System and method for determining movement during respiratory therapy

Abstract

The present invention relates to a method for determining user movement during use of a respiratory treatment system, comprising: receiving acoustic data associated with a user of the respiratory treatment system; analyzing the received acoustic data; and determining movement events associated with the user based at least in part on the analyzed acoustic data.

Description

[Technical Field]

[0001] The present disclosure relates generally to systems and methods for detecting movement and body position, and more particularly to systems and methods for detecting movement and body position of a user during respiratory therapy. [Background technology]

[0002] Many people suffer from sleep-related and / or respiratory disorders such as periodic limb movement disorder (PLMD), restless legs syndrome (RLS), sleep-disordered breathing (SDB), obstructive sleep apnea (OSA), central sleep apnea (CSA), as well as other types of apnea such as mixed apneas and hypopneas, respiratory effort-related arousals (RERA), Cheyne-Stokes respiration (CSR), respiratory failure, obesity hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular disorders (NMD), rapid eye movement (REM) behavior disorder (also known as RBD), dream actout (DEB), hypertension, diabetes, stroke, insomnia, and chest wall disorders. These disorders are often treated using respiratory therapy systems.

[0003] However, for some users, such systems are uncomfortable, difficult to use, expensive, aesthetically unpleasing, and / or the benefits associated with using the system are not recognized. As a result, some users choose not to start using a respiratory treatment system or to discontinue use of the respiratory treatment system if there is no evidence of symptom severity when not using respiratory treatment. As a further result, some users discontinue use of a respiratory treatment system if there is no encouragement or confirmation that the respiratory treatment system is improving sleep quality and reducing symptoms of these disorders. The present disclosure aims to solve these and other problems. For example, when a user is receiving respiratory treatment, motion information associated with the user can be used to determine sleep-wake status. Therefore, there is a need for a system and method for determining motion associated with a user receiving respiratory treatment. Summary of the Invention

[0004] According to some implementations of the present disclosure, a method for determining user movement during use of a respiratory treatment system is disclosed, including receiving acoustic data associated with a user of the respiratory treatment system, analyzing the received acoustic data, and determining a movement event associated with the user based at least in part on the analyzed acoustic data.

[0005] According to some implementations of the present disclosure, a method for determining user movement during use of a respiratory treatment system is disclosed, including receiving flow data associated with a plurality of flow values ​​of pressurized air directed to an airway of a user of the respiratory treatment system, analyzing the received flow data, and determining a movement event associated with the user based at least in part on the analyzed flow data.

[0006] According to some implementations of the present disclosure, a method for determining a body position of a user during a respiratory treatment session is disclosed, including receiving flow data associated with a user of a respiratory treatment system, analyzing the received flow data to determine one or more characteristics, and determining the body position of the user based at least in part on the determined one or more characteristics.

[0007] According to some implementations of the present disclosure, another method for determining a user's body position during a respiratory treatment session is disclosed: receiving acoustic data associated with a user of a respiratory treatment system; analyzing the received acoustic data to determine one or more characteristics; and determining the user's body position based at least in part on the determined one or more characteristics.

[0008] According to some implementations of the present disclosure, a method is disclosed for monitoring a patient during use of a respiratory therapy system, comprising: determining a motion event associated with the patient using any of the methods disclosed above and further described herein; transmitting a notification to a monitoring device or personnel; and associating the notification with the determined motion event associated with the patient.

[0009] According to some implementations of the present disclosure, a method for monitoring a patient during use of a respiratory therapy system is disclosed, comprising: determining a patient's physical location using any of the methods disclosed above and further described herein; transmitting a notification to a monitoring device or personnel; and transmitting the notification associated with the determined patient's physical location.

[0010] According to some implementations of the present disclosure, a system includes a control system having one or more processors and a memory storing machine-readable instructions. The control system is coupled to the memory. Any of the methods disclosed above and further described herein are performed when the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system.

[0011] According to some implementations of the present disclosure, a system for determining user movement during use of a respiratory treatment system includes a control system configured to perform any of the methods disclosed above and further described herein.

[0012] According to some implementations of the present disclosure, a system for determining body position during use of a respiratory treatment system includes a control system configured to perform any of the methods disclosed above and further described herein.

[0013] According to some implementations of the present disclosure, a system for monitoring a patient during use of a respiratory treatment system includes a control system configured to perform any of the methods disclosed above and further described herein.

[0014] According to some implementations of the present disclosure, 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 summary is not intended to describe each implementation or every aspect of the present disclosure. Additional features and benefits of the present disclosure will be apparent from the following detailed description and drawings.

[0016] These and other advantages of the present disclosure will become apparent from the following detailed description when taken in conjunction with the drawings. [Brief explanation of the drawings]

[0017] [Figure 1] FIG. 1 is a functional block diagram of a system according to some implementations of the present disclosure. [Figure 2] FIG. 2 is a perspective view of at least a portion of the system of FIG. 1, a user wearing a full face mask, and a bed companion, according to some implementations of the present disclosure. [Figure 3] FIG. 3 illustrates the generation of acoustic data responsive to acoustic reflexes associated with a user during use of a respiratory treatment system, according to some implementations of the present disclosure. [Figure 4A] FIG. 4A shows flow data associated with a user of a respiratory treatment system, according to some implementations of the present disclosure. [Figure 4B] FIG. 4B illustrates pressure data associated with a user of a continuous positive airway pressure system, according to some implementations of the present disclosure. [Figure 4C] FIG. 4C illustrates pressure data associated with a user of a respiratory treatment system having an expiratory pressure relief module, according to some implementations of the present disclosure. [Figure 5] FIG. 5 is a flow diagram of a method for determining user movement during use of a respiratory treatment system according to some implementations of the present disclosure. [Figure 6A] FIG. 6A shows radio frequency (RF) data measured during a treatment session according to some implementations of the present disclosure. [Figure 6B] FIG. 6B shows audio data measured during the therapy session of FIG. 6A according to some implementations of the present disclosure. [Figure 6C]FIG. 6C shows processed audio data calculated using the audio data of FIG. 6B according to some implementations of the present disclosure. [Figure 6D] FIG. 6D shows motion activity data calculated using the RF data of FIG. 6A and separately using the processed audio data of FIG. 6C according to some implementations of the present disclosure. [Figure 7A] FIG. 7A shows EMFIT activity data measured during a first treatment session according to some implementations of the present disclosure. [Figure 7B] FIG. 7B shows processed audio data derived from the audio signal generated during the first therapy session of FIG. 7A, according to some implementations of the present disclosure. [Figure 7C] FIG. 7C illustrates EMFIT activity data measured during a second treatment session, according to some implementations of the present disclosure. [Figure 7D] FIG. 7D illustrates audio data measured during the second treatment session of FIG. 7C, according to some implementations of the present disclosure. [Figure 8] FIG. 8 is a flow diagram of a method for determining a user's body position during a respiratory therapy session according to some implementations of the present disclosure. [Figure 9] FIG. 9 shows real-time flow and pressure signals measured during a treatment session according to some implementations of the present disclosure. [Figure 10] FIG. 10 is a flow diagram of a method for determining a user's body position during a respiratory therapy session according to some implementations of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0018] While the present disclosure is susceptible to various modifications and alternative forms, specific implementations and embodiments of the present disclosure have been shown by way of example in the drawings and are herein described in detail. It is to be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but that the present disclosure is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.

[0019] The present disclosure will be described with reference to the accompanying drawings, in which the same or equivalent components are designated by the same reference numerals in the various drawings. The drawings are not drawn to scale and are provided solely to illustrate the present disclosure. Several aspects of the present disclosure are described below with reference to illustrative example applications.

[0020] Many people suffer from sleep-related and / or breathing disorders, including, for example, sleep-disordered breathing (SDB) such as periodic limb movement disorder (PLMD), restless legs syndrome (RLS), obstructive sleep apnea (OSA), central sleep apnea (CSA), other types of apnea such as mixed apneas and hypopneas, respiratory effort-related arousals (RERA), Cheyne-Stokes respiration (CSR), respiratory failure, obesity hypoventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular diseases (NMD), rapid eye movement (REM) behavior disorder (also known as RBD), dream actout (DEB), hypertension, diabetes, stroke, insomnia, and chest wall disorders.

[0021] Obstructive sleep apnea (OSA) is a form of sleep-disordered breathing (SDB) characterized by events such as upper airway obstruction or blockage during sleep due to an abnormally small upper airway combined with a normal loss of muscle tone in the tongue, soft palate, and posterior oropharynx. More generally, apnea generally refers to pauses in breathing (obstructive sleep apnea) or cessation of respiratory function (often referred to as central sleep apnea) caused by air blockage. Typically, individuals stop breathing for approximately 15 to 30 seconds during an obstructive sleep apnea event.

[0022] Other types of apnea include hypopnea, hyperpnea, and hypercapnia. Hypopnea is generally characterized by slow or shallow breathing caused by a narrowed, rather than obstructed, airway. Hyperpnea is generally characterized by an increase in the depth and / or rate of breathing. Hypercapnia is generally characterized by a sudden or excessive amount of carbon dioxide in the bloodstream and is usually caused by insufficient breathing.

[0023] Cheyne-Stokes respiration (CSR) is another form of sleep-disordered breathing. CSR is a disturbance in a patient's respiratory control system that results in alternating periods of waxing and waning ventilation, known as the CSR cycle. CSR is characterized by repeated deoxygenation and reoxygenation of arterial blood.

[0024] Obesity-hypoventilation syndrome (OHS) is defined as the combination of severe obesity and chronic awake hypercapnia in the absence of other causes of hypoventilation. Symptoms include dyspnea, morning headache, and excessive daytime sleepiness.

[0025] Chronic obstructive pulmonary disease (COPD) encompasses any of a group of diseases of the lower respiratory tract that share certain characteristics, such as increased resistance to air movement, a prolonged expiratory phase of breathing, and loss of the lungs' normal elasticity.

[0026] Neuromuscular disorders (NMDs) encompass a number of diseases and illnesses that impair muscle function directly through intrinsic muscle pathology or indirectly through neuropathology. Chest wall disorders are a group of thoracic deformities that result in inefficient connections between the respiratory muscles and the rib cage.

[0027] Respiratory effort-related arousal (RERA) events are typically characterized by increased respiratory effort for 10 seconds or more leading to arousal from sleep, without meeting the criteria for an apnea or hypopnea event. RERAs are defined as a series of breaths characterized by increased respiratory effort leading to arousal from sleep, but without meeting the criteria for an apnea or hypopnea. These events must meet both criteria: (1) a pattern of gradually increasing esophageal negative pressure terminated by a sudden drop in the negative pressure level and arousal; and (2) the event must last 10 seconds or more. In some implementations, a nasal cannula / pressure transducer system is sufficient and reliable for detecting RERAs. The RERA detector can be based on an actual flow signal derived from a respiratory therapy device. For example, a measure of flow limitation can be determined based on the flow signal. A measure of arousal can then be derived as a function of the measure of flow limitation and the measure of sudden increase in ventilation. One such method is described in International Patent Publication No. 2008 / 138040 and U.S. Patent Publication No. 9,358,353, both issued to ResMed, Inc., the entire disclosures of each of which are incorporated herein by reference.

[0028] These and other disorders are characterized by specific events that occur during an individual's sleep (e.g., snoring, apnea, hypopnea, restless legs, sleep disturbances, choking, increased heart rate, labored breathing, asthma attack, epileptic episode, seizure, or any combination thereof).

[0029] The apnea-hypopnea index (AHI) is an index used to indicate the severity of sleep apnea during a sleep session. The AHI is calculated by dividing the number of apnea and / or hypopnea events experienced by a user during a sleep session by the total number of hours of sleep in that sleep session. An event can be, for example, a pause in breathing lasting at least 10 seconds. An AHI of less than 5 is considered normal. An AHI of 5 to less than 15 is considered to indicate mild sleep apnea. An AHI of 15 to less than 30 is considered to indicate moderate sleep apnea. An AHI of 30 or greater is considered to indicate severe sleep apnea. In children, an AHI greater than 1 is considered abnormal. Sleep apnea can be considered "controlled" when the AHI is normal or when the AHI is normal or mild. The AHI, in combination with oxygen saturation, can also be used to indicate the severity of obstructive sleep apnea.

[0030] Generally, activity level during respiratory therapy can be directly estimated from the flow signal alone. While flow data provides some information about activity level over longer time frames, it does not identify movement with precise temporal resolution. Furthermore, features of the flow signal that identify regions of high activity can be confused with other respiratory events, such as coughing, asthma, etc. Therefore, aspects of the present disclosure relate to using echo and / or audio data to determine a user's movement and / or activity level.

[0031] Referring to FIG. 1 , a system 100 according to some implementations of the present disclosure is shown. The system 100 is intended to provide, among other uses, a variety of different sensors associated with a user's use of a respiratory treatment system. The 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, the system 100 further includes a respiratory treatment system 120 including a respiratory treatment device 122. As disclosed in further detail herein, the system 100 can be used to determine a user's movements during use of the respiratory treatment system and / or the user's body position during a respiratory treatment session. The user's body position can include, for example, a supine position, a prone position, a left lateral position, a right lateral position, etc.

[0032] Control system 110 includes one or more processors 112 (hereinafter processors 112). Control system 110 is generally used to control (e.g., operate) 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 microprocessor. While one processor 112 is shown in FIG. 1 , control system 110 may include any suitable number of processors (e.g., one processor, two processors, five processors, ten processors, etc.), which may reside in a single housing or may be located remotely from one another. Control system 110 (or any other control system) or a portion of control system 110, such as processor 112 (or any other processor or portion of any other control system), may be used to perform any one or more steps of the methods described and / or claimed herein. Control system 110 may be coupled to and / or located within the housing of user device 170 and / or the housing of one or more of sensors 130, for example. Control system 110 may be centralized (within one such housing) or distributed (within two or more such housings that are physically distinct). In such implementations that include two or more housings that house control system 110, such housings may be located adjacent to and / or apart from one another.

[0033] The storage device 114 stores machine-readable instructions executable by the processor 112 of the control system 110. The storage device 114 may be any suitable computer-readable storage device or medium, such as, for example, a random or serial access memory device, a hard drive, a solid-state drive, a flash memory device, etc. Although one storage device 114 is shown in FIG. 1 , the system 100 may include any suitable number of storage devices 114 (e.g., one storage device, two storage devices, five storage devices, ten storage devices, etc.). The storage device 114 may be coupled to and / or located within the housing of the respiratory treatment device 122, the housing of the user device 170, the housing of one or more sensors 130, or any combination thereof. Like the control system 110, the storage device 114 may be centralized (within one such housing) or distributed (within two or more such housings that are physically distinct).

[0034] In some implementations, the storage device 114 stores a user profile associated with the user. The user profile may include, for example, demographic information associated with the user, biometric information associated with the user, medical information associated with the user, self-reported user feedback, sleep parameters associated with the user (e.g., sleep-related parameters recorded from one or more previous sleep sessions), or any combination thereof. The demographic information may include, for example, information indicative of the user's age, the user's gender, the user's race, the user's geographic location, relationship status, family history of insomnia or sleep apnea, the user's employment status, the user's education status, the user's socioeconomic status, or any combination thereof. The medical information may include, for example, information indicative of one or more medical conditions associated with the user, medication usage by the user, or both. The medical information may also include a fall risk assessment associated with the user (e.g., a fall risk score using the Morse Fall Scale). The medical information may include, for example, information indicative of one or more medical conditions associated with the user, medication usage by the user, or both. The medical information data may further include a Multiple Sleep Latency Test (MSLT) result or score and / or a Pittsburgh Sleep Quality Index (PSQI) score or value. The medical information data may further include information indicative of a self-reported subjective sleep score (poor, fair, good, etc.), a user's self-reported subjective stress level, a user's self-reported subjective fatigue level, a user's self-reported subjective health status, a recent life event experienced by the user, or any combination thereof. In some implementations, the storage device 114 stores media content that can be displayed on the display device 128.

[0035] The electronic interface 119 is configured to receive data (e.g., physiological data) from one or more sensors 130 so that the data can be stored in the storage device 114 and / or analyzed by the processor 112 of the control system 110. The electronic interface 119 can communicate with the one or more sensors 130 using a wired or wireless connection (e.g., an RF communication protocol, a WiFi communication protocol, a Bluetooth® communication protocol, an IR communication protocol, a cellular network, other optical communication protocols, etc.). The electronic interface 119 may include an antenna, a receiver (e.g., an RF receiver), a transmitter (e.g., an RF transmitter), a transceiver, or any combination thereof. The electronic interface 119 may also include another processor and / or another storage device that is the same as or similar to the processor 112 and storage device 114 described herein. In some implementations, the electronic interface 119 is coupled to or integrated with the user device 170. In other implementations, the electronic interface 119 is coupled to or integrated with (eg, within the housing of) the control system 110 and / or the storage device 114 .

[0036] Respiratory treatment system 120 may include a respiratory pressure therapy device (also referred to as respiratory treatment device 122), a user interface 124, a conduit 126 (also referred to as tubing or an air circuit), a display 128, a humidification tank 129, or a combination thereof. In some implementations, control system 110, memory 114, display 128, one or more of sensors 130, and humidification tank 129 are part of respiratory treatment device 122. Respiratory pressure therapy refers to the application of an air supply to the entrance of a user's airway at a controlled target pressure that is nominally positive relative to the atmosphere throughout the user's respiratory cycle (as opposed to negative pressure therapy, such as a tank ventilator or a positive-negative pressure external ventilator (cuirass)). Respiratory treatment 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, mixed sleep apnea).

[0037] Respiratory treatment device 122 is typically used to generate pressurized air delivered to a user (e.g., using one or more motors driving one or more compressors). In some implementations, respiratory treatment device 122 generates a continuous, constant air pressure delivered to a user. In other implementations, respiratory treatment device 122 generates two or more predetermined pressures (e.g., a first predetermined air pressure and a second predetermined air pressure). In yet other implementations, respiratory treatment device 122 is configured to generate a variety of different air pressures within a predetermined range. For example, respiratory treatment device 122 can deliver, e.g., at least about 6 cmH2O, at least about 10 cmH2O, at least about 20 cmH2O, between about 6 cmH2O and about 10 cmH2O, between about 7 cmH2O and about 12 cmH2O, etc. Respiratory treatment device 122 can also deliver pressurized air at a predetermined flow rate, e.g., between about -20 L / min and about 150 L / min, while maintaining a positive pressure (relative to ambient pressure).

[0038] The user interface 124 engages a portion of the user's face to deliver pressurized air from the respiratory treatment device 122 to the user's airway, helping to prevent the airway from narrowing and / or closing during sleep. This can also increase the user's oxygen intake while sleeping. Typically, the user interface 124 engages the user's face to deliver pressurized air to the user's airway through the user's mouth, nose, or both the user's mouth and nose. The respiratory treatment device 122, the user interface 124, and the conduits 126s form an airway fluidly connected to the user's airway. The pressurized air also increases the user's oxygen intake while sleeping. Depending on the therapy being applied, the user interface 124 can, for example, form a seal with an area or portion of the user's face to facilitate delivery of gas at a pressure sufficiently different from ambient pressure to effect therapy, for example, a positive pressure of approximately 10 cmH2O relative to ambient pressure. In other forms of therapy, such as oxygen delivery, the user interface may not include a seal sufficient to facilitate delivery of a gas supply at a positive pressure of approximately 10 cmH2O to the airways.

[0039] As shown in FIG. 2 , in some implementations, the user interface 124 is or includes a facial mask (e.g., a full-face mask) that covers at least a portion of the nose and mouth of the user 210. Alternatively, in some implementations, the user interface 124 may be a nasal mask that provides air to the user's nose or a nasal pillow mask that delivers air directly to the user's nostrils. The user interface 124 may include multiple straps (e.g., including hook-and-loop fasteners) for positioning and / or stabilizing the interface on a portion of the user (e.g., the face) and a conformable cushion (e.g., silicone, plastic, foam, etc.) that helps provide an airtight seal between the user interface 124 and the user. The user interface 124 may also include one or more vents to allow carbon dioxide and other gases exhaled by the user 210 to escape. In other implementations, the user interface 124 includes a mouthpiece (e.g., a night guard mouthpiece shaped to fit the user's teeth, a mandibular repositioning device, etc.).

[0040] A conduit 126 (also called an air circuit or tubing) allows air to flow between components of the respiratory treatment system 120, such as the respiratory treatment device 122 and the user interface 124. In some implementations, there may be separate branches of this conduit for inhalation and exhalation. In other implementations, a single-branch conduit is used for both inhalation and exhalation.

[0041] One or more of the respiratory treatment device 122, the user interface 124, the conduit 126, the display device 128, and the humidification tank 129 may include one or more sensors (e.g., a pressure sensor, a flow sensor, or more generally, any of the other sensors 130 described herein) that can be used, for example, to measure the air pressure and / or flow rate of the pressurized air supplied by the respiratory treatment device 122.

[0042] The display device 128 is generally used to display images and / or information, including still images, moving images, or both, related to the respiratory treatment device 122. For example, the display device 128 can provide information regarding the status of the respiratory treatment device 122 (e.g., whether the respiratory treatment device 122 is on / off, the pressure of the air being delivered by the respiratory treatment device 122, the temperature of the air being delivered by the respiratory treatment device 122, etc.) and / or other information (e.g., a sleep score and / or a treatment score (also referred to as a myAir™ score, as described in International Publication No. WO 2016 / 061629 and U.S. Patent Application Publication No. 2017 / 0311879, each of which is incorporated by reference herein in its entirety), the current date / time, personal information of the user 210, etc.). In some implementations, the display device 128 functions as a human-machine interface (HMI) that includes a graphical user interface (GUI) configured to display images as an input interface. The display device 128 can be an LED display, an OLED display, an LCD display, etc. The input interface may be, for example, a touch screen or touch-sensitive board, a mouse, a keyboard, or any sensor system configured to sense inputs made by a human user interacting with respiratory treatment device 122 .

[0043] The humidification tank 129 is coupled to or integrated with the respiratory treatment device 122 and includes a reservoir for storing water that can be used to humidify the pressurized air delivered from the respiratory treatment device 122. The respiratory treatment device 122 may include a heater that heats the water in the humidification tank 129 to humidify the pressurized air provided to the user. Additionally, in some implementations, the conduit 126 may also include a heating element (e.g., coupled to and / or embedded in the conduit 126) that heats the pressurized air delivered to the user. The humidification tank 129 is fluidly coupled to a water vapor inlet of the air path and can deliver water vapor to the air path via the water vapor inlet or can be part of the air path itself and formed in line with the air path. In other implementations, the respiratory treatment device 122 or the conduit 126 may include a waterless humidifier. The waterless humidifier can incorporate sensors that interface with other sensors located elsewhere in the system 100.

[0044] In some implementations, system 100 can be used to deliver at least a portion of a substance from receptacle 180 to a user's airway based at least in part on physiological data, sleep-related parameters, other data or information, or a combination thereof. Generally, altering the delivery of the portion of a substance to the airway can include (i) initiating delivery of the substance to the airway, (ii) terminating delivery of the portion of a substance to the airway, (iii) altering an amount of the substance delivered to the airway, (iv) altering a temporal characteristic of the delivery of the portion of a substance to the airway, (v) altering a quantitative characteristic of the delivery of the portion of a substance to the airway, (vi) altering a parameter associated with the delivery of the substance to the airway, or (vii) a combination of (i)-(vi).

[0045] Altering the temporal characteristics of the transport of the portion of the substance into the airway can include changing the rate of transport of the substance, starting and / or ending at different times, continuing for different time periods, changing the time distribution or characteristics of transport, changing the amount distribution independently of the time distribution, etc. Independent time and amount variations can change the amount of substance released each time separately from changing the frequency of release of the substance. In this manner, many different combinations of release frequency and release amount can be achieved (e.g., higher frequency and lower release amount, higher frequency and higher amount, lower frequency and higher amount, lower frequency and lower amount, etc.). Other modifications to the transport of the portion of the substance into the airway can also be utilized.

[0046] Respiratory treatment system 120 may be, for example, a mechanical ventilator or a positive airway pressure (PAP) system, such as a continuous positive airway pressure (CPAP) system, an automatic 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 air pressure to a user (e.g., determined by a sleep physician). An APAP system automatically varies the air pressure delivered to a user based, for example, on respiratory data associated with the user. A BPAP or VPAP system is configured to deliver a first predetermined pressure (e.g., inspiratory positive airway pressure or IPAP) and a second predetermined pressure (e.g., expiratory positive airway pressure or EPAP) that is lower than the first predetermined pressure.

[0047] 1 , the one or more sensors 130 of the system 100 may include 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 photoplethysmogram (PPG) sensor 154, an electrocardiogram (ECG) sensor 156, an electroencephalogram (EEG) sensor 158, a capacitance sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyogram (EMG) sensor 166, an oxygen sensor 168, an analyte sensor 174, a moisture sensor 176, a LiDAR sensor 178, or a combination thereof. Generally, each of the one or more sensors 130 is configured to output sensor data that is received and stored by the storage device 114 or one or more other storage devices.

[0048] Although the one or more sensors 130 are illustrated and described as including each of a pressure sensor 132, a flow sensor 134, a temperature sensor 136, a motion sensor 138, a microphone 140, a speaker 142, an RF receiver 146, an RF transmitter 148, a camera 150, an IR sensor 152, a PPG sensor 154, an ECG sensor 156, an EEG sensor 158, a capacitance sensor 160, a force sensor 162, a strain gauge sensor 164, an EMG sensor 166, an oxygen sensor 168, an analyte sensor 174, a moisture sensor 176, and a LidAR sensor 178, more generally, the one or more sensors 130 may include any combination and any number of the sensors described and / or illustrated herein.

[0049] As described herein, system 100 generally can be used to generate physiological data associated with a user (e.g., a user of respiratory treatment system 120 shown in FIG. 2 ) during a sleep session. The physiological data can be analyzed to generate one or more sleep-related parameters, which can include any parameter, measurement, or the like, associated with the user during a sleep session. The one or more sleep-related parameters that can be determined for user 210 during a sleep session can include, for example, an apnea-hypopnea index (AHI) score, a sleep score, a flow signal, a respiratory signal, a respiratory rate, an inspiratory amplitude, an expiratory amplitude, an inspiratory-to-expiratory ratio, events per hour, an event pattern, a stage, a pressure setting of respiratory treatment device 122, a heart rate, a heart rate variability, movement of user 210, a temperature, an EEG activity, an EMG activity, arousals, snoring, choking, coughing, whistling, wheezing, or a combination thereof.

[0050] In some implementations, physiological data generated by one or more sensors 130 may be used by control system 110 to determine a sleep-wake signal and one or more sleep-related parameters associated with the user during a sleep session. The sleep-wake signal may indicate one or more sleep states, including sleep, wakefulness, relaxed wakefulness, micro-arousal, or distinct sleep stages such as rapid eye movement (REM) stage, first non-REM stage (often referred to as “N1”), second non-REM stage (often referred to as “N2”), third non-REM stage (often referred to as “N3”), or any combination thereof. Methods for determining sleep states and / or sleep stages based on physiological data generated by one or more sensors, such as one or more sensors 130, are described, for example, in International Publication No. WO 2014 / 047310, U.S. Patent Application Publication No. 2014 / 0088373, WO 2017 / 132726, WO 2019 / 122413, WO 2019 / 122414, and U.S. Patent Application Publication No. 2020 / 0383580, each of which is incorporated herein by reference in its entirety.

[0051] The sleep-wake signal may also be time-stamped to determine the time the user gets into bed, the time the user gets out of bed, the time the user attempts to fall asleep, etc. The sleep-wake signal may be measured by one or more sensors 130 at a predetermined sampling rate during the sleep session, such as one sample per second, one sample per 30 seconds, one sample per minute, etc. In some implementations, the sleep-wake signal may also indicate a respiratory signal, a respiratory rate, an inspiratory amplitude, an expiratory amplitude, an inspiratory-to-expiratory ratio, an event count per hour, an event pattern, a pressure setting of the respiratory treatment device 122, or any combination thereof during the sleep session. The events may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, mouth leak, mask leak (e.g., leak through the user interface 124), restless legs, sleep disorder, choking, increased heart rate, heart rate variability, labored breathing, asthma attack, epileptic episode, seizure, fever, coughing, sneezing, snoring, gasping, presence of illness such as a cold or flu, or any combination thereof. One or more sleep-related parameters that may be determined for the user during a sleep session based on the sleep-wake signal include sleep quality metrics such as total time in bed, total sleep time, sleep onset latency, wake-after-sleep parameter, sleep efficiency, fragmentation index, or any combination thereof. As described in further detail herein, the physiological data and / or the sleep-related parameters may be analyzed to determine one or more sleep-related scores.

[0052] Physiological and / or audio data generated by one or more sensors 130 can also be used to determine a respiratory signal associated with the user during a sleep session. The respiratory signal generally indicates the user's breathing or breathing during a sleep session. Data from one or more sensors 130 can be analyzed to determine one or more sleep-related parameters, which may include a respiratory signal, a respiratory rate, a respiratory pattern, an inhalation amplitude, an exhalation amplitude, an inhalation-to-exhalation ratio, the occurrence of one or more events, the number of events per hour, an event pattern, a sleep state, an apnea-hypopnea index (AHI), or any combination thereof. The one or more events may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, mask leak (e.g., leak through the user interface 124), coughing, restless legs, sleep disorder, choking, increased heart rate, labored breathing, asthma attack, epileptic episode, seizure, elevated blood pressure, or any combination thereof. While many of the sleep-related parameters described are physiological parameters, some of the sleep-related parameters are considered non-physiological parameters. Other types of physiological and / or non-physiological parameters may also be determined based either on data from one or more sensors 130 or other types of data.

[0053] Generally, a sleep session includes any time after the user 210 lies or sits in bed 230 (or another area or object used for sleeping) and turns on the respiratory treatment device 122 and puts on the user interface 124. Thus, a sleep session may include (i) a time period during which the user 210 is using the CPAP system but before attempting to fall asleep (e.g., a time period during which the user 210 is lying in bed 230 reading a book), (ii) a time period during which the user 210 begins to attempt to fall asleep but is still awake, (iii) a time period during which the user 210 is in light sleep (also called stages 1 and 2 of non-rapid eye movement (NREM) sleep), (iv) a time period during which the user 210 is in deep sleep (also called slow wave sleep (SWS) or stage 3 of NREM sleep), (v) a time period during which the user 210 is in rapid eye movement (REM) sleep, (vi) a time period during which the user 210 is waking periodically between light sleep, deep sleep, or REM sleep, or (vii) a time period during which the user 210 is awake and does not return to sleep.

[0054] In general, a sleep session can be defined to end when the user 210 removes the user interface 124, turns off the respiratory treatment device 122, and leaves the bed 230. In some implementations, a sleep session can include additional time periods or be limited to only some of the time periods disclosed above. For example, a sleep session can be defined to encompass a period that begins when the respiratory treatment device 122 begins to deliver pressurized air to the airway or user 210, ends when the respiratory treatment device 122 stops delivering pressurized air to the airway of the user 210, and includes some or all of the time points in between when the user 210 is asleep or awake.

[0055] The pressure sensor 132 outputs pressure 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 pressure sensor 132 is an air pressure sensor (e.g., a barometric sensor) that generates sensor data indicative of a user's breathing (e.g., inhalation and / or exhalation) and / or ambient pressure of the respiratory treatment system 120. In such implementations, the pressure sensor 132 can be coupled to or integrated with the respiratory treatment device 122, the user interface 124, or the conduit 126. The pressure sensor 132 is used to determine the air pressure within the respiratory treatment device 122, the air pressure within the conduit 126, the air pressure within the user interface 124, or any combination thereof. The pressure sensor 132 can be, for example, a capacitive sensor, an electromagnetic sensor, an inductive sensor, a resistive sensor, a piezoelectric sensor, a strain gauge sensor, an optical sensor, a potentiometric sensor, or any combination thereof. In some examples, the pressure sensor 132 can be used to determine the user's blood pressure.

[0056] 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. Examples of flow sensors (e.g., flow sensor 214) are described in International Publication No. WO 2012 / 012835 and U.S. Patent Application Publication No. 10,328,219, which are incorporated herein by reference in their entireties. In some implementations, the flow sensor 134 is used to determine the airflow rate from the respiratory treatment device 122, the airflow rate through the conduit 126, the airflow rate through the user interface 124, or any combination thereof. In such implementations, the flow sensor 134 can be coupled to or integrated with the respiratory treatment device 122, the user interface 124, or the conduit 126. The flow sensor 134 can be, for example, a mass flow sensor such as a rotary flow meter (e.g., a Hall effect flow meter), a turbine flow meter, an orifice flow meter, an ultrasonic flow meter, a hot wire sensor, a vortex sensor, a membrane sensor, or any combination thereof. In some implementations, the flow sensor 214 is configured to measure airflow (e.g., intentional "leak"), unintentional leak (e.g., mouth leak and / or mask leak), patient flow (e.g., air entering or leaving the lungs), or any combination thereof. In some implementations, the flow data can be analyzed to determine the user's cardiogenic oscillations.

[0057] The temperature sensor 136 outputs temperature data that may be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some implementations, the temperature sensor 136 generates temperature data indicative of the core body temperature of the user 210 ( FIG. 2 ), the skin temperature of the user 210, the temperature of the air flowing from the respiratory treatment device 122 and / or through the conduit 126, the temperature of the air within the user interface 124, the ambient temperature, or any combination thereof. The temperature sensor 136 may be, for example, a thermocouple sensor, a thermistor sensor, a silicon bandgap temperature sensor or semiconductor-based sensor, a resistance temperature detector, or any combination thereof.

[0058] The motion sensor 138 outputs motion data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. The motion sensor 138 can be used to detect the movement of the user 210 during a sleep session and / or the movement of any of the components of the respiratory treatment system 120, such as the respiratory treatment device 122, the user interface 124, or the conduit 126. The motion sensor 138 can include one or more inertial sensors, such as an accelerometer, a gyroscope, and a magnetometer. In some implementations, the motion sensor 138 alternatively or additionally generates one or more signals indicative of the user's body movements, from which a signal indicative of the user's sleep state can be obtained, for example, via the user's respiratory movements. In some implementations, the motion data from the motion sensor 138 can be used in conjunction with additional data from another sensor 130 to determine the user's sleep state.

[0059] The microphone 140 outputs audio data that can be stored in the storage device 114 and / or analyzed by the processor 112 of the control system 110. The audio data generated by the microphone 140 can be played back as one or more sounds (e.g., sounds from the user 210) during a sleep session. As described in further detail herein, the audio data from the microphone 140 can also be used to identify events experienced by the user during a sleep session (e.g., using the control system 110). The microphone 140 can be coupled to or integrated with (e.g., on an interior or exterior surface of) the respiratory treatment device 122, the user interface 124, the conduit 126, or the user device 170. In some implementations, the system 100 includes multiple microphones (e.g., two or more microphones and / or an array of microphones using beamforming) such that audio data generated by each of the multiple microphones can be used to identify audio data generated by other microphones of the multiple microphones.

[0060] The speaker 142 can output sound waves that are audible to a user of the system 100 (e.g., user 210 in FIG. 2 ) or sound waves that are inaudible to a user of the system (e.g., ultrasound). The speaker 142 can be used, for example, as an alarm clock or to play alerts or messages to the user 210 or a caregiver (e.g., in response to a movement event and / or a change in body position). In some implementations, the speaker 142 can be used to communicate audio data generated by the microphone 140 to the user. The speaker 142 can be coupled to or integrated with the respiratory treatment device 122, the user interface 124, the conduit 126, or the external device 170.

[0061] The microphone 140 and the speaker 142 can be used as independent devices. In some implementations, the microphone 140 and the speaker 142 can be combined into an acoustic sensor 141 (e.g., a SONAR sensor), for example, as described in International Publication Nos. WO 2018 / 050913 and WO 2020 / 104465, each of which is incorporated by reference in its entirety. In such implementations, the speaker 142 generates or emits sound waves at predetermined intervals, and the microphone 140 detects reflections of the sound waves emitted from the speaker 142. In one or more implementations, the sound waves generated or emitted by the speaker 142 can have a frequency inaudible to the human ear (e.g., below 20 Hz or above about 18 kHz) so as not to disturb the sleep of the user 210 or bedmate 220 ( FIG. 2 ). Based at least in part on data from microphone 140 and / or speaker 142, control system 110 can determine user 210's ( FIG. 2 ) position and / or one or more of the sleep-related parameters described herein, such as, for example, movement, body position, respiratory signal, respiratory rate, inhalation amplitude, exhalation amplitude, inhalation-to-exhalation ratio, number of events per hour, event pattern, sleep state, sleep stage, pressure setting of respiratory treatment device 122, or any combination thereof. In this context, sonar sensors may be understood to involve active acoustic sensing, such as by generating and / or transmitting ultrasonic and / or low-frequency ultrasonic sensing signals (e.g., in a frequency range of approximately 17-23 kHz, 18-22 kHz, or 17-18 kHz) into the air.

[0062] In some implementations, sensor 130 includes (i) a first microphone that is the same as or similar to microphone 140 and integrated into acoustic sensor 141, and (ii) a second microphone that is the same as or similar to microphone 140 but is independent and separate from the first microphone that is integrated into acoustic sensor 141.

[0063] The RF transmitter 148 generates and / or emits radio waves having a predetermined frequency and / or a predetermined amplitude (e.g., within a high-frequency band, within a low-frequency band, a long-wave signal, a short-wave signal, etc.). The RF receiver 146 detects reflections of the radio waves emitted from the RF transmitter 148, and this data can be analyzed by the control system 110 to determine the position and / or movement of the user 210 ( FIG. 2 ), such as breathing and / or body movement, and / or one or more of the sleep-related parameters described herein. The RF receiver (either the RF receiver 146 and the RF transmitter 148 or another RF pair) can also be used for wireless communication between the control system 110, the respiratory treatment device 122, one or more sensors 130, the user device 170, or any combination thereof. Although the RF receiver 146 and the RF transmitter 148 are shown in FIG. 1 as separate and distinct elements, in some implementations the RF receiver 146 and the RF transmitter 148 are combined as part of an RF sensor 147 (e.g., a RADAR sensor). In some such implementations, the RF sensor 147 includes control circuitry. The particular form of RF communication may be Wi-Fi, Bluetooth, or the like.

[0064] In some implementations, RF sensor 147 is part of a mesh system. One example of a mesh system is a Wi-Fi mesh system, which may include mesh nodes, mesh router(s), and mesh gateway(s), each of which may be mobile / movable or fixed. In such implementations, the Wi-Fi mesh system includes a Wi-Fi router and / or a Wi-Fi controller, and one or more satellites (e.g., access points), each of which includes an RF sensor identical or similar to RF sensor 147. The Wi-Fi router and satellite continuously communicate with each other using Wi-Fi signals. The Wi-Fi mesh system can be used to generate motion data based on changes in the Wi-Fi signal between the router and the satellite (e.g., differences in received signal strength) due to the movement of an object or person partially obstructing the signal. This motion data can indicate movement, breathing, heart rate, gait, falls, behavior, etc., or any combination thereof.

[0065] The camera 150 outputs image data that can be played back as one or more images (e.g., still images, video images, thermal images, or a combination thereof) that can be stored in the storage device 114. The image data from the camera 150 can be used by the control system 110 to determine one or more sleep-related parameters described herein. The control system 110 can use the image data from the camera 150 to determine one or more of the sleep-related parameters described herein, such as, for example, one or more events (e.g., periodic limb movement or restless legs syndrome), a respiratory signal, a respiratory rate, an inhalation amplitude, an exhalation amplitude, an inhalation-to-exhalation ratio, a number of events per hour, an event pattern, a sleep state, a sleep stage, or a combination thereof. Additionally, the image data from the camera 150 can be used to identify the position of the user, determine chest movement of the user 210, determine airflow at the mouth and / or nose of the user 210, determine the time the user 210 enters the bed 230, and determine the time the user 210 leaves the bed 230. The camera 150 can also be used to track eye movement, pupil dilation (if one or both of the user's 210 eyes are open), blink rate, or any changes during REM sleep. In some implementations, the camera 150 includes a wide-angle or fisheye lens.

[0066] The infrared (IR) sensor 152 outputs infrared image data that can be played back as one or more infrared images (e.g., still images, moving images, or both) that can be stored in the storage device 114. The infrared data from the IR sensor 152 can be used to determine one or more sleep-related parameters during a sleep session, including the temperature of the user 210 and / or the movement of the user 210. The IR sensor 152 can also be used in combination with the camera 150 in measuring the presence, location, and / or movement of the user 210. The IR sensor 152 can detect infrared light having a wavelength between about 700 nm and about 1 mm, for example, while the camera 150 can detect visible light having a wavelength between about 380 nm and about 740 nm.

[0067] The PPG sensor 154 outputs physiological data associated with the user 210 ( FIG. 2 ) that can be used to determine one or more sleep-related parameters, such as, for example, heart rate, heart rate pattern, heart rate variability, cardiac cycle, respiratory rate, inspiration amplitude, expiration amplitude, inspiration-to-expiration ratio, estimated blood pressure parameters, or any combination thereof. The PPG sensor 154 is worn by the user 210, and can be embedded in clothing and / or fabric worn by the user 210, embedded in and / or coupled to the user interface 124 and / or its associated headgear (e.g., straps, etc.).

[0068] The ECG sensor 156 outputs physiological data associated with the electrical activity of the heart of the user 210 (FIG. 2). In some implementations, the ECG sensor 156 includes one or more electrodes placed on or around a portion of the user 210 during a sleep session. The physiological data from the ECG sensor 156 can be used to determine, for example, one or more sleep-related parameters described herein.

[0069] The EEG sensor 158 outputs physiological data associated with the electrical activity of the brain of the user 210. In some implementations, the EEG sensor 158 includes one or more electrodes placed on or around the scalp of the user 210 during a sleep session. The physiological data from the EEG sensor 158 can be used, for example, to determine the sleep state of the user 210 at any given time during the sleep session. In some implementations, the EEG sensor 158 can be integrated into the user interface 124 and / or its associated headgear (e.g., straps, etc.).

[0070] The capacitance sensor 160, the force sensor 162, and the strain gauge sensor 164 output data that may be stored in the memory device 114 and used by the control system 110 to determine one or more sleep-related parameters described herein. The EMG sensor 166 outputs physiological data associated with electrical activity produced by one or more muscles. The oxygen sensor 168 outputs oxygen data indicative of the oxygen concentration of a gas (e.g., in the conduit 126 or at the user interface 124). The oxygen sensor 168 may be, for example, an ultrasonic oxygen sensor, an electrical oxygen sensor, a chemical oxygen sensor, an optical oxygen sensor, a pulse oximeter (e.g., an SpO2 sensor), or any combination thereof. In some implementations, the one or more sensors 130 also include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a sphygmomanometer sensor, an oximetry sensor, or any combination thereof.

[0071] The analyte sensor 174 can be used to detect the presence of analytes in the exhaled breath of the user 210. Data output by the analyte sensor 174 can be stored in the storage device 114 and used by the control system 110 to determine the identity and concentration of any analytes in the user's 210 breath. In some implementations, the analyte sensor 174 is positioned near the mouth of the user 210 to detect analytes in the breath exhaled from the user's 210 mouth. For example, if the user interface 124 is a face mask that covers the nose and mouth of the user 210, the analyte sensor 174 can be positioned within the face mask to monitor the user's 210 mouth breathing. In other implementations, if the user interface 124 is a nasal mask or nasal pillows mask, the analyte sensor 174 can be positioned near the nose of the user 210 to detect analytes in the breath exhaled from the user's 210 nose. In yet another implementation, if the user interface 124 is a nasal mask or nasal pillows mask, the analyte sensor 174 can be positioned near the mouth of the user 210. In some implementations, the analyte sensor 174 can be used to detect whether air is inadvertently leaking from the mouth of the user 210. In some implementations, the analyte sensor 174 is a volatile organic compound (VOC) sensor that can be used to detect carbon-based chemicals or compounds. In some implementations, the analyte sensor 174 can also be used to detect whether the user 210 is breathing through their nose or mouth. For example, if the presence of an analyte is detected by data output by the analyte sensor 174 positioned near the mouth of the user 210 or in a face mask (in implementations where the user interface 124 is a face mask), the control system 110 can use this data as an indicator that the user 210 is breathing through their mouth.

[0072] The moisture sensor 176 outputs data that can be stored in the memory device 114 and used by the control system 110. The moisture sensor 176 can be used to detect moisture in various areas surrounding the user (e.g., inside the conduit 126 or the user interface 124, near the face of the user 210, near the connection between the conduit 126 and the user interface 124, near the connection between the conduit 126 and the respiratory treatment device 122, etc.). Thus, in some implementations, the moisture sensor 176 can be located within the user interface 124 or the conduit 126 to monitor the humidity of the pressurized air from the respiratory treatment device 122. In other implementations, the moisture sensor 176 is located near any area where humidity levels need to be monitored. The moisture sensor 176 can also be used to monitor the humidity of the ambient environment surrounding the user 210, such as the air in the user's 210 bedroom. The moisture sensor 176 can also be used to track the user's 210 biological response to environmental changes.

[0073] One or more light detection and ranging (LiDAR) sensors 178 can be used for depth sensing. Such optical sensors (e.g., laser sensors) can be used to detect objects and create three-dimensional (3D) maps of surrounding environments, such as living spaces. LiDAR typically uses a pulsed laser to measure time of flight. LiDAR is also known as 3D laser scanning. In one use case of such sensors, a fixed or mobile device (such as a smartphone) equipped with a LiDAR sensor 178 can measure and map an area more than five meters away from the sensor. LiDAR data can be fused with point cloud data estimated by, for example, an electromagnetic RADAR sensor. The LiDAR sensor 178 can also automatically create geofences for RADAR systems by using artificial intelligence (AI) to detect and classify spatial features that may pose problems for the RADAR system, such as glass windows (which may be highly reflective to RADAR). LiDAR can also be used to estimate a person's height and changes in height that occur when a person sits, falls, etc. LiDAR can be used to create a 3D mesh representation of the environment. In a further application, solid surfaces through which radio waves pass (e.g., radio-transparent materials) allow LiDAR to reflect off such surfaces, thereby enabling classification of different types of obstacles.

[0074] In some implementations, the one or more sensors 130 also include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a blood pressure sensor, an oximetry sensor, a sonar sensor, a RADAR sensor, a blood glucose sensor, a color sensor, a pH sensor, an air quality sensor, a tilt sensor, a rain sensor, a soil moisture sensor, a water flow sensor, an alcohol sensor, or any combination thereof.

[0075] 1 , any combination of one or more sensors 130 may be integrated with and / or coupled to any one or more of the components of system 100, including respiratory treatment device 122, user interface 124, conduit 126, humidification tank 129, control system 110, user device 170, or any combination thereof. For example, acoustic sensor 141 and / or RF sensor 147 may be integrated with and / or coupled to user device 170. In such implementations, user device 170 may be considered a secondary device that generates additional or secondary data used by system 100 (e.g., control system 110) according to certain aspects of the present disclosure. In some implementations, at least one of the one or more sensors 130 is not physically and / or communicatively coupled to the respiratory treatment device 122, the control system 110, or the user device 170, but is positioned generally adjacent to the user 210 during a sleep session (e.g., positioned on or in contact with a portion of the user 210, worn by the user 210, coupled to or positioned on a nightstand, coupled to a mattress, coupled to a ceiling, etc.).

[0076] One or more of the respiratory treatment device 122, the user interface 124, the conduit 126, the display device 128, and the humidification tank 129 may include one or more sensors (e.g., a pressure sensor, a flow sensor, or more generally, any of the other sensors 130 described herein) that may be used, for example, to measure the air pressure and / or flow rate of the pressurized air supplied by the respiratory treatment device 122.

[0077] Data from one or more sensors 130 can be analyzed to determine one or more sleep-related parameters, which may include a respiratory signal, a respiratory rate, a respiratory pattern, an inspiratory amplitude, an expiratory amplitude, an inspiratory-to-expiratory ratio, the occurrence of one or more events, the number of events per hour, an event pattern, a sleep state, an apnea-hypopnea index (AHI), or any combination thereof. The one or more events may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, an intentional mask leak, an unintentional mask leak, a mouth leak, coughing, restless legs, a sleep disorder, choking, increased heart rate, labored breathing, asthma attack, epileptic episode, seizure, elevated blood pressure, or any combination thereof. While many of these sleep-related parameters are physiological, some sleep-related parameters are considered non-physiological. Non-physiological parameters may also include operating parameters of the respiratory therapy system, including flow rate, pressure, humidity of the pressurized air, motor speed, etc. Other types of physiological and non-physiological parameters may also be determined based either on data from one or more sensors 130 or other types of data.

[0078] User device 170 ( FIG. 1 ) includes a display device 172. User device 170 may be, for example, a mobile device such as a smartphone, tablet, or laptop. Alternatively, user device 170 may be an external sensing system, a television (e.g., a smart television), or another smart home device (e.g., a smart speaker such as Google Home, Amazon Echo, or Alexa). In some implementations, user device 170 is a wearable device (e.g., a smart watch). Display device 172 is typically used to display images, including still images, moving images, or both. In some implementations, display device 172 functions as a human-machine interface (HMI) that includes a graphical user interface (GUI) configured to display images and an input interface. Display device 172 may be an LED display, an OLED display, an LCD display, or the like. The input interface may be, for example, a touchscreen or touch-sensitive board, a mouse, a keyboard, or any sensor system configured to sense inputs made by a human user interacting with user device 170. In some implementations, one or more user devices can be used by and / or included in the system 100.

[0079] 1 as separate and distinct components of system 100, in some implementations control system 110 and / or storage 114 are integrated into user device 170 and / or respiratory treatment device 122. Alternatively, in some implementations control system 110 or portions thereof (e.g., processor 112) can be located in the cloud (e.g., integrated into a server, integrated into an Internet of Things (IoT) device, connected to the cloud, subject to edge cloud processing), located on one or more servers (e.g., remote servers, local servers, etc., or any combination thereof).

[0080] Although system 100 is shown as including all of the above components, according to various implementations of the present disclosure, a system for analyzing data associated with a user's use of respiratory treatment system 120 can include more or fewer components. For example, a first alternative system includes control system 110, storage device 114, and at least one of one or more sensors 130, but does not include respiratory treatment system 120. As another example, a second alternative system includes control system 110, storage device 114, at least one of one or more sensors 130, and user device 170. As yet another example, a third alternative system includes control system 110, storage device 114, respiratory treatment system 120, at least one of one or more sensors 130, and user device 170. Thus, any portion of the components shown and described herein can be used and / or combined with one or more other components to form various systems for implementing the present disclosure.

[0081] Referring generally to FIG. 2, a portion of system 100 (FIG. 1) according to some implementations is shown. A user 210 and bed partner 220 of respiratory treatment system 120 are positioned in bed 230 and lying on mattress 232. A user interface 124 may be worn by user 210 during a sleep session. User interface 124 is fluidly coupled and / or connected to respiratory treatment device 122 via conduit 126. Respiratory treatment device 122 then delivers pressurized air to user 210 via conduit 126 and user interface 124 to increase air pressure in the user's 210 throat and help prevent airway closure and / or narrowing during sleep. Respiratory treatment device 122 may be placed on a nightstand 240 directly adjacent to bed 230, as shown in FIG. 2, or more generally, on any surface or structure generally adjacent to bed 230 and / or user 210.

[0082] In some implementations, the control system 110, the memory 114, and / or the one or more sensors 130 can be located on and / or within any surface and / or structure generally adjacent to the bed 230 and / or the user 210. For example, in some implementations, at least one of the one or more sensors 130 can be located at a first location 225A on and / or within one or more components of the respiratory treatment system 120 adjacent to the bed 230 and / or the user 210. The one or more sensors 130 can be coupled to the respiratory treatment system 120, the user interface 124, the conduit 126, the display 128, the humidification tank 129, or a combination thereof.

[0083] Alternatively or additionally, at least one of the one or more sensors 130 can be positioned at a second location 225B on and / or within the bed 230 (e.g., the one or more sensors 130 are coupled to and / or integrated with the bed 230). Further, alternatively or additionally, at least one of the one or more sensors 130 can be positioned at a third location 225C on and / or within the mattress 232 adjacent the bed 230 and / or user 210 (e.g., the one or more sensors 130 are coupled to and / or integrated with the mattress 232). Alternatively or additionally, at least one of the one or more sensors 130 can be positioned at a fourth location 225D on and / or within a pillow generally adjacent the bed 230 and / or user 210.

[0084] Alternatively or additionally, at least one of the one or more sensors 130 can be positioned at a fifth location 225E on and / or within the bed 230 and / or nightstand 240 generally adjacent to the user 210. Alternatively or additionally, at least one of the one or more sensors 130 can be positioned at a sixth location 225F such that it is coupled to and / or located on the user 215 (e.g., one or more sensors 130 are embedded in or coupled to fabric, clothing 212 and / or smart device 270 worn by the user 210). More generally, at least one of the one or more sensors 130 can be positioned at any suitable location relative to the user 210 such that it can generate sensor data related to the user 210.

[0085] In some implementations, a primary sensor, such as microphone 140, is configured to generate acoustic data related to user 210 during a sleep session. For example, one or more microphones (the same as or similar to microphone 140 of FIG. 1 ) can be integrated into and / or coupled to (i) a circuit board of respiratory treatment device 122, (ii) conduit 126, (iii) connectors between components of respiratory treatment system 120, (iv) user interface 124, (v) headgear (e.g., straps) associated with the user interface, or (vi) combinations thereof.

[0086] In some implementations, in addition to the primary sensor, one or more secondary sensors can generate additional data. In some such implementations, the one or more secondary sensors include a microphone (e.g., microphone 140 of system 100), 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-based air flow sensor (VAF), a thermal air flow sensor (MAF), a cold wire, a laminar flow sensor, an ultrasonic sensor, an inertial sensor, or a combination thereof.

[0087] Alternatively or additionally, one or more microphones (identical or similar to microphone 140 of FIG. 1) may be integrated into and / or coupled to a collocated smart device such as user device 170, a TV, a watch (e.g., a mechanical watch or smart device 270), a pendant, mattress 232, bed 230, bedding disposed on bed 230, a pillow, a speaker (e.g., speaker 142 of FIG. 1), a radio, a tablet, a waterless humidifier, or a combination thereof.

[0088] Alternatively or additionally, in some implementations, one or more microphones (identical to or similar to microphone 140 of FIG. 1) may be remote from system 100 ( FIG. 1 ) and / or user 210 ( FIG. 2 ), provided there is an air passage through which the acoustic signal can be transmitted to them. For example, one or more microphones may be located in a room different from the room in which system 100 is housed.

[0089] 3 illustrates the generation of acoustic data in the form of echo data in response to acoustic reflections indicative of one or more characteristics of a user interface (e.g., user interface 124) according to an embodiment of the present disclosure. The generation of echo data involves an acoustic sensor 141 including a microphone 140 (or any type of sound transducer) and a speaker 142. However, as noted above, the speaker 142 can alternatively be replaced by another device capable of generating an acoustic signal, such as a motor in the respiratory treatment device 122. The microphone 140 and speaker 142 are shown in specific locations relative to the conduit 126 connected to the respiratory treatment device 122 (not shown). However, as noted above, the locations of the microphone 140 and speaker 142 may differ from those illustrated. Examples of echo data generation and analysis are described in International Publication No. WO 2010 / 091462, which is incorporated herein by reference in its entirety.

[0090] The speaker 142 emits an acoustic signal 302 within the conduit 126. The acoustic signal 302 is in the form of sound. The sound may be one or more of a standard sound (e.g., an original, unmodified sound from a commercially available sound application), a custom sound, an inaudible frequency, a white noise sound, a broadband impulse, a continuous sine wave, a square wave, a sawtooth wave, or a frequency-modulated sine wave (e.g., a chirp). According to some other implementations, the acoustic signal 302 may be in the form of one or more of an audible sound or an ultrasonic sound. According to some other implementations, the acoustic signal 302 is in the form of an inaudible sound, where the sound is inaudible based on one or both of the frequency of the sound (e.g., a frequency outside the frequency range of human hearing) or the amplitude of the sound (e.g., an amplitude so low that the sound is not loud enough for human perception).

[0091] In one or more implementations, the acoustic signal 302 is emitted at a specific time, such as when the user first puts on the user interface, after the user removes the user interface, or after detecting that an apnea or hypopnea event is occurring (e.g., after detecting that an apnea or hypopnea event is occurring using a respiratory treatment device). The specific monitoring time is selected, for example, to be at least 4 seconds in duration at 0.1 second intervals. To continuously monitor the user, in determining the user's movements and / or body position, the acoustic signal 302 can be emitted continuously or at intervals throughout the entire course of a treatment session, or for one or more portions thereof.

[0092] The acoustic signal 302 travels down the length L of the conduit 126 until it contacts a feature 304 of the user interface 124 at or near a junction 306 between the user interface 124 and the conduit 126. The feature 304 comprises a widening of the path 308 formed by the conduit 126 and / or the user interface 124. The widening at the feature 304 causes a change in the acoustic impedance of the acoustic signal 302 and an acoustic reflection 310. The acoustic reflection 310 travels back down the length L of the conduit 126 until it reaches the microphone 140. The microphone 140 detects the acoustic reflection 310 and generates echo data in response to the acoustic reflection 310. The generated data is subsequently analyzed to determine the user's movement and / or the user's body position, for example, as further described below with respect to FIG. 5 and / or FIG. 8.

[0093] Acoustic signal 302 may continue beyond feature 304 into user interface 124. Although not shown, user interface 124 and / or conduit 126 may include one or more additional features that change the acoustic impedance of acoustic signal 302, further generating acoustic reflection 310. Thus, although only feature 304 is shown and described as causing acoustic reflection 310, there may be multiple features of user interface 124 and / or conduit 126 that can all contribute to acoustic reflection 310.

[0094] As such, in some implementations, system 100 is configured to generate acoustic data in the form of echo data, which is then analyzed by control system 110. In some implementations, the echo data includes reflected sound waves transmitted from a speaker (e.g., speaker 142 of system 100 or an external speaker) and received by a microphone (e.g., microphone 140 of system 100). The reflected sound waves indicate the shape and dimensions of components in the path of the sound waves. Additionally or alternatively, the acoustic data includes audio data, such as sounds from the user (e.g., nose breathing, mouth breathing, snoring, sniffing), that are indicative of one or more sleep-related parameters.

[0095] For example, acoustic data (e.g., in the form of echo data) may include data generated by microphone 140. Speaker 142 (or other device capable of generating an acoustic signal, such as a motor of respiratory treatment device 122) generates sound. The sound may travel through humidification tank 129, along first connection and conduit 126, through second connection and waterless humidifier (if installed), to one or more cavities (e.g., nostrils and / or mouth) and the user's respiratory treatment system (including nose and / or mouth, airways, lungs, etc.). For each change or feature in the path (e.g., cavity, junction, change in shape (e.g., due to movement of the conduit and / or other components of the respiratory treatment system), change in reflection location (e.g., due to change in effective length of the conduit during movement as the conduit curls and / or stretches), and / or change in length of the conduit that may occur due to movement of the conduit and / or other components of the respiratory treatment system), a reflection at that point will be seen, and its location may be determined based on the known speed of sound.

[0096] In some implementations, cepstrum analysis is performed to analyze acoustic data. The cepstrum is the "quefrency" domain, also known as the spectrum of the log of a time-domain waveform. For example, the cepstrum can be viewed as the inverse Fourier transform of the log spectrum of the Fourier transform of the decibel spectrum. The operation essentially converts the convolution of an impulse response function (IRF) and a sound source into a summation operation, thus isolating the IRF data for analysis, making the sound source easier to interpret or remove. Cepstrum analysis techniques are described in detail in the academic paper "The Cepstrum: A Guide to Processing" (Childers et al., Proceedings of the IEEE, Vol. 65, No. 10, October 1977) and in "Frequency Analysis" by Randall R.B. (Copenhagen: Bruel & Kjaer, p. 344 (1977, revised edition 1987)).

[0097] Such a method can be understood in terms of the properties of convolution. The convolution of f and g can be written as f*g. This operation allows us to integrate the product of two functions (f and g) after inverting and shifting one of them. Thus, it is an integral transform as shown in Equation 1:

[0098]

number

[0099] Although the symbol t is used above, it does not necessarily represent the time domain. In that context, however, the convolution formula can be described as a weighted average of a function f(τ) at instant t, where the weighting is simply given by g(-τ) shifted by an amount t. As t changes, the weighting function emphasizes different parts of the input function.

[0100] More generally, if f and g are complex-valued functions over Rd, then their convolution can be defined as the integral of Eq.

[0101]

number

[0102] A mathematical model that can relate the acoustic system output to the input to a linear time-invariant system (which may include any person or other unknown part of the system), such as one that includes the conduits of a respiratory treatment device, can be based on this convolution. As shown in Equation 3, the output measured at the system's microphones can be thought of as the input noise being "convolved" with the system impulse response function (IRF) as a function of time (t).

[0103]

number

[0104] where * denotes the convolution function, y(t) is the signal measured by the sound sensor, S1(t) is the sound or noise source, such as noise or sound in or generated by a flow generator in a respiratory treatment device, and 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.

[0105] Transforming Equation 3 into the frequency domain via a Fourier transform (e.g., a discrete Fourier transform (“DFT”) or a fast Fourier transform (“FFT”)) of the measured sound data, and considering the convolution theorem, Equation 4 is developed.

[0106]

number

[0107] 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.

[0108] Applying the logarithm of Equation 4 converts multiplication into addition, resulting in Equation 5.

[0109]

number

[0110] Next, by transforming Equation 5 back into the time domain via an inverse Fourier transform (IFT) (e.g., inverse DFT or inverse FFT), we obtain the complex cepstrum (K(τ)) (which is complex because we can work from a complex spectrum)—the inverse Fourier transform of the logarithm of the spectrum, Equation 6.

[0111]

number

[0112] where "τ" is a real-valued variable known as the quefrency, measured in seconds, so that effects that are convolutional in the time domain become additive in the logarithm of the spectrum and remain so in the cepstrum.

[0113] Consideration of data from cepstral analysis, such as examining quefrency data values, can provide information about a system. For example, by comparing a system's cepstral data from a previous or known baseline of cepstral data for the system, the comparison, such as a difference, can be used to recognize differences or similarities between the systems, which can then be used to perform various functions or purposes disclosed herein, including determining movement events and body positions. The following disclosure can utilize the analysis methodologies described herein to perform any movement of a user and / or the determination of a user's body position.

[0114] In some implementations, direct spectral methods can be implemented to analyze acoustic data. Examples of direct spectral methods include discrete Fourier transforms (DFTs), fast Fourier transforms (FFTs) (optionally using sliding windows), short-time Fourier transforms (STFTs), wavelet-based analysis, wavelet-based cepstrum calculations, Hilbert-Huang transforms (HHTs), empirical mode decomposition (EMD), blind source separation (BSS), Kalman filters, or combinations thereof. In some implementations, cepstral coefficients (CCs), such as Mel-Frequency Cepstrum Coefficients (MFCCs), can be used to process acoustic data analysis in the same way as speech recognition analysis, for example, by using machine learning / classification systems. In other implementations, deep neural networks are employed using image analysis methods applied to spectrograms.

[0115] In some implementations, the system of the present disclosure includes a flow sensor (e.g., flow sensor 134 of FIG. 1 ) and / or a pressure sensor (e.g., pressure sensor 132 of FIG. 1 ). The flow sensor 134 can be used to generate flow data related to a user 210 of the respiratory treatment device 122 ( FIG. 2 ) during a sleep session. Examples of flow sensors (e.g., flow sensor 134, etc.) are described in International Publication No. WO 2012 / 012835, which is incorporated herein by reference in its entirety. In some implementations, the flow sensor 134 is configured to measure airflow (e.g., intentional “leak”), unintentional leak (e.g., mouth leak and / or mask leak), patient flow (e.g., air entering or exiting the lungs), or a combination thereof.

[0116] In some implementations, the flow sensor and / or pressure sensor are configured to generate flow and / or pressure data over a treatment period. For example, Figure 4A shows a portion of flow data associated with a user (e.g., user 210 of Figure 2) of a respiratory treatment system (e.g., respiratory treatment system 120 of Figure 1) according to some implementations of the present disclosure. As shown in Figure 4A, multiple flow values ​​measured over approximately seven complete respiratory cycles (401-407) are plotted as a continuous curve 410.

[0117] In some implementations, the pressure sensor is configured to generate pressure data over a treatment period. For example, FIG. 4B illustrates pressure data associated with a user of a CPAP system according to some implementations of the present disclosure. The pressure data illustrated in FIG. 4B was generated over the same treatment period as FIG. 4A. As illustrated in FIG. 4B, multiple pressure values ​​measured over approximately seven full respiratory cycles (401-407) are plotted as a continuous curve 420. As the CPAP system is used, the continuous pressure curve in FIG. 4B exhibits a generally sinusoidal pattern with a relatively small amplitude as the CPAP system attempts to maintain a constant, predetermined air pressure in the system over the seven full respiratory cycles.

[0118] Referring to Figure 4C, pressure data associated with a user of a respiratory treatment system having an expiratory pressure relief (EPR) module, according to some implementations of the present disclosure, is shown. The pressure data shown in Figure 4C was generated over the same treatment period as Figure 4A. As shown in Figure 4C, multiple pressure values ​​measured over approximately seven complete respiratory cycles (401-407) are plotted as a continuous curve 430. The continuous curve in Figure 4C differs from the continuous curve in Figure 4B because the EPR (expiratory pressure relief) module (used for the pressure data in Figure 4C) may have different settings for the EPR level, which is related to the difference between the pressure level during inspiration and the decompression level during expiration.

[0119] Referring to FIG. 5, a flow diagram of a method 500 for determining user movement during use of a respiratory therapy system is disclosed. One or more steps of the method 500 can be implemented using any element or aspect of the system 100 (FIGS. 1-2) described herein. Advantages of having the method 500 for motion detection during therapy include improved sleep staging (e.g., classifying wakefulness, light sleep, deep sleep, and / or REM sleep). Previous sleep staging developments have primarily been based solely on flow signals. However, activity levels while a person is asleep correspond to specific sleep states. When a person is awake, they typically move frequently, whereas when in deep or REM sleep, they typically move little or not at all. Therefore, improved movement and / or activity detection can help better classify sleep states.

[0120] At step 510, acoustic data associated with a user of a respiratory treatment system (e.g., respiratory treatment system 120 of system 100) is received. For example, in some implementations, the acoustic data can be received from a microphone associated with the respiratory treatment system (e.g., microphone 140 of system 100). In some such implementations, the microphone is configured to generate the acoustic data based at least in part on detected sounds associated with the respiratory treatment system. For example, in some implementations, the acoustic data can be reproduced as one or more sounds associated with movement of a component of the respiratory treatment system, such as a conduit (e.g., conduit 126 of system 100). Additionally and / or in some cases, in some implementations, the movement causes at least a portion of the component (e.g., the conduit) to rub against one or more surfaces, such as a bed surface, a bed cover, a user's body, or a surface of the component (e.g., the conduit) itself or another component of the respiratory treatment system.

[0121] In some implementations, the microphone is located external to the respiratory treatment system. In such implementations, the microphone is coupled to a smart device, a smartphone, a smart speaker, or any combination thereof. In some implementations, the microphone is (i) internal to the respiratory treatment system, (ii) integrated into the respiratory treatment system, or (iii) both (i) and (ii). In some such implementations, the microphone is at least partially coupled to a component of the respiratory treatment system, such as (i) a conduit 126 of a respiratory treatment device 122 of the respiratory treatment system 120, (ii) a circuit board of a respiratory treatment device 122 of the respiratory treatment system 120, (iii) a connector of the respiratory treatment system 120, (iv) a user interface 124 of the respiratory treatment system 120, or (v) another component of the respiratory treatment system 120. For example, in some implementations, the microphone may be located within the housing of the respiratory treatment device 122.

[0122] It should be noted that more or fewer microphones may be implemented in method 500. For example, method 500 may be practiced using a first microphone that is external to the respiratory treatment system and a second microphone that is (i) internal to the respiratory treatment system, (ii) integrated into the respiratory treatment system, or (iii) both (i) and (ii).

[0123] While existing flow signals can be used to determine motion data, in some cases, acoustic signals are more accurate than flow signals and can be used to determine motion events or to confirm / reinforce the determination of motion events from flow signals. For example, some patients may stop breathing or experience a decrease in breathing consistency when they move; flow signals may not accurately reflect such motion, but acoustic signals can. Using both flow and acoustic signals to obtain motion data not only provides a synergistic effect, but also allows for better detection of motion when a patient stops breathing and / or experiences a decrease in breathing consistency. The acoustic signal can be used to confirm and / or improve the reliability of motion detected via flow signals, and vice versa.

[0124] In step 520, the received acoustic data is analyzed. In some implementations, analyzing the received acoustic data (step 520) may include one or more of the following steps 522-526: In step 522, a plurality of audio signal amplitudes for time periods (e.g., 2 seconds, 3 seconds, 4 seconds, 5 seconds, 6 seconds, 7 seconds, 8 seconds, 9 seconds, 10 seconds, etc.) are determined from the received acoustic data. For example, in some implementations, the time periods correspond to a number of respiratory cycles, each respiratory cycle including an inhalation portion and an exhalation portion. Additionally or alternatively, in some implementations, the number of respiratory cycles is 1 respiratory cycle, 2 respiratory cycles, 3 respiratory cycles, 4 respiratory cycles, or 5 respiratory cycles.

[0125] In step 524, a standard deviation for the time period is calculated based at least in part on the determined audio signal amplitudes, corresponding to the standard deviation of the audio signal amplitudes. In step 526, the standard deviation for the time period is compared to a predetermined threshold. In some implementations, the predetermined threshold (step 526) to which the standard deviation for the time period is compared can be determined by one or more of steps 530-536 below. In step 530, a plurality of baseline audio signal amplitudes for a first time period and a plurality of active audio signal amplitudes for a second time period are determined from the received acoustic data. For example, the plurality of baseline audio signal amplitudes for the first time period can correspond to no motion or minute motion associated with the user (e.g., motion due to the user's normal breathing, motion due to a normal heartbeat, motion due to ambient airflow, rapid eye movement during sleep, etc.). And, the plurality of active audio signal amplitudes for the second time period can correspond to active motion associated with the user (e.g., motion due to the user rolling from one body position to another, such as lying on their left side from a supine position).

[0126] In step 532, a baseline standard deviation is calculated based at least in part on the determined plurality of baseline audio signal amplitudes. In step 534, an active standard deviation is calculated based at least in part on the determined plurality of active audio signal amplitudes. In step 536, a predetermined threshold is determined based at least in part on the calculated baseline standard deviation and the calculated active standard deviation. For example, the predetermined threshold may be determined by averaging (i) the baseline standard deviation and (ii) the active standard deviation. In some implementations, the predetermined threshold may be calculated using historical data and / or real-time data. In some examples, not all recordings have the same baseline audio signal amplitude. The predetermined threshold and / or baseline audio signal amplitude are selected to provide the best motion detection across different recordings. Additionally or alternatively, the predetermined threshold and / or baseline audio signal amplitude are performed and / or adjustable based on real-time data.

[0127] In some implementations, the variation is evaluated using a metric different from standard deviation, such as variance. Additionally or alternatively, in some implementations, the variation is evaluated over various window lengths, such as 1 second, 2 seconds, 3 seconds, 4 seconds, 5 seconds, 6 seconds, 7 seconds, 9 seconds, 10 seconds, etc. Additionally or alternatively, in some implementations, the predetermined threshold is applied in another manner, such as, for example, using a running and / or adjustable threshold.

[0128] In some implementations, analyzing the received acoustic data (step 520) can include cepstral analysis, autocepstral analysis, autocorrelation analysis, spectral analysis, or any combination thereof. In some such implementations, the spectral analysis includes a fast Fourier transform (FFT) (optionally using a sliding window), a spectrogram, a short-time Fourier transform (STFT), a wavelet-based analysis, or any combination thereof.

[0129] In some implementations, analyzing the received acoustic data (step 520) may include processing the received acoustic data to identify multiple features at step 540. In some such implementations, the analyzed acoustic data may include (i) cepstral data, (ii) spectral data, e.g., including an acoustic spectral signature, or (iii) both (i) and (ii). For example, in some implementations, the multiple features include (i) a change in the spectral signature, (ii) a change in frequency, (iii) a change in signal amplitude, (iv) a change in position, or (v) any combination thereof. These one or more changes may include changes that occur as a result of motion, such as a change in one or more features from pre-motion to post-motion. Specifically, for example, the plurality of features may include (i) a change in spectral signature from a pre-motion spectral signature to a post-motion spectral signature, (ii) a change in frequency from a pre-motion frequency to a post-motion frequency, (iii) a change in signal amplitude from a pre-motion signal amplitude to a post-motion signal amplitude, (iv) a change in position from a pre-motion position to a post-motion position, (v), or any combination thereof. In some implementations, with respect to changes in position features, movement of the conduit may cause stretching and / or bending, thus resulting in a change in position associated with the received acoustic data. For example, in some such implementations, when the conduit is stretched, the position of a physical feature within the conduit may change, such as relative to another position in the conduit and / or another physical feature within the conduit.

[0130] Additionally or alternatively, in some implementations, analyzing the received acoustic data (step 520) can include analyzing the multiple features using a machine learning model (e.g., Markov, Bayesian, 1D convolutional, logistic regression, or any combination thereof). Such a model can be trained based on historical body position data and historical acoustic data (e.g., from a user or population of users).

[0131] At step 550, a motion event associated with the user is determined based at least in part on the analysis (e.g., step 520). In some implementations, the motion event is associated with (i) a change in user position, (ii) a sleep state, (iii) a change in sleep state, (iv) a sleep stage, (v) a change in sleep stage, or (vi) the occurrence of a respiratory event (e.g., an inhalation, exhalation, cough, gasp, sneeze, laugh, cry, scream, snore, apnea, or any combination thereof). In some implementations, the motion event includes multiple motion events.

[0132] In some implementations, determining motion events associated with the user (step 550) includes determining a motion frequency in step 552. In some implementations, the motion frequency indicates the user's sleep stage and / or sleep state, as different sleep stages and / or sleep states have different levels of motion frequency. In some such implementations, a high motion frequency indicates the user's wakefulness and / or restlessness, a low motion frequency indicates the user may be in light sleep, and a minimum and / or zero motion frequency indicates the user may be in deep or REM sleep. In some implementations, some individuals may move a lot while sleeping, while others move less, so the high, low, and / or minimum motion frequencies are relative and / or user-specific. In some implementations, a cluster of motion may indicate a specific sleep state (e.g., wakefulness). In some implementations, any numeric value may be assigned, for example, 0 = no motion and likely asleep, while 3 may be associated with some movement and a high likelihood of wakefulness. In some implementations, the movement frequency may be combined with other features and / or data (e.g., respiratory data), which together may indicate and / or confirm a sleep state and / or sleep stage associated with the user. In some implementations, other demographic data (e.g., the user's age) may be factored in. For example, the movement frequency of a user while asleep typically changes with age. Additionally or alternatively, in some implementations, the movement frequency may be further analyzed to detect sleep movement disorders such as periodic leg movements and / or restless legs syndrome. Additionally or alternatively, in some implementations, the movement frequency may be combined with other data (e.g., flow data and / or pressure data) that may indicate the user's sleep state and / or sleep stage. The movement frequency features are then analyzed to indicate and / or confirm movement.

[0133] In some implementations, the audio data may be preprocessed before being analyzed in step 520. For example, in some such implementations, the preprocessing may include (i) filtering for a specific frequency range (e.g., high-frequency components are typically desired for fast events such as movement), (ii) downsampling the audio signal to lower frequencies, (iii) a normalization step, or (iv) any combination thereof. Regarding the normalization step, the section values ​​of the conduit without movement are normalized (e.g., scaled) so that they are equal for different sessions of the same user and / or different users. For example, after normalizing all values ​​based on equal no-motion section values, the same threshold (e.g., a predetermined threshold disclosed herein) is applied to each user to help distinguish between movement and non-motion if movement actually occurs. As another example, a user may sleep in a quiet room versus a noisy room. Acoustic data received in a quiet room (e.g., the acoustic data received in step 510) may contain less ambient noise than that received in a noisy room. Additionally and / or alternatively, in some implementations, ambient noise may also include background noise generated by components of the respiratory treatment system (e.g., microphones and / or flow generators). Thus, baseline values ​​associated with analyzed acoustic data from a noisy room may be higher than those from a quiet room, at least in part because acoustic data is received at different scales between the two scenarios, making it more difficult to find a threshold value that detects sounds indicative of movement in the user's ducts. A normalization step can eliminate such scaling differences and use the same threshold value for both scenarios.

[0134] Referring to FIGS. 6A-6D, test data support that the systems (e.g., system 100) and methods (e.g., method 500) disclosed herein can effectively determine user movement during use of a respiratory therapy system. For example, in some implementations, method 500 identifies movement by extracting changes (e.g., standard deviation) in the audio signal over a time window (e.g., a 5-second window (or approximately one or two breaths)). Sliding and / or shifting this window in time thus obtains the running standard deviation of the audio signal. Active movement then results in a peak in this metric, while steady breathing with no or minimal movement serves as a baseline with a low, consistent standard deviation. The increase in this metric is due to impulses (e.g., vascular movement) and more varied and inconsistent breathing patterns during physical movement.

[0135] FIG. 6A shows RF (e.g., RADAR) data measured during a treatment session as indicative of a subject's movement, according to some implementations of the present disclosure. FIG. 6B shows audio data measured during the treatment session of FIG. 6A. FIG. 6C shows processed audio data calculated using the audio data of FIG. 6B. FIG. 6D shows movement activity data calculated using the processed audio data of FIG. 6C. Thus, FIGS. 6B-6C show movement analysis relative to the validated baseline (FIG. 6A).

[0136] In this example, to determine the processed audio of Figure 6C, the standard deviation is calculated for the first audio sample (comprising an 8-second period from 0 to 8 seconds), and then the sliding window shifts to the next sample 0.1 seconds earlier in time (comprising an 8-second period from 0.1 to 8.1 seconds). Any limitations of the system due to buffering samples can be mitigated by first downsampling.

[0137] As shown in Figure 6B, the audio signal between 10 and 15 seconds shows some disturbances. Conversely, before and after 10 seconds, the audio signal shows steady breathing with no or minimal movement. As shown in Figure 6C, the processed audio metrics pick up on this change, moving from a baseline of approximately 0.05 to over 0.1 standard deviations during the movement period.

[0138] In Figures 6A-6D, the X-axis is time. In Figure 6A, the Y-axis is the RF sensor output (units: volts (V)). The RF sensor has two channels, in-phase (I) and quadrature (Q), each of which is plotted in Figure 6A. In Figure 6B, the Y-axis is the amplitude of the audio signal recorded during the same period as the RF signal in Figure 6A. In Figure 6C, the Y-axis is the standard deviation of the processed audio signal from Figure 6B. In Figure 6D, the Y-axis is either 1 or 0, with 1 indicating motion and 0 indicating no motion, with motion defined as when the standard deviation (Figure 6C) is greater than 0.075. Specifically, Figure 6D is plotted such that motion is true (=1) if the processed audio signal (Figure 6C) exceeds a theoretical threshold of standard deviation (i.e., 0.075 in this example), and motion is false (=0) if the processed audio signal (Figure 6C) does not exceed the same theoretical threshold of standard deviation. In other words, by setting a predetermined threshold for the processed audio metric (e.g., 0.075 in the present example of FIG. 6C ), each sample for which the processed audio metric exceeds 0.075 is marked as a motion event (e.g., motion may be either 0: no motion or little motion, or 1: a motion event). While this example shows 0.075 as the predetermined threshold, the predetermined threshold for the processed audio metric can be other values ​​between about 0.05 and about 0.1. In some implementations, the predetermined threshold can be any selected value that distinguishes motion.

[0139] 7A-7D, additional test data further support that the systems (e.g., system 100) and methods (e.g., method 500) disclosed herein can effectively determine user movement during use of a respiratory treatment system. FIG. 7A shows EMFIT activity data measured during a first treatment session according to some implementations of the present disclosure. FIG. 7B shows processed audio data derived from audio signals detected by a microphone in a conduit of a respiratory treatment system measured during the first treatment session of FIG. 7A according to some implementations of the present disclosure. FIG. 7C shows EMFIT activity data measured during a second treatment session according to some implementations of the present disclosure. FIG. 7D shows audio data measured during the second treatment session of FIG. 7C according to some implementations of the present disclosure. Compared to an EMFIT device, this activity metric (calculated by comparing breath-to-breath variations and / or fixed 8-second averages capturing approximately two breaths) demonstrates good alignment.

[0140] In the example test data shown in FIGS. 7A-7D, the microphone is positioned inside the conduit, near the end of the conduit that is connected to the respiratory device (including the flow generator). Placing the microphone inside the respiratory system, such as the conduit, the respiratory device, or the user interface, makes the microphone particularly sensitive to picking up sounds caused by movement of respiratory system components (particularly the conduit). In some such implementations, sounds detected by the microphone may be caused by the conduit moving on / against bedding. Additionally or alternatively, in some other implementations, sounds detected by the microphone may be caused by (or may be caused by) another source where the conduit does not contact (e.g., rub) another surface, such as movement of the conduit itself causing vibrations within the conduit. In some such implementations, the microphone may optionally be positioned elsewhere, such as external to the respiratory treatment system. Such placement outside the respiratory treatment system may improve detection of other sounds associated with user movement, such as creaks from the bed and / or rustling of bedding as the user turns over.

[0141] Referring to FIG. 8, a flow diagram of a method 800 for determining a user's body position during a respiratory treatment session is disclosed. One or more steps of method 800 can be implemented using any element or aspect of system 100 (FIGS. 1-2) described herein. In step 810, flow data (e.g., generated by flow sensor 134) associated with a user of a respiratory treatment system (e.g., respiratory treatment system 120 of system 100) is received. In step 820, the received flow data is analyzed to determine one or more characteristics. In step 830, the user's body position is determined based at least in part on the determined one or more characteristics. For example, if a user is sleeping on their back, clusters of respiratory events are likely to occur. A relative increase in the frequency of respiratory events and / or clusters of respiratory events may also indicate that the user is sleeping on their back. In some implementations, if the analyzed flow data indicates clusters of apnea, movement, and fewer apneas, method 800 provides the possibility of changing the user's body position from a supine position to a non-supine position.

[0142] Additionally or alternatively, in some implementations, pressure data (e.g., generated by pressure sensor 132) is received and analyzed in the same or similar manner as described herein. Thus, while FIG. 8 illustrates an example using flow data, it is contemplated that flow data, pressure data, or both, may be used to determine the user's body position in method 800.

[0143] Body positions can include (i) left side, (ii) right side, (iii) prone (face down), and (iv) supine (back up). Sleeping on the left side can reduce problems such as insomnia and / or gastroesophageal reflux disease (GERD), which adversely affect sleep apnea. Sleeping on the left side can result in the user experiencing the best quality of sleep (better blood flow and reduced respiratory resistance). Unfortunately, depending on the mask type and / or whether the mask is fitted correctly, a left side body position can also cause higher mask leakage than other body positions, such as a supine position. For those with coexisting congestive heart failure (CHF), a left side body position may not be a good position, and the user's heart rate should be monitored. Sleeping on the right side can be an alternative to a left side body position and has the same or similar advantages and disadvantages as those discussed herein for a left side body position.

[0144] A prone (face-down) body position can reduce obstructive breathing events because the user's tongue tends to roll forward rather than backward, as can occur with obstructive breathing events. However, the user's mouth may be blocked by pillow bedding. A prone body position may also cause mask leakage and / or discomfort, depending on the type of mask. A supine (back-up) body position may provide the best mask seal. However, a supine body position requires more pressure because the user's tongue tends to roll backward. Therefore, a supine body position tends to be the worst position for users with positional apnea.

[0145] In some implementations, determining the user's body position includes comparing one or more features determined from the acoustic data and / or flow data to a plurality of historical features associated with a plurality of historical body positions in step 832. For example, in some implementations, step 840 receives historical flow data associated with a user of a respiratory treatment system during a respiratory treatment session.

[0146] In step 850, a plurality of motion events associated with the user are determined using any suitable means, such as an RF sensor, an EMFIT device, a pressure-sensitive mattress, etc. Based at least in part on the determined plurality of motion events, in optional step 852, the respiratory treatment session is divided into a plurality of respiratory treatment sections. In optional step 854, the received historical flow data for each of the plurality of respiratory treatment sections is analyzed to extract a plurality of historical features. Alternatively, the plurality of historical features are extracted from the historical flow data without dividing the respiratory treatment session into sections. Based at least in part on the analysis, in step 856, optionally for each of the plurality of respiratory treatment sections, one of a plurality of historical body positions is determined and associated with one or more of the plurality of historical features extracted from the historical flow data.

[0147] In some implementations, steps 840-856 may include a reference data set where (i) the user's body position within a given time frame is known, (ii) flow and / or pressure signal features associated with the user's body position within the given time frame are extracted, and (iii) a machine learning model is then trained based on these body position data and flow and / or pressure signal features. The user's body position for newly collected flow and / or pressure signal data can then be determined by (i) extracting features useful for determining the user's body position and providing these features to the trained machine learning model, or (ii) providing the flow and / or pressure signal data directly to the trained machine learning model and (iii) receiving the body position returned by the machine learning model. In some implementations, the machine learning model derived using the reference data set in steps 840-856 may then be used in steps 820 and / or 830 of method 800.

[0148] In some implementations, features (e.g., features related to acoustic, flow, and / or pressure data) are extracted on an epoch-by-epoch basis. For example, a sleep session (during which acoustic, flow, and / or pressure data is generated) is divided into multiple discrete segments called epochs. Features are extracted for each epoch. The features may be analyzed independently or relative to one another across the entire sleep session. Additionally or alternatively, in some implementations, physiological data may also be generated. The physiological data may include a respiratory signal representative of the user's breathing. Typically, the respiratory signal is a measure of the amplitude of the user's breathing. Furthermore, additionally or alternatively, in some implementations, temporal data (e.g., data related to the duration of the sleep session, data related to which epoch in the sleep session is the current epoch, etc.) may also be generated by system 100.

[0149] The received data may be analyzed to determine the user's physical position for each epoch of the sleep session. Typically, the data is analyzed in real time, so that after each epoch, the data from that epoch is analyzed to determine the user's physical position for that epoch. For example, in some implementations, each epoch may last 30 seconds, so the data in this example is analyzed in 30-second chunks. However, in other implementations, epochs of different lengths may be used. For example, the length of an epoch may be 1 second, 5 seconds, 10 seconds, 20 seconds, 1 minute, 2 minutes, 5 minutes, or 10 minutes. The length of an epoch may also be set to correspond to a specific breathing rate, such as 1 breath, 2 breaths, or 5 breaths. The length may be determined based on the user's average breathing rate or the average breathing rate of a population to which the user belongs.

[0150] As another example, an epoch-to-epoch based analysis may be performed as follows: First, data associated with a sleep session having multiple epochs is received. In some implementations, the data includes flow data representing the flow of pressurized air from the respiratory treatment device 122 through the conduit 126 to the user interface 124. The flow data is analyzed to identify features associated with the current epoch. As disclosed herein, the sleep session may be divided into multiple epochs. An epoch may be of any suitable length, such as 30 seconds in length or the length of a single breath.

[0151] The flow data representing the pressurized airflow for the epoch is analyzed. In some implementations, any respiratory data representing the user's respiratory rate for the epoch is also analyzed, which may be determined based on the flow data and / or other data generated using one or more sensors 130. Many different features can be identified. In some implementations, the features include one or more features related to the pressurized airflow, such as (i) a maximum flow value over the current epoch and one or more previous epochs, (ii) a flow skew for the current epoch, (iii) a median flow skew over the current epoch and one or more previous epochs, (iv) a standard deviation of the flow values ​​for the current epoch, (v) a standard deviation of the flow values ​​for the current epoch and one or more previous epochs, (vi) a standard deviation of the flow volume for the current epoch and one or more previous epochs, (vii) a time ratio between inspiration and expiration for the current epoch, (viii) a time ratio between inspiration volume and expiration volume for the current epoch, or (ix) any combination of (i)-(viii).

[0152] In some implementations, the features include one or more features related to the user's respiration rate, such as the average respiration rate over the current epoch, the standard deviation of the respiration rate over the current epoch and one or more previous epochs, or both. In some implementations, the features can include at least one feature related to a temporal property of the current epoch. Generally, the temporal property is a measure of where the epoch is located in the sleep session. For example, the temporal property can be the number of the current epoch within the current sleep session or the nth root of the number of the current epoch within the current sleep session. In some implementations, n=20, and the temporal property is the twentieth root of the number of the current epoch within the current sleep session.

[0153] The features extracted from the flow data (and / or respiration data) are then analyzed to identify user-related movements in the current epoch. This analysis may indicate the presence and / or frequency of user movement in the current epoch. After extracting features from the current epoch and identifying movements that occurred in the current epoch, multiple body position probabilities may be adjusted based on movements that occurred in the current epoch, movements that occurred in previous epochs, or determined body positions in previous epochs.

[0154] In some examples, a sleep session can be divided into different sections by detecting when a movement event occurs. In an illustrative example, 0 represents no movement or little movement (e.g., breathing movement, slight body movement), and X represents a movement event (e.g., limb movement and / or body movement from one sleeping position to another, such as from supine to left side). A sleep session can be represented as follows:

[0155] 0 0 0 0 0 0 0 X 0 0 0 0 0 0 0 0 0 0 0 0

[0156] These sections can then be analyzed separately. Extracting features of the flow and / or pressure signals within the sections can help determine which position the user is in. For example, in some implementations, features related to breathing mechanics for each position can help identify the body position (e.g., respiratory effort may be greater / less in a supine position compared to a lateral position). If breathing is more difficult in a certain body position, the user may breathe less air. By extracting features (e.g., flow signal amplitude, tidal volume, and / or minute ventilation) from the flow signal and comparing them with pre-movement features, method 500 can determine whether the user has moved from one position to another and / or which body position the user may be in. For example, in some implementations, features such as flow signal amplitude, tidal volume, and / or minute ventilation can decrease as the user moves from a supine position to a lateral position and from a lateral position to a prone position.

[0157] In some implementations, the real-time flow signal is analyzed to detect changes in body position and then classify the new position. Method 800 then enables system 100 to modify the pressure of respiratory treatment system 120 to provide optimal treatment to the user based on the user's body position. If the user turns over and returns to the same position within a short period of time (e.g., within about 5 seconds) and / or if the user moves around in bed without changing position, method 800 may employ processing to avoid changing the settings.

[0158] Other examples of flow and / or pressure data features that may be used to determine body position include signal amplitude (e.g., peak inhalation / exhalation), respiratory waveform morphology, respiratory frequency, inspiration to exhalation duration ratio, analysis of the respiratory signal envelope over time, or combinations thereof. In some implementations, these features are partially user-specific and may show the same trends for each user, but may have different values ​​between different users.

[0159] Leak information, such as mask leak or mouth leak information, can be derived from the flow and / or pressure signals (and / or acoustic signals) and can also be used to help infer changes in body position. For example, a sudden change in leak may mean that a position change has caused the mask to shift slightly on the user's face and / or that the user has started (or stopped) mouth breathing. Other information, such as determining snoring from flow, pressure, and / or acoustic data, may also indicate that the user is likely sleeping in a supine position.

[0160] In some implementations, signal processing techniques such as frequency domain analysis, autocorrelation, filtering, finding fiducials, and / or calculating signal derivatives can be applied as a preprocessing step before extracting features. Any extracted features can then be input into any of a variety of statistical or machine learning models, such as Markov, Bayesian, 1D convolution, logistic regression, and / or any other such classifier, to determine the current position as either supine, lateral, or prone. Such models can be trained based on historical body position data (e.g., from a user or population of users) and historical flow and / or pressure data / extracted features.

[0161] In some implementations, for example, step 860 includes time stamping the user's body position. In some implementations, for example, step 862 includes modifying one or more parameters of the respiratory therapy session (e.g., motor speed, pressure, flow rate, or any combination thereof) based at least in part on the determined body position of the user. Additionally or alternatively, in some implementations, step 864 includes generating an alert, notification, or instruction based at least in part on the determined body position of the user. Additionally or alternatively, in some implementations, method 500 disclosed herein includes determining user movement (step 810) based at least in part on the received acoustic data.

[0162] In some implementations, in addition to the flow data, secondary data (e.g., received from another sensor, such as one or more sensors 130 of system 100) may be used to determine one or more characteristics (step 820). For example, in some such implementations, step 870 receives acoustic data (e.g., generated by microphone 140) associated with a user of the respiratory treatment system. In some such implementations, a body position of the user is further determined based at least in part on the received acoustic data associated with the user of the respiratory treatment system.

[0163] Method 800 allows for the detection of a user's body position and / or changes in body position during sleep. As disclosed herein, position changes can be detected by tracking flow features after significant movements (e.g., as detected by a microphone in a respiratory treatment system). In some implementations, these features and / or characteristics in the flow signal are variable with respect to sleep position. Because treatment conditions are also variable with sleep position, treatment can be customized accordingly, based at least in part on determined position changes, throughout a treatment session.

[0164] 9A shows real-time flow and pressure signals measured simultaneously during a treatment session, according to some implementations of the present disclosure. Method 800 (FIG. 8) processes the flow signal in real time and calculates the signal's long-term baseline trend, peak-to-trough amplitude, respiratory rate, and / or respiratory shape to determine the user's body position (and thus detect changes in position) and classify new positions. This can be coupled to a respiratory treatment system to monitor for apneas and hypopneas.

[0165] In some implementations, body position is estimated from flow-based and / or pressure-based features at regular intervals. Then, a change in body position is determined based on whether there is a change in the estimated body position. Additionally or alternatively, in some implementations, body position is determined using only flow-based and / or pressure-based features during stable time periods. Therefore, any randomness in the flow and / or pressure signals (e.g., due to possible limb (but not body position) movement, coughing, or respiratory events) does not affect the body position estimation. In some other implementations, any randomness in the flow and / or pressure signals may indicate a new body position change, and therefore, flow-based and / or pressure-based features during these unstable time periods may be analyzed under the assumption that the relative position is new. Additionally or alternatively, in some implementations, the frequency of respiratory events indicates body position. Furthermore, additionally or alternatively, in some implementations, an algorithm is trained to classify body position based on flow-based and / or pressure-based data or a selection of extracted features, as described herein.

[0166] In some implementations, the flow features may include (i) baseline and peak-peak of the flow signal over many breaths (long time scale); (ii) interference with respiratory metrics (real time), analysis over longer time scales (e.g., 30 seconds, 60 seconds, 90 seconds, 5 minutes); respiratory rate variability, which may include stability over time (related to variability) and / or standard deviation of respiratory rate; (iii) respiratory depth (e.g., shallow, deep, etc.) and / or relative flow signal amplitude of adjacent breaths, which may include mean and / or trimmed mean values ​​(e.g., 10% trimmed mean values) of respiratory rate to eliminate outliers; (iv) wakefulness or sleep (e.g., the user's detected sleep state), where rapid increases (e.g., sudden accelerations or decelerations) in respiratory rate are observed during quiet periods and REM sleep; (v) skewness of respiratory shape metrics; (vi) kurtosis of respiratory shape metrics; (vii) characteristic patterns in the spectrogram; and (vii) relative proportions of REM sleep and deep sleep to date.

[0167] As shown in Figure 9, eight suspected body position changes based on the baseline amplitude of the flow signal are shown at 910, 920, 930, 940, 950, 960, 970, and 980. The method 800 (Figure 8) disclosed herein may be used to determine body position changes. The pressure signal below the flow signal indicates a delay in the action of the APAP in adjusting the pressure.

[0168] One advantage of being able to detect movement (e.g., method 500) is detecting changes in body position. Body positions (e.g., supine, prone, sideways) change throughout the night. For there to be changes in body position, there must have been movement. Referring to FIG. 10, a flow diagram of a method 1000 for determining a user's body position during a respiratory therapy session is disclosed. Any element or aspect of system 100 (FIGS. 1-2) and / or method 500 (FIG. 5) described herein can be used to implement one or more steps of method 1000.

[0169] At step 1010, acoustic data associated with a user of a respiratory treatment system (e.g., respiratory treatment system 120 of system 100) is received. For example, in some implementations, the acoustic data may be received from a microphone associated with the respiratory treatment system (e.g., microphone 140 of system 100). In some such implementations, the microphone is configured to generate the acoustic data based at least in part on detected sounds associated with the respiratory treatment system. For example, in some implementations, the acoustic data can be reproduced as one or more sounds associated with movement of a conduit of the respiratory treatment system (e.g., conduit 126 of system 100). Additionally and / or optionally, in some implementations, the movement causes at least a portion of the conduit to rub against one or more surfaces.

[0170] In step 1020, the received acoustic data is analyzed to determine one or more characteristics. In step 1030, a body position of the user is determined based at least in part on the determined one or more characteristics. In some implementations, the acoustic data received from the microphone in step 1010 may include echo data (e.g., based on acoustic reflections), audio data (e.g., based on passive audio signals), or both. For example, method 1000 may include one or more of the following steps in steps 1010, 1020, and / or 1030: (i) in step 1010, receiving acoustic data relating to acoustic reflections of sound signals emitted into the conduit and / or mask (or, alternatively, in step 1010, receiving acoustic data relating to the sound of the conduit rubbing against itself or another surface (e.g., a user's surface, a bedding surface, etc.)); (ii) in step 1020, performing cepstral or spectral analysis of the acoustic data (which may include observing the effective length of the conduit or abrupt changes in the cepstrum or spectrum with movement of the conduit / mask / user) (or, alternatively, the noise generated by the action of the conduit rubbing against itself or another surface generates a characteristic resonant sound that serves as a noise source for the analysis (e.g., cepstral or spectral analysis) performed in step 1020).

[0171] In some implementations, determining the user's body position includes comparing the determined one or more characteristics to a plurality of historical characteristics associated with a plurality of historical body positions, in step 1032. For example, in some implementations, in step 1040, historical acoustic data associated with a user of a respiratory treatment system during a respiratory treatment session is received.

[0172] Based at least in part on the received historical acoustic data, step 1050 determines a plurality of motion events associated with the user. Based at least in part on the determined plurality of motion events, optional step 1052 divides the respiratory treatment session into a plurality of respiratory treatment sections. Based at least in part on the determined plurality of motion events, optional step 1054 analyzes the received historical acoustic data for each of the plurality of respiratory treatment sections to extract a plurality of historical features. Based at least in part on the analysis, optional step 1056 determines one of a plurality of historical body positions for each of the plurality of respiratory treatment sections.

[0173] In some implementations, steps 1040-1056 may include a reference data set where (i) the user's physical position within a given time frame is known, (ii) features of the audio signal and / or processed audio data related to the user's physical position within the given time frame are extracted, and (iii) a machine learning model is then trained based on these physical position data and audio signal / processed audio data features. The user's physical position for newly collected audio signals / processed audio data can then be determined by (i) extracting features useful for determining the user's physical position, (ii) feeding these features to the trained machine learning model, and (iii) receiving the body position returned by the machine learning model. In some implementations, the machine learning model derived using the reference data set in steps 1040-1056 may then be used in steps 1020 and / or 1030 of method 1000.

[0174] In some implementations, for example, step 1060 includes time stamping the user's body position. In some implementations, for example, step 1062 includes modifying one or more parameters of the respiratory therapy session (e.g., motor speed, pressure, flow rate, or any combination thereof) based at least in part on the determined body position of the user. Additionally or alternatively, in some implementations, step 1064 includes generating an alert, notification, or instruction based at least in part on the determined body position of the user. Additionally or alternatively, in some implementations, method 500 disclosed herein includes determining user movement (step 1010) based at least in part on the received acoustic data.

[0175] In some implementations, secondary data (e.g., received from another sensor, such as one or more sensors 130 of system 100) in addition to the acoustic data may be used to determine one or more characteristics (step 1020). For example, in some such implementations, flow data associated with a user of the respiratory treatment system is received in step 1070. In some such implementations, a body position of the user is further determined based at least in part on the received flow data associated with the user of the respiratory treatment system.

[0176] The ability to detect changes in body position (e.g., methods 800 and 1000) provides many benefits to the user during treatment. Similar to differences in respiratory mechanics due to body position, the likelihood of obstructive respiratory events (e.g., apneas, hypopneas, etc.) varies with body position. For example, because obstructive sleep apnea (OSA) is due to obstruction of the respiratory pathway, a greater mass is imposed on the user's airway when the user is sleeping in a supine position. If the user is prone to OSA events when in a particular body position, a higher pressure setting may be required to keep the airway open in that body position. Conversely, if the user moves to a lateral position, the same level of treatment pressure may not be required. Thus, by knowing the body position, system 100 can adjust the treatment pressure to suit the body position and, optionally, the sleep state (e.g., obstructive respiratory events are more likely to occur during REM sleep, and therefore, the treatment pressure may be adjusted if a body position is detected that is supine during REM sleep), thereby improving patient comfort and / or treatment effectiveness.

[0177] Examples of therapy adjustments based on detected body position: - The patient is in the recumbent position and the treatment pressure is 10cmH2O -Patient transfer - The patient is currently in the supine position and the treatment pressure is increased to 12cmH2O

[0178] The user's body position during treatment may also be used by system 100 to recommend alternative solutions to help the user manage their condition. For example, if the user is determined to suffer from primarily positional apnea, system 100 may recommend a particular pillow designed to reduce supine sleeping to lower the AHI, thereby improving the patient's comfort and sleep quality. Additionally, body position may be tracked over time to indicate the effectiveness of this solution in reducing the AHI.

[0179] Generally, a system including a control system having one or more processors and a memory storing machine-readable instructions can be used to implement methods 600, 800, 1000. The control system can be coupled to the memory, and the machine-readable instructions, when executed by at least one of the processors of the control system, can implement methods 600, 800, 1000. Methods 600, 800, 1000 can also be implemented using a computer program product (e.g., a non-transitory computer-readable medium) including instructions that, when executed by a computer, cause the computer to perform the steps of methods 600, 800, 1000.

[0180] Although the system 100 and methods 600, 800, 1000 are described herein with reference to one user, more generally, the system 100 and methods 600, 800, 1000 can be used with multiple users simultaneously (e.g., two users, five users, ten users, twenty users, etc.) For example, the system 100 and methods 600, 800, 1000 can be used in a cloud monitoring setting.

[0181] Additionally or alternatively, in some implementations, system 100 and / or methods 600, 800, 1000 can be used to monitor one or more patients while using one or more respiratory treatment systems (e.g., respiratory treatment systems described herein). For example, in some such implementations, notifications associated with motion events and / or body positions related to one or more patients can be sent to a monitoring device or personnel. One or more steps of methods 600, 800, and / or 1000 can be used to determine the motion events and / or body positions. Additionally or alternatively, in some implementations, the motion events and / or body positions are simply recorded.

[0182] One or more elements, aspects, steps or portions thereof from any one or more of claims 1-72 below may be combined with one or more elements, aspects, steps or portions thereof from any one or more of the other claims 1-72 or combinations thereof to form one or more further implementations and / or claims of the present disclosure.

[0183] While the present disclosure has been described with reference to one or more particular embodiments or implementations, those skilled in the art will recognize that many modifications are possible without departing from the spirit and scope of the present disclosure. Each of these implementations and obvious variations thereof is considered to be within the spirit and scope of the present disclosure. It is also contemplated that additional implementations according to aspects of the present disclosure may combine any number of features from any of the implementations described herein.

[0184] [CROSS-REFERENCE TO RELATED APPLICATIONS]

[0185] This application claims the benefit of and priority to U.S. Provisional Patent Application No. 62 / 706,104, filed July 31, 2020, which is incorporated herein by reference in its entirety.

Claims

1. 1. A system for determining user movement during use of a respiratory treatment system, comprising: The system comprises: the respiratory treatment system including a conduit, a user interface, and a respiratory treatment device; a microphone included in the respiratory treatment system and configured to generate acoustic data; a control system including one or more processors; a memory storing machine-readable instructions; The machine-readable instructions, when executed by the one or more processors, cause the system to: receiving acoustic data associated with the user of the respiratory treatment system, the acoustic data associated with the user being generated by the microphone based at least in part on detected audio data that is reproducible as one or more sounds associated with movement of the component of the respiratory treatment system, the one or more sounds associated with movement of the component of the respiratory treatment system being caused by movement of the component of the respiratory treatment system rubbing against one or more surfaces; analyzing the received acoustic data; determining a motion event associated with the user based at least in part on the analyzed acoustic data; and To implement system.

2. The system of claim 1 , wherein the respiratory treatment system comprises the control system and the memory.

3. 3. The system of claim 2, wherein the microphone is (i) internal to the respiratory treatment system, (ii) integrated into the respiratory treatment system, or (iii) both (i) and (ii).

4. The microphone is connected to a component of the respiratory treatment system selected from (i) a conduit of a respiratory treatment device of the respiratory treatment system, (ii) a circuit board of the respiratory treatment device of the respiratory treatment system, (iii) a connector of the respiratory treatment system, (iv) a user interface of the respiratory treatment system, or (v) any other component of the respiratory treatment system. The system of claim 3, wherein the microphone is a coupled microphone.

5. 5. The system of claim 1, wherein the movement event is associated with (i) a change in user position, (ii) a sleep state, (iii) a change in sleep state, (iv) a sleep stage, (v) a change in sleep stage, (vi) the occurrence of a respiratory event, or any combination of (i)-(vi).

6. 6. The system of claim 2, wherein the microphones include a first microphone external to the respiratory treatment system and a second microphone that is (i) internal to the respiratory treatment system, (ii) integrated into the respiratory treatment system, or (iii) both (i) and (ii).

7. The system of claim 6 , wherein the respiratory events include inhalation, exhalation, coughing, gasping, sneezing, laughing, crying, screaming, snoring, apnea, or any combination thereof.

8. The machine-readable instructions, when executed by the one or more processors, cause the system to: determining a plurality of audio signal amplitudes versus time periods from the received acoustic data; calculating a standard deviation for the time period based at least in part on the determined audio signal amplitudes; comparing the standard deviation for the time period to a predetermined threshold; Further implementation of The system according to any one of claims 1 to 7.

9. The machine-readable instructions, when executed by the one or more processors, cause the system to: determining a plurality of baseline audio signal amplitudes for a first time period and a plurality of active audio signal amplitudes for a second time period from the received acoustic data; calculating a baseline amplitude standard deviation based at least in part on the determined plurality of baseline audio signal amplitudes; calculating an active amplitude standard deviation based at least in part on the determined plurality of active audio signal amplitudes; determining the predetermined threshold based at least in part on the calculated baseline amplitude standard deviation and the calculated active amplitude standard deviation; Further implementation of The system of claim 8.

Images