Systems and methods for detecting nozzle leaks

Abstract

This invention relates to a method for determining a mouth leak status associated with a user of a breathing apparatus. Airflow data associated with the user of the breathing apparatus is received. The breathing apparatus is configured to supply pressurized air to the user's airway during a treatment period. The airflow data includes pressure data. The airflow data associated with the user is analyzed. Based at least in part on the analysis, a mouth leak status associated with the user is determined. The mouth leak status indicates whether air is leaking from the user's mouth.

Description

[0001] Cross-reference to related applications

[0002] This application claims the benefit and priority of U.S. Provisional Patent Application No. 62 / 968,889, filed January 31, 2020, and U.S. Provisional Patent Application No. 63 / 198,137, filed September 30, 2020, each of which is incorporated herein by reference in its entirety. Technical Field

[0003] The present invention generally relates to systems and methods for determining the mouth leakage status of a user, and more specifically, to systems and methods for determining the mouth leakage status of a user based on sound and / or airflow data generated during the user's sleep period. Background Technology

[0004] Breathing not only provides our bodies with oxygen but also releases carbon dioxide and waste products. The nose and mouth form two air passages leading to our lungs and facilitate gas exchange. If their nasal airway is blocked (completely or partially), people will breathe through their mouths at night. Some people develop a habit of breathing through their mouths instead of their noses even after the nasal obstruction is cleared. For some people with sleep apnea, this may become a sleep habit, with their mouths open to accommodate their oxygen needs.

[0005] Furthermore, when sleep apnea patients begin CPAP therapy using a nasal mask or nasal pillow, they may inadvertently breathe through their mouth (“mouth leak”). For example, when the pressure difference between the mouth and atmospheric pressure exceeds a threshold, the mouth (e.g., the lips) may suddenly open to normalize the pressure. The lips may close again upon inhalation. This may not wake the patient, but when they do, it can cause dry mouth, dry lips, and discomfort. Some patients cannot tolerate this for long and are likely to discontinue their required treatment. Therefore, it is necessary to detect and / or monitor patients experiencing mouth leaks during respiratory therapy.

[0006] This invention aims to solve these problems, as well as other problems. Summary of the Invention

[0007] According to some implementations of the invention, a system includes a memory storing machine-readable instructions and a control system including one or more processors. The control system is configured to execute the machine-readable instructions to: receive first acoustic data associated with a user of a breathing device from a microphone; analyze the first acoustic data associated with the user; and determine a mouth leak status based at least in part on the analysis of the first acoustic data. The breathing device is configured to supply pressurized air to the user's airway during sleep periods. The mouth leak status indicates air leakage from the user's mouth.

[0008] According to some implementations of the present invention, a system includes: a memory storing machine-readable instructions and a control system including one or more processors. The control system is configured to execute the machine-readable instructions to: receive acoustic data associated with a user of a breathing device from a microphone; and process the acoustic data using a machine learning algorithm to output a mouth leak status for the user. The breathing device is configured to supply pressurized air to the user's airway during sleep periods. The mouth leak status indicates air leakage from the user's mouth.

[0009] According to some implementations of the invention, a system includes a memory storing machine-readable instructions and a control system including one or more processors. The control system is configured to execute the machine-readable instructions to: receive acoustic data associated with a user of a breathing device from a microphone during multiple sleep periods; receive pressure data associated with pressurized air supplied to the user's airway during the multiple sleep periods; analyze the acoustic data to determine the user's mouth leak status for each of the multiple sleep periods; and determine the user's optimal inspiratory pressure and optimal expiratory pressure based at least in part on (i) the user's mouth leak status during each of the multiple sleep periods and (ii) the pressure data. The microphone is associated with a user of the breathing device. The breathing device is configured to supply pressurized air to the user's airway. The acoustic data includes inhalation acoustic data and exhalation acoustic data. The pressure data includes inhalation pressure data and expiratory pressure data. The mouth leak status indicates air leakage from the user's mouth.

[0010] According to some implementations of the present invention, a system includes: a memory storing machine-readable instructions and a control system including one or more processors. The control system is configured to execute the machine-readable instructions to: receive acoustic data associated with a user from a microphone during a plurality of sleep periods; receive physiological data associated with the user from a sensor for each of the plurality of sleep periods; analyze the acoustic data to determine the user's mouth leak status for each of the plurality of sleep periods; and train a machine learning algorithm using (i) the user's mouth leak status for each of the plurality of sleep periods and (ii) the physiological data, such that the machine learning algorithm is configured to: receive current physiological data associated with the current sleep period as input; and determine an estimated mouth leak status for the current sleep period as output. The microphone is associated with a user of a breathing device. The breathing device is configured to supply pressurized air to the user's airway. The mouth leak status indicates air leakage from the user's mouth.

[0011] According to some implementations of the present invention, a method for determining a mouth leak state associated with a user of a breathing apparatus is disclosed. Airflow data associated with the user of the breathing apparatus is received. The breathing apparatus is configured to supply pressurized air to the user's airway during treatment. The airflow data includes pressure data. The airflow data associated with the user is analyzed. Based at least in part on the analysis, a mouth leak state associated with the user is determined. The mouth leak state indicates whether air is leaking from the user's mouth.

[0012] According to some implementations of the present invention, a system includes: a control system having one or more processors, and a memory storing machine-readable instructions thereon. The control system is coupled to the memory. When the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system, any of the methods disclosed above and further described herein are implemented.

[0013] According to some implementations of the invention, a system for determining a mouth leakage state associated with a user of a breathing apparatus includes a control system having one or more processors configured to implement any of the methods disclosed above and further described herein.

[0014] According to some implementations of the present invention, a computer program product includes instructions that, when executed by a computer, cause the computer to perform any of the methods disclosed above and further described herein. In some implementations, the computer program product is a non-transitory computer-readable medium.

[0015] The above overview is not intended to represent every implementation or aspect of the invention. Additional features and advantages of the invention will become apparent from the detailed description and accompanying drawings. Attached Figure Description

[0016] Figure 1 This is a functional block diagram of a system for determining the status of a user's leak nozzle according to some implementations of the present invention;

[0017] Figure 2A This is according to some implementations of the present invention. Figure 1 A perspective view of at least a portion of the system, the user wearing a full-face mask, and their bed partner;

[0018] Figure 2B 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 the nasal mask, and the bed partner;

[0019] Figure 3 This is a flowchart of a method for determining a user's mouth leakage status according to some implementations of the present invention;

[0020] Figure 4A A visual indicator for assessing mouth leakage of a user on a display device according to some implementations of the present invention is described;

[0021] Figure 4B Visual indicators illustrating messages associated with the user's mouth leakage status on a display device according to some implementations of the present invention;

[0022] Figure 4C This describes a user interface on a display device for receiving user feedback from a user, according to some implementations of the present invention.

[0023] Figure 5 This is a flowchart of a method for determining the optimal inhalation pressure and optimal expiratory pressure for a user according to some implementations of the present invention.

[0024] Figure 6 This is a flowchart of a method for estimating mouth leakage status for a user using a machine learning algorithm according to some implementations of the present invention;

[0025] Figure 7 This is a process flowchart of a method for determining the mouth leakage status associated with a user of a breathing device, according to some implementations of the present invention.

[0026] Figure 8 The invention describes a first breath when the user breathes normally and a second breath when the user exhales through the mouth, according to some implementations of the invention.

[0027] Figure 9 This describes several features identified during the respiratory cycle according to some implementations of the present invention;

[0028] Figure 10A Laboratory data measured during a user's treatment period according to some implementations of the present invention are described, showing valve-type mouthpiece leakage, mask leakage, and continuous mouthpiece leakage;

[0029] Figure 10B This describes a user's method for displaying valve-type nozzle leakage according to some implementations of the present invention. Figure 10A Part of the laboratory data;

[0030] Figure 10C This describes the user's experience with display mask leakage according to some implementations of the present invention. Figure 10A Part of the laboratory data;

[0031] Figure 10D This invention illustrates a user's method for displaying continuous nozzle leakage according to some implementations of the present invention. Figure 10A Part of the laboratory data;

[0032] Figure 11 Histograms of multiple epochs of mouth leakage based on the level of unintentional leakage according to some implementations of the present invention are illustrated.

[0033] Figure 12A This describes the actual mouth leakage duration according to some implementations of the present invention;

[0034] Figure 12B This describes the prediction of mouth leakage duration according to some implementations of the present invention;

[0035] Figure 13 This invention illustrates the ratio of mouth leakage to the duration of blockage, according to some implementations thereof;

[0036] Figure 14 This invention illustrates the signed covariance between unintentional leakage and ventilation for determining mouth leakage according to some implementations of the invention;

[0037] Figure 15 This invention illustrates the characteristic separation of ventilation at the level of unintentional leakage according to some implementations of the invention;

[0038] Figure 16A This describes, according to some implementations of the present invention, multiple negative periods and multiple positive periods for each user before normalization;

[0039] Figure 16B This describes, according to some implementations of the present invention, multiple negative periods and multiple positive periods for each user after normalization;

[0040] Figure 17 This describes the separation of unintentional leakage variability characteristics according to some implementations of the present invention;

[0041] Figure 18A This invention illustrates exemplary variations of unintentional leakage for high levels of unintentional leakage in users with mouth leaks, according to some implementations of the invention.

[0042] Figure 18B This invention illustrates exemplary variations of unintentional leakage for high levels of unintentional leakage in users who do not have mouth leakage, according to some implementations of the invention;

[0043] Figure 19 This invention describes respiratory segmentation based on flow data according to some implementations of the present invention;

[0044] Figure 20A This describes specific respiratory characteristics calculated based on some implementations of the present invention;

[0045] Figure 20B Additional respiratory-specific features calculated on a portion of the respiration according to some implementations of the present invention are described;

[0046] Figure 21 This describes the 90th percentile epoch according to some implementations of the present invention. th The ratio of breathing area to frame area in the flow data (percentile);

[0047] Figure 22 This describes the skewness applied to flow data based on period averages according to some implementations of the present invention;

[0048] Figure 23 This describes the skewness of the time-averaged value for the derivative blower pressure according to some implementations of the present invention;

[0049] Figure 24A This refers to the sound power levels during periods of no mask leakage and periods of mask leakage, according to some implementations of the present invention.

[0050] Figure 24B According to some implementations of the present invention Figure 24A A comparative graphical representation of leakage rate, flow rate, and mask pressure during the periods of no mask leakage and mask leakage.

[0051] Figure 25 A comparative graphical representation of the maximum sound intensity, standard deviation of sound intensity, leakage rate, flow rate, and mask pressure over a time period is provided according to some implementations of the present invention.

[0052] Figure 26A The sound power levels during the time periods in which different types of leakage occur, according to some implementations of the present invention; and

[0053] Figure 26B According to some implementations of the present invention Figure 26A A graph comparing leakage rate, flow rate, and mask pressure over a given time period.

[0054] While the invention is susceptible to various modifications and alternatives, 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 alternatives falling within the spirit and scope of the invention as defined by the appended claims. Detailed Implementation

[0055] Normally, healthy individuals breathe through their nose during sleep. Chronic mouth breathing can lead to increased congestion, dry mouth, bad breath, gingivitis, discomfort, and / or potential nosebleeds.

[0056] There are many reasons why someone might breathe through their mouth. If someone's nasal airway is blocked (completely or partially blocked) due to allergies, a cold, or a sinus infection, they may breathe through their mouth at night. Some people are prone to having a blocked nasal airway, which can be caused by enlarged adenoids, enlarged tonsils, a deviated septum, nasal polyps, or benign growths in the nasal lining. Additionally, enlarged turbinate bones, the shape of the nose, and the shape and size of the jaw can contribute to a blocked nasal airway.

[0057] Sleep apnea patients often also have obstructed airways. For some people with sleep apnea, it may become a sleep habit to keep their mouths open to accommodate their oxygen needs. In some cases, when sleep apnea patients begin CPAP therapy using a nasal mask or nasal pillow, they may inadvertently breathe through their mouths (“mouth leak”). For example, when the pressure difference between the mouth and atmospheric pressure exceeds a threshold, the mouth (e.g., the lips) may suddenly open to normalize the pressure. The lips may close again upon inhalation. This may not wake the patient, but when they do, it can cause dry mouth, dry lips, and discomfort. Some patients cannot tolerate this condition for long and are likely to discontinue their required treatment.

[0058] Some sleep apnea patients may experience continuous mouth leakage for at least part of the night, where their mouth remains open and a continuous loop is formed (air enters through the nasal mask and exits through the mouth). Some patients tolerate continuous mouth leakage—even up to 70% of the night—but they are unlikely to adhere to treatment long-term and / or may only wear their mask earlier in the night (when the patient is in deep sleep rather than REM sleep). Therefore, mouth leakage may reduce the effectiveness and / or comfort of treatment for sleep apnea patients, which in turn leads to poorer outcomes and / or treatment adherence.

[0059] Therefore, there is a need for a system capable of detecting whether a user is breathing through their mouth, adjusting appropriate settings on related devices, and / or providing notifications to the user. This invention relates to such a system.

[0060] Reference Figure 1 The present invention describes a system 100 according to some implementations thereof. System 100 includes a control system 110, a memory device 114, an electronic interface 119, one or more sensors 130, and one or more user devices 170. In some implementations, system 100 further includes a respiratory system 120.

[0061] Control system 110 includes one or more processors 112 (hereinafter, processor 112). Control system 110 is typically used to control various components of system 100 and / or analyze data acquired and / or generated by the components of system 100. Processor 112 may be a general-purpose or special-purpose processor or a microprocessor. Although in Figure 1 The diagram shows a processor 112, 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, a portion of the breathing system 120 (e.g., a housing), and / or the housing of 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, these housings may be positioned close to and / or far from each other.

[0062] Memory device 114 stores machine-readable instructions executable by processor 112 of control system 110. 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 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).

[0063] In some implementations, memory device 114 ( Figure 1The system stores user profiles associated with each user. User profiles may include, for example, user-associated demographic information, user-associated biostatistics, user-associated medical information, self-reported user feedback, user-associated sleep parameters (e.g., sleep-related parameters recorded from one or more earlier sleep periods), or any combination thereof. Demographic information may include, for example, information indicating the user's age, gender, ethnicity, geographic location, relationship status, family history of insomnia, employment status, user identity, education, socioeconomic status, or any combination thereof. Medical information may include, for example, information indicating one or more medical conditions associated with the 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. Self-reported user feedback may include information indicating self-reported subjective treatment ratings (e.g., poor, average, excellent), user's self-reported subjective stress levels, user's self-reported subjective fatigue levels, user's self-reported subjective health status, recent life events experienced by the user, or any combination thereof.

[0064] Electronic interface 119 is configured to receive data (e.g., physiological data and / or audio data) 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. Electronic interface 119 can communicate with one or more sensors 130 using wired or wireless connections (e.g., using RF communication protocols, Wi-Fi communication protocols, Bluetooth communication protocols, via cellular networks, etc.). Electronic interface 119 may include an antenna, a receiver (e.g., an RF receiver), a transmitter (e.g., an RF transmitter), a 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, electronic interface 119 is coupled to or integrated with control system 110 and / or memory device 114 (e.g., within a housing).

[0065] As described above, in some embodiments, system 100 may include a respiratory system 120 (also referred to as a respiratory therapy system). The respiratory system 120 may include a respiratory pressure therapy (RPT) device 122 (also referred to herein as a breathing device 122), a user interface 124, a catheter 126 (also referred to herein as a tube or air circuit), a display device 128, a humidifier canister 129, 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 canister 129 are part of the breathing device 122. Respiratory pressure therapy refers to supplying air to the user's airway inlet at a controlled target pressure that is nominally positive relative to atmosphere throughout the user's respiratory cycle (e.g., the opposite of negative pressure therapy with a canister ventilator or tubing ventilator). The respiratory system 120 is 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).

[0066] 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).

[0067] 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 also increases 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. Pressurized air also increases the user's oxygen intake during sleep.

[0068] 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.

[0069] like Figure 2A As shown, in some implementations, user interface 124 is a mask (e.g., a full-face mask) that covers the user's nose and mouth. Alternatively, as... Figure 2B As shown, user interface 124 is a nasal mask that delivers air to a user's nose or a nasal pillow that delivers air directly to a user's nostrils. 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 user interface 124 and the user. 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 may include a mouthpiece (e.g., a night-protective mouthpiece molded to conform to the user's teeth, a jaw repositioning device, etc.).

[0070] The conduit 126 (also referred to as an air circuit or tube) allows air to flow between two components of the respiratory 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.

[0071] 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, or any other sensor 130 described more generally herein). 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.

[0072] 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)). TMRatings, such as those described in WO 2016 / 061629 (which is incorporated herein by reference in its 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.

[0073] 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 delivered 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 delivered 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.

[0074] 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 temporal 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) combinations of (i) to (vi).

[0075] Modifying the temporal characteristics of the delivery of a portion of the substance entering the air channel can include changing the delivery rate, starting and / or ending at different times, lasting for different periods, altering 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 changed. 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.

[0076] The respiratory system 120 can be used as a ventilator or a positive airway pressure (PAP) system, such as a continuous positive airway pressure (CPAP) system, an 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 associated with the user. A BPAP or VPAP system is configured to deliver a first predetermined pressure (e.g., inspiratory positive airway pressure or IPAP) and a second predetermined pressure lower than the first predetermined pressure (e.g., expiratory positive airway pressure or EPAP).

[0077] Still referencing Figure 1 The 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, a radio frequency (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, a lidar sensor 178, or any combination thereof. Typically, each of the one or more sensors 130 is configured to output sensor data received and stored in a memory device 114 or one or more other memory devices.

[0078] 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 sensor 178, more generally, one or more sensors 130 may include combinations and any number of each of the sensors described and / or shown herein.

[0079] As described herein, system 100 can typically be used to generate information with the user (e.g., during sleep periods) Figure 2A-2B Physiological data associated with the user (shown in the respiratory system 120). Physiological data can be analyzed to generate one or more sleep-related parameters, which may include any parameters, measurements, etc., related to the user during sleep periods. One or more sleep-related parameters may be determined for the user 210 during sleep periods, including, for example, apnea-hypopnea index (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 the 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.

[0080] One or more sensors 130 may be used to generate, for example, physiological data, audio data, or both. The control system 110 may use the physiological data generated by the one or more sensors 130 to determine sleep-wake signals and one or more sleep-related parameters associated with the user 210 during sleep periods. Sleep-wake signals may indicate one or more sleep states and / or one or more sleep stages, including wakefulness, relaxed wakefulness, micro-wakefulness, rapid eye movement (REM) stage, first non-REM stage (commonly referred to as "N1"), second non-REM stage (commonly referred to as "N2"), third non-REM stage (commonly referred to as "N3"), or any combination thereof.

[0081] The sleep-wake signal can also be timestamped to determine the time when the user enters the bed, the time when the user leaves the bed, the time when 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. Events can include snoring, sleep apnea, central sleep apnea, obstructive sleep apnea, mixed sleep apnea, hypoventilation, mask leakage (e.g., from user interface 124), restless legs, sleep disturbance, choking, increased heart rate, difficulty breathing, asthma attack, seizure, epilepsy, or any combination thereof. One or more sleep-related parameters that can be determined for a user during a sleep period based on sleep-wake signals include, for example, 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.

[0082] Physiological and / or audio data generated by one or more sensors 130 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 may include snoring, sleep apnea, central sleep apnea, obstructive sleep apnea, mixed sleep apnea, hypopnea, mask leakage (e.g., from user interface 124), restless legs, sleep disturbance, apnea, increased heart rate, difficulty breathing, asthma attack, seizure, epilepsy, or any combination thereof.

[0083] 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 has turned on the breathing apparatus 122 and put on the user interface 124. A sleep period can therefore include time intervals (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 is still 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 up between light sleep, deep sleep, or REM sleep; or (vii) when the user 210 wakes up without falling back asleep.

[0084] A sleep period is typically defined as ending once user 210 removes user interface 124, shuts off breathing apparatus 122, and leaves bed 230. In some implementations, the 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.

[0085] 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 system 120. In such implementations, pressure sensor 132 can be coupled to or integrated into respiratory device 122. Pressure sensor 132 can be, for example, a capacitive sensor, an electromagnetic sensor, a piezoelectric sensor, a strain gauge sensor, an optical sensor, a potentiometric sensor, or any combination thereof. In one example, pressure sensor 132 can be used to determine the user's blood pressure.

[0086] The flow sensor 134 outputs flow data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some implementations, the flow sensor 134 is used to determine the airflow rate from the breathing apparatus 122, the airflow rate through the duct 126, the airflow rate 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.

[0087] 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 2A-2B Temperature data may include the user's core body temperature, the user's skin temperature, the temperature of the air flowing from the breathing apparatus 122 and / or through the conduit 126, the temperature in the user interface 124, the 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.

[0088] 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 movement of any component of respiratory system 120, such as breathing apparatus 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 may alternatively or additionally generate one or more signals representing the user's body movements, from which signals representing the user's sleep state can be obtained; for example, through the user's breathing movements. In some implementations, motion data from motion sensor 138 may be combined with additional data from another sensor 130 to determine the user's sleep state.

[0089] The output of microphone 140 can be stored in memory device 114 and / or analyzed by processor 112 of control system 110. The audio data generated by microphone 140 can be reproduced as one or more sounds (e.g., sounds from user 210) during sleep periods. The audio data from microphone 140 can also be used to identify (e.g., using control system 110) events experienced by the user during sleep periods, as described further in detail herein. Microphone 140 can be coupled to or integrated into breathing apparatus 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.

[0090] The speaker 142 outputs to the user of the system 100 (e.g., Figure 2A-2B The speaker 142 can be used as, for example, an alarm clock or to play alarms or messages to the user 210 (e.g., in response to an event). In some implementations, the speaker 142 can be used to transmit audio data generated by the microphone 140 to the user. The speaker 142 can be coupled to or integrated into the breathing device 122, the user interface 124, the conduit 126, or the external device 170.

[0091] 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, as described, for example, in WO2018 / 050913 and WO 2020 / 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 2A-2B Based at least in part on data from microphone 140 and / or speaker 142, control system 110 can determine user 210 ( Figure 2A-2BThe location of the breathing device 122 and / or one or more of the sleep-related parameters described herein (e.g., mouth leak status), such as respiratory signal, 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.

[0092] In some implementations, 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.

[0093] 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 2A-2B The location of the device 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. While 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. In some such implementations, the RF sensor 147 includes control circuitry. The specific format of the RF communication can be Wi-Fi, Bluetooth, etc.

[0094] 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 variations in the Wi-Fi signals between the routers and satellites (e.g., differences in received signal strength), said variations being 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.

[0095] 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. The 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, the image data from camera 150 can be used, for example, to identify the user's location, determine chest movement of user 210, determine airflow through user 210's mouth and / or nose, determine the time user 210 enters bed 230, and determine the time user 210 leaves bed 230.

[0096] 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 380 nm and about 740 nm.

[0097] PPG sensor 154 output and user 210 ( Figure 2A-2BThe associated physiological data can be used to determine one or more sleep-related parameters, such as heart rate, 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.).

[0098] ECG sensor 156 outputs physiological data correlated with the electrical activity of the user 210's heart. Figure 2A-2B In some implementations, the ECG sensor 156 includes one or more electrodes located above or around a portion of the user 210 during sleep periods. Physiological data from the ECG sensor 156 can be used, for example, to determine one or more of the sleep-related parameters described herein.

[0099] EEG sensor 158 outputs physiological data associated with the electrical activity of the user 210's brain. In some implementations, 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 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.).

[0100] 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 skin conductance 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.

[0101] 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 implementations, analyte sensor 174 is located 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 of user 210. 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 this implementation, 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 processor 112 can use that data as an indication that user 210 is breathing through their mouth.

[0102] 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.

[0103] The optical detection and ranging (LiDAR) sensor 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 an example using this sensor, a fixed or mobile device (such as a smartphone) with LiDAR sensor 166 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.

[0104] 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 rain sensor, a soil moisture sensor, a water flow sensor, an alcohol sensor, or any combination thereof.

[0105] Although Figure 1 While shown separately, combinations 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 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.).

[0106] 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, apnea-hypopnea index (AHI), or any combination thereof. One or more events may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, mask leakage, coughing, restless legs, sleep disturbance, apnea, increased heart rate, 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. 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.

[0107] User equipment 170 ( Figure 1 The system includes a display device 128. The user device 170 may be, for example, a mobile device such as a smartphone, tablet, game console, smartwatch, laptop, etc. Alternatively, the user device 170 may be an external sensing system, a television (e.g., a smart TV), or another smart home device (e.g., 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). The display device 172 is typically used to display images including still images, video images, or both. In some implementations, the display device 172 acts as a human-machine interface (HMI) including a graphical user interface (GUI) configured to display images and provide input interfaces. The display device 172 may be an LED display, OLED display, 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 user device 170. In some implementations, the system 100 may use and / or include one or more user devices.

[0108] Although the control system 110 and the memory device 114 are in Figure 1While 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).

[0109] Although system 100 is shown as including all of the components described above, according to embodiments of the invention, a system for generating physiological data and determining a recommended bedtime for a user may include more or fewer components. For example, a first alternative system includes a control system 110, a storage 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 storage device 114, at least one of one or more sensors 130, and a user device 170. As yet another example, a third alternative system includes a control system 110, a storage device 114, a respiratory system 120, at least one of one or more sensors 130, and a user device 170. Therefore, various systems for determining a recommended bedtime for a user can be formed using any part or multiple parts of the components shown and described herein and / or in combination with one or more other components.

[0110] Typically, users designated to use the respiratory system 120 tend to experience higher quality sleep and less fatigue throughout the day following use, especially when the user has sleep apnea or other sleep-related conditions. However, many users do not adhere to the prescribed usage due to discomfort or inconvenience with the user interface 124, or due to other side effects such as dry mouth, dry lips, dry throat, discomfort, etc. If users fail to perceive any benefits they are experiencing (e.g., less fatigue during the day), they are more likely to fail to use the respiratory system 120 as prescribed (or discontinue use altogether).

[0111] However, side effects and / or lack of improvement in sleep quality may be due to mouth leakage rather than a lack of therapeutic efficacy. Therefore, it is beneficial to identify the user's mouth leakage status and communicate this status to the user to help them achieve higher quality sleep, so that the user does not discontinue or reduce their use of the respiratory system 120 due to a perceived lack of benefit.

[0112] Generally refer to Figure 2A-2B The system 100 is shown according to some implementation methods. Figure 1Part of the respiratory system 120. The user 210 and bed partner 220 are located in the bed 230 and lying on the mattress 232. User interface 124 (e.g., Figure 2A Full face mask or Figure 2B The nasal mask (as described) can be worn by user 210 during sleep. User interface 124 is fluidly connected and / or connected 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 as follows: Figure 2A 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.

[0113] In some implementations, the control system 110, memory 214, any one or more sensors 130, or any combination thereof, may be located on and / or in any surface and / or structure typically adjacent to bed 230 and / or user 210. For example, in some implementations, at least one of the one or more sensors 130 may be located on and / or in one or more components of the respiratory system 120 adjacent to a first position 255A of bed 230 and / or user 210. The one or more sensors 130 may be coupled to the respiratory system 120, user interface 124, catheter 126, display device 128, humidifier 129, or any combination thereof.

[0114] Alternatively or additionally, at least one of the one or more sensors 130 may be located at a second position 255B on and / or within the bed 230 (e.g., one or more sensors 130 are coupled to and / or integrated into the bed 230). Furthermore, alternatively or additionally, at least one of the one or more sensors 130 may be located at a third position 255C on and / or within the mattress 232, adjacent to the bed 230 and / or the user 210 (e.g., one or more sensors 130 are coupled to and / or integrated into the mattress 232). Alternatively or additionally, at least one of the one or more sensors 130 may be located at a fourth position 255D on and / or within a pillow, generally adjacent to the bed 230 and / or the user 210.

[0115] Alternatively or additionally, at least one of the one or more sensors 130 may be positioned at a fifth position 255E on and / or within the bed seat 240, generally adjacent to the bed 230 and / or the user 210. Alternatively or additionally, at least one of the one or more sensors 130 may be positioned at a sixth position 255F, such that at least one of the one or more sensors 130 is coupled to and / or positioned on the user 215 (e.g., one or more sensors 130 are embedded in or coupled to fabric, clothing 212, and / or a smart device 270 worn by the user 210). More generally, at least one of the one or more sensors 130 may be positioned relative to the user 210 at any suitable location, such that the one or more sensors 130 can generate sensor data associated with the user 210.

[0116] In some implementations, a master sensor, such as microphone 140, is configured to generate acoustic data associated with user 210 during sleep periods. For example, one or more microphones (with...) Figure 1 The microphone (identical or similar to microphone 140) may be integrated into and / or coupled to (i) the circuit board of the breathing apparatus 122, (ii) the conduit 126, (iii) the connector between components of the breathing system 120, (iv) the user interface 124, (v) a headband (e.g., a strap) associated with the user interface, or (vi) any combination thereof. In some implementations, the microphone is in fluid and / or acoustic communication with an airflow passage (e.g., an air passage fluidly connected to the user's airway). For example, in some implementations, the microphone is located on a printed circuit board connected to the airflow passage via a conduit.

[0117] Additional or alternative, one or more microphones (with) Figure 1 The microphone 140 (same as or similar to the microphone 140) can be integrated into and / or connected to a co-location smart device, such as a user device 170, TV, watch (e.g., a mechanical watch or smart device 270), pendant, mattress 232, bed 230, bedding located on bed 230, pillow, speaker (e.g., Figure 1 The speaker 142), radio, tablet computer, waterless humidifier, or any combination thereof.

[0118] Additionally or alternatively, in some implementations, one or more microphones (with) Figure 1 The microphone 140 (same or similar) can be located away from system 100. Figure 1 ) and / or User 210 ( Figure 2A-2B This applies as long as there is an air passage that allows sound signals to propagate to one or more microphones. For example, one or more microphones may be in a different room than the room containing system 100.

[0119] Mouth leak status can be determined, at least in part, based on the analysis of acoustic data. Mouth leak status indicates air leakage from the user's mouth (e.g., mouth leak as described herein). Additionally, in some implementations, determining mouth leak status includes distinguishing mouth leak from mask leak. In some implementations, the method 300 of the present invention is used. Figure 3 ), 500 ( Figure 5 ) and 600 ( Figure 6 One or more steps are used to determine the mouth leakage status.

[0120] refer to Figure 3 This illustrates a method 300 for determining the state of a user's mouth leak. One or more steps of method 300 can be used with the system 100 described herein. Figure 1 and 2A -2B) can be implemented by any element or aspect.

[0121] Step 310 of method 300 includes generating or acquiring acoustic data associated with the user during at least a portion of a sleep period. For example, step 310 may include using one or more sensors 130 during the sleep period. Figure 1 At least one of the following is used to generate or obtain acoustic data: (e.g., microphone 140 described above). In some implementations, one or more microphones (such as microphone 140 described above) are used to generate acoustic data. In some implementations, at least one of the one or more microphones is coupled to or integrated into user interface 124. Additionally or alternatively, in some implementations, an external microphone that is not a component of system 100 is used to generate acoustic data. In some implementations, a microphone coupled to or integrated into respiratory system 120 is used to generate acoustic data. Figure 1 The acoustic sensor 141 and / or RF sensor 147 described above are used to generate acoustic data. Information describing the acoustic data generated or acquired during step 310 can be stored in memory device 114. Figure 1 )middle.

[0122] Step 310 may include generating acoustic data (via a primary sensor such as microphone 140) during a segment of a sleep period, throughout the entire sleep period, or across multiple segments of a first sleep period. For example, step 310 may include generating acoustic data continuously, or based solely on auxiliary sensor data generated by secondary auxiliary sensors. For example, a temperature sensor (e.g., temperature sensor 136) and / or an analyte sensor (e.g., analyte sensor 174) may be placed close to the user's mouth to directly detect mouth breathing.

[0123] In some implementations, in addition to the main sensor, one or more auxiliary sensors may be used to confirm the nozzle leak status. In some such implementations, the one or more auxiliary sensors include: a flow sensor (e.g., flow sensor 134 of system 100), a temperature sensor (e.g., temperature sensor 136 of system 100), a camera (e.g., camera 150 of system 100), a vane sensor (VAF), a hot filament sensor (MAF), a cold filament, a laminar flow sensor, an ultrasonic sensor, an inertial sensor, or any combination thereof.

[0124] Flow sensor 134 can be used to generate a flow rate during sleep in relation to user 210 of breathing device 122. Figure 2A-2B The associated flow data (in the form of flow data). An example of a flow sensor (e.g., flow sensor 134) is described in International Publication No. WO 2012 / 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, the flow data can be analyzed to determine the user’s cardiogenic oscillation.

[0125] Camera 150 can be used to generate image data associated with a user during sleep periods. As described herein, the camera can be configured to detect facial anatomy (e.g., the shape (e.g., open, partially open, or closed) and / or size of the mouth and nostrils), respiratory signals, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, number of events per hour, pattern of events, sleep state, sleep stage, or any combination thereof.

[0126] Therefore, in some implementations, step 310 of method 300 further includes generating or acquiring physiological data associated with the user during the sleep period. For example, step 310 may include using one or more sensors 130 during the sleep period. Figure 1 At least one of the following can be used to generate or obtain physiological data: Information describing the physiological data generated during step 310 can be stored in memory device 114. Figure 1 )middle.

[0127] In some implementations, a single sensor can generate both acoustic and physiological data. Alternatively, acoustic data can be generated using a first sensor in sensor 130, and physiological data can be generated using a second sensor in sensor 130 that is separate from and different from the first sensor. In some implementations, the first and second sensors can be sensors of different types (e.g., the first sensor is the same as or similar to microphone 140, and the second sensor is the same as or similar to motion sensor 138). Alternatively, in some implementations, the first and second sensors can be two identical sensors (e.g., two microphones the same as or similar to microphone 140). For example, in some implementations, the first microphone is an integrated microphone coupled to a catheter of a breathing apparatus. The second microphone is an external microphone.

[0128] Step 320 of method 300 includes analyzing acoustic data associated with the user. Control system 110 may analyze the acoustic data stored in storage device 114 to determine the mouth leakage state. In some implementations, to analyze the acoustic data (step 310), the acoustic data is compared with predetermined data indicating a negative mouth leakage state. The predetermined data may include analog data, historical data, or both.

[0129] For example, in some implementations, acoustic data indicating intentional leakage of the mask can be estimated for any given mask. The type of mask can be identified using, for example, cepstral analysis as described herein. The acoustic data measured by microphone 140 is compared to the estimated intentional leakage. If the breathing system is a closed system (e.g., no mouth leakage), a reasonable match should be made. However, if the system is “open” due to, for example, a mouth leakage, the acoustic data deviates (above a predetermined threshold) from the estimated intentional leakage.

[0130] In some implementations, the acoustic data (step 310) includes reflected sound waves received by a microphone (e.g., microphone 140 of system 100) and transmitted from a speaker (e.g., speaker 142 of system 100, or an external speaker). The reflected sound waves represent the shape and size of the components in the sound wave path. Additionally or alternatively, the acoustic data includes sounds from the user indicating one or more sleep-related parameters (e.g., breathing through the nose, breathing through the mouth, snoring, sniffing).

[0131] For example, acoustic data (step 310) may include data generated by microphone 140. Speaker 142 generates sound. The sound can travel through humidifier canister 129, along a first connection, along conduit 126, via a second connection, via a waterless humidifier (if assembled), to one or more mask cavities (e.g., nostrils and / or mouth), and to the user's respiratory system (including nose and / or mouth, airways, lungs, etc.). For each change in the path (e.g., changes in cavity, knot, shape), a sound velocity-based reflection is seen at that point. Different types and distances of reflection can be used to define the type and / or model of user interface 124.

[0132] Further reflections can be used to define aspects of the user's respiratory system, including whether one or both nostrils are used, and / or whether the user breathes through their mouth. These reflections change as the user inhales and exhales, and further change during exhalation if the mouth is open. In some implementations, a reduction in the mask cavity response can be seen in the reflections when a mouth leak occurs. For example, if the user has a mouth leak, the expected echo signal (e.g., that might be detected at other times of the night when the mouth is closed) exits from the mouth instead of returning along the conduit 126 to the microphone 140.

[0133] In some implementations, cepstral analysis is used to analyze acoustic data. The cepstral is the "quefrency" domain, also known as the logarithmic spectrum of a time-domain waveform. For example, the cepstral can be considered as the inverse Fourier transform of the logarithmic spectrum of the forward Fourier transform of the decibel spectrum, etc. This operation essentially transforms the convolution of the impulse response function (IRF) and the sound source into an additive operation, making it easier to consider or remove the sound source to isolate the IRF data for analysis. Cepstral analysis techniques are described in detail in the scientific papers entitled "Cepstral: A Processing Guide" (Childers et al., IEEE Transactions on Physics, Vol. 65, No. 10, October 1977) and Randall RB, Frequency Analysis, Copenhagen: Bruel & Kjaer, p. 344 (1977, revised 1987).

[0134] This method can be understood based on the properties of convolution. The convolution of f and g can be written as... This operation can be the integral of the product of two functions (ƒ and g) after being inverted and shifted. Therefore, it is an integral transform as shown in Equation 1, as follows:

[0135] Equation 1

[0136] Although the symbol t is used above, it does not need to represent the time domain. However, in this context, the convolution formula can be described as a weighted average of the function f(τ) at time t, where the weights are given by g(-τ) with a simple shift of t. As t changes, the weighting function emphasizes different parts of the input function.

[0137] More generally, if f and g are R d For complex-valued functions on the x-axis, their convolution can be defined as the integral of Equation 2:

[0138] Equation 2

[0139] A mathematical model that correlates the output of an acoustic system with the input of a time-constant linear system can be based on this convolution. The time-constant linear system is, for example, a system involving catheters in a respiratory therapy device (which may include some or other unknown parts of the system). The output measured at the system's microphone can be considered as the input noise "convolved" with the system's impulse response function (IRF) as a function of time (t), as shown in Equation 3:

[0140] Equation 3

[0141] Where * denotes the convolution function; y(t) is the signal measured at the sound sensor; S1(t) is the sound or noise source, such as noise or sound generated by the airflow generator in a respiratory therapy device; h1(t) is the system IRF from the noise or sound source to the sound sensor. The impulse response function (IRF) is the system response to a unit impulse input.

[0142] By measuring the Fourier transform of the sound data, such as the Discrete Fourier Transform (“DFT”) or the Fast Fourier Transform (“FFT”), and considering the convolution theorem, Equation 3 is transformed into the frequency domain, generating Equation 4:

[0143] Equation 4

[0144] Where Y(f) is the Fourier transform of y(t); S1(f) is the Fourier transform of s1(t); and H1(f) is the Fourier transform of h1(t). In this case, convolution in the time domain becomes multiplication in the frequency domain.

[0145] We can apply the logarithm of equation 4 to convert multiplication into addition, resulting in equation 5:

[0146] Equation 5

[0147] Then, Equation 5 can be transformed back to the time domain by the inverse Fourier transform (IFT) (e.g., inverse DFT or inverse FFT), which yields the inverse Fourier transform of the logarithm of the complex cepstral (K(τ)) (a complex number, since it can work from the complex spectrum) - the spectrum Y(f); Equation 6

[0148] Equation 6

[0149] Here, "τ" is a real-valued variable called the cepstral frequency, measured in seconds. Thus, the convolution effect in the time domain becomes additivity in the logarithm of the spectrum, and this remains true in the cepstral frequency.

[0150] Considering data from cepstral analysis, such as examining data values ​​at the cepstral frequencies, can provide information about the system. For example, by comparing the system's cepstral data with a previous or known baseline of the system's cepstral data, this comparison (e.g., difference) can be used to identify differences or similarities within the system, which can then be used to achieve the different functions or purposes disclosed herein. The following disclosures can utilize this analytical approach as explained herein to achieve cardiac output detection.

[0151] Therefore, in some implementations, cepstral acoustic data analysis can be used to measure the cross-sectional area and changes in cross-sectional area of ​​the user interface 124, nasal passages, and estimated sinus dimensions. Changes in the estimated dimensions of the nasal passages and sinuses can indicate inflammation and / or congestion.

[0152] In some implementations, direct spectral methods can be used to analyze acoustic data. Examples of direct spectral methods include processing Discrete Fourier Transform (DFT), Fast Fourier Transform (FFT) with a sliding window, Short-Time Fourier Transform (STFT), wavelets, wavelet-based cepstral computation, deep neural networks (e.g., using imaging methods applied to the spectrogram), Hilbert-Huang Transform (HHT), Empirical Mode Decomposition (EMD), Blind Source Separation (BSS), Kalman filters, or any combination thereof. In some implementations, cepstral coefficients (CCs), such as Mel-frequency cepstral coefficients (MFCCs), can be used, for example, by treating acoustic data analysis as a speech recognition problem and using a machine learning / classification system.

[0153] For example, in some implementations, acoustic data (step 310) can be analyzed to detect congestion and / or obstruction of one or both nasal passages (due to, for example, disease or allergies). In some implementations, acoustic data (step 310) can be analyzed to measure parameters associated with the user's respiratory anatomy. For example, as discussed herein, certain abnormalities in respiratory anatomy are associated with obstructed nasal air passages, such as enlarged adenoids, enlarged tonsils, deviated septum, nasal polyps, or benign growths in the nasal lining. Furthermore, enlarged turbinate bones, the shape of the nose, and the shape and size of the jaw can also contribute to obstruction of the nasal air passages. In some implementations, acoustic data and / or any changes in size can be used to analyze acoustic data (step 310) to measure the dimensions of the nasal passages.

[0154] In some implementations, acoustic data can be processed to determine cardiac oscillations caused by, for example, heartbeats in acoustic signals. Analysis of these cardiac oscillations can then be processed to determine the state of a mouth leak. When the mouth is open rather than closed, the characteristics of the cardiac oscillations can differ between inhalation and / or exhalation. Changes in heart rate due to micro-awakenings (e.g., brief awakenings) during a mouth leak can also be observed, indicating the physiological effects on the brain in detecting a mouth leak. In some implementations, weak or no cardiac oscillations are indicated. For example, cardiac oscillations exhibit reduced fidelity when a mouth leak is present.

[0155] In some implementations, to analyze the acoustic data, the acoustic data is processed (step 310) to identify multiple features. These multiple features may indicate the mouth leakage state and / or be further processed to determine the mouth leakage state. For example, the multiple features may include: one or more variations in the spectral characteristics of the acoustic signal, one or more variations in the frequency of the sound wave, one or more variations in the amplitude of the sound wave, Mel-frequency cepstral coefficients (MFCC), spectral flux, spectral centroid, harmonic product spectrum, spectral spread, spectral autocorrelation coefficient, spectral kurtosis, linear predictive coding (LPC), or any combination thereof.

[0156] Additionally or alternatively, multiple features may include: root mean square (RMS) based on autocorrelation, zero crossing, envelope, spacing, or any combination thereof. Additionally or alternatively, multiple features may include: changes in the shape of the echo reflected signal (e.g., a decrease in amplitude and / or a significant shift in shape as the air loop properties change).

[0157] In some implementations, a bandpass-filtered white noise source generates or emits sound waves at predetermined intervals, and a microphone (e.g., Figure 1The microphone 140 detects the reflection of sound waves emitted from the white noise source. The signature can be synchronized with exhalation and can be separated from the typical sound of exhalation when the mouth is closed (e.g., if the user is using a nasal mask). In some such implementations, multiple features may include a signature synchronized with exhalation.

[0158] Step 330 of method 300 includes determining the user's mouth leakage status based at least in part on acoustic data, physiological data, or both during sleep periods.

[0159] In some implementations, acoustic data (step 310) can be analyzed (step 320; independently or in combination with physiological data) to determine the probability of mouth leakage and / or the probability associated with the severity of mouth leakage. In some implementations, physiological data can be analyzed (independently or in combination with acoustic data) to determine the probability of mouth leakage and / or the probability associated with the severity of mouth leakage. For example, snoring, sleep position, head position, sleep stage, congestion, pillow configuration, alcohol consumption, body temperature, allergens in ambient air, weight, body composition, neck size, gender, being a new user, mask type, or any combination thereof can contribute to one or both of these probabilities.

[0160] In some implementations, at step 330, the mouth leak state is determined based on data generated by two or more separate and distinct sensors. Having two or more sensors can increase the fidelity of determining the mouth leak state. For example, the system may include a microphone (identical or similar to microphone 140 of system 100) and a flow sensor (identical or similar to flow sensor 134 of system 100). Acoustic data associated with the user of the breathing apparatus (e.g., user 210 of breathing apparatus 122) is received from the microphone (e.g., step 310). Additionally, flow data associated with the user of the breathing apparatus is received from the flow sensor. The acoustic data is analyzed (e.g., step 320). Flow data is also analyzed (e.g., by referring to one or more steps disclosed in WO 2012 / 012835, which is incorporated herein by reference). The mouth leak state is then determined based at least in part on the analysis of the acoustic data and the analysis of the flow data.

[0161] In some implementations, step 330 includes using a machine learning algorithm to determine the user's mouth leakage state. For example, step 330 may include using a neural network (e.g., a shallow or deep method) to determine the mouth leakage state. Step 330 may include using supervised machine learning algorithms / techniques and / or unsupervised machine learning algorithms / techniques. For example, in some implementations, a machine learning algorithm is used to process acoustic data (step 310) to output the user's mouth leakage state.

[0162] Optionally, in some implementations, step 340 of method 300 includes displaying the user's mouth leakage status on a display device (e.g., display device 172 of user device 170 and / or display device 128 of respiratory system 120).

[0163] In some implementations, method 300 further includes step 331, wherein the AHI number (or treatment number, such as the MyAir™ number) and / or AHI score (or treatment score, such as the MyAir™ score) are calculated and / or modified based at least in part on the mouth leak status. For example, in some cases, the determined mouth leak status can be used to update the AHI number and / or treatment number calculations, where a mouth leak might otherwise appear as apnea (e.g., the AHI number and / or treatment score could be higher than accurate). The treatment number or score may include or be derived from one or more metrics selected from treatment usage time during a sleep period; the AHI of the period; the average leak flow rate of the period; the average mask pressure used for the period; the number of sub-segments within the period; sleep status and / or sleep stage information; and whether the period is a compliant period according to compliance rules. One example of a CPAP treatment compliance rule is requiring a patient to use the respiratory system for at least four hours each night for at least 21 or 30 consecutive days to be considered compliant. Other such compliance rules may be selected, as will be understood.

[0164] In some such implementations, to calculate and / or modify the AHI score and / or treatment score, sensor data associated with the user during a sleep period is received from sensors connected to the breathing device. The sensor data indicates the number of sleep-disordered breathing events during the sleep period. The AHI score and / or treatment score are determined based at least in part on the number of sleep-disordered breathing events. Mouth leak status is correlated with the sensor data to output one or more false-positive sleep-disordered breathing events. One or more false-positive sleep-disordered breathing events are subtracted from the total number of sleep-disordered breathing events to output a modified number of sleep-disordered breathing events. The AHI score and / or treatment score are calculated based at least in part on the modified number of sleep-disordered breathing events.

[0165] For example, in some implementations, the mouth leak status may include the duration and / or severity of the mouth leak. Sleep or treatment scores (e.g., the sleep or treatment scores described herein) are modified (e.g., reduced or decreased) at least in part based on the duration and / or severity of the mouth leak. Sleep scores referred to herein are exemplified by those described in International Publication No. WO 2015 / 006364, such as in paragraphs

[0056] -

[0058] and

[0278] -

[0285] , which are incorporated herein by reference in their entirety. Alternative definitions are also possible.

[0166] Furthermore, excessive titration (e.g., high) pressure settings can promote undesirable mouth leaks. Accordingly, in some implementations, method 300 further includes step 332, wherein the pressure setting of the breathing apparatus is adjusted at least in part based on the mouth leak state. For example, system 100 may be configured to lower the pressure level and / or suggest and / or approve such a treatment change to a qualified person and / or intelligent system.

[0167] In some implementations, the breathing system 120 includes an automatic setting function for the RPT. The automatic setting module allows the RPT to adjust pressure levels throughout the night based on the user's needs. Undetected mouth leaks can cause the RPT to incorrectly determine that apnea has occurred. In some cases, allowing a mouth leak can confuse the automatic setting function (especially if the user is not already at their maximum available pressure). During mouth breathing, the automatic setting / RPT treatment engine may assume the user has apnea (potentially a very long apnea) until breathing is finally detected, and it begins to increase pressure. After some breaths following a leak, the machine may incorrectly increase pressure (e.g., using the automatic setting) to "treat" what is actually a mouth leak, leading to more mouth leaks when pressure is higher. In other words, increased pressure can worsen a mouth leak (e.g., prolong its duration and / or worsen its severity). This, in turn, increases discomfort and may eventually wake the user, and / or cause the mask to be removed, and / or worsen dry mouth or other mouth leak-related symptoms.

[0168] In some implementations, in response to a mouth leak, the pressure setting of the breathing device is adjusted, wherein the pressure setting is associated with the pressurized air supplied to the user's airway. In some such implementations, acoustic data associated with the user is analyzed to determine that the user is exhaling. In response to the determination that the user is exhaling, the pressure of the pressurized air supplied to the user's airway is reduced during the user's exhalation. In some such implementations, reducing the pressure of the pressurized air includes increasing the expiratory pressure reduction (EPR) level associated with the breathing device, which is relevant to method 500 in this context. Figure 5 (To be described in more detail)

[0169] In some implementations, method 300 further includes step 333, wherein the humidification setting is adjusted in response to the user's mouth leakage status. For example, in some implementations, if the user has some minor mouth leakage (e.g., low severity, but causing a feeling of dry mouth in the morning), higher humidity will help keep the mouth and lips moist—up to a point. Therefore, adjusting humidity is one way to balance dryness. The more humidity blown into the nose from the humidifier's duct and / or tube, the more humidity (e.g., moisture) is expelled through the mouth. Additionally or alternatively, a substance may be released into the moisture to be introduced into the compressed air to adjust the humidification setting. The substance may be stored, for example, in container 180, until a portion of it is ready for release. The substance may include saline solution, decongestant, essential oil, fragrance, medicine, or any combination thereof.

[0170] Mouth leak status can be influenced by various factors. In some cases, mouth leak status is associated with the user's sleeping position. For example, mouth leaks may be more severe in a non-supine position. In other words, side sleepers may have a higher risk of mouth leaks, but conversely, if they have positional apnea, they require less pressure. In some cases, the user sleeps on a smart pillow. In some implementations, method 300 further includes step 334, wherein the smart pillow is adjusted such that it prompts the user to change the position of the user's head in response to the mouth leak status. In some cases, the user sleeps on a smart mattress. In some implementations, method 300 further includes step 335, wherein the smart mattress is adjusted in response to the mouth leak status such that the smart bed or smart mattress prompts the user to change the position of the user's body.

[0171] In some implementations, the user utilizes a wearable sensor to sleep. The wearable sensor may be attached to and / or integrated into a watch worn by the user. In some such implementations, method 300 further includes step 336, wherein the wearable sensor is adjusted in response to a mouth leakage state, such that the wearable sensor stimulates the user's neck or jaw to close the user's mouth.

[0172] In some implementations, method 300 includes step 337, wherein a notification is provided to a user (and / or physician, healthcare provider, etc.) via a display device (e.g., display device 172 and / or display device 128) to warn the user of a mouth leak status. The notification may include a visual notification, an audio notification, a haptic notification, or any combination thereof.

[0173] In some implementations, the notification (step 337) includes a message (visual, audio, and / or tactile) that reminds the user to (i) close his / her jaw during a sleep period (e.g., via a jaw strap or similar device), (ii) moisten his / her lips before the next sleep period, or (iii) both (i) and (ii). Alternatively or additionally, the message may include suggestions or instructions to the user, (i) to use another mask, (ii) to wake up, (iii) that the user has a mouth leak, or any combination thereof. Further examples of visual notifications are in Figures 4A-4C It is shown in the figure and discussed here.

[0174] One or more of the steps in the method 300 described herein may be repeated once or multiple times for additional sleep periods (e.g., a second sleep period, a third sleep period, a fifth sleep period, a tenth sleep period, etc.). This allows sound data to be received and accumulated over several sleep periods. If analysis of the accumulated data suggests that the user is regularly breathing through their mouth during sleep periods, the user may have the wrong type of mask (e.g., a nasal mask or nasal pillow) when a full-face mask would be more suitable for their breathing.

[0175] When proactively offering a "better" (more suitable) full-face mask is a better outcome, users will discontinue treatment due to their frequent mouth leaks. Therefore, in some implementations, if a user regularly breathes through their mouth, method 300 suggests (or automatically delivers to the user) a more suitable mask. Additionally or alternatively, method 300 provides a medically recognized AI system to automatically generate prescriptions for more suitable masks (e.g., current users of nasal masks or nasal pillows could receive a full-face mask recommendation). Full-face mask users are less likely to experience mouth leaks than nasal mask users. Therefore, over time, mouth-breathing users can be trained with full-face masks to stop their mouth-breathing habit and then revert to nasal masks.

[0176] Other examples of follow-up actions after detecting a user's regular mouth breathing behavior include: suggesting (or automatically deploying it to the user) a chin strap, which helps maintain jaw closure at night; and / or suggesting (or automatically deploying it to the user) a nose bridge and / or another suitable bracket instead of the standard one. Different brackets can provide reinforcement to the mask to provide a good seal, even when the user is sleeping in different positions.

[0177] Figure 4AA visual indicator on the display device shows the user's mouth leak assessment (e.g., mouth leak score). The mouth leak score may be determined at least in part based on: the percentage of time the user experiences mouth leaks during a sleep period (e.g., mouth leak duration as a percentage of total treatment time), peak mouth leak volume, total mouth leak volume, or any combination thereof. In some implementations, sleep stage data associated with the user during a sleep period is received. The sleep stage data is analyzed to determine the sleep stage. Sleep stages may include wakefulness (awake, drowsy), sleep (non-REM light sleep N1, N2, deep sleep N3, REM sleep), sleep stage segmentation (due to, for example, residual apnea), hypopnea, or any combination thereof. Mouth leak status (which may include one or more of the time, duration, and frequency of mouth leaks) and / or mouth leak score may be associated with the determined sleep stage, thus allowing mouth leaks to be associated at least in part with the sleep stage.

[0178] like Figure 4A As shown, Jane's visual indicators include a separate mouth leak score for each sleep stage displayed on her mobile phone. Jane's mouth leak assessment shows three emoji icons for each sleep stage. Determining the mouth leak status for each sleep stage can help adjust treatments tailored to each sleep stage to improve overall sleep quality. For Jane, she has almost no to no mouth leaks during the waking and light sleep stages, earning her the "happy face" emoji. She has some mouth leaks during deep sleep, earning her the "OK face" emoji. She has significant mouth leaks during REM sleep, earning her the "sad face" emoji. Therefore, pressure and / or humidity settings can be adjusted for the REM stage, as Jane is more likely to have mouth leaks during the REM stage.

[0179] Figure 4B A visual indicator on the display device is shown that relates to a message on the user's mouth leak status. This message can be any suitable message provided to the user to alert them to the mouth leak status (e.g., step 337 of method 300). As shown in the figure, Figure 4B The message included a reminder to the user to switch to a full-face mask because she was breathing through her mouth.

[0180] Figure 4C A user interface for receiving user feedback from a user is shown on a display device. As shown, user input data is received from the display device (same as or similar to user device 170) after a sleep period. The user can provide subjective feedback on sleep quality and / or symptoms experienced during the sleep period. The mouth leakage score can be modified, at least in part, based on the user input data. Figure 4AUser input data may also be included in one or more steps of any of the methods described herein to help determine the state of mouth leakage, including, for example, step 330 of method 300, steps 530 and / or 540 of method 500, and step 640 of method 600.

[0181] refer to Figure 5 This illustrates a method 500 for determining the optimal inspiratory and expiratory pressures for a user. One or more steps of method 500 can be used with the system 100 described herein. Figure 1 and 2A This can be achieved by any element or aspect of (-2B). Method 500 can also be used in conjunction with one or more steps of method 300.

[0182] Step 510 of method 500 includes receiving inspiratory pressure data and expiratory pressure data associated with pressurized air supplied to the user during multiple sleep periods. For example, in some implementations, the inspiratory pressure data and expiratory pressure data are transmitted via at least one or more sensors 130 ( Figure 1 (such as pressure sensor 132) generated.

[0183] Step 520 of method 500 includes receiving inspiratory acoustic data and expiratory acoustic data associated with the user during multiple sleep periods. For example, in some implementations, this is achieved via at least one or more sensors 130 ( Figure 1 (e.g., microphone 140) generates inhalation acoustic data and exhalation acoustic data. Step 520 may be the same as or similar to step 310 of method 300.

[0184] Step 530 of method 500 includes analyzing inhalation sound data and exhalation sound data associated with the user. Step 530 may be the same as, similar to, or repeat step 320 of method 300. In some implementations, inhalation acoustic data and exhalation acoustic data are analyzed to determine mouth leakage status. The determination step is the same as, similar to, or repeats step 330 of method 300.

[0185] Step 540 of method 500 includes: determining the user’s optimal inspiratory pressure and optimal expiratory pressure based at least in part on (i) the user’s mouth leakage status in each of a plurality of sleep periods and (ii) pressure data.

[0186] In some implementations, method 500 further includes step 550, wherein optimal inhalation pressure and optimal exhalation pressure are set as pressure settings for pressurized air supplied to the user for subsequent sleep periods. Alternatively, if the current pressure setting differs significantly from the optimal pressure, the pressure setting is adjusted slowly to avoid abrupt changes.

[0187] Method 500 may also include a feedback loop to assess whether the adjustment has the desired result and / or whether the pressure level needs to be increased or decreased. For example, subsequent acoustic data during subsequent sleep periods are received from a microphone. Optimal inhalation pressure and optimal expiratory pressure are received as subsequent pressure data for subsequent sleep periods. The analysis step (530) and determination step (540) are repeated to update the user's optimal inhalation pressure and optimal expiratory pressure (550).

[0188] Additionally or alternatively, method 500 may include a machine learning algorithm (similar to the machine learning algorithm in method 600) that determines whether the user has genuine apnea or is merely "masquerading" as apnea due to mouth leakage. Based on this determination, the pressure level is further increased (e.g., to treat genuine apnea that the current pressure level has not managed to treat) or kept the same (or even reduced).

[0189] For example, in some implementations, the breathing device may include an expiratory pressure reduction (EPR) module. The EPR module may have different settings for the EPR level, which are associated with the difference between the pressure level during inspiration and the reduced pressure level during expiration. Based on the determined optimal inspiratory and expiratory pressures, activating and / or adjusting the EPR level (e.g., setting a relatively low expiratory pressure) can reduce mouth leakage (step 550). The EPR level may also be adjusted during specific sleep stages, as discussed herein.

[0190] refer to Figure 6 This illustrates a method 600 for estimating a user's mouth leakage status using a machine learning algorithm. One or more steps of method 600 can be used with the system 100 described herein. Figure 1 and 2A Method 600 can be implemented by any element or aspect of (-2B). Method 600 can also be used in conjunction with one or more steps of method 300 and / or one or more steps of method 500.

[0191] Even when users have a “good” (e.g., properly fitting) mask for their use in a more general sense, they may experience congestion and / or illness during the day, such as during one or more sleep periods. Users may temporarily require different settings and / or interventions to minimize the risk of mouth leakage during sleep periods of congestion and / or illness. Therefore, in some implementations, method 600 allows for the prediction of whether a user is likely to have mouth leakage during one or more sleep periods and for taking and / or recommending actions to reduce or mitigate this risk. For example, for some people, drinking alcohol may lead to more mouth leakage due to the effects of relaxants; alcohol-induced dehydration may also affect the lip seal. A common cold or flu may lead to more mouth leakage due to congestion.

[0192] Step 610 of method 660 involves receiving acoustic data associated with the user of the breathing device during multiple sleep periods. For example, in some implementations, this is done via at least one or more sensors 130. Figure 1 (such as microphone 140) to generate acoustic data. Step 610 may be the same as or similar to step 310 of method 300 and / or step 520 of method 500.

[0193] Step 620 of method 660 includes receiving physiological data associated with a user for multiple sleep periods. For example, in some implementations, this is done via at least one or more sensors 130 ( Figure 1 Physiological data is generated. Physiological data can be generated as described herein, for example, by reference method 300. Some examples of physiological data generated by sensors are: breath alcohol data, blood alcohol data, blood pressure data, blood glucose data, congestion data, obstruction data, body temperature data, heart rate data, exercise data, respiratory data (e.g., respiratory rate and / or respiratory pattern), sleep stage data, mask data, and CO2 level data.

[0194] Step 630 of method 660 includes analyzing acoustic data to determine the user's mouth leakage status for each of multiple sleep periods. Step 530 may be the same as, similar to, or repeat steps 320 and / or 330 of method 300.

[0195] Step 640 of method 660 includes training a machine learning algorithm using (i) mouth leak status of the user for each of multiple sleep periods and (ii) physiological data, such that the machine learning algorithm is configured to receive current physiological data associated with the current sleep period as input and determine an estimated mouth leak status for the current sleep period as output. Training the machine learning algorithm may include analyzing acoustic and / or airflow data corresponding to known mouth leak events (e.g., identified by a camera).

[0196] One or more of steps 610 to 640 of method 600 described herein can be repeated to create a feedback loop similar to that described in reference method 500. The feedback loop allows for continuous improvement of the machine learning algorithm to suit the user.

[0197] Machine learning algorithms can be used in various implementations. For example, in some implementations, current physiological data during the current sleep period is received as input to the machine learning algorithm (step 650). An estimated mouth leak state for the current sleep period is generated as the output of the machine learning algorithm (step 652). The pressure setting of the breathing device is adjusted based at least in part on the estimated mouth leak state (step 654).

[0198] For example, in some implementations, current physiological data prior to the next sleep period is received as input to a machine learning algorithm (step 660). An estimated mouth leakage state for the next sleep period is generated as output of the machine learning algorithm (step 662). Based at least in part on the estimated mouth leakage state, suggested adjustments for display on the user device are determined (step 664).

[0199] Some examples of suggested adjustments include: (i) adjusting the pressure setting of the breathing apparatus, which is associated with the pressurized air supplied to the user's airway; (ii) adjusting the humidification setting of a humidifier connected to the breathing apparatus, which is configured to introduce moisture into the pressurized air supplied to the user's airway; (iii) suggesting a mask type for the breathing apparatus; (iv) suggesting a sleep position for the user; (v) suggesting a chin strap for the user; and (vi) suggesting a nose bridge for the user. The suggested adjustments can be made in conjunction with... Figure 4B Similar manner as described in its corresponding description and / or shown in step 337 of method 300.

[0200] Furthermore, in some implementations, the data generated by method 600 can provide a classification of physiological factors associated with mouth leakage that may cause irritation (e.g., mask removal, interruption of sleep stages, changes in heart rate, or reported symptoms the following morning, such as dry mouth).

[0201] See Figure 7 According to some implementations of the present invention, a method 700 for determining the mouth leakage state associated with a user of a breathing apparatus is disclosed. In step 710, the method receives information related to the breathing apparatus (e.g., Figure 1 The system 100 shown (breathing device 122) uses user-associated airflow data. In step 720, the user-associated airflow data is analyzed. In some implementations, analyzing the user-associated airflow data includes processing the airflow data to identify one or more features that distinguish mouth leaks from (i) normal breathing during treatment and / or (ii) other types of unintentional leaks (e.g., unintentional leaks from the user interface). Based at least in part on this analysis, in step 730, the user-associated mouth leak status (e.g., no mouth leak, valve leak, continuous mouth leak) is determined. In some implementations, the mouth leak status indicates whether air is leaking from the user's mouth.

[0202] Airflow data may include pressure data associated with pressure signals within the respiratory system, such as mask pressure measured by the respiratory system. In some implementations, airflow data further includes flow rate data. In some such implementations, airflow data may be received from a flow sensor associated with the respiratory device (e.g., flow sensor 134 of system 100); pressure data may be received from a pressure sensor associated with the respiratory device (e.g., pressure sensor 132 of system 100).

[0203] In some implementations, within the received airflow data (step 710) and / or using analyzed airflow data (step 720), at least a first breathing cycle of the user is identified in step 722. For example, in some such implementations, two, three, four, five, six, seven, or eight breathing cycles may be identified in step 722, and processing is then performed in step 724. The first breathing cycle may include an inhalation portion (e.g., Figure 8 The inhalation portion 810) and the exhalation portion (e.g., Figure 8 (Exhalation portion 820). The first breathing cycle (and / or additional breathing cycles) can be determined by any suitable method as disclosed herein. In some examples, the first breathing cycle can be determined by using the user's average breathing length, for example, approximately five seconds. In some examples, the first breathing cycle can be identified at least in part based on airflow data received from step 710. In some examples, identifying at least the first breathing cycle (step 722) includes identifying the start and / or end of the first breath. The start and / or end of the first breath signifies the transition between the first breath and its adjacent breath.

[0204] In some implementations, in step 724, airflow data is processed to identify one or more features associated with at least a first respiratory cycle. For example, in some such implementations, airflow data is processed to identify one or more features associated with two, three, four, five, six, seven, or eight respiratory cycles. The one or more features may include pressure range, minimum pressure, maximum pressure, pressure skewness, pressure kurtosis, pressure power spectral density (e.g., pressure power spectral density in the 1-3 Hz range), flow range, minimum flow rate, maximum flow rate, flow skewness, flow kurtosis, flow area ratio (e.g., the ratio of the expiratory peak area of ​​the flow data to the total expiratory area), or any combination thereof. In some implementations, a specific combination of one or more features is used to determine the mouth leakage state, such as a combination of pressure range, minimum pressure, and flow area ratio. Each of the one or more features may be determined and / or extracted from detrended pressure data and / or detrended flow rate data (discussed in more detail below). In some such implementations, the pressure range and minimum pressure are determined and / or extracted from detrended pressure data; and the flow area ratio is determined and / or extracted from flow data.

[0205] Additionally or alternatively, in some implementations, one or more features include spectral characteristics based on pressure data. For example, since valve-type nozzle leaks tend to manifest as abrupt pressure changes, the pressure signal is represented and / or plotted as a high peak in the power spectral density of the pressure signal at high frequencies. An FFT can be performed over a five-second window of the pressure signal, and the peak at high frequencies (e.g., 1-3 Hz) can be calculated for each window. Additionally or alternatively, in some implementations, one or more features include optionally detrended skewness and / or kurtosis of the pressure signal, which can also characterize abrupt changes and / or asymmetries in the pressure signal. Furthermore, in some implementations, the same calculations applied to pressure data can also be applied to airflow data to extract additional features for determining the nozzle leak state.

[0206] refer to Figure 9 Some of these features are discussed in more detail. In some examples, one or more features associated with at least the first breathing cycle are calculated over 1, 2, 3, 4, 5, 6, 7, or 8 adjacent (e.g., consecutive) breathing cycles. In some examples, one or more features associated with the first breathing cycle are calculated over a predetermined duration (e.g., 30 seconds). This is because, in some cases, mouth leakage tends to occur over a series of breaths. Therefore, statistics on multiple breaths can be analyzed to exclude “one-off” events that might result in only a single independent change in breathing, and / or events that are actually associated with other processes (e.g., user inhalation, apnea, etc.).

[0207] In some implementations, pressure data (e.g., pressure time traces) is detrended to account for the effects of expiratory pressure release (EPR) or autosetting before any features are extracted based on the pressure data. EPR effectively increases pressure during inspiration and decreases it at the onset of expiration (maintaining this low value throughout the expiratory phase). Autosetting increases therapeutic pressure after the onset of a respiratory event and decreases it once the user no longer exhibits respiratory events. These pressure variations are independent of mouth leakage and can lead to changes in minimum, maximum, and pressure ranges. Therefore, in certain operating modes, these pressure variations need to be accounted for, resulting in detrended pressure data, such as a detrended minimum pressure. Once the trend is removed from the pressure time series, the detrended minimum, maximum, and / or pressure ranges can be extracted for mouth leakage status analysis in these operating modes. Additionally or alternatively, features derived from the flow signal can be detrended in the same or similar manner.

[0208] For example, in some implementations, in step 740, the operating mode of the breathing device (e.g., CPAP, APAP, or BiPAP) is determined. In some such implementations, one or more features are determined (step 724) based at least in part on the determined operating mode (step 740). For example, one or more features may be determined (step 724) based at least in part on the expiratory decompression (EPR) component removed from the pressure data (received at step 710).

[0209] In some implementations, one or more features can then be fed into a logistic regression model to determine the mouth leak status (step 730). For example, these features can be input into a logistic regression model, which outputs a probability (e.g., a single digit). A threshold is then applied to this probability to determine the mouth leak status (e.g., whether the user is experiencing any mouth leaks). In some examples, the threshold indicating the probability of a mouth leak is 0.6.

[0210] In some examples, for any given period (e.g., a 30-second range, or based on breaths), the threshold can be calculated using the following formula:

[0211]

[0212] in It refers to the pressure range. It is the least resistance to trend reversal, and It is the flow area ratio for the given period. 'b' represents the weights of the logistic regression. 'b' is the bias. In this example, The values ​​of are -6.12339829, 0.87103483, and -5.26285759, respectively; and the value of b is -1.2533223418287587. If p > 0.6, the time period is classified as containing mouth leakage; otherwise, the time period is marked as negative (e.g., no mouth leakage).

[0213] While this example involves three features (i.e., pressure range, minimum pressure, and flow carrier area ratio), other features and more or fewer features may also be used. In some implementations, the number of weights in the formula and / or their values ​​will vary, at least in part, based on the features considered and / or the available training data. Additionally or alternatively, in some implementations, a probability threshold... It can be a dynamic value that modifies over time, a dynamic value modified based on the desired sensitivity and / or specificity in the system, or a dynamic value modified based on a specific user; therefore, the probability threshold... It can be an adjustable value. For example, a probability threshold for periods classified as having mouth leaks. It can be > 0.25, 0.3, 0.35, 0.4, 0.45, 0.5, 0.55, 0.6, 0.65, or 0.7.

[0214] Brief Reference Figure 8 According to some implementations of the invention, a graph illustrating the flow rate versus time for a first breath 830 and a second breath 840 is illustrated. It is understood that "I" represents the inspiratory portion of the first breath 830 and "E" represents the expiratory portion. The first breath 830 corresponds to normal breathing by the user. The second breath 840 corresponds to exhaling through the user's mouth (i.e., mouth leakage). As shown, when the user exhales through their mouth, the beginning of the expiratory portion 820 has a sharper peak 842 compared to the corresponding peak 832 during normal breathing. This "sharpness" of the peak can be measured using method 700 (e.g., as one of the features processed in step 724) and / or... Figure 9 As shown in the diagram. For example, the “sharpness” of a peak can be determined using the flow carrier area ratio described herein.

[0215] Additionally or alternatively, in some implementations, when a user exhales through their mouth, the exhalation portion 820 has a flatter curve 844 after the peak 842, compared to the corresponding curve 834 when the user breathes normally. In some such implementations, method 700 (e.g., as one of the features processed in step 724) and / or Figure 9The method shown in the figure measures the degree of exhalation flattening after the peak. For example, the degree of exhalation flattening can be determined by (i) calculating the skewness and / or kurtosis of the flow signal, and / or (ii) assessing the length of time intervals in which the derivative of the flow signal approaches zero and / or the standard deviation of the flow signal approaches zero.

[0216] Now for reference Figure 9 This illustrates several features identified within a respiratory cycle 900 according to some implementations of the invention. The respiratory cycle 900 includes an inhalation portion 910 and an exhalation portion 920. One or more steps of method 700, such as step 720 and / or step 722, can be used to determine the inhalation portion 910 and / or the exhalation portion 920. One or more steps of method 700 (e.g., step 724) can be used to identify several features.

[0217] In some implementations, multiple features may include flow-based features and pressure-based features. For example, flow-based features may include minimum flow rate, maximum flow rate, flow range, the ratio of peak expiratory area to total expiratory surface area (or "flow-sub-area ratio"), flow skewness, flow kurtosis, flatness during exhalation, or any combination thereof. Pressure-based features may include minimum pressure, maximum pressure, pressure range, power spectral density of pressure in the 1-3 Hz range, pressure signal skewness, pressure signal kurtosis, or any combination thereof. In some such implementations, flow-based features and / or pressure-based features may be derived after applying a detrending operation to the flow and / or pressure signals.

[0218] Still referencing Figure 9 The diagram illustrates a flow range 930, a minimum flow rate 932, and a maximum flow rate 934. The minimum flow rate 932 and maximum flow rate 934 can be used as intermediate steps to derive the ratio of the expiratory peak to the total expiratory area. In some such implementations, the minimum flow rate 932 is associated with the end of the inhalation portion 910 and / or the beginning of the exhalation portion 920. In some implementations, the boundaries of the flow range 930 are defined by the minimum flow rate 932 and the maximum flow rate 934.

[0219] In some implementations, multiple features further include a flow area ratio, which can be calculated by dividing a first sub-area 940 by a second sub-area 942. The first sub-area 940 is defined by a region calculated from a minimum flow rate 932 to a flow threshold level 936. In some implementations, the flow threshold level (e.g., a cutoff level, which may be a depiction level of the expiratory peak) is set as an intermediate step to derive the ratio of the expiratory peak to the total expiratory area (or "flow area ratio"): first, the minimum flow rate 932 and the maximum flow rate 934 are determined, and then the flow threshold level is determined as a set percentage of that range. In some such implementations, 25% of the distance between the minimum flow rate 932 and the maximum flow rate 934 is selected as the flow threshold level 936. Additionally or alternatively, the flow threshold level 936 is adjustable.

[0220] To calculate the flow subarea ratio, the first subarea 940 (e.g., area 1) is the area below the flow threshold level 936 (in... Figure 9 (shown as a horizontal dashed line). In some implementations, the first sub-area 940 characterizes the sharpness of the expiratory peak. The second sub-area 942 is defined by a region calculated from the minimum flow rate 932 to zero (i.e., the flow rate at the point between inhalation and exhalation, or between inhalation and exhalation). For example, the second sub-area 942 (region 2) is the region below zero and includes all exhalation regions. The flow sub-area ratio (e.g., region 1 / region 2) is then calculated by dividing the first sub-area 940 by the second sub-area 942. In some such implementations, the flow threshold level 936 may be a dynamic value modified over time, a dynamic value modified based on desired sensitivity and / or specificity in mouth leak detection, or a dynamic value modified based on a specific user; therefore, the flow threshold level 936 may be an adjustable value. For example, in some implementations, the flow threshold level 936 is adjusted at least in part based on further analysis of airflow data associated with the user (e.g., ...). Figure 7 Step 720 of method 700 shown.

[0221] In some implementations, flow range 930 is analyzed to distinguish between valve-type nozzle leakage and continuous nozzle leakage. In some implementations, valve-type nozzle leakage can be characterized by a small value of the flow carrier area ratio characteristic. Conversely, a larger value may correspond to no nozzle leakage (and / or continuous nozzle leakage). Therefore, in some such implementations, the flow range 930 becomes larger than the flow range for users experiencing either valve-type or no nozzle leakage. This difference is illustrated here, for example, in... Figure 10A-10D As shown in the image.

[0222] Overall reference Figure 10A-10D , Figure 10ALaboratory data measured during the user's treatment sessions are shown, including valve mouth leakage (treatment session 1010), mask leakage (treatment session 1020), and continuous mouth leakage (treatment session 1030). Figure 10B This shows the user's view of the valve nozzle leaking. Figure 10A The treatment period 1010 in the laboratory data indicates the end of the valve nozzle leakage event. Figure 10C The user's face mask was shown to be leaking. Figure 10A The treatment period for the laboratory data is 1020, and the dashed line indicates the start of the mask leakage event. Figure 10D This shows a user displaying continuous mouth leakage. Figure 10A The laboratory data for treatment period 1030 is shown, with the dashed line indicating the start of a continuous mouth leak event. The figure illustrates patient flow, mask pressure, tidal volume, and calculated leakage. In some implementations, the pressurized air supplied to the user's airway during the treatment period is between 4 cmH2O and 20 cmH2O. In... Figure 10A-10D In the example shown, approximately 8 cmH2O of pressurized air is supplied to the user's airway during the treatment period.

[0223] Specific reference Figure 10A The mask pressure changed more during valve-type nozzle leakage (time period 1010) than during mask leakage (time period 1020), and changed the most during continuous nozzle leakage (time period 1030).

[0224] Unintentional leaks can include genuine mask leaks (e.g., poor mask seal) and / or mouth leaks (e.g., occurring with nose / pillow masks). In some examples, genuine mask leaks are a key confounding factor. One of the objectives of the mouth leak detection algorithm of this invention is to separate the two types of unintentional leaks.

[0225] refer to Figure 11 Histograms showing multiple periods with mouth leakage are presented based on the level of unintentional leakage. The histograms include data from six users (“Achill ECS” data), targeting multiple periods where mouth leakage was detected using a microphone connected to a mask. As shown, most periods with mouth leakage had some degree of unintentional leakage detected by the system (e.g., the flow generator of a respiratory therapy system).

[0226] Interim characteristics were developed based on 143 nights from 19 users. The "Achill ECS" data included data from 6 users (with varying degrees of mouth leakage), 14 nights per user. The "Pacific ECS AUS" data included data from 12 users (using full-face masks), 7 nights per user. The "Achill ECS" data was used as clinical data to develop initial characteristics. The "Pacific ECS AUS" data was used to test specific characteristics.

[0227] Features capturing slow variability (e.g., on the order of minutes) in ventilation, leaks, and / or their correlations were adapted to detect continuous mouth leaks (“CML”). Features capturing rapid variability (e.g., over the duration of a breath) based on respiratory morphology were adapted to detect valve-type mouth leaks (“VML”), as a faster timescale can indicate VML, which occurs only (or more significantly) during exhalation. In this example, a set of features was selected that demonstrated some of the ability of a patient with isolated mouth leaks.

[0228] Figure 12A The actual mouth leak duration is shown using data from "Achill ECS" and "Pacific ECS AUS". The X-axis represents each user. The Y-axis represents the number of time periods measured per user throughout the night (30 seconds each in this example). As shown in the figure, no actual mouth leak was detected because the 12 users using the "Pacific ECS AUS" data had full masks.

[0229] Figure 12B The diagram shows the predicted duration of mouth leaks using "Achill ECS" and "Pacific ECS AUS" data. The X-axis represents each user. The Y-axis represents the number of time periods (30 seconds each in this example) measured per user throughout the night. The algorithm predicts these multiple periods by comparing selected features to a threshold for each feature. As shown, these features provide a good estimate of mouth leaks compared to actual leaks. Figure 12A ).

[0230] Figure 13 The graph shows the percentage of scores based on block duration. As the figure illustrates, mouth leaks are not always intermittent. Instead, mouth leaks typically occur in blocks longer than 1 minute. Only 13.6% of the scores occur in blocks shorter than 5 minutes, while over 30% of mouth leaks occur in blocks longer than 0.5 hours. Therefore, in some implementations, such as in this example, a 30-second resolution for the mouth leak feature is sufficient.

[0231] Figure 14The signed covariance between unintentional leaks and ventilations used to determine mouth leaks is shown. In this example, features used to estimate and / or determine the state of a mouth leak may include the signed covariance (1440) between unintentional leaks (1420) and ventilations (1430), which is used to isolate the onset and offset (1410) of a mouth leak event. The 3-minute ventilation is equal to half the integral of the absolute value of the patient flow over a 3-minute window.

[0232] By using feature (1440) at a set threshold ( Figure 14 The system detects the start of a mouth leak blockage below a threshold (displayed as "0") and detects the offset of the mouth leak block by a feature (1440) exceeding a set threshold. In some implementations, the features used to estimate and / or determine the mouth leak state may include the time the covariance is below a set threshold (for the start) and above a set threshold (for the offset). For example, the time the signed covariance remains above a threshold may be a feature.

[0233] Figure 15 The characteristic separation of ventilation at the level of unintentional leakage is shown. As illustrated, the actual ventilation level on the mouth leak block itself has good discriminative power. Although ventilation can be used directly as a characteristic, user bias may exist, which could reduce the accuracy of estimating and / or determining the mouth leak status.

[0234] Figure 16A The diagram shows multiple negative periods (e.g., negative for mouth leakage) and multiple positive periods (e.g., positive for mouth leakage) for each user before normalization. Figure 16A Clear user trends in ventilation levels are shown (e.g., due to variations in BMI and / or vital capacity among users). In some implementations, a user-specific baseline value exists when user bias is present. Therefore, the algorithm can be configured to (i) select a period in the record where there is no unintentional leakage, calculate the mean ventilation, and use it as a baseline; (ii) use multiple iterations; and / or (iii) normalize after the treatment period is completed.

[0235] Figure 16B The diagram illustrates multiple negative and positive periods for each user after normalization. As shown, baseline level normalization increases separation. Baselines can be derived as: (i) the time-period average over segments without unintentional leaks, (ii) ventilation before the increase in unintentional leaks, (iii) the overall time-period baseline over segments without unintentional leaks, and / or (iv) user-specific baselines (e.g., from multiple nights). Normalization can be performed as: (i) a ratio (e.g., a percentage decrease relative to the baseline), and / or (ii) a difference (e.g., the actual decrease relative to the baseline).

[0236] Figure 17This illustrates the separation of unintentional leakage variability features. Unintentional leakage variability features are derived by obtaining the standard deviation of unintentional leaks over a set time interval (e.g., 30 seconds). In this example, high levels of unintentional leakage (e.g., >0.5 L / s) might be associated with CML, where mouth leakage is more stable than mask leakage. Medium levels of leakage (e.g., <0.5 L / s) might be associated with VML, where mouth leakage is less stable than mask leakage. In some implementations, the level of unintentional leakage can be used to more effectively fuse VML and CML features. For example, for low levels of leakage, VML features are weighted more than CML features; for high levels of leakage, VML features are weighted less than CML features.

[0237] Figure 18A An exemplary variation of unintentional leakage is shown for a user with a high level of unintentional leakage. Figure 18B This illustrates an exemplary variation of unintentional leakage by a user at a high level, assuming no mouth leakage. (As shown...) Figure 18A As shown, for users with mouth leaks, even with high levels of unintentional leakage, the variation in unintentional leakage is small. Conversely, as Figure 18B As shown, for high levels of mask leakage, unintentional leakage varies considerably (because there is no mouth leakage).

[0238] In some implementations, features used to estimate and / or determine the state of mouth leaks may include normalized respiratory rate (e.g., similar to normalized ventilation) and / or respiratory rate variability (e.g., similar to unintentional leak variability).

[0239] Figure 19 This illustrates respiratory segmentation based on flow data. The user's flow is plotted. The derivative of the flow is plotted on a low-pass filter (for smoothing). The detrended cumulative sum is plotted on a high-pass filter (for better per-breath separation). Each breath is segmented by taking the minimum or maximum value of the plot. For example, the negative peak of the first derivative of the flow is used for segmentation. The positive peak of the detrended cumulative sum is used for segmentation.

[0240] Once segmentation is complete, features can be computed on any respiratory device signal (e.g., any 25-Hz signal, such as patient flow, mask pressure, blower flow, blower pressure). Each signal can be analyzed, totaling at least 44 features (e.g., 11+ features for each of four signals). For example, each signal can be analyzed to compute (i) frame area (e.g., range x duration); (ii) respiratory area (AUC); (iii) complement of respiratory area; (iv) ratio of respiratory area to frame area; (v) ratio of respiratory area to complement of respiratory area; (vi) skewness of the original signal; (vii) kurtosis of the original signal; (viii) first derivative of skewness; (ix) first derivative of kurtosis; (x) second derivative of skewness; (xi) second derivative of kurtosis. For example, Figure 20A Some of these characteristics calculated in respiration are shown.

[0241] Additionally or alternatively, other characteristics of each signal can be analyzed, such as the region between the straight line (from minimum to maximum) and the actual signal. For example, Figure 20B Additional respiratory-specific features calculated on a portion of the respiration are shown. The ratio of the area above and below the line can represent the skewness of the signal.

[0242] In some implementations, all breaths over a time period can be grouped by period (e.g., 30 seconds per period). Period-based features are derived by obtaining statistics such as mean, median, and percentiles. In some such implementations, features can be further normalized using baseline values, similar to the normalization described above for ventilation. Figure 21-23 Separability using some period-based features is shown. Figure 21 The ratio of respiratory area to frame area for flow data at the 90th percentile is shown. Figure 22 This shows the skewness applied to the flow data using the period average. Figure 23 The skewness of the derivative blower pressure taken from the period average value.

[0243] In some implementations, the internal microphone of the respiratory therapy system can detect variability in noise levels and / or acoustic characteristics associated with mask leakage. For example, leakage detection can be performed based on (i) sound level characteristics and / or (ii) spectral characteristics (e.g., the ratio of energy content in various frequency bands).

[0244] Figure 24A This refers to the sound power levels during the periods of no mask leakage and the periods of mask leakage. (Sound power levels measured by microphone 140...) Figure 1The generated acoustic data is used to detect the noise level and acoustic characteristics or pattern variability associated with the acoustic features corresponding to the five-minute periods of no mask leakage and the five-minute periods of mask leakage within the respiratory therapy system 120. For example... Figure 24A As shown, this can be based on sound level characteristics and / or spectral characteristics, such as different frequency bands (in Figure 24A The acoustic energy ratio in the graph (between approximately 0 and approximately 8 kHz) can be used to detect leakage (mask leakage) in user interface 124 from acoustic data plotted over time periods.

[0245] Figure 24B yes Figure 24A A comparative graphical representation of leakage rate, flow rate, and mask pressure during the periods of no mask leakage and mask leakage. (e.g.) Figure 24B As shown, from Figure 24A The detection of mask leakage in the user interface 124 is related to the indication of mask leakage in the user interface 124 based on the data of pressure, flow rate and leakage rate from the user interface 124, at the same five-minute time period without mask leakage and at the same five-minute time period with mask leakage in the user interface 124.

[0246] Figure 25 A comparative graphical representation of the maximum sound intensity, standard deviation of sound intensity, leakage rate (measured in liters per second), flow rate (measured in liters per second), and mask pressure (measured in cmH2O) over a time period exceeding 20,000 seconds, during which leakage occurred in the respiratory therapy system. Sound intensity is from... Figure 25 One of the parameters determined by sound data generated by a microphone positioned together with the breathing therapy device.

[0247] Throughout the overlapping or non-overlapping time window within a time period, statistical data related to the parameters are extracted from a short window (e.g., 0.1 seconds) of acoustic data sampled at predetermined time intervals (e.g., 1 second). These statistical data include, but are not limited to, the standard deviation of acoustic intensity, the maximum acoustic intensity, and the percentile of acoustic intensity. The statistical data collected over this time period are then low-pass filtered (e.g., by moving average or by applying a digital filter such as a finite impulse response (FIR) or infinite impulse response (IIR) filter). The occurrence of leakage is determined based on whether the parameters meet the conditions described herein (e.g., above a predetermined threshold).

[0248] like Figure 25 As shown, the statistical data are plotted together with the mask pressure, flow rate, and leakage rate over the time period. Figure 25The comparative illustrations show the correlation between statistics on sound intensity, flow rate, mask pressure, and leakage rate to indicate no leakage (Illustration C) and high levels of leakage (Illustration A); relatively low levels of leakage (Illustration B) are comparable to typical errors associated with inaccurate estimation of airflow impedance within a respiratory therapy system. In some implementations, another parameter, such as the sound energy ratio in different frequency bands, can be used to extract statistics from the acoustic data generated by the microphone, such as regarding... Figures 24A-24B and Figures 26A-26B As described.

[0249] Figure 26A The sound power levels are shown over time periods when different types of leaks occur, where leaks can be distinguished based on their location within the respiratory therapy system. Acoustic data generated by the microphone can have acoustic characteristics that differ depending on the type of leak. Depending on the type of leak, different conditions may have to be met (e.g., different thresholds may be applied to parameters in the acoustic data).

[0250] like Figure 26A As shown, based on acoustic and spectral characteristics, such as in different frequency bands (in Figure 26A The acoustic energy ratio in the curve (between approximately 0 and approximately 8 kHz) indicates mask leakage, which is represented by a different acoustic notation than mouth leakage (CML or VML). Figure 26A The acoustic energy distribution across different frequency bands in the data reveals a clear difference between the two types of leakage, as indicated by the higher acoustic energy content in the lower frequency band of the mask leakage and the higher acoustic energy content in the higher frequency band of the mouth leakage.

[0251] Figure 26B Is Figure 26A A graph comparing leakage rate, flow rate, and mask pressure over a given time period. (See figure.) Figure 26B As shown, from Figure 26A The detection of mask leakage and mouth leakage (CML or VML) from acoustic data is clearly related to the detection of... Figure 26A The data on mask pressure, flow rate, and leakage rate over the same time period are correlated with the corresponding indications of mask leakage and mouth leakage.

[0252] Alternative implementation methods

[0253] Alternative Implementation 1. A method for determining a mouth leak state, comprising: receiving from a microphone the first acoustic data associated with a user of a breathing device, the breathing device being configured to supply pressurized air to the user's airway during a sleep period; analyzing the first acoustic data associated with the user; and determining the mouth leak state based at least in part on the analysis of the first acoustic data, the mouth leak state indicating air leakage from the user's mouth.

[0254] Alternative implementation 2. The method as described in alternative implementation 1 further includes comparing the first acoustic data with predetermined data indicating the leakage state of the nozzle in order to analyze the first acoustic data.

[0255] Alternative implementation method 3. The method as described in alternative implementation method 2, wherein the predetermined data includes simulation data, historical data, or both.

[0256] Alternative Implementation 4. The method of any one of Alternative Implementations 1 to 3, wherein the analysis of the first acoustic data is based at least in part on cepstral analysis, autocepstral analysis, autocorrelation analysis, spectral analysis, or any combination thereof.

[0257] Alternative Implementation 5. The method as described in alternative implementation 4, wherein the spectral analysis includes Fast Fourier Transform (FFT) with a sliding window, spectrogram, neural network, Short Time Fourier Transform (STFT), wavelet-based analysis, or any combination thereof.

[0258] Alternative implementation method 6. The method of any one of alternative implementation methods 1 to 5 further includes processing the first acoustic data to identify a plurality of features for analyzing the first acoustic data.

[0259] Alternative implementation method 7. The method as described in alternative implementation method 6, wherein the plurality of features includes: (i) a change in spectral characteristics, (ii) a change in frequency, (iii) a change in amplitude, or (iv) any combination thereof.

[0260] Alternative Embodiment 8. The method of any one of Alternative Embodiments 1 to 7, wherein the microphone is an integrated microphone connected to (i) the conduit of the breathing device, (ii) the circuit board of the breathing device, (iii) a connector of the breathing system having the breathing device, (iv) the user interface of the breathing system, or (v) any other component of the breathing system.

[0261] Alternative Implementation 9. The method of any one of Alternative Implementations 1 to 8 further includes: receiving second acoustic data associated with a user of the breathing device from an external microphone during the sleep period; analyzing the second acoustic data associated with the user; and determining the mouth leakage state based at least in part on both the analysis of the first acoustic data and the analysis of the second acoustic data.

[0262] Alternative implementation 10. The method of any one of alternative implementations 1 to 9 further includes: receiving airflow data associated with a user of the breathing device from a flow sensor during the sleep period; analyzing the airflow data associated with the user; and determining a mouth leakage state based at least in part on both the analysis of the first acoustic data and the analysis of the user's airflow data.

[0263] Alternative Implementation 11. The method of any one of Alternative Implementations 1 to 10 further includes: receiving physiological data associated with the user from a physiological sensor during the sleep period; analyzing the physiological data to determine the user's cardiogenic oscillation; and determining the mouth leakage state based at least in part on both the analysis of first acoustic data and the user's cardiogenic oscillation.

[0264] Alternative Implementation 12. The method of any one of Alternative Implementations 1 to 11 further includes: receiving image data associated with the user from a camera during the sleep period; analyzing the image data to determine sleep-related parameters associated with the user; and determining the mouth leakage state based at least in part on both the analysis of the first acoustic data and the sleep-related parameters associated with the user.

[0265] Alternative implementation method 13. The method of any one of alternative implementation methods 1 to 12 further includes: calculating an apnea-hypopnea index (AHI) score based at least in part on the mouth leak status.

[0266] Alternative Implementation 14. The method as described in Alternative Implementation 13, wherein, in order to calculate the AHI score, the control system is configured to execute the machine-readable instructions to: receive sensor data associated with the user from sensors coupled to the breathing device during the sleep period, the sensor data indicating multiple sleep-disordered breathing events during the sleep period; associate the mouth leak state with the sensor data to output one or more false-positive sleep-disordered breathing events; subtract the one or more false-positive sleep-disordered breathing events from the multiple sleep-disordered breathing events to output modified multiple sleep-disordered breathing events; and calculate the AHI score based at least in part on the number of modified sleep-disordered breathing events.

[0267] Alternative Implementation 15. The method of any one of Alternative Implementations 1 to 14, wherein the mouth leakage state includes the duration of the mouth leakage, the severity of the mouth leakage, or both; and wherein the method further includes reducing the sleep score or treatment score at least in part based on the duration of the mouth leakage, the severity of the mouth leakage, or both.

[0268] Alternative implementation method 16. The method, as described in any one of alternative implementation methods 1 to 15, further includes: providing a control signal to the breathing device; and adjusting a pressure setting of the breathing device in response to the mouth leakage state, the pressure setting being associated with pressurized air supplied to the user's airway.

[0269] Alternative implementation 17. The method as in alternative implementation 16, further comprising: analyzing first acoustic data associated with the user to determine that the user is exhaling; and in response to determining that the user is exhaling, reducing the pressure of pressurized air into the user's airway during the user's exhalation.

[0270] Alternative implementation 18. The method as described in alternative implementation 17, wherein reducing the pressure of the pressurized air includes increasing the expiratory decompression (EPR) level associated with the breathing device.

[0271] Alternative Embodiment 19. The method of any one of alternative embodiments 1 to 18 further includes: providing a control signal to a humidifier connected to the breathing device, the humidifier being configured to introduce moisture into pressurized air supplied to the user's airway; and adjusting a humidification setting associated with the humidifier in response to a mouth leak, such that more moisture is introduced into the pressurized air supplied to the user's airway.

[0272] Alternative implementation method 20. The method described in alternative implementation method 19 further includes: releasing a portion of the decongestant into the moisture introduced into the compressed air for adjusting the humidification setting.

[0273] Alternative Implementation 21. The method of any one of Alternative Implementations 1 to 20 further includes: providing a control signal to the smart pillow; and adjusting the smart pillow in response to the mouth leakage state such that the smart pillow causes the user to change the position of the user's head.

[0274] Alternative Implementation 22. The method of any one of alternative implementations 1 to 21 further includes: providing a control signal to the smart bed or smart mattress; and adjusting the smart bed or smart mattress in response to the mouth leakage state, such that the smart bed or smart mattress causes the user to change the position of the user's body.

[0275] Alternative Implementation 23. The method of any one of Alternative Implementations 1 to 22 further includes: providing a control signal to a wearable sensor, the wearable sensor being connectable to a part of the user's body; and adjusting the wearable sensor in response to the mouth leakage state such that the wearable sensor stimulates the user's neck or jaw to close the user's mouth.

[0276] Alternative implementation method 24. The method of any one of alternative implementation methods 1 to 23 further includes: in response to the mouth leakage state, providing a notification to the user via an electronic device, thereby alerting the user to the mouth leakage state.

[0277] Alternative implementation 25. The method as described in alternative implementation 24, wherein the electronic device is an electronic display device, and the provision of the notification includes displaying a message on the electronic display device.

[0278] Alternative implementation 26. The method as described in alternative implementation 25, wherein the electronic display device is a mobile phone.

[0279] Alternative Implementation 27. The method of any one of Alternative Implementations 24 to 26, wherein the notification comprises: reminding the user (i) to close his / her mouth during a sleep period, (ii) to moisten his / her lips before the next sleep period, or (iii) both of (i) and (ii).

[0280] Alternative Implementation 28. The method of any one of Alternative Implementations 24 to 27, wherein the notification includes instructions and / or suggestions to the user: (i) to use another mask, (ii) to wake up, (iii) the user has a mouth leak, or any combination thereof.

[0281] Alternative implementation 29. The method of any one of alternative implementations 24 to 28, wherein the electronic device includes a speaker, and providing the notification includes playing sound via the speaker.

[0282] Alternative implementation 30. The method as described in alternative implementation 29, wherein the sound is loud enough to wake the user.

[0283] Alternative implementation method 31. The method of any one of alternative implementation methods 1 to 30, wherein the mouth leakage state includes a mouth leakage score during the sleep period.

[0284] Alternative Implementation 32. The method as described in Alternative Implementation 31, wherein the mouth leakage score is determined at least in part based on the percentage of mouth leakage during sleep, peak mouth leakage volume, total mouth leakage volume, or any combination thereof.

[0285] Alternative implementation method 33. The method, such as alternative implementation method 31 or alternative implementation method 32, further includes: receiving user input data from a user device, the user input data indicating subjective feedback associated with the user; and determining the mouth leakage score based at least in part on the user input data.

[0286] Alternative implementation method 34. The method of any one of alternative implementation methods 1 to 33 further includes: receiving sleep stage data associated with the user during the sleep period; determining a sleep stage based at least in part on the sleep stage data; and associating the mouth leakage state with the sleep stage.

[0287] Alternative implementation method 35. The method as described in alternative implementation method 34, wherein the sleep stages include wakefulness, drowsiness, sleep, light sleep, deep sleep, N1 sleep, N2 sleep, N3 sleep, REM sleep, sleep stage segmentation, or any combination thereof.

[0288] Alternative implementation 36. The method, such as alternative implementation 34 or alternative implementation 35, further includes: displaying an indication on a display device, the indication including a separate mouth leakage status for each sleep stage.

[0289] Alternative Implementation 37. A method for outputting a mouth leak status to a user of a breathing device, comprising: receiving acoustic data associated with a user of the breathing device from a microphone, the breathing device being configured to supply pressurized air to the user's airway during a sleep period; and processing the acoustic data using a machine learning algorithm to output a mouth leak status of the user, the mouth leak status indicating that air is leaking from the user's mouth.

[0290] Alternative Implementation 38. A method for determining optimal inspiratory pressure and optimal expiratory pressure for a user of a breathing device, comprising: receiving acoustic data from a microphone associated with a user of the breathing device during a plurality of sleep periods, the microphone being configured to supply pressurized air to the user's airway, the acoustic data including inspiratory acoustic data and expiratory acoustic data; receiving pressure data associated with the pressurized air supplied to the user's airway during the plurality of sleep periods, the pressure data including inspiratory pressure data and expiratory pressure data; analyzing the acoustic data to determine a mouth leakage state of the user for each of the plurality of sleep periods, the mouth leakage state indicating air leakage from the user's mouth; and determining the optimal inspiratory pressure and the optimal expiratory pressure of the user based at least in part on (i) the user's mouth leakage state for each of the plurality of sleep periods and (ii) the pressure data.

[0291] Alternative implementation method 39. The method as described in alternative implementation method 12 or alternative implementation method 38, wherein the pressure data is received from a pressure sensor connected to the breathing device.

[0292] Alternative implementation method 40. The method described in alternative implementation methods 12, 38 or 39, wherein the pressure data is received from a pressure sensor external to the breathing device.

[0293] Alternative implementation method 41. The method described in alternative implementation methods 12, 38, 39 or 40, wherein the pressure data is received from the breathing device.

[0294] Alternative implementation method 42. The method of any one of alternative implementation methods 38 to 41 further includes adjusting the pressure setting of the breathing device based at least in part on the user's optimal inspiratory pressure and optimal expiratory pressure.

[0295] Alternative implementation method 43. The method, as described in any one of alternative implementation methods 38 to 42, further includes: receiving subsequent acoustic data from the microphone during a subsequent sleep period; receiving the optimal inspiratory pressure and the optimal expiratory pressure as subsequent pressure data for the subsequent sleep period; and repeating the analysis and the determination to update the user's optimal inspiratory pressure and the optimal expiratory pressure.

[0296] Alternative Implementation 44. A method for determining an estimated mouth leak state, comprising receiving acoustic data associated with a user of a breathing device from a microphone during a plurality of sleep periods, the breathing device being configured to supply pressurized air to the user's airway; receiving physiological data associated with the user from a sensor for each of the plurality of sleep periods; analyzing the acoustic data to determine the user's mouth leak state for each of the plurality of sleep periods, the mouth leak state indicating air leakage from the user's mouth; and training a machine learning algorithm using (i) the user's mouth leak state for each of the plurality of sleep periods and (ii) the physiological data, such that the machine learning algorithm is configured to: receive current physiological data associated with the current sleep period as input; and determine an estimated mouth leak state for the current sleep period as output.

[0297] Alternative implementation 45. The method as described in alternative implementation 44, wherein the microphone and the sensor are the same.

[0298] Alternative Implementation 46. The method as described in alternative implementation 11 or alternative implementation 44, wherein the physiological data generated by the sensor includes: respiratory alcohol data, blood alcohol data, blood pressure data, blood glucose data, congestion data, occlusion data, body temperature data, heart rate data, exercise data, respiratory data, sleep stage data, mask data, CO2 level data, or any combination thereof.

[0299] Alternative implementation 47. The method as described in alternative implementation 46, wherein the respiratory data includes respiratory rate, respiratory shape, or both.

[0300] Alternative implementation 48. The method of any one of alternative implementations 38 to 47 further includes: receiving the current physiological data during the current sleep period as input to the machine learning algorithm; generating an estimated mouth leakage state for the current sleep period as output of the machine learning algorithm; and adjusting the pressure setting of the breathing device based at least in part on the estimated mouth leakage state.

[0301] Alternative Implementation 49. The method of any one of Alternative Implementations 38 to 48 further includes: receiving the current physiological data as input to the machine learning algorithm before the next sleep period; generating an estimated mouth leakage state for the next sleep period as output of the machine learning algorithm; and determining adjustments for recommendations to be displayed on a user device based at least in part on the estimated mouth leakage state.

[0302] Alternative Implementation 50. The method as described in Alternative Implementation 49, wherein the suggested adjustments include (i) adjusting the pressure setting of the breathing device, the pressure setting being associated with pressurized air supplied to the user's airway; (ii) adjusting the humidification setting of a humidifier connected to the breathing device, the humidifier being configured to introduce moisture into the pressurized air supplied to the user's airway; (iii) suggesting a mask type for the breathing device; (iv) suggesting a sleeping position for the user; (v) suggesting a chin strap for the user; (vi) suggesting a nose bridge for the user; (vii) any combination thereof.

[0303] Alternative Embodiment 51. A system comprising: a control system including one or more processors; and a memory storing machine-readable instructions thereon; wherein 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 as described in any one of Alternative Embodiments 1 to 50 is implemented.

[0304] Alternative Implementation 52. A system comprising a control system configured to implement the method of any one of alternative implementations 1 to 50.

[0305] Alternative Implementation 53. A computer program product comprising instructions that, when executed by a computer, cause the computer to perform a method as described in any one of Alternative Implementations 1 to 50.

[0306] Alternative implementation 54. The computer program product as described in alternative implementation 53, wherein the computer program product is a non-transient computer-readable medium.

[0307] Alternative Implementation 55. A method for determining a mouth leak state associated with a user of a breathing device, comprising: receiving airflow data associated with a user of the breathing device, the breathing device being configured to supply pressurized air to the user's airway during a treatment period, the airflow data including pressure data; analyzing the airflow data associated with the user; and determining a mouth leak state associated with the user, at least in part based on the analysis, the mouth leak state indicating whether air is leaking from the user's mouth.

[0308] Alternative implementation 56. The method as described in alternative implementation 55, wherein the airflow data further includes flow rate data.

[0309] Alternative implementation 57. The method as described in alternative implementation 56, wherein the flow data is received from a flow sensor associated with the breathing device.

[0310] Alternative implementation 58. The method as described in alternative implementation 57, wherein the flow sensor is integrated into the breathing device, coupled to the breathing device, or both.

[0311] Alternative implementation method 59. The method of any one of alternative implementation methods 55 to 58, wherein the pressure data is received from a pressure sensor associated with the breathing device.

[0312] Alternative implementation 60. The method as described in alternative implementation 59, wherein the pressure sensor is integrated into the breathing device, coupled to the breathing device, or both.

[0313] Alternative implementation method 61. The method of any one of alternative implementation methods 55 to 60 further includes: identifying a first breathing cycle of the user within the received airflow data, the first breathing cycle having an inhalation portion and an exhalation portion.

[0314] Alternative implementation method 62. The method as described in alternative implementation method 61, wherein the length of the user’s first breathing cycle is about five seconds.

[0315] Alternative implementation 63. The method as described in alternative implementation 55, wherein identifying the first respiratory cycle includes identifying the start of the first breath, the end of the first breath, or both.

[0316] Alternative implementation method 64. The method of any one of alternative implementation methods 61 to 63, wherein analyzing airflow data associated with the user includes processing the airflow data to identify one or more features associated with the first respiratory cycle.

[0317] Alternative Implementation 65. The method as described in Alternative Implementation 64, wherein one or more features include minimum pressure, maximum pressure, pressure skewness, pressure kurtosis, pressure power spectral density, flow range, minimum flow rate, maximum flow rate, flow skewness, flow kurtosis, flow carrier area ratio, or any combination thereof.

[0318] Alternative implementation 66. The method as described in alternative implementation 65, wherein the boundary of the pressure range is defined by the minimum pressure and the maximum pressure.

[0319] Alternative implementation method 67. The method described in alternative implementation method 65 or alternative implementation method 66, wherein the minimum pressure is associated with the end of the inhalation portion, the beginning of the exhalation portion, or both.

[0320] Alternative implementation method 68. The method of any one of alternative implementation methods 65 to 67, wherein one or more features associated with the first respiratory cycle are calculated on 1, 2, 3, 4, 5, 6, 7 or 8 adjacent respiratory cycles.

[0321] Alternative implementation 69. The method as described in alternative implementation 68, wherein one or more features associated with the first respiratory cycle are calculated over approximately 30 seconds.

[0322] Alternative implementation method 70. The method of any one of alternative implementation methods 65 to 69, wherein the flow sub-area ratio is calculated by dividing a first sub-area by a second sub-area, the first sub-area being a portion of the flow exhalation area and the second sub-area being the flow exhalation area, wherein the flow exhalation area is defined by a flow exhalation curve and zero flow rate, wherein a portion of the flow exhalation area is defined by the flow exhalation curve and a flow rate threshold level.

[0323] Alternative implementation 71. The method as described in alternative implementation 70, wherein the flow threshold level is calculated by adding a predetermined percentage of the flow range to the minimum flow.

[0324] Alternative implementation 72. The method as described in alternative implementation 71, wherein the predetermined percentage is 25%.

[0325] Alternative implementation method 73. The method of any one of alternative implementation methods 70 to 72, wherein the flow rate threshold level is adjusted at least in part based on further analysis of airflow data associated with the user.

[0326] Alternative implementation method 74. The method of any one of alternative implementation methods 70 to 73, wherein the nozzle leakage state is determined at least in part based on the pressure range, the minimum pressure of detrending, and the flow area ratio.

[0327] Alternative implementation method 75. The method of any one of alternative implementation methods 70 to 74, wherein the mouth leakage state is determined at least in part based on the output from a logistic regression model, and wherein the logistic regression model is calculated by:

[0328]

[0329] Alternative implementation 76. The method as described in alternative implementation 75, wherein the output from the logistic regression model that is greater than or equal to a threshold indicates that the mouth leakage state is a valve-type mouth leakage or a continuous mouth leakage.

[0330] Alternative implementation method 77. The method as described in alternative implementation method 76, wherein the threshold is 0.6.

[0331] Alternative implementation method 78. The method of any one of alternative implementation methods 65 to 77 further includes: determining the operating mode of the breathing device.

[0332] Alternative implementation method 79. The method as described in alternative implementation method 78, wherein the operating mode is CPAP, APAP, or BiPAP.

[0333] Alternative implementation method 80. The method of any one of alternative implementation methods 78 to 79, wherein the one or more features are determined at least in part based on the determined operating mode.

[0334] Alternative implementation method 81. The method of any one of alternative implementation methods 78 to 80, wherein the one or more features are determined at least in part based on removing the expiratory decompression (EPR) component from the pressure data.

[0335] Alternative implementation method 82. The method of any one of alternative implementation methods 55 to 81, wherein the nozzle leakage state is (i) no nozzle leakage, (ii) valve-type nozzle leakage, or (iii) continuous nozzle leakage.

[0336] Alternative implementation method 83. The method as described in alternative implementation method 82, wherein the mouth-leaking-free method is associated with a full-face mask, nose mask, or pillow mask.

[0337] Alternative implementation method 84. The method of any one of alternative implementation methods 82 to 83, wherein the valve-type mouth leakage is associated with a nose mask or pillow mask.

[0338] Alternative implementation method 85. The method of any one of alternative implementation methods 82 to 84, wherein the continuous mouth leakage is associated with a full face mask, nose mask, or pillow mask.

[0339] Alternative implementation method 86. The method of any one of alternative implementation methods 55 to 85, wherein the pressurized air supplied to the user's airway during the treatment period is between 4 cmH2O and 20 cmH2O.

[0340] Alternative implementation method 87. The method as described in alternative implementation method 86, wherein the pressurized air supplied to the user's airway during the treatment period is approximately 8 cmH2O.

[0341] Alternative implementation method 88. The method of any one of alternative implementation methods 55 to 87 further includes calculating a treatment score or AHI score based at least in part on the determined mouth leakage status.

[0342] Alternative Implementation 89. The method as described in Alternative Implementation 88 further includes: receiving sensor data associated with the user from a sensor coupled to the breathing device during the treatment period, the sensor data indicating the number of multiple sleep-disordered breathing events during the treatment period; associating the mouth leakage state with the sensor data to output one or more false-positive sleep-disordered breathing events; subtracting the one or more false-positive sleep-disordered breathing events from the multiple sleep-disordered breathing events to output modified multiple sleep-disordered breathing events; and calculating a treatment score based at least in part on the number of modified multiple sleep-disordered breathing events.

[0343] Alternative implementation 90. The method of any one of alternative implementations 55 to 89, wherein the mouth leakage state includes the duration of the mouth leakage, the severity of the mouth leakage, or both; and wherein the method further includes reducing the sleep score or treatment score at least in part based on the duration of the mouth leakage, the severity of the mouth leakage, or both.

[0344] Alternative implementation 91. The method of any one of alternative implementations 55 to 90 further includes: providing a control signal to the breathing device; and adjusting a pressure setting of the breathing device in response to the mouth leakage state, the pressure setting being associated with pressurized air supplied to the user's airway.

[0345] Alternative implementation 92. The method as described in alternative implementation 91 further includes: analyzing airflow data associated with the user to determine that the user is exhaling; and in response to determining that the user is exhaling, reducing the pressure of pressurized air into the user's airway during the user's exhalation.

[0346] Alternative implementation 93. The method as described in alternative implementation 92, wherein reducing the pressure of the pressurized air includes increasing the expiratory decompression (EPR) level associated with the breathing device.

[0347] Alternative implementation 94. The method of any one of alternative implementations 55 to 93 further includes: providing a control signal to a humidifier connected to the breathing device, the humidifier being configured to introduce moisture into pressurized air supplied to the user's airway; and adjusting a humidification setting associated with the humidifier in response to a mouth leak, such that more moisture is introduced into the pressurized air supplied to the user's airway.

[0348] Alternative implementation method 95. The method, as in alternative implementation method 94, further includes: releasing a portion of the decongestant into the moisture introduced into the compressed air for adjusting the humidification setting.

[0349] Alternative implementation 96. The method of any one of alternative implementations 55 to 95 further includes: providing a control signal to the smart pillow; and adjusting the smart pillow in response to the mouth leakage state such that the smart pillow causes the user to change the position of the user's head.

[0350] Alternative Implementation 97. The method of any one of Alternative Implementations 55 to 96 further includes: providing a control signal to the smart bed or smart mattress; and adjusting the smart bed or smart mattress in response to the mouth leakage state such that the smart bed or smart mattress causes the user to change the position of the user's body.

[0351] Alternative Implementation 98. The method of any one of Alternative Implementations 55 to 97 further includes: providing a control signal to a wearable sensor, the wearable sensor being connectable to a part of the user's body; and adjusting the wearable sensor in response to the mouth leakage state such that the wearable sensor stimulates the user's neck or jaw to close the user's mouth.

[0352] Alternative implementation 99. The method of any one of alternative implementations 55 to 98 further includes, in response to the mouth leakage condition, providing a notification to the user via an electronic device, thereby alerting the user to the mouth leakage condition.

[0353] Alternative implementation 100. The method as described in alternative implementation 99, wherein the electronic device is an electronic display device, and the provision of the notification includes displaying a message on the electronic display device.

[0354] Alternative implementation 101. The method as described in alternative implementation 100, wherein the electronic display device is a mobile phone.

[0355] Alternative implementation 102. The method of any one of alternative implementations 99 to 101, wherein the notification includes reminding the user (i) to close his / her mouth during the treatment session, (ii) to moisturize the lips before the next treatment session, or (iii) both of (i) and (ii).

[0356] Alternative implementation method 103. The method of any one of alternative implementation methods 99 to 102, wherein the notification includes instructions and / or suggestions to the user: (i) to use another mask, (ii) to wake up, (iii) the user has a mouth leak, or a combination thereof.

[0357] Alternative implementation 104. The method of any one of alternative implementations 99 to 103, wherein the electronic device includes a speaker, and providing the notification includes playing sound via the speaker.

[0358] Alternative implementation 105. The method as described in alternative implementation 104, wherein the sound is loud enough to wake the user.

[0359] Alternative implementation method 106. The method of any one of alternative implementation methods 55 to 105, wherein the mouth leakage status includes a mouth leakage score during the treatment period.

[0360] Alternative implementation 107. The method as described in alternative implementation 106, wherein the mouth leakage score is determined at least in part based on the following: the percentage of mouth leakage during the treatment period, the peak volume of mouth leakage, the total volume of mouth leakage, or a combination thereof.

[0361] Alternative implementation 108. The method, such as alternative implementation 106 or alternative implementation 107, further includes: receiving user input data from a user device, the user input data indicating subjective feedback associated with a user; and determining the mouth leakage score based at least in part on the user input data.

[0362] Alternative implementation 109. The method of any one of alternative implementations 55 to 108 further includes: receiving sleep stage data associated with the user during the treatment period; determining a sleep stage based at least in part on the sleep stage data; and associating the mouth leakage state with the sleep stage.

[0363] Alternative implementation method 110. The method as described in alternative implementation method 109, wherein the sleep stages include wakefulness, drowsiness, sleep, light sleep, deep sleep, N1 sleep, N2 sleep, N3 sleep, REM sleep, sleep stage segmentation, or a combination thereof.

[0364] Alternative implementation 111. The method, as described in alternative implementation 109 or alternative implementation 110, further includes: displaying an indication on a display device, the indication including a separate mouth leakage status for each sleep stage.

[0365] Alternative Implementation 112. A system comprising: a control system including one or more processors; and a memory storing machine-readable instructions thereon; wherein 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 as described in any one of Alternative Implementations 55 to 111 is performed.

[0366] Alternative Implementation 113. A system for determining a mouth leakage state associated with a user of a breathing apparatus, the system comprising a control system configured to implement the method of any one of Alternative Implementations 55 to 111.

[0367] Alternative Implementation 114. A computer program product comprising instructions that, when executed by a computer, cause the computer to perform a method as described in any one of Alternative Implementations 55 to 111.

[0368] Alternative implementation 115. The computer program product as described in alternative implementation 114, wherein the computer program product is a non-transient computer-readable medium.

[0369] 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 embodiments according to various aspects of the invention are also contemplated, which can combine any number of features from any of the embodiments described herein.

Claims

1. 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-readable instructions in the memory are executed by at least one of the one or more processors of the control system, a method is implemented, the method comprising: Receive airflow data associated with a user of a breathing device configured to supply pressurized air to the user's airway during treatment periods, the airflow data including pressure data and / or flow rate data; Analyzing airflow data associated with the user, wherein the analysis includes processing the airflow data to identify one or more features that distinguish mouth leaks from: (i) normal breathing during treatment and / or (ii) other types of unintentional leaks; and wherein the one or more features include one or both of normalized ventilation relative to baseline ventilation and normalized respiratory rate relative to baseline respiratory rate; and Based at least in part on the analysis, a mouth leakage state associated with the user is determined, the mouth leakage state indicating whether air is leaking from the user's mouth.

2. The system of claim 1, wherein one or more features further include: The covariance between leakage and ventilation, the time during which the covariance remains above a threshold, the variability of unintentional leakage, the variability of respiratory rate, or any combination thereof.

3. The system of claim 1, wherein the one or more features are calculated based on: user flow signal, mask pressure signal, blower flow signal, blower pressure signal, or any combination thereof; wherein for each signal, the one or more features include: (i) Frame area, (ii) Breath area, (iii) Complement of breath area, (iv) Ratio of breath area to frame area, (v) Ratio of breath area to complement of breath area, (vi) Skewness of signal, (vii) Kurtosis of signal, (viii) First derivative of skewness, (ix) First derivative of kurtosis, (x) Second derivative of skewness, (xi) Second derivative of kurtosis, or (xii) any combination thereof.

4. The system of claim 1, wherein one or more features include: Minimum pressure, maximum pressure, pressure skewness, pressure kurtosis, pressure power spectral density, flow range, minimum flow rate, maximum flow rate, flow skewness, flow kurtosis, flow carrier area ratio, or any combination thereof.

5. The system of claim 4, wherein the minimum pressure is associated with the end of the inhalation portion, the beginning of the exhalation portion, or both.

6. The system of claim 1, wherein one or more features are calculated over 1, 2, 3, 4, 5, 6, 7 or 8 adjacent breaths.

7. The system of claim 1, wherein one or more features are calculated over 30 seconds.

8. The system of any one of claims 4 or 5, wherein the flow sub-area ratio is calculated by dividing a first sub-area by a second sub-area, the first sub-area being a portion of the flow expiratory area, and the second sub-area being the flow expiratory area, wherein, The flow expiratory area is defined by the flow expiratory curve and zero flow rate, wherein a portion of the flow expiratory area is defined by the flow expiratory curve and a flow rate threshold level.

9. The system of claim 8, wherein the flow threshold level is calculated by adding a predetermined percentage of the flow range to the minimum flow.

10. The system of claim 9, wherein the predetermined percentage is 25%.

11. The system of claim 8, wherein the nozzle leakage state is determined at least in part based on the pressure range, the minimum pressure for detrending, and the flow area ratio.

12. The system of claim 8, wherein the mouth leakage state is determined at least in part based on the output from a logistic regression model, and wherein the logistic regression model is calculated as follows: in, P is the probability output, b is the bias, x1 is the pressure range, x2 is the minimum pressure for detrending, x3 is the flow area ratio, and α1, α2, and α3 are the weights of the logistic regression.

13. The system of claim 12, wherein the output from the logistic regression model that is greater than or equal to a threshold indicates that the mouth leakage state is a valve-type mouth leakage or a continuous mouth leakage.

14. The system of claim 13, wherein the threshold is 0.

6.

15. The system of claim 1, wherein the method further comprises determining an operating mode of the breathing device, wherein the one or more features are determined at least in part based on the determined operating mode.

16. The system of claim 15, wherein the operating mode is continuous positive airway pressure (CPAP), automatic positive airway pressure (APAP), or bilevel positive airway pressure (BiPAP).

17. The system of claim 15 or claim 16, wherein one or more features are determined at least in part based on removing the expiratory decompression component from the pressure data.

18. The system of claim 1, wherein one or more features are associated with a first respiration.

19. The system of claim 18, wherein the method further comprises: The user's first breath is identified within the received airflow data, the first breath having an inhalation portion and an exhalation portion.

20. The system of claim 19, wherein recognizing the first breath includes recognizing the start of the first breath, the end of the first breath, or both.

21. The system of claim 1, wherein the nozzle leakage state is (i) no nozzle leakage, (ii) valve-type nozzle leakage, or (iii) continuous nozzle leakage.

22. The system of claim 1, wherein the pressurized air supplied to the user's airway during the treatment period is between 4 cmH2O and 20 cmH2O.

23. The system of claim 1, wherein the method further comprises: Treatment scores or apnea-hypopnea index (AHI) scores are calculated based at least in part on the determined mouth leakage status.

24. The system of claim 23, wherein the method further comprises: During the treatment period, sensor data associated with the user is received from sensors connected to the breathing device, the sensor data indicating the number of multiple sleep-disordered breathing events during the treatment period; The mouth leakage status is correlated with the sensor data to output one or more false positive sleep apnea events; Subtract the one or more false-positive sleep apnea events from the plurality of sleep apnea events to output the modified number of plurality of sleep apnea events; as well as The treatment score is calculated at least in part based on the number of modified sleep-disordered breathing events.

25. The system of claim 1, wherein the mouth leakage state includes the duration of the mouth leakage, the severity of the mouth leakage, or both; and wherein the method further includes reducing the sleep score or treatment score at least in part based on the duration of the mouth leakage, the severity of the mouth leakage, or both.

26. The system of claim 1, wherein the method further comprises: Provide control signals to the breathing device; as well as In response to the mouth leakage condition, the pressure setting of the breathing device is adjusted, the pressure setting being associated with the pressurized air supplied to the user's airway.

27. The system of claim 26, wherein the method further comprises: Analyze the airflow data associated with the user to determine if the user is exhaling; as well as In response to determining that the user is exhaling, the pressure of the pressurized air delivered to the user's airway is reduced during the user's exhalation.

28. The system of claim 27, wherein reducing the pressure of the pressurized air includes increasing the expiratory decompression level associated with the breathing device.

29. The system of claim 1, wherein the method further comprises: A control signal is provided to a humidifier connected to the breathing device, the humidifier being configured to introduce moisture into pressurized air supplied to the user's airway; as well as In response to the mouth leakage condition, the humidification setting associated with the humidifier is adjusted so that more moisture is introduced into the pressurized air supplied to the user's airway.

30. The system of claim 29, wherein the method further comprises: A portion of the decongestant is released into the moisture introduced into the pressurized air to adjust the humidification setting.

31. The system of claim 1, wherein the method further comprises: Provide control signals to the smart pillow; as well as In response to the mouth leakage state, the smart pillow is adjusted so that it prompts the user to change the position of the user's head.

32. The system of claim 1, wherein the method further comprises: Provide control signals to smart beds or smart mattresses; as well as In response to the mouth leakage state, the smart bed or smart mattress is adjusted so that the smart bed or smart mattress prompts the user to change the position of the user's body.

33. The system of claim 1, wherein the method further comprises: Provide control signals to wearable sensors that can be attached to parts of the user's body; as well as In response to the mouth leakage state, the wearable sensor is adjusted such that it stimulates the user's neck or jaw to close the user's mouth.

34. The system of claim 1, wherein the method further comprises: In response to the mouth leak condition, a notification is provided to the user via an electronic device, thereby alerting the user to the mouth leak condition.

35. The system of claim 34, wherein the electronic device is an electronic display device, and the provision of the notification includes displaying a message on the electronic display device.

36. The system of claim 34 or 35, wherein the notification includes reminding the user (i) to close his / her mouth during the treatment session, (ii) to moisten his / her lips before the next treatment session, or (iii) both of (i) and (ii).

37. The system of claim 34 or 35, wherein the notification includes instructions and / or suggestions to the user: (i) to use another mask, (ii) to wake up, (iii) the user has a mouth leak, or a combination thereof.

38. The system of claim 34 or 35, wherein the electronic device includes a speaker, and providing the notification includes playing sound via the speaker.

39. The system of claim 38, wherein the sound is loud enough to wake the user.

40. The system of claim 1, wherein the mouth leakage status includes a mouth leakage score during the treatment period.

41. The system of claim 40, wherein the mouth leakage score is determined at least in part based on the following: the percentage of mouth leakage during the treatment period, the peak volume of mouth leakage, the total volume of mouth leakage, or a combination thereof.

42. The system of claim 40 or claim 41, wherein the method further comprises: Receive user input data from the user device, the user input data indicating subjective feedback associated with the user; as well as The mouth leakage score is determined at least in part based on the user input data.

43. The system of claim 1, wherein the method further comprises: During the treatment period, sleep stage data related to the user is received; Sleep stages are determined at least in part based on the sleep stage data; as well as The mouth leakage state is associated with the sleep stage.

44. The system of claim 43, wherein the sleep stages include wakefulness, drowsiness, sleep, light sleep, deep sleep, N1 sleep, N2 sleep, N3 sleep, REM sleep, sleep stage segmentation, or a combination thereof.

45. The system of claim 43 or 44, wherein the method further comprises: The indicator is displayed on the display device, and the indicator includes the individual mouth leakage status for each sleep stage.

46. ​​A computer program product including instructions that, when executed by a computer, cause the computer to perform a method comprising: Receive airflow data associated with a user of a breathing device configured to supply pressurized air to the user's airway during treatment periods, the airflow data including pressure data and / or flow rate data; Analyzing airflow data associated with the user, wherein the analysis includes processing the airflow data to identify one or more features that distinguish mouth leaks from: (i) normal breathing during treatment and / or (ii) other types of unintentional leaks; and wherein the one or more features include one or both of normalized ventilation relative to baseline ventilation and normalized respiratory rate relative to baseline respiratory rate; and Based at least in part on the analysis, a mouth leakage state associated with the user is determined, the mouth leakage state indicating whether air is leaking from the user's mouth.

47. The computer program product of claim 46, wherein the computer program product is a non-transient computer-readable medium.

48. The computer program product of claim 46, wherein one or more of the features further include: The covariance between leakage and ventilation, the time during which the covariance remains above a threshold, the variability of unintentional leakage, the variability of respiratory rate, or any combination thereof.

49. The computer program product of claim 46, wherein the one or more features are calculated based on: user flow signal, mask pressure signal, blower flow signal, blower pressure signal, or any combination thereof; wherein for each signal, the one or more features include: (i) frame area, (ii) breathing area, (iii) complement of breathing area, (iv) ratio of breathing area to frame area, (v) ratio of breathing area to complement of breathing area, (vi) skewness of signal, (vii) kurtosis of signal, (viii) first derivative of skewness, (ix) first derivative of kurtosis, (x) second derivative of skewness, (xi) second derivative of kurtosis, or (xii) any combination thereof; and wherein said one or more features include: minimum pressure, maximum pressure, pressure skewness, pressure kurtosis, pressure power spectral density, flow range, minimum flow rate, maximum flow rate, flow skewness, flow kurtosis, flow carrier area ratio, or any combination thereof.

50. The computer program product of claim 49, wherein the minimum pressure is associated with the end of the inhalation portion, the beginning of the exhalation portion, or both.

51. The computer program product of claim 49 or 50, wherein the flow area ratio is calculated by dividing a first sub-area by a second sub-area, the first sub-area being a portion of the flow exhalation area, and the second sub-area being the flow exhalation area, wherein, The flow expiratory area is defined by the flow expiratory curve and zero flow rate, wherein a portion of the flow expiratory area is defined by the flow expiratory curve and a flow rate threshold level.

52. The computer program product of claim 51, wherein the nozzle leakage state is determined at least in part based on the pressure range, the minimum pressure of detrending, and the flow area ratio.

53. The computer program product of claim 51, wherein the mouth leakage state is determined at least in part based on the output from a logistic regression model, and wherein the logistic regression model is calculated as follows: in, P is the probability output, b is the bias, x1 is the pressure range, x2 is the minimum pressure for detrending, x3 is the flow area ratio, and α1, α2, and α3 are the weights of the logistic regression.

54. The computer program product of claim 53, wherein the output from the logistic regression model that is greater than or equal to a threshold indicates that the mouth leakage state is a valve-type mouth leakage or a continuous mouth leakage.

55. The computer program product of claim 46, wherein the method further comprises determining an operating mode of the breathing device, wherein the determination of the one or more features is based at least in part on the determined operating mode, and wherein the operating mode is continuous positive airway pressure (CPAP), automatic positive airway pressure (APAP), or bilevel positive airway pressure (BiPAP).

56. The computer program product of claim 46, wherein one or more features are associated with a first breath; wherein the method further comprises: Identify the user's first breath within the received airflow data, the first breath having an inhalation portion and an exhalation portion; and wherein identifying the first breath includes identifying the start of the first breath, the end of the first breath, or both.

57. The computer program product of claim 46, wherein the nozzle leakage state is (i) no nozzle leakage, (ii) valve-type nozzle leakage, or (iii) continuous nozzle leakage.

58. The computer program product of claim 46, wherein the method further comprises: Treatment scores or apnea-hypopnea index (AHI) scores are calculated based at least in part on the determined mouth leakage status. During the treatment period, sensor data associated with the user is received from sensors connected to the breathing device, the sensor data indicating the number of multiple sleep-disordered breathing events during the treatment period; The mouth leakage status is correlated with the sensor data to output one or more false positive sleep apnea events; Subtract the one or more false-positive sleep apnea events from the plurality of sleep apnea events to output the modified number of plurality of sleep apnea events; as well as The treatment score is calculated at least in part based on the number of modified sleep-disordered breathing events.

59. The computer program product of claim 46, wherein the method further comprises: Provide control signals to the breathing device; as well as In response to the mouth leakage condition, the pressure setting of the breathing device is adjusted, the pressure setting being associated with the pressurized air supplied to the user's airway.

60. The computer program product of claim 46, wherein the method further comprises: A control signal is provided to a humidifier connected to the breathing device, the humidifier being configured to introduce moisture into pressurized air supplied to the user's airway; as well as In response to the mouth leakage condition, the humidification setting associated with the humidifier is adjusted so that more moisture is introduced into the pressurized air supplied to the user's airway.

61. The computer program product of claim 46, wherein the method further comprises: Provide control signals to smart pillows, smart beds, or smart mattresses; as well as In response to the mouth leakage state, the smart pillow is adjusted such that it prompts the user to change the position of the user's head, or the smart bed or smart mattress is adjusted such that it prompts the user to change the position of the user's body.

62. The computer program product of claim 46, wherein the method further comprises: Provide control signals to wearable sensors that can be attached to parts of the user's body; as well as In response to the mouth leakage state, the wearable sensor is adjusted such that it stimulates the user's neck or jaw to close the user's mouth.

63. The computer program product of claim 46, wherein the method further comprises: In response to the mouth leak condition, a notification is provided to the user via an electronic device, thereby alerting the user to the mouth leak condition.

64. The computer program product of claim 46, wherein the mouth leakage status includes a mouth leakage score during the treatment period; The mouth leakage score is determined at least in part based on the following: the percentage of mouth leakage during the treatment period, the peak volume of mouth leakage, the total volume of mouth leakage, or a combination thereof; and The method further includes: Receive user input data from the user device, the user input data indicating subjective feedback associated with the user; as well as The mouth leakage score is determined at least in part based on the user input data.

65. The computer program product of claim 46, wherein the method further comprises: During the treatment period, sleep stage data related to the user is received; Sleep stages are determined at least in part based on the sleep stage data; The mouth leakage state is associated with the sleep stage, wherein the sleep stage includes wakefulness, drowsiness, sleep, light sleep, deep sleep, N1 sleep, N2 sleep, N3 sleep, REM sleep, sleep stage segmentation, or a combination thereof; and The indicator is displayed on the display device, and the indicator includes the individual mouth leakage status for each sleep stage.

Images