

[0145] More specifically, similar to the implementations discussed above regarding mobility, in one or more implementations, the sensor can be a radio frequency (RF) sensor, either separate from or integrated with the breathing device. The sensor can transmit an RF signal to the user. The reflected signal is then received, amplified, and mixed with a portion of the original signal. The mixer output can be low-pass filtered. The resulting signal contains information about the user's cardiac activity and is typically superimposed on the breathing signal collected from the user. In another implementation, the sensor can also use orthogonal transmission, where two carrier signals with a 90-degree phase difference are used. Given the limitation that the pulse becomes very short in time, such a system can be characterized as an ultra-wideband (UWB) RF sensor.

[0146] In one or more implementations, one or more parameters may relate 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 time periods of one minute, five minutes, ten minutes, half an hour, one hour, two hours, three hours, or four hours.

[0147] In step 504, the respiratory therapy system 120 processes one or more parameters to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage. Similar to the above, in one or more implementations, the respiratory system may 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 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 fully sleep-leveling classifier using a one-dimensional convolutional neural network. In this method, a set of feature decoders is learned directly from the raw or pre-processed streaming signal.

[0148] In step 506, the respiratory therapy system 120 calculates the user's apnea-hypopnea index (AHI) for the period of time, at least in part, based on sleep state. As described above, AHI is typically calculated based on respiratory data collected from a flow sensor in the breathing apparatus. Knowledge of the user's sleep state allows the calculation of the AHI index such that, in response to a sleep state determined to be awake during one or more events affecting the calculation of the user's apnea-hypopnea index, said one or more events are ignored. The one or more events can be one or more apneas, one or more hypopneas, or a combination thereof. Therefore, when one or more SBD events occur but the sleep state determined at that time indicates the user is awake, the SBD events are ignored, so that the AHI is not affected by incorrectly scored events.

[0149] Figure 6 An example of a process 600 for detecting sleep state based on audio parameters associated with a user, according to an aspect of the present invention, is described below. For convenience, the following description will refer to process 600 performed by a respiratory therapy system 120. However, process 600 may be performed by the respiratory therapy system 120 in conjunction with additional sensors and computing devices, such as... Figure 1 Any sensor / device (local or otherwise) indicated in System 100.

[0150] In step 602, the respiratory therapy system 120 uses an internal (for the respiratory system) or external microphone to detect one or more parameters relating to audio associated with the user during a sleep period. In one or more implementations, the sleep period may optionally include a period of time during which pressurized air is applied to the user's airway. The audio parameters may relate to sounds passively heard by, for example, a microphone located near the user. For example, a tubing system can generate sound by dragging across an object such as paper or running along a side panel.

[0151] Alternatively, the audio parameters may involve sound emitted and received via echo at a microphone located near the user. The sound may be emitted by a device specifically configured to emit sound (e.g., a speaker) or by a device that emits sound indirectly (e.g., a blower on a breathing apparatus).

[0152] In one or more specific implementations, audio may be associated with: (1) one or more movements of the user, (2) one or more movements of a tube, mask, or combination thereof connected to a breathing apparatus configured to apply pressurized air to the user, or (3) combinations thereof. For example, the user may move, and this movement may produce sound picked up by a microphone. Alternatively, the user may move a device of the breathing system, such as a tubing system, and the sound of the tubing system may be picked up by a microphone. Movement of the tube may indicate the user's activity. Or, loud snoring may indicate that the user has fallen asleep quickly.

[0153] In one or more implementations, detecting one or more parameters of audio associated with one or more movements of a tube, mask, or combination thereof is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more audio signals. The audio may be detected based on one or more microphones within the tube, mask, or a device connected to the tube and device and supplying pressurized air to the user's airway.

[0154] More specifically, the conduit system can be used as a waveguide. As the conduit system moves along the waveguide, changes in its characteristics alter the position of reflections (e.g., echoes) within the conduit system. Mathematical processing of these changes in reflection, such as through cepstral processing, wavelet analysis, squared signals, or root-mean-square signals, can detect these changes and make them equal to the changes in user motion. Further details of the mathematical processing can be found in International Patent Application Publication No. WO 2010 / 091362 (PCT / AU2010 / 000140) entitled “ACOUSTIC DETECTION FOR RESPIRATORY TREATMENT APPARATUS,” the contents of which are incorporated herein by reference in their entirety. The additional acoustic sensors are disclosed in the following: International Patent Application Publication No. WO 2018 / 050913 (PCT / EP2017 / 073613) entitled "APPARATUS, SYSTEM, AND METHOD FOR DETECTING PHYSIOLOGICAL MOVEMENT FROM AUDIO AND MULTIMODALSIGNALS", International Patent Application Publication No. WO 2019 / 122412 (PCT / EP2018 / 086762) entitled "APPARATUS, SYSTEM, AND METHOD FORMOTION SENSING", International Patent Application Publication No. WO 2019 / 122414 (PCT / EP2018 / 086764) entitled "APPARATUS, SYSTEM, AND METHOD FORMOTION SENSING", and International Patent Application Publication No. WO 2019 / 122414 (PCT / EP2018 / 086764) entitled "APPARATUS, SYSTEM, AND METHOD FOR PHYSIOLOGICAL SENSING IN The entire contents of the international patent application publication No. WO 2019 / 122414 (PCT / EP2018 / 086765) for “VEHICLES” are incorporated herein by reference.

[0155] In step 604, the respiratory therapy system 120 processes one or more parameters to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage. Similar to the above, in one or more implementations, the respiratory therapy system 120 may 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 may receive the parameters from step 602 as input and process the parameters to determine the sleep state. In one or more implementations, the classifier may be a fully sleep-leveling classifier using a one-dimensional convolutional neural network. In this method, a set of feature decoders is learned directly from the raw or preprocessed streaming signal.

[0156] In step 606, the respiratory therapy system 120 calculates the user's apnea-hypopnea index (AHI) for the period of time, at least in part, based on the sleep state. In response to the sleep state being determined to be awake during one or more events affecting the calculation of the user's AHI, the AHI is calculated such that the one or more events are ignored. The one or more events can be one or more apneas, one or more hypopneas, or a combination thereof. Therefore, when 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 incorrect events.

[0157] Figure 7 An example of a process 700 for detecting a user's sleep state based on multiple different modalities according to various aspects of the present invention is shown. For convenience, the following description will refer to the process 700 performed by the respiratory therapy system 120. However, the process 700 may be combined with the respiratory therapy system 120. Figure 1 It can be performed by any other sensors or devices included (local or otherwise).

[0158] In step 702, the respiratory therapy system 120 detects multiple parameters associated with the user during the period when pressurized air is applied to the user's airway. Each of the multiple parameters is associated with at least one modality, such as the user's movement, the flow of pressurized air, the user's cardiac activity, audio associated with the user, etc. The detection is multimodal, such that the multiple parameters cover at least two of the modalities. For example, the parameters may include body movement and respiratory flow, cardiac activity and respiratory flow, audio and respiratory flow, etc.

[0159] In step 704, the respiratory therapy system 120 processes multiple parameters to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage. Similar to the above, in one or more implementations, the respiratory therapy system 120 may 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 may receive the parameters from step 702 as input and process the parameters to determine the sleep state. In one or more implementations, the classifier may be a fully sleep-leveling classifier using a one-dimensional convolutional neural network. In this method, a set of feature decoders is learned directly from the raw or preprocessed streaming signal.

[0160] In one or more implementations, the parameters of the three different modalities are segmented into time epochs, and statistical features are generated for each epoch. These features could be signal variance, spectral components, or peak values, and are grouped into vectors Xr, Xn, and Xc. These can then form a single vector X of features. These features are combined to determine the probability that an epoch corresponds to a specific sleep state (e.g., the user is asleep or awake). The classification from the epochs can be further combined with classifications from other epochs to form higher-level decisions, such as the user's sleep stage.

[0161] In one or more implementations using RF sensors to detect body motion, respiratory activity, and cardiac activity, body motion can be identified using zero-crossing or energy envelope detection algorithms (or more complex algorithms) and used to form "motion on" or "motion off" indicators. Respiratory activity is typically in the range of 0.1 to 0.8 Hz and can be derived by filtering the sensor's raw signal with a bandpass filter, the passband of which is in this region. Cardiac activity (i.e., in the respiratory flow signal collected by a breathing device or other contact or non-contact sensors) can be detected as a flow signal, which can be accessed by filtering with a bandpass filter having a passband of, for example, 1 to 10 Hz.

[0162] In one or more implementations, the system begins by testing which modalities provide the best quality signal. These modalities are then used in any further measurements. In another implementation, the system may begin with two or more predetermined modalities. However, in some cases, the processing may determine that the user's sleep state cannot be determined based on one or more parameters associated with one of the two or more predetermined modalities. For example, one of the predetermined modalities could be respiratory flow. If the breathing device determines that sleep state cannot be determined solely based on flow, then, for the inadequacy of flow discussed above, one or more parameters from the processing can subsequently be associated with a second of the two predetermined modalities, or with the second plus an additional (third) modality. For example, the second or third modality could be one of the user's body movements, the user's heart activity, audio associated with the user, etc.

[0163] In one or more implementations, determining that a user's sleep state cannot be determined can be satisfied based on a threshold determination metric. The threshold determination metric can be based on two or more parameters that conflict with each other regarding sleep state, sleep stage, or a combination thereof. In one or more implementations, the two or more conflicting parameters can come from two or more different modalities. In one or more implementations, conflicts between two or more conflicting parameters are resolved by ignoring parameters derived from low-quality data and / or by giving increased weight to parameters extracted from higher-quality data. Therefore, each modality and / or parameter can be weighted according to data quality. Sleep state (e.g., sleep state and sleep stage) can be determined based on modalities and / or parameters with higher weights, for example, those that are traditionally more accurate. Therefore, in one or more implementations, processing multiple parameters can be based on a subset of multiple parameters from two or more selected modalities among multiple modalities. The selected two or more modalities can be selected based on weighting based on data quality.

[0164] The threshold determination metric can be based on multiple prior parameters associated with the user during one or more previous periods of time when pressurized air was applied to the user's airway. These prior parameters can be validated, based on the previous periods, to accurately reflect the user's sleep state. Subsequently, a classifier can be used to provide the threshold determination based on this learned information. This process is performed by a sleep segmentation classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks.

[0165] For example, Table 1 lists the characteristics used by the respiratory system in determining sleep stages—specifically, the user's physiological responses.

[0166]

[0167] Table 1

[0168] For Table 1, the listed sleep stages in the context of sleep states are non-REM sleep and REM sleep. The listed sleep states are awake and asleep. The user's physiological responses are respiratory rate, activity, tidal volume, heart rate, airway resistance, obstructive apnea, central apnea, snoring (non-apnea), and snoring (apnea). Each of these characteristics can potentially be determined based on flow signals from the breathing apparatus and subsequently used to determine the sleep stage. However, this determination is based on probability, such as more likely, less likely, and variables. However, combining additional modalities with the flow modalities used to determine sleep states and sleep stages increases the accuracy of the determined states / stages. Increased accuracy leads to better determinations and results, such as more accurate AHI.

[0169] In step 706, the respiratory therapy system 120 calculates the user's apnea-hypopnea index (AHI) for the period of time, at least in part, based on the sleep state. In response to the sleep state being determined to be awake during one or more events affecting the calculation of the user's AHI, the AHI is calculated such that the one or more events are ignored. The one or more events can be one or more apneas, one or more hypopneas, or a combination thereof. Therefore, when 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 incorrect events.

[0170] Figure 8 Several graphs associated with a user's sleep periods are shown. These include a respiratory flow graph 804 and a respiratory rate (in heart rate per minute) graph 806. Parameters associated with these graphs are processed to determine the sleep graph 806, which shows the user's sleep state (i.e., awake or not awake) and sleep stages (if not awake) (i.e., N1+N2, N3, and REM). The respiratory rate graph 806 can be based on data received from the respiratory flow graph 804. In many respiratory therapy devices, the respiratory flow graph 804 is plotted, and the AHI is calculated based on data obtained using the flow sensor of the respiratory device. However, respiratory flow data can also be obtained by independent measurement, for example, by additional contact or non-contact sensors, as discussed earlier herein. Therefore, the calculation of AHI can also be performed based on data obtained from these alternative sensors. Furthermore, such additional sensors can provide information on other modalities such as the user's heart or body movements, as well as any audible signals generated by the user during sleep. By processing data associated with more than one modality, a more accurate sleep curve 806 can be generated, which precisely reflects the user's sleep state during the period when pressurized air is supplied to the ventilator. This can lead to a more accurate calculation of the user's AHI.

[0171] In one or more implementations, after determining the above reference Figure 4-7 Following any one or more of the described procedures, an action may be initiated based at least in part on the sleep state, AHI, or a combination thereof. In one or more implementations, the action may include one or more of the following: (1) saving a record of the apnea-hypopnea index, (b) transmitting the apnea-hypopnea index to an external device to display information on a screen, or (c) adjusting the operating settings of the device. For example, one or more settings of the breathing device 122 may be adjusted based on the detected sleep state, sleep stage, and / or AHI. In one example, a more accurate detection of the AHI may indicate an improvement in the user's sleep-disordered breathing and may automatically reduce the breathing pressure setting of the breathing device 122. This may improve user comfort without compromising the therapeutic effect of using the breathing device 122 and may also improve user adherence to prescribed treatment. Where the device detecting the sleep state and / or AHI is not the breathing device 122 (such as user device 170), the sleep state, sleep stage, and / or AHI may be transmitted to the breathing device 122 or the respiratory therapy system 120. Therefore, one or more actions can be taken, such as making the use of therapy more compelling by providing users with richer feedback on sleep quality (e.g., more accurate AHI and / or sleep states). More precise sleep segmentation can also be used to provide users with more information to improve engagement by providing consumer characteristics and to improve patient adherence by providing users with feedback that quantifies the benefits of treatment.

[0172] While the invention has been described with reference to one or more specific embodiments or implementations, those skilled in the art will recognize that many changes can be made thereto without departing from the spirit and scope of the invention. Each of these implementations and their obvious variations is considered to fall within the spirit and scope of the invention. Additional implementations of aspects of the invention are also contemplated that can combine any number of features from any of the implementations described herein.

Claims

1. A method comprising: Detect one or more parameters related to the user's movement during the user's sleep period; Process the one or more parameters to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. as well as The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disordered breathing events that occurred during the sleep period.

2. The method of claim 1, wherein the sleep period includes a period during which pressurized air is applied to the user's airway.

3. The method of claim 1 or 2, wherein the sleep stage includes indications of non-rapid eye movement sleep, N1 sleep, N2 sleep, N3 sleep, or rapid eye movement sleep.

4. The method of claim 1, wherein the one or more events are one or more apneas, one or more hypoventilations, or a combination thereof.

5. The method of claim 1 or 2, wherein the one or more parameters relate to duration, period, rate, frequency, intensity, user movement type, or a combination thereof.

6. The method of claim 1 or 2, wherein the one or more parameters are measured based on one or more sensors placed on, near, or in combination thereof on the user.

7. The method of claim 6, wherein pressurized air is applied to the user's airway through a tube and a mask connected to the breathing apparatus, 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.

8. The method of claim 7, wherein the at least one sensor comprises a motion sensor, the motion sensor being on or inside the tube, on or inside the mask, or a combination thereof.

9. The method of claim 6, wherein at least one of the one or more sensors comprises a motion sensor within a smart device.

10. The method of claim 9, wherein the smart device is one or more of the following: (1) a smartwatch, smart phone, smart mask, smart clothing, smart mattress, smart pillow, smart sheet or smart ring, each in contact with the user; (2) a radar-based sensor, a sonar-based sensor, a lidar-based sensor or other non-contact motion sensor, each near the user; (3) a combination thereof.

11. The method of claim 1 or 2, wherein processing the one or more parameters includes processing a signal representing a change of at least one of the one or more parameters over time.

12. A method comprising: Detect one or more parameters related to the user's cardiac activity during the user's sleep period; Process the one or more parameters to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage; as well as The sleep state is used to calculate the user's apnea-hypopnea index during the sleep period, wherein the sleep state is determined to be awake during one or more events that affect the calculation of the user's apnea-hypopnea index, and the one or more events are ignored.

13. The method of claim 12, wherein the one or more events are one or more apneas, one or more hypoventilations, or a combination thereof.

14. The method of claim 12 or 13, wherein the one or more parameters are related to the user's heart rate, heart rate variability, cardiac output, or a combination thereof.

15. The method of claim 14, wherein the heart rate variability is calculated over time periods of one minute, five minutes, ten minutes, half an hour, one hour, two hours, three hours, or four hours.

16. The method of claim 12 or 13, wherein pressurized air is applied to the user's airway through a tube and a mask connected to the breathing apparatus, 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.

17. The method of claim 12 or 13, wherein the sleep period includes a period in which pressurized air is applied to the user's airway.

18. The method of claim 12 or 13, wherein the detection of the one or more parameters is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more streaming signals, one or more audio signals, or combinations thereof.

19. A method comprising: Detect one or more parameters related to audio associated with the user during the user's sleep period; Process the one or more parameters to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. as well as The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disordered breathing events that occurred during the sleep period.

20. The method of claim 19, wherein the one or more events are one or more apneas, one or more hypoventilations, or a combination thereof.

21. The method of claim 19 or 20, wherein the audio is associated with: (1) one or more movements of the user, (2) one or more movements of a tube, mask, or combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof.

22. The method of claim 21, wherein the detection of one or more parameters relating to audio associated with 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 stream signals, one or more audio signals, or a combination thereof.

23. The method of claim 19 or 20, wherein the audio is detected based on one or more microphones within a tube, mask, or device connected to the tube and supplying pressurized air to the user's airway.

24. A method comprising: During sleep periods when pressurized air is applied to the user's airway, multiple parameters associated with the user are detected, each of which is associated with at least one modality and the multiple parameters cover multiple modalities; The multiple parameters are processed to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. as well as The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disorder events that occurred during the sleep period.

25. The method of claim 24, wherein the modality includes the user's movement, the flow of the pressurized air, the user's heart activity, and audio associated with the user.

26. The method of claim 25, wherein the one or more events include one or more apneas, one or more hypoventilations, or a combination thereof.

27. The method of any one of claims 24 to 26, wherein processing the plurality of parameters further comprises: It was determined that the user's sleep state could not be determined based on one or more of the parameters associated with the first modality of the plurality of modalities; as well as Process one or more of the plurality of parameters associated with a second modality of the plurality of modalities to determine the user’s sleep state.

28. The method of claim 27, wherein determining that the user's sleep state cannot be determined is based on a threshold-based metric that is satisfied.

29. The method of claim 28, wherein the threshold determination metric is based on two or more parameters among the plurality of parameters that conflict with sleep state, sleep stage, or a combination thereof.

30. The method of claim 29, wherein two or more conflicting parameters are derived from the plurality of modes.

31. The method of claim 29 or 30, wherein a conflict between two or more conflicting parameters is resolved by ignoring parameters derived from low-quality data and / or by giving increased weight to parameters extracted from higher-quality data.

32. The method of claim 31, wherein the threshold determination metric is based on a plurality of prior parameters associated with the user during one or more prior periods during which the pressurized air was applied to the user's airway.

33. The method of any one of claims 24 to 26, wherein the processing is performed by a sleep segmentation classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks.

34. The method of any one of claims 24 to 26, wherein processing of the plurality of parameters is based on a subset of the plurality of parameters from two or more selected modalities, the two or more selected modalities being chosen based on a weighted average of data quality.

35. A system comprising: One or more sensors are configured to detect one or more parameters relating to the user's movement during the user's sleep period; Memory, which stores machine-readable instructions; as well as 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 is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. as well as The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disordered breathing events that occurred during the sleep period.

36. The system of claim 35, wherein the one or more events are one or more apneas, one or more hypoventilations, or a combination thereof.

37. The system of claim 35 or 36, wherein one or more parameters relate to duration, period, rate, frequency, intensity, user movement type, or a combination thereof.

38. The system of claim 37, wherein the at least one sensor is placed on the user, placed near the user, or a combination thereof.

39. The system of claim 38, further comprising: A breathing device having a tube and a mask connected to the user. 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 on or inside the tube, on or inside the mask, or a combination thereof.

40. The system of claim 39, wherein the one or more sensors include motion sensors, the motion sensors being on or inside the tube, on or inside the mask, or a combination thereof.

41. The system of claim 35 or 36, wherein at least one of the one or more sensors comprises a motion sensor within a smart device.

42. The system of claim 41, wherein the smart device is one or more of the following: (1) a smartwatch, smart phone, smart mask, smart clothing, smart mattress, smart pillow, smart sheet or smart ring, each in contact with the user; (2) a smart speaker or smart TV, each in the vicinity of the user; (3) or a combination thereof.

43. The system of claim 35 or 36, wherein processing the one or more parameters includes processing a signal representing a change of at least one of the one or more parameters over time.

44. A system comprising: At least one sensor is configured to detect one or more parameters relating to the user’s cardiac activity during the user’s sleep period; Memory, which stores machine-readable instructions; as well as 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 is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. as well as The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disordered breathing events that occurred during the sleep period.

45. The system of claim 44, wherein the one or more events are one or more apneas, one or more hypoventilations, or a combination thereof.

46. ​​The system of claim 44 or 45, wherein one or more parameters are related to the user's heart rate, heart rate variability, cardiac output, or a combination thereof.

47. The system of claim 46, wherein the heart rate variability is calculated over time periods of one minute, five minutes, ten minutes, half an hour, one hour, two hours, three hours, or four hours.

48. The system of claim 44 or 45, further comprising: A breathing device having a tube and a mask connected to the user. 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 on or inside the tube, on or inside the mask, or a combination thereof.

49. The system of claim 48, wherein the at least one sensor is a microphone.

50. The system of claim 49, wherein the detection of the one or more parameters is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more stream signals, one or more audio signals, or combinations thereof detected by the microphone.

51. A system comprising: One or more sensors are configured to detect one or more parameters relating to audio associated with the user during the user's sleep period; Memory, which stores machine-readable instructions; and 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 is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. as well as The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disordered breathing events that occurred during the sleep period.

52. The system of claim 51, wherein the one or more events are one or more apneas, one or more hypoventilations, or a combination thereof.

53. The system of claim 51 or 52, further comprising: A breathing device having a tube and a mask connected to the user. 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, the breathing device being configured to apply pressurized air to the user, or (3) a combination thereof.

54. The system of claim 53, wherein the detection of one or more parameters relating to the audio associated with 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 stream signals, one or more audio signals, or a combination thereof.

55. The system of claim 51 or 52, further comprising: A breathing device having a tube and a mask connected to the user. The one or more sensors are one or more microphones within a tube, mask, or device connected to the tube and supplying pressurized air to the user's airway.

56. A system comprising: One or more sensors are configured to detect a plurality of parameters associated with the user during a sleep period in which pressurized air is applied to the user's airway, wherein each of the plurality of parameters is associated with at least one modality and the plurality of parameters cover multiple modalities; Memory, which stores machine-readable instructions; as well as The control system includes one or more processors configured to execute the machine-readable instructions, to: The multiple parameters are processed to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. as well as The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disorder events that occurred during the sleep period.

57. The system of claim 56, wherein the modality includes the user's movement, the flow of the pressurized air, the user's heart activity, and audio associated with the user.

58. The system of claim 56, wherein the one or more events include one or more apneas, one or more hypoventilations, or a combination thereof.

59. The system of any one of claims 56 to 58, wherein the control system is further configured to execute the machine-readable instructions to further process a plurality of parameters, to: Determining that the user's sleep state cannot be determined based on one or more of the parameters associated with a first modality among the plurality of modalities; and Process one or more of the plurality of parameters associated with a second modality of the plurality of modalities to determine the user’s sleep state.

60. The system of claim 59, wherein determining that the user's sleep state cannot be determined is based on a threshold-based metric that is satisfied.

61. The system of claim 60, wherein the threshold determination metric is based on two or more parameters among the plurality of parameters that conflict with sleep state, sleep stage, or a combination thereof.

62. The system of claim 61, wherein two or more conflicting parameters originate from the plurality of modes.

63. The system of claim 61 or 62, wherein a conflict between two or more conflicting parameters is resolved by ignoring parameters derived from low-quality data and / or by giving increased weight to parameters extracted from higher-quality data.

64. The system of claim 63, wherein the threshold determination metric is based on a plurality of prior parameters associated with the user during one or more prior periods during which the pressurized air was applied to the user's airway.

65. The system of any one of claims 56 to 58, wherein the processing is performed by a sleep segmentation classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks.

66. The system of any one of claims 56 to 58, wherein the sleep stage includes indications of non-rapid eye movement (NREM) sleep or rapid eye movement (REM) sleep.

67. The system of any one of claims 56 to 58, wherein the sleep stage includes indications of N1 sleep, N2 sleep, N3 sleep, or REM sleep.

68. The system of any one of claims 56 to 58, wherein the control system is further configured to execute the machine-readable instructions to process the plurality of parameters to determine the user's sleep state based on a subset of the plurality of parameters from two or more selected modalities, the two or more selected modalities being chosen based on a data quality-weighted average.

69. A method for calculating a user's apnea-hypopnea index, comprising: Detect one or more parameters related to the user's movement during the user's sleep period; Process the one or more parameters to determine the user's sleep state, which is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disordered breathing events that occurred during the sleep period. as well as The action is initiated at least in part based on the apnea-hypopnea index, sleep state, or a combination thereof.

70. The method of claim 69, wherein the sleep period includes a period in which pressurized air is applied to the user's airway.

71. The method of claim 69 or 70, wherein the sleep stage includes indications of N1 sleep, N2 sleep, N3 sleep, or REM sleep.

72. The method of claim 69 or 70, wherein the action includes one or more of the following: (1) saving a record of the apnea-hypopnea index, (b) transmitting the apnea-hypopnea index to an external device, or (c) adjusting the operating settings of the device.

73. The method of claim 72, wherein the device is a breathing device that supplies pressurized air to the user's airway.

74. The method of claim 69 or 70, wherein the one or more events are one or more apneas, one or more hypoventilations, one or more periodic limb movements, or a combination thereof.

75. The method of claim 69 or 70, wherein the one or more parameters relate to duration, period, rate, frequency, intensity, user movement type, or a combination thereof.

76. The method of claim 69 or 70, wherein the one or more parameters are measured based on one or more sensors placed on, near, or in combination thereof on the user.

77. The method of claim 76, wherein pressurized air is applied to the user's airway via a tube and a mask connected to the breathing apparatus, 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.

78. The method of claim 77, wherein the at least one sensor comprises a physical motion sensor, the physical motion sensor being on or inside the tube, on or inside the mask, or a combination thereof.

79. The method of claim 77, wherein at least one of the one or more sensors comprises a physical motion sensor within a smart device.

80. The method of claim 79, wherein the smart device is one or more of the following: (1) a smartwatch, smart phone, smart mask, smart clothing, smart mattress, smart pillow, smart sheet or smart ring, each in contact with the user; (2) a smart speaker or smart TV, each in the vicinity of the user; (3) or a combination thereof.

81. The method of claim 69 or 70, wherein processing the one or more parameters includes processing a signal representing a change of at least one of the one or more parameters over time.

82. The method of claim 69 or 70, wherein the user's movement is associated with the user's cardiac or respiratory activity.

83. The method of claim 82, wherein the at least one sensor is a microphone.

84. The method of claim 83, wherein the detection of the one or more parameters is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more streaming signals, one or more audio signals, or combinations thereof.

85. The method of claim 69, wherein the detection of the one or more parameters relates to audio associated with the user during the sleep period.

86. The method of claim 85, wherein the audio is associated with: (1) one or more movements of the user, (2) one or more movements of a tube, mask, or combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof.

87. The method of claim 85, wherein the detection of one or more parameters relating to audio is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more streaming signals, one or more audio signals, or combinations thereof.

88. The method of any one of claims 84 to 87, wherein the audio is detected based on one or more microphones within a tube, mask, or device connected to the tube and supplying pressurized air to the user's airway.

89. The method of claim 69 or 70, wherein each of the one or more parameters is associated with at least one modality, and the one or more parameters encompass multiple modalities including the user's movement, the flow of pressurized air, the user's cardiac activity, and audio associated with the user, and wherein processing the multiple parameters further comprises: It was determined that the user's sleep state could not be determined based on one or more of the parameters associated with the first modality of the plurality of modalities; as well as Process one or more of the plurality of parameters associated with a second modality of the plurality of modalities to determine the user’s sleep state.

90. The method of claim 89, wherein determining that the user's sleep state cannot be determined is based on a threshold-based metric that is satisfied.

91. The method of claim 90, wherein the threshold determination metric is based on two or more parameters among the plurality of parameters that conflict with the determined sleep state, sleep stage, or combination thereof.

92. The method of claim 91, wherein two or more conflicting parameters are derived from the plurality of modes.

93. The method of claim 91 or 92, wherein a conflict between two or more conflicting parameters is resolved by ignoring parameters derived from low-quality data and / or by giving increased weight to parameters extracted from higher-quality data.

94. The method of claim 90 or 91, wherein the threshold determination metric is based on a plurality of prior parameters associated with the user during one or more prior periods of applying pressurized air to the user's airway.

95. The method of claim 69 or 70, wherein each of the one or more parameters is associated with at least one modality, and the one or more parameters cover multiple modalities, and wherein processing of the multiple parameters is based on a subset of the multiple parameters from two or more selected modalities, the two or more selected modalities being chosen based on a weighted average of data quality.

96. The method of claim 69 or 70, wherein the processing is performed by a sleep segmentation classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks.

97. A system for calculating a user's apnea-hypopnea index, comprising: One or more sensors are configured to detect one or more parameters relating to the user's movement during the user's sleep period; Memory, which stores machine-readable instructions; as well as 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 is at least one of being awake, asleep, or in a sleep stage; Determine the occurrence of sleep-disordered breathing events during the said sleep period; In response to the sleep state being determined to be awake during one or more sleep-disordered breathing events, the one or more sleep-disordered breathing events are ignored. The apnea-hypopnea index of the user during the sleep period is calculated at least in part based on the residual sleep-disordered breathing events that occurred during the sleep period. as well as The action is initiated at least in part based on the apnea-hypopnea index, sleep state, or a combination thereof.

98. The system of claim 97, wherein the action includes one or more of the following: (1) saving a record of the apnea-hypopnea index, (b) transmitting the apnea-hypopnea index to an external device, or (c) adjusting the operating settings of the device.

99. The system of claim 98, wherein the device is a breathing device that supplies pressurized air to the user's airway.

100. The system of claim 97, wherein the one or more events are one or more apneas, one or more hypoventilations, one or more periodic limb movements, or a combination thereof.

101. The system of any one of claims 97 to 100, wherein the one or more parameters relate to duration, period, rate, frequency, intensity, user movement type, or a combination thereof.

102. The system of any one of claims 97 to 100, wherein the one or more sensors are placed on the user, placed near the user, or a combination thereof.

103. The system of claim 102, further comprising: A breathing device having a tube and a mask connected to the user. 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 on or inside the tube, on or inside the mask, or a combination thereof.

104. The system of any one of claims 97 to 100, wherein the one or more sensors include physical motion sensors, said physical motion sensors being on or within a tube, mask, or combination thereof.

105. The system of any one of claims 97 to 100, wherein at least one of the one or more sensors comprises a physical motion sensor within a smart device.

106. The system of claim 105, wherein the smart device is one or more of the following: (1) a smartwatch, smart phone, smart mask, smart clothing, smart mattress, smart pillow, smart sheet or smart ring, each in contact with the user; (2) a smart speaker or smart TV, each in the vicinity of the user; (3) or a combination thereof.

107. The system of any one of claims 97 to 100, wherein processing the one or more parameters includes processing a signal representing a change of at least one of the one or more parameters over time.

108. The system of any one of claims 97 to 100, wherein the user's movement is associated with the user's cardiac or respiratory activity.

109. The system of claim 108, wherein the at least one sensor is a microphone.

110. The system of claim 109, wherein the detection of the one or more parameters is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more stream signals, one or more audio signals, or combinations thereof detected by the microphone.

111. The system of claim 97, wherein the detection of the one or more parameters relates to audio associated with the user during the sleep period.

112. The system of claim 111, wherein the audio is associated with: (1) one or more movements of the user, (2) one or more movements of a tube, mask, or combination thereof connected to a breathing device configured to apply pressurized air to the user, or (3) a combination thereof.

113. The system of claim 111, wherein the detection of one or more parameters relating to the audio is based on cepstral analysis, spectral analysis, fast Fourier transform, or a combination thereof of one or more streaming signals, one or more audio signals, or combinations thereof.

114. The system of any one of claims 110 to 113, wherein the audio is detected based on one or more microphones within a tube, mask, or device connected to the tube and supplying pressurized air to the user's airway.

115. The system of any one of claims 97 to 100, wherein each of the one or more parameters is associated with at least one modality, and the one or more parameters cover multiple modalities including the user's movement, the flow of pressurized air, the user's cardiac activity, and audio associated with the user, and wherein the control system is configured to execute the machine-readable instructions to: Determining that the user's sleep state cannot be determined based on one or more of the parameters associated with a first modality among the plurality of modalities; and Process one or more of the plurality of parameters associated with a second modality of the plurality of modalities to determine the user’s sleep state.

116. The system of claim 115, wherein determining that the user's sleep state cannot be determined is based on a threshold-based metric that is satisfied.

117. The system of claim 116, wherein the threshold determination metric is based on two or more parameters among the plurality of parameters that conflict with the determined sleep state, sleep stage, or combination thereof.

118. The system of claim 117, wherein the two or more conflicting parameters are derived from the plurality of modes.

119. The system of claim 117 or claim 118, wherein a conflict between two or more conflicting parameters is resolved by ignoring parameters derived from low-quality data and / or by giving increased weight to parameters extracted from higher-quality data.

120. The system of claim 116, wherein the threshold determination metric is based on a plurality of prior parameters associated with the user during one or more prior periods of applying the pressurized air to the user's airway.

121. The system of any one of claims 97 to 100, wherein each of the one or more parameters is associated with at least one modality, and the one or more parameters cover multiple modalities, and wherein the control system is further configured to execute the machine-readable instructions to process the multiple parameters to determine the user's sleep state based on a subset of the multiple parameters from two or more selected modalities, the selected two or more modalities being selected according to a weighted average based on data quality.

122. The system of any one of claims 97 to 100, wherein the processing is performed by a sleep segmentation classifier based on one or more of supervised machine learning, deep learning, convolutional neural networks, or recurrent neural networks.

123. The system of any one of claims 97 to 100, wherein the sleep stage includes indications of non-rapid eye movement (NREM) sleep or rapid eye movement (REM) sleep.

124. The system of claim 123, wherein, The sleep stages include indicators of N1 sleep, N2 sleep, N3 sleep, or REM sleep.

125. A system comprising: A control system, which includes one or more processors; as well as Memory on which machine-readable instructions are stored; The control system is coupled to the memory, and when the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system, the method of any one of claims 1 to 34 and the method of any one of claims 69 to 96 are implemented.

126. A system comprising a control system configured to implement the method of any one of claims 1 to 34 and the method of any one of claims 69 to 96.

127. A computer program product comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 34 and the method of any one of claims 69 to 96.

128. The computer program product of claim 127, wherein the computer program product is a non-transient computer-readable medium.

Images