System and method for identifying breathing comfort

Abstract

A method for classifying a user of a respiratory pressure therapy (RPT) device is disclosed, the method comprising: identifying that the user has started a therapy session using the RPT device; receiving first input data associated with the user and the therapy session; training a machine learning model based on a plurality of pre-classified users and the first input data to determine associations between the user and the plurality of classifications; classifying the user as a classification in the plurality of classifications; and causing a user device and / or the RPT device to perform an action in response to classifying the user as the classification. The first input data may include a selection of the user in response to a survey cue.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of priority under 35 U.S.C. §119(e) to U.S. Provisional Application No. 63 / 4481,229, filed on January 24, 2023, entitled “SYSTEMS AND METHODS FOR IDENTIFYING BREATHING COMFORT,” the disclosure of which is hereby incorporated by reference in its entirety for all purposes. Technical Field

[0003] The present technology relates to one or more of the screening, diagnosis, monitoring, treatment, prevention, and improvement of respiratory-related disorders. The present technology also relates to medical devices or apparatuses and their uses. Background Art

[0004] Many individuals suffer from sleep-related and / or breathing disorders. Examples of sleep-related and / or breathing disorders include periodic limb movement disorder (PLMD), restless legs syndrome (RLS), sleep-disordered breathing (SDB), obstructive sleep apnea (OSA), apnea, Cheyne-Stokes respiration (CSR), respiratory insufficiency, obesity hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular disease (NMD), and chest wall disorders.

[0005] These and other disorders are characterized by specific events that occur while an individual sleeps (e.g., snoring, apnea, hypopnea, restless legs, sleep disturbances, choking, increased heart rate, breathing difficulties, asthma attacks, epileptic seizures, convulsions, or any combination thereof).

[0006] To alleviate some of these sleep-related and / or breathing disorders, users may be prescribed respiratory devices or systems. For example, a continuous positive airway pressure (CPAP) machine may be used to increase the air pressure in the throat of a respiratory device user and prevent the airway from closing and / or narrowing during sleep.

[0007] While these respiratory devices or systems can improve a user's sleep quality, they can sometimes compromise the user's comfort. For example, when trying to fall asleep, the user may experience some discomfort, including a feeling of air deprivation when first donning the mask associated with the respiratory device, or other discomfort due to air being forced into their airways.

[0008] Discomfort experienced by a user of a respiratory therapy system is often more pronounced when they first begin sleep therapy using the system. If the initial user experience is unsatisfactory or uncomfortable, the user is more likely to abandon therapy and sacrifice sleep quality in pursuit of greater sleep comfort. Delays in treatment can lead to a poorer quality of life because the user does not achieve high-quality sleep. Therefore, there is a need to help users achieve comfort, including early in treatment, and to identify users who may be experiencing discomfort so that interventions can be implemented to improve their comfort during treatment. Summary of the Invention

[0009] In one aspect of the present disclosure, a method for classifying a user of a respiratory pressure therapy (RPT) device is disclosed, the method comprising: identifying that the user has begun a therapy session using the RPT device; receiving first input data associated with the user and the therapy session; training a machine learning model based on a plurality of pre-classified users and the first input data to determine associations between the user and a plurality of classifications; classifying the user into a classification among the plurality of classifications; and causing the user device and / or the RPT device to perform an action in response to classifying the user into the classification.

[0010] In another aspect of the present disclosure, a system for classifying users of a respiratory pressure therapy (RPT) device is disclosed, the system comprising: a memory storing instructions and a machine learning model, the machine learning model being trained based on a pre-classified user to learn associations between the pre-classified user and a plurality of classifications, such that the machine learning model is configured to perform the classification based on the learned associations; and a processor operably connected to the memory and configured to execute the instructions to perform operations including: identifying that the user has started a therapy session on the RPT device; receiving first input data associated with the user and the therapy session; classifying the user into a classification among the plurality of classifications by inputting the first input data into the machine learning model; and causing the user device and / or the RPT device to perform an action in response to classifying the user into the classification.

[0011] In another aspect of the present disclosure, a non-transitory computer-readable storage medium having instructions is disclosed. The instructions are executable by one or more processors to perform a method for training a machine learning model to classify users of a respiratory pressure therapy (RPT) device, the method comprising: receiving input data associated with a user and an associated therapy session. Each user has one or more classifications. The method further comprises: processing the input data to extract one or more features from the input data; training the machine learning model to classify one or more other users into the one or more classifications based on the one or more features extracted from the input data; and providing communication between the machine learning model and one or both of a user device and the RPT device, wherein the communication comprises at least causing the user device and / or the RPT device to perform an action.

[0012] The described methods, systems, devices, and apparatus can be implemented to improve the functionality of processors, such as dedicated computers, respiratory monitors, and / or respiratory therapy devices. Furthermore, the described methods, systems, devices, and apparatus can provide improvements in the art of automated management, monitoring, and / or treatment of respiratory conditions, including, for example, sleep-disordered breathing.

[0013] Certainly, each part of these aspects can form sub-aspects of the present technology.In addition, each sub-aspect and / or aspect in these sub-aspects and / or aspects can be combined in various ways, and also constitute additional aspects or sub-aspects of the present technology.

[0014] Other features of the present technology will become apparent by considering the information contained in the following detailed description, abstract, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a functional block diagram of a system according to some embodiments of the present disclosure.

[0016] Figure 2 According to some embodiments of the present disclosure Figure 1 A perspective view of at least a portion of a system, a user, and a bed partner.

[0017] Figure 3 is a graph of ramp characteristics and respiratory flow according to some embodiments of the present disclosure.

[0018] Figure 4A is a block diagram illustrating a respiratory pressure therapy system according to one embodiment of the present disclosure.

[0019] Figure 4B is a block diagram illustrating a respiratory pressure therapy system according to another embodiment of the present disclosure.

[0020] Figure 5A is an exemplary graphical user interface (GUI) depicting a first sleep survey window according to some embodiments of the present disclosure.

[0021] Figure 5B is an exemplary GUI depicting a second sleep survey window according to some embodiments of the present disclosure.

[0022] Figure 6 is an exemplary GUI depicting instructions guiding a user to turn a ramp on or off, according to some embodiments of the present disclosure.

[0023] Figure 7 is an exemplary GUI depicting instructions guiding a user to turn an EPR on or off, according to some embodiments of the present disclosure.

[0024] Figure 8 is an exemplary GUI depicting a sleep survey follow-up according to some embodiments of the present disclosure.

[0025] Figure 9 A typical breathing waveform model of a person during sleep is shown.

[0026] Figure 10 A flow chart depicts an exemplary process for training a machine learning model to learn associations between user data and user classifications, according to some embodiments.

[0027] Figure 11 Depicted is a flow diagram of an exemplary process for classifying users based on a trained machine learning model in accordance with some embodiments.

[0028] Figure 12 Depicted is a flow diagram of an alternative exemplary process for classifying users based on a trained machine learning model in accordance with some embodiments. DETAILED DESCRIPTION

[0029] Before describing the present technology in further detail, it should be understood that the present technology is not limited to the specific examples described herein, which may vary. It should also be understood that the terminology used in this disclosure is for the purpose of describing the specific examples discussed herein only and is not intended to be limiting.

[0030] The following description is provided about various examples that can share one or more common characteristics and / or features. It should be understood that one or more features of any one example can be combined with one or more features of another example or other examples. In addition, any single feature or combination of features in any of these examples can constitute another example.

[0031] refer to Figure 1, illustrates a system 100 according to some embodiments of the present disclosure. The system 100 includes a control system 110, a memory device 114, an electronic interface 119, a respiratory therapy system 120, one or more sensors 130, and one or more user devices 170. In some embodiments, the system 100 also includes a blood pressure device 182, an activity tracker 190, or both.

[0032] The control system 110 includes one or more processors 112 (hereinafter referred to as processors 112). The control system 110 is generally used to control (e.g., actuate) various components of the system 100 and / or analyze data obtained and / or generated by the components of the system 100. The processor 112 can be a general or special purpose processor or microprocessor. Although in Figure 1 1 , the control system 110 may include any suitable number of processors (e.g., one processor, two processors, five processors, ten processors, etc.), which may be in a single housing or located remotely from one another. The control system 110 may be coupled to and / or located within, for example, the housing of the user device 170 and / or one or more of the sensors 130 or the housing of the respiratory therapy system 120. The control system 110 may be centralized (within one such housing) or decentralized (within two or more such housings that are physically distinct). In such embodiments including two or more housings containing the control system 110, such housings may be located proximate to and / or remotely from one another.

[0033] The memory device 114 stores machine-readable instructions that are executable by the processor 112 of the control system 110. The memory device 114 may be any suitable computer-readable memory 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. Figure 1 1 , the system 100 may include any suitable number of memory devices 114 (e.g., one memory device, two memory devices, five memory devices, ten memory devices, etc.). The memory device 114 may be coupled to and / or located within the housing of the RPT device 122, the housing of the user device 170, the housing of one or more of the sensors 130, or any combination thereof. As with the control system 110, the memory device 114 may be centralized (within one such housing) or distributed (within two or more physically distinct such housings).

[0034] In some embodiments, the memory device 114 ( Figure 1) stores a user profile associated with a 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 earlier sleep sessions), or any combination thereof. Demographic information may include, for example, information indicating the user's age, gender, race, geographic location, relationship status, family history of insomnia or sleep apnea, employment status, educational status, socioeconomic status, or any combination thereof. Medical information may include, for example, information indicating one or more medical conditions associated with the user, medication use by the user, or both. Medical information data may also include Multiple Sleep Latency Test (MSLT) results or scores and / or Pittsburgh Sleep Quality Index (PSQI) scores or values. Self-reported user feedback may include information indicating a self-reported subjective sleep score (e.g., poor, average, excellent), the user's self-reported subjective stress level, the user's self-reported subjective fatigue level, the user's self-reported subjective health status, recent life events experienced by the user, or any combination thereof.

[0035] The electronic interface 119 is configured to receive data (e.g., physiological data and / or acoustic data) from one or more sensors 130 so that the data can be stored in the memory 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 connection or a wireless connection (e.g., using an RF communication protocol, a WiFi communication protocol, a Bluetooth communication protocol, via a cellular network, 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 one or more processors and / or one or more memory devices that are the same or similar to the processor 112 and memory device 114 described herein. In some embodiments, the electronic interface 119 is coupled to or integrated into the user device 170. In other embodiments, the electronic interface 119 is coupled to or integrated with the control system 110 and / or the memory device 114 (e.g., within a housing).

[0036] As described above, in some embodiments, system 100 includes a respiratory therapy system 120. Respiratory therapy system 120 can include a respiratory pressure therapy (RPT) device 122 (referred to herein as RPT device 122), a user interface 124, a conduit 126 (also referred to as a tube or air circuit), a display device 128, a humidifier tank 129, a receiver 180, or any combination thereof. In some embodiments, control system 110, memory device 114, display device 128, one or more of sensors 130, and humidifier tank 129 are part of RPT device 122. Respiratory pressure therapy refers to the application of a controlled target pressure that is nominally positive relative to atmosphere (e.g., as opposed to negative pressure therapy such as a tank ventilator or chest plate) to the entrance of a user's airway throughout the user's respiratory cycle. Respiratory therapy system 120 is typically used to treat individuals suffering from one or more sleep-related breathing disorders (e.g., obstructive sleep apnea, central sleep apnea, or mixed sleep apnea).

[0037] The RPT device 122 has a blower motor (not shown) that is typically used to generate pressurized air for delivery to the user (e.g., using one or more motors driving one or more compressors). In some embodiments, the RPT device 122 generates a continuous, constant air pressure that is delivered to the user. In other embodiments, the RPT device 122 generates two or more predetermined pressures (e.g., a first predetermined air pressure and a second predetermined air pressure). In yet other embodiments, the RPT device 122 is configured to generate a variety of different air pressures within a predetermined range. For example, the RPT device 122 can deliver at least about 4 cm H2O, at least about 10 cm H2O, at least about 20 cm H2O, from about 6 cm H2O to about 10 cm H2O, from about 7 cm H2O to about 12 cm H2O, etc. The RPT device 122 can also deliver pressurized air at a predetermined flow rate of, for example, about -20 liters / minute to about 150 liters / minute while maintaining a positive pressure (relative to ambient pressure).

[0038] The user interface 124 engages a portion of the user's face and delivers pressurized air from the RPT device 122 to the user's airway to help prevent the airway from narrowing and / or collapsing during sleep. Typically, the user interface 124 engages the user's face so that pressurized air is delivered to the user's airway via the user's mouth, the user's nose, or the user's mouth and nose. The RPT device 122, the user interface 124, and the conduit 126 together form an air passageway fluidically coupled to the user's airway. Pressurized air also increases the user's oxygen intake during sleep. Depending on the therapy to be 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 air at a pressure sufficiently different from ambient pressure (e.g., at a positive pressure of approximately 10 cm H2O relative to ambient pressure) to achieve therapy. For other forms of therapy, such as delivery of oxygen, the user interface may not include a seal sufficient to facilitate delivery of gas supply to the airway at a positive pressure of approximately 10 cm H2O.

[0039] like Figure 2 As shown, in some embodiments, the user interface 124 is a mask (e.g., a full-face mask) that covers the nose and mouth of the patient or user 210. Throughout this specification, the terms "patient" and "user" can be understood to be used interchangeably, both referring to the user of the respiratory pressure therapy device. Alternatively, the user interface 124 can be a nasal mask that provides air to the nose of the user 210 or a nasal pillow mask that delivers air directly to the nostrils of the user 210. The user interface 124 can include a plurality of straps that form a headband, for example, to help position and / or stabilize the interface on a part of the user 210 (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 210. The user interface 124 can also include one or more vents for allowing carbon dioxide and other gases exhaled by the user 210 to escape. In other embodiments, the user interface 124 includes a mouthpiece (e.g., a night guard mouthpiece molded to conform to the teeth of the user 210, a jaw repositioning device, etc.).

[0040] Conduit 126 (also referred to as an air circuit or tube) allows air to flow between two components of respiratory therapy system 120, such as RPT device 122 and user interface 124. In some embodiments, there may be separate branches of conduit 126 for inhalation and exhalation. In other embodiments, a single branch conduit is used for both inhalation and exhalation.

[0041] One or more of the RPT device 122, user interface 124, conduit 126, display device 128, and 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). These one or more sensors may be used, for example, to measure the air pressure, flow, and / or other parameters of the pressurized air supplied by the RPT device 122.

[0042] The display device 128 is generally used to display images, including still images, video images, or both, and / or information about the RPT device 122. For example, the display device 128 may provide information about the status of the RPT device 122 (e.g., whether the RPT device 122 is on / off, the pressure, temperature, and / or other parameters of the air delivered by the respiratory device 122, etc.) and / or other information (e.g., a sleep score and / or a therapy score (also referred to as myAir TM scores, such as described in US 2017 / 0311879 A1, which is hereby incorporated by reference in its entirety), the current date / time, personal information of the user 210, questions seeking feedback from the user 210 and / or suggestions for the user 210, etc. In some embodiments, the display device 128 acts as a human-machine interface (HMI) that includes a graphical user interface (GUI) configured to display an image as an input interface. The display device 128 can be an LED display, an OLED display, an LCD display, etc. The input interface can be, for example, a touch screen or touch-sensitive substrate, a mouse, a keyboard, or any sensor system configured to sense input made by a human user interacting with the RPT device 122.

[0043] The humidification tank 129 is coupled to the RPT device 122 or integrated therein and includes a water reservoir that can be used to humidify the pressurized air delivered from the RPT device 122. The RPT device 122 may include one or more vents (not shown) and a heater for heating the water in the humidification tank 129 so as to humidify the pressurized air provided to the user 210. Additionally, in some embodiments, the conduit 126 may also include a heating element (e.g., coupled to the conduit 126 and / or embedded therein) that heats the pressurized air delivered to the user 210. The humidification tank 129 may be fluidically coupled to the water vapor inlet of the air passage and deliver water vapor into the air passage via the water vapor inlet, or may be formed in line with the air passage as part of the air passage itself. In some embodiments, the humidification tank 129 may not include a water reservoir and is therefore waterless.

[0044] In some embodiments, system 100 can be used to deliver at least a portion of a substance from receiving portion 180 to the air passageway of a user based at least in part on physiological data, sleep-related parameters, other data or information, or any combination thereof. Generally, modifying the delivery of the portion of the substance into the air passageway can include (i) initiating delivery of the substance into the air passageway, (ii) ending delivery of the portion of the substance into the air passageway, (iii) modifying an amount of the substance delivered into the air passageway, (iv) modifying a temporal characteristic of delivery of the portion of the substance into the air passageway, (v) modifying a quantitative characteristic of delivery of the portion of the substance into the air passageway, (vi) modifying any parameter associated with delivery of the substance into the air passageway, or (vii) a combination of (i) through (vi).

[0045] Modifying the temporal characteristics of the delivery of the portion of the substance to the air passage can include changing the rate of delivery of the substance, starting and / or ending at different times, continuing different time periods, changing the temporal distribution or characteristics of delivery, changing the amount distribution independently of the temporal distribution, etc. Independent temporal and amount variations ensure that, in addition to changing the frequency of substance release, the amount of substance released at each time can be changed. In this way, a variety of different combinations of release frequency and release amount (e.g., higher frequency but lower release amount, higher frequency and higher amount, lower frequency and higher amount, lower frequency and lower amount, etc.) can be achieved. Other modifications to the delivery of the portion of the substance to the air passage can also be utilized.

[0046] The respiratory therapy system 120 can be used as, for example, a ventilator or a positive airway pressure (PAP) system, such as a continuous positive airway pressure (CPAP) system, an automatic positive airway pressure system (APAP), a bi-level or variable positive airway pressure system (BPAP or VPAP), or any combination thereof. The CPAP system delivers a predetermined amount of pressurized air to the user 210 (e.g., determined by a sleep physician). The APAP system automatically changes the pressurized air delivered to the user 210 based on, for example, respiratory data associated with the user. The 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] Still refer to Figure 1The one or more sensors 130 of system 100 include a pressure sensor 132, a flow sensor 134, a temperature sensor 136, a motion sensor 138, a microphone 140, a speaker 142, a radio frequency (RF) receiver 146, an RF transmitter 148, a camera 150, an infrared sensor 152, a photoplethysmography (PPG) sensor 154, an electrocardiogram (ECG) sensor 156, an electroencephalogram (EEG) sensor 158, a capacitive sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyography (EMG) sensor 166, an oxygen sensor 168, an analyte sensor 174, a humidity sensor 176, a LiDAR sensor 178, or any combination thereof. Typically, each of the one or more sensors 130 is configured to output sensor data, which is received and stored in memory device 114 or one or more other memory devices.

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

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

[0050] The one or more sensors 130 may be used to generate, for example, physiological data, acoustic data, or both. The control system 110 may use the physiological data generated by one or more of the sensors 130 to determine whether the user 210 ( Figure 2 ) and one or more sleep-related parameters. The sleep-wake signal may indicate one or more sleep states, including wakefulness, relaxed wakefulness, micro-arousal, or different sleep stages, such as, for example, rapid eye movement (REM) stage, first non-REM stage (commonly referred to as “N1”), second non-REM stage (commonly referred to as “N2”), third non-REM stage (commonly referred to as “N3”), or any combination thereof.

[0051] In some embodiments, the sleep-wake signal described herein can be time-stamped to indicate the time the user entered the bed, the time the user left the bed, the time the user attempted to fall asleep, etc. The sleep-wake signal can be measured by one or more sensors 130 during a sleep session at a predetermined sampling rate (such as, for example, one sample per second, one sample per 30 seconds, one sample per minute, etc.). In some embodiments, the sleep-wake signal can also indicate a respiratory signal, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, number of events per hour, event pattern, pressure setting of the RPT device 122, or any combination thereof during the sleep session. Events can include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, mask leak (e.g., from the user interface 124), restless legs, sleep disturbance, apnea, increased heart rate, difficulty breathing, asthma attack, epileptic seizure, convulsion, or any combination thereof. One or more sleep-related parameters that can be determined for a user based on the sleep-wake signal during a sleep session include, for example, total time in bed, total sleep time, sleep onset latency, wake parameter after sleep onset, sleep efficiency, segmentation index, or any combination thereof. As described in further detail herein, physiological data and / or sleep-related parameters can be analyzed to determine one or more sleep-related scores.

[0052] In general, a sleep session includes any point in time after the user 210 has been lying or sitting in the bed 230 (or another area or object where they intend to sleep) and / or has turned on the respiratory device 122 and / or put on the user interface 124. A sleep session may thus include the following time periods: (i) when the user 210 is using the CPAP system but before the user 210 attempts to fall asleep (e.g., when the user 210 is lying in the bed 230 reading a book); (ii) when the user 210 begins to try to fall asleep but is still awake; (iii) when the user 210 is in light sleep (also known as stages 1 and 2 of non-rapid eye movement (NREM) sleep); (iv) when the user 210 is in deep sleep (also known as slow wave sleep (SWS) or stage 3 of NREM sleep); (v) when the user 210 is in rapid eye movement (REM) sleep; (vi) when the user 210 is awake periodically between light sleep, deep sleep, or REM sleep; or (vii) when the user 210 wakes up and does not fall back asleep.

[0053] A sleep session is generally defined as ending once user 210 removes user interface 124, turns off respiratory device 122, and / or leaves bed 230. In some embodiments, a sleep session may include additional time periods, or may be limited to only some of the time periods disclosed above. For example, a sleep session may be defined as a time period that begins when respiratory device 122 begins supplying pressurized air to the airway of user 210, ends when respiratory device 122 stops supplying pressurized air to the airway of user 210, and includes some or all points in between when user 210 falls asleep or is awake.

[0054] 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 embodiments, the pressure sensor 132 is an air pressure sensor (e.g., a barometric pressure sensor) that generates sensor data indicative of the respiration (e.g., inhalation and / or exhalation) of the user of the respiratory therapy system 120 and / or ambient pressure. In such embodiments, the pressure sensor 132 can be coupled to or integrated into the RPT device 122. The pressure sensor 132 can be, for example, a capacitive sensor, an electromagnetic sensor, a piezoelectric sensor, a strain gauge sensor, an optical sensor, a potentiometric sensor, or any combination thereof.

[0055] The flow sensor 134 outputs flow data, which can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some embodiments, the flow sensor 134 is used to determine the air flow from the RPT device 122, the air flow through the conduit 126, the air flow through the user interface 124, or any combination thereof. In such embodiments, the flow sensor 134 can be coupled to or integrated into the RPT device 122, the user interface 124, or the conduit 126. The flow sensor 134 can be a mass flow sensor, such as, for example, a rotary flow meter (e.g., a Hall effect flow meter), a turbine flow meter, an orifice plate flow meter, an ultrasonic flow meter, a hot wire sensor, a vortex sensor, a membrane sensor, or any combination thereof. In some embodiments, the flow sensor 134 is configured to measure ventilator flow (e.g., intentional "leak"), unintentional leak (e.g., mouth leak and / or mask leak), patient flow (e.g., air entering and / or leaving the lungs), or any combination thereof. In some implementations, the flow data can be analyzed to determine the user's cardiogenic oscillations.In one example, the pressure sensor 132 can be used to determine the user's blood pressure.

[0056] The temperature sensor 136 outputs temperature data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some embodiments, the temperature sensor 136 generates a signal indicating to the user 210 ( Figure 2 ), the core body temperature of the user 210, the skin temperature of the user 210, the temperature of the air flowing out of the RPT device 122 and / or through the conduit 126, the temperature in the user interface 124, the ambient temperature, or any combination thereof. The temperature sensor 136 can be, for example, a thermocouple sensor, a thermistor sensor, a silicon bandgap temperature sensor or a semiconductor-based sensor, a resistance temperature detector, or any combination thereof.

[0057] The motion sensor 138 outputs motion data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. The motion sensor 138 can be used to detect movement of the user 210 during a sleep session, and / or detect movement of any of the components of the respiratory therapy system 120 (such as the RPT device 122, the user interface 124, or the catheter 126). The motion sensor 138 may include one or more inertial sensors, such as an accelerometer, a gyroscope, and a magnetometer. In some embodiments, the motion sensor 138 alternatively or additionally generates one or more signals representing the user's body motion, from which a signal representing the user's sleep state can be obtained; for example, via the user's respiratory motion. In some embodiments, the motion data from the motion sensor 138 can be used in combination with additional data from another sensor 130 to determine the user's sleep state.

[0058] The microphone 140 outputs sounds and / or audio data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. The audio data generated by the microphone 140 can be reproduced as one or more sounds (e.g., sounds from the user 210) during a sleep session. The audio data from the microphone 140 can also be used to identify (e.g., using the control system 110) one or more sleep-related parameters or events experienced by the user 210 during the sleep session, as described in further detail herein. The microphone 140 can be coupled to or integrated into the RPT device 122, the user interface 124, the catheter 126, or the user device 170. In some embodiments, the system 100 includes multiple microphones (e.g., two or more microphones and / or a microphone array with beamforming) such that the sound data generated by each of the multiple microphones can be used to distinguish the sound data generated by another of the multiple microphones.

[0059] Speaker 142 outputs information to the user of system 100 (e.g., Figure 2 The speaker 142 can be used, for example, as an alarm clock or to play an alert or message to the user 210 (e.g., in response to an event). In some embodiments, the speaker 142 can be used to communicate audio data generated by the microphone 140 to the user 210. The speaker 142 can be coupled to or integrated into the RPT device 122, the user interface 124, the catheter 126, or the user device 170.

[0060] The microphone 140 and the speaker 142 can be used as separate devices. In some embodiments, the microphone 140 and the speaker 142 can be combined into an acoustic sensor 141 (e.g., a sonar sensor). In such embodiments, the speaker 142 generates or emits sound waves at predetermined intervals, and the microphone 140 detects reflections of the emitted sound waves from the speaker 142. The sound waves generated or emitted by the speaker 142 have a frequency that is inaudible to the human ear (e.g., below 20 Hz or above approximately 18 kHz) so as not to disturb the sleep of the user 210 or the bed partner 220 ( Figure 2 Based at least in part on data from microphone 140 and / or speaker 142, control system 110 may determine that user 210 ( Figure 2 ) and / or one or more of the sleep-related parameters described herein, such as, for example, a respiratory signal, a respiratory rate, an inspiratory amplitude, an expiratory amplitude, an inspiratory-expiratory ratio, a number of events per hour, a pattern of events, a sleep state, a sleep stage, a pressure setting of the RPT device 122, or any combination thereof. In such context, a sonar sensor may be understood as involving active acoustic sensing, such as generating and / or transmitting ultrasound and / or low-frequency ultrasound sensing signals (e.g., in a frequency range of, for example, approximately 17 kHz-23 kHz, 18 kHz-22 kHz, or 17 kHz-18 kHz) through air.

[0061] In some embodiments, sensor 130 includes: (i) a first microphone that is the same as or similar to microphone 140 and is integrated into acoustic sensor 141; and (ii) a second microphone that is the same as or similar to microphone 140, but is separate and different from the first microphone integrated into acoustic sensor 141.

[0062] The RF transmitter 148 generates and / or transmits 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 transmitted from the RF transmitter 148, and this data can be analyzed by the control system 110 to determine whether the user 210 ( Figure 2 ) and / or one or more of the sleep-related parameters described herein. The RF receiver (RF receiver 146 and RF transmitter 148 or another RF pair) may also be used for wireless communication between the control system 110, the RPT device 122, one or more sensors 130, the user device 170, or any combination thereof. Although the RF receiver 146 and RF transmitter 148 are Figure 1146 and 148 are shown as separate and distinct elements, but in some embodiments, the RF receiver 146 and the RF transmitter 148 are combined as part of the RF sensor 147 (e.g., a RADAR sensor). In some such embodiments, the RF sensor 147 includes control circuitry. The specific format of RF communication can be Wi-Fi, Bluetooth, etc.

[0063] In some embodiments, RF sensor 147 is part of a mesh system. An example of a mesh system is a Wi-Fi mesh system, which can include mesh nodes, mesh routers, and mesh gateways, each of which can be mobile / removable or fixed. In such embodiments, the Wi-Fi mesh system includes a Wi-Fi router and / or Wi-Fi controller and one or more satellites (e.g., access points), each of which includes an RF sensor that is the same or similar to RF sensor 147. The Wi-Fi router and satellites 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), caused by a moving object or person partially blocking the signal. The motion data can indicate movement, breathing, heart rate, gait, falls, behavior, or any combination thereof.

[0064] The camera 150 outputs image data that can be reproduced as one or more images (e.g., still images, video images, thermal images, or any combination thereof) that can be stored in the memory device 114. The image data from the camera 150 can be used by the control system 110 to determine one or more of the sleep-related parameters described herein, such as, for example, one or more events (e.g., periodic limb movements or restless legs syndrome), a respiratory signal, a respiratory rate, an inspiratory amplitude, an expiratory amplitude, an inspiratory-expiratory ratio, a number of events per hour, an event pattern, a sleep state, a sleep stage, or any combination thereof. In addition, the image data from the camera 150 can be used, for example, to identify the location of the user to determine whether the user 210 ( Figure 2 ), determining the chest movement of the user 210, determining the airflow over the mouth and / or nose of the user 210, determining when the user 210 gets into the bed 230, and determining when the user 210 leaves the bed 230. In some embodiments, the camera 150 includes a wide-angle lens or a fish-eye lens.

[0065] Infrared (IR) sensor 152 outputs infrared image data that can be reproduced as one or more infrared images (e.g., still images, video images, or both) that can be stored in memory device 114. Infrared data from IR sensor 152 can be used to determine one or more sleep-related parameters during a sleep session, including the temperature of user 210 and / or the movement of user 210. IR sensor 152 can also be used in conjunction with camera 150 when measuring the presence, position, and / or movement of user 210. For example, IR sensor 152 can detect infrared light having wavelengths between approximately 700 nm and approximately 1 cm, while camera 150 can detect visible light having wavelengths between approximately 380 nm and approximately 740 nm.

[0066] The PPG sensor 154 outputs the same signal as the user 210 ( Figure 2 ), which can be used to determine one or more sleep-related parameters such as, for example, heart rate, heart rate variability, cardiac cycle, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiration-expiratory ratio, estimated blood pressure parameters, or a combination thereof. The PPG sensor 154 can be worn by the user 210, embedded in clothing and / or fabric worn by the user 210, embedded in and / or coupled to the user interface 124 and / or its associated headband (e.g., a strap, etc.), etc.

[0067] The ECG sensor 156 outputs physiological data associated with the electrical activity of the heart of the user 210. In some embodiments, the ECG sensor 156 includes one or more electrodes positioned on or around a portion of the user 210 during a sleep session. The physiological data from the ECG sensor 156 can be used, for example, to determine one or more of the sleep-related parameters described herein.

[0068] The EEG sensor 158 outputs physiological data associated with the electrical activity of the brain of the user 210. In some embodiments, the EEG sensor 158 includes one or more electrodes positioned 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 and / or sleep stage of the user 210 at any given time during a sleep session. In some embodiments, the EEG sensor 158 can be integrated into the user interface 124 and / or an associated headband (e.g., a strap, etc.).

[0069] The capacitance sensor 160, the force sensor 162, and the strain gauge sensor 164 output data that can be stored in the memory device 114 and used by the control system 110 to determine one or more of the sleep-related parameters described herein. The EMG sensor 166 outputs physiological data associated with the electrical activity generated by one or more muscles. The oxygen sensor 168 outputs oxygen data indicating the oxygen concentration of a gas (e.g., in the conduit 126 or at the user interface 124). The oxygen sensor 168 can be, for example, an ultrasonic oxygen sensor, an electrical oxygen sensor, a chemical oxygen sensor, an optical oxygen sensor, a pulse oximeter (e.g., a SpCh sensor), or any combination thereof. In some embodiments, the one or more sensors 130 further include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a blood pressure sensor, an oximetry sensor, or any combination thereof.

[0070] Analyte sensor 174 can be used to detect the presence of an analyte in the exhaled breath of user 210. Data output by analyte sensor 174 can be stored in memory device 114 and used by control system 110 to determine the identity and concentration of any analyte in the breath of user 210. In some embodiments, analyte sensor 174 is positioned near the mouth of user 210 to detect analytes in breath exhaled from the mouth of user 210. For example, when user interface 124 is a mask covering the nose and mouth of user 210, analyte sensor 174 can be positioned within the mask to monitor the mouth breathing of user 210. In other embodiments, such as when user interface 124 is a nasal mask or a nasal pillow mask, analyte sensor 174 can be positioned near the nose of user 210 to detect analytes in breath exhaled through the user's nose. In still other embodiments, when user interface 124 is a nasal mask or a nasal pillow mask, analyte sensor 174 can be positioned near the mouth of user 210. In this embodiment, the analyte sensor 174 can be used to detect whether any air is inadvertently leaking from the mouth of the user 210. In some embodiments, the analyte sensor 174 is a volatile organic compound (VOC) sensor that can be used to detect carbon-based chemicals or compounds. In some embodiments, the analyte sensor 174 can also be used to detect whether the user 210 is breathing through their nose or mouth. For example, if the data output by the analyte sensor 174 positioned near the mouth of the user 210 or positioned within the mask (in embodiments where the user interface 124 is a mask) detects the presence of an analyte, the control system 110 can use this data as an indication that the user 210 is breathing through their mouth.

[0071] The humidity sensor 176 outputs data that can be stored in the memory device 114 and used by the control system 110. The humidity sensor 176 can be used to detect the humidity in various areas around the user (e.g., inside the conduit 126 or 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 RPT device 122, etc.). Thus, in some embodiments, the humidity sensor 176 can be coupled to or integrated into the user interface 124 or conduit 126 to monitor the humidity of the pressurized air from the RPT device 122. In other embodiments, the humidity sensor 176 is placed near any area where humidity levels need to be monitored. The humidity sensor 176 can also be used to monitor the humidity of the ambient environment around the user 210 (e.g., the air inside the bedroom of the user 210).

[0072] One or more light detection and ranging (LiDAR) sensors 178 can be used for depth sensing. This type of optical sensor (e.g., a laser sensor) can be used to detect objects and build a three-dimensional (3D) map of the surrounding environment (e.g., a living space). LiDAR can typically use a pulsed laser to perform time-of-flight measurements. LiDAR is also known as 3D laser scanning. In an example using such a sensor, a fixed or mobile device (such as a smartphone) with a LiDAR sensor 178 can measure and map an area extending 5 meters or more away from the sensor. For example, LiDAR data can be fused with point cloud data estimated by an electromagnetic RADAR sensor. The LiDAR sensor 178 can also use artificial intelligence (AI) to automatically enable the RADAR system to enter a geofence by detecting and classifying features in the space that may cause problems for the RADAR system, such as glass windows (which may be highly reflective to RADAR). For example, LiDAR can also be used to provide an estimate of a person's height, as well as changes in height when a person sits down or falls. LiDAR can be used to form a 3D grid representation of the environment. In a further application, LiDAR can reflect radio waves off solid surfaces (e.g., semi-transparent materials) through which they pass, allowing for the classification of different types of obstacles.

[0073] In some embodiments, the one or more sensors 130 further include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a sphygmomanometer sensor, an oximeter sensor, a sonar sensor, a RADAR sensor, a blood glucose sensor, a color sensor, a pH sensor, an air quality sensor, a tilt sensor, a rain sensor, a soil moisture sensor, a water flow sensor, an alcohol sensor, or any combination thereof.

[0074] Although Figure 112, the one or more sensors 130 are shown separately in FIG, but any combination of the one or more sensors 130 can be integrated into and / or coupled to any one or more of the components of the system 100, including the RPT device 122, the user interface 124, the conduit 126, the humidifier tank 129, the control system 110, the user device 170, the activity tracker 190, or any combination thereof. For example, the microphone 140 and the speaker 142 can be integrated into and / or coupled to the user device 170, and the pressure sensor 130 and / or the flow sensor 132 are integrated into and / or coupled to the RPT device 122. In some embodiments, at least one of the one or more sensors 130 is not coupled to the RPT device 122, the control system 110, or the user device 170 and is positioned generally proximate 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.).

[0075] Data from one or more sensors 130 can be analyzed to determine one or more sleep-related parameters, which can include a respiratory signal, respiratory rate, respiratory pattern, inspiratory amplitude, expiratory amplitude, inspiratory-expiratory ratio, occurrence of one or more events, number of events per hour, event pattern, sleep state, apnea-hypopnea index (AHI), or any combination thereof. The one or more events can include snoring, apnea, central apnea, obstructive apnea, mixed apnea, hypopnea, mask leak, cough, restless legs, sleep disorder, choking, increased heart rate, dyspnea, asthma attack, epileptic seizure, convulsion, increased blood pressure, or any combination thereof. Although some parameters of the sleep-related parameters can be considered non-physiological parameters, many parameters of these sleep-related parameters are physiological parameters. Other types of physiological parameters and non-physiological parameters can also be determined based on data from one or more sensors 130 or based on other types of data.

[0076] User equipment 170 ( Figure 1) includes a display device 172. User device 170 can be, for example, a mobile device such as a smartphone, tablet, game console, smartwatch, laptop, etc. Alternatively, user device 170 can be an external sensing system, a television (e.g., a smart TV), or another smart home device (e.g., a smart speaker such as Google Home, Amazon Echo, Alexa, etc.). In some embodiments, the user device is a wearable device (e.g., a smartwatch). Display device 172 is typically used to display images including still images, video images, or both. In some embodiments, display device 172 acts as a human-machine interface (HMI) that includes a graphical user interface (GUI) configured to display images and an input interface. Display device 172 can be an LED display, an OLED display, an LCD display, etc. The input interface can be, for example, a touch screen or touch-sensitive substrate, a mouse, a keyboard, or any sensor system configured to sense input made by a human user interacting with user device 170. In some embodiments, system 100 can use and / or include one or more user devices.

[0077] Blood pressure device 182 is generally used to facilitate generation of cardiovascular data to determine one or more blood pressure measurements associated with user 210. Blood pressure device 182 may include at least one of one or more sensors 130 to measure, for example, a systolic blood pressure component and / or a diastolic blood pressure component.

[0078] In some embodiments, the blood pressure device 182 is a sphygmomanometer that includes an inflatable cuff and a pressure sensor (e.g., the pressure sensor 132 described herein) that can be worn by a user. Figure 2 As shown in the example of , the blood pressure device 182 can be worn on the upper arm of the user 210. In such embodiments where the blood pressure device 182 is a sphygmomanometer, the blood pressure device 182 also includes a pump (e.g., a manually operated inflation bulb) for inflating the cuff. In some embodiments, the blood pressure device 182 is coupled to the respiratory device 122 of the respiratory therapy system 120, which in turn delivers pressurized air to inflate the cuff. More generally, the blood pressure device 182 can be communicatively coupled to and / or physically integrated therein (e.g., within a housing) with the control system 110, the memory 114, the respiratory therapy system 120, the user device 170, and / or the activity tracker 190.

[0079] The activity tracker 190 is generally used to help generate physiological data to determine activity measurements associated with the user 210. The activity tracker 190 can include one or more of the sensors 130 described herein, such as, for example, a motion sensor 138 (e.g., one or more accelerometers and / or gyroscopes), a PPG sensor 154, and / or an ECG sensor 156. The physiological data from the activity tracker 190 can be used to determine, for example, the number of steps, distance traveled, number of steps climbed, duration of physical activity, type of physical activity, intensity of physical activity, time spent standing, respiratory rate, average respiratory rate, resting respiratory rate, maximum respiratory heart rate, respiratory rate variability, heart rate, average heart rate, resting heart rate, maximum heart rate, heart rate variability, calories burned, blood oxygen saturation, electrodermal activity (also known as skin conductance or galvanic skin response), or any combination thereof. In some embodiments, the activity tracker 190 is coupled (e.g., electronically or physically) to the user device 170.

[0080] In some embodiments, the activity tracker 190 is a wearable device such as a smartwatch, wristband, ring, or patch that can be worn by the user 210. For example, Figure 2 , activity tracker 190 is worn on the wrist of user 210. Activity tracker 190 can also be coupled to or integrated into clothing or an article of clothing worn by user 210. Still alternatively, activity tracker 190 can also be coupled to or integrated into user device 170 (e.g., within the same housing). More generally, activity tracker 190 can be communicatively coupled to or physically integrated into (e.g., within a housing) control system 110, memory device 114, respiratory therapy system 120, user device 170, and / or blood pressure device 182.

[0081] Although the control system 110 and the memory device 114 are Figure 1 100, but in some embodiments, the control system 110 and / or the memory device 114 are integrated into the user device 170 and / or the RPT device 122. Alternatively, in some embodiments, the control system 110 or a portion thereof (e.g., the processor 112) can be located in the cloud (e.g., integrated in a server, integrated in an Internet of Things (IoT) device, connected to the cloud, subject to edge cloud processing, etc.), located in one or more servers (e.g., a remote server, a local server, etc., or any combination thereof).

[0082] Although system 100 is shown as including all of the above components, more or fewer components may be included in systems according to embodiments of the present invention. For example, a first alternative system includes control system 110, memory device 114, and at least one of one or more sensors 130, and does not include respiratory therapy system 120. As another example, a second alternative system includes control system 110, memory 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, memory device 114, respiratory therapy system 120, at least one of one or more sensors 130, and optional user device 170. Thus, various systems may be formed using any one or more portions of the components shown and described herein and / or in combination with one or more other components.

[0083] Overall reference Figure 2 , illustrating a system 100 ( Figure 1 ). A user 210 and a bed partner 220 of the respiratory therapy system 120 are positioned in a bed 230 and lying on a mattress 232. A user interface 124 (also referred to herein as a mask, e.g., a full face mask) can be worn by the user 210 during a sleep session. The user interface 124 is fluidly coupled and / or connected to the respiratory device 122 via a conduit 126. The RPT device 122, in turn, delivers pressurized air to the user 210 via the conduit 126 and the user interface 124 to increase the air pressure in the throat of the user 210 to help prevent the airway from closing and / or narrowing during sleep. The RPT device 122 can be positioned such as Figure 2 It is shown on a nightstand 240 directly adjacent to the bed 230 , or more generally, positioned on any surface or structure generally adjacent to the bed 230 and / or the user 210 .

[0084] In some embodiments, the control system 110, the memory 114, any of the one or more sensors 130, or a combination thereof can be located on and / or in any surface and / or structure that is generally proximate to the bed 230 and / or the user 210. For example, in some embodiments, at least one of the one or more sensors 130 can be located at a first location 255A on and / or in one or more components that are proximate to the respiratory therapy system 120 and the bed 230 and / or the user 210. The one or more sensors 130 can be coupled to the respiratory therapy system 120, the user interface 124, the conduit 126, the display device 128, the humidifier tank 129, or a combination thereof.

[0085] Alternatively or additionally, at least one of the one or more sensors 130 may be located at a second location 255B on and / or in the bed 230 (e.g., the one or more sensors 130 are coupled to and / or integrated into the bed 230). Further, alternatively or additionally, at least one of the one or more sensors 130 may be located at a third location 255C on and / or in the mattress 232 that is proximate to the bed 230 and / or the user 210 (e.g., the one or more sensors 130 are coupled to and / or integrated into the mattress 232). Alternatively or additionally, at least one of the one or more sensors 130 may be located at a fourth location 255D on and / or in the pillow that is generally proximate to the bed 230 and / or the user 210.

[0086] Alternatively or additionally, at least one of the one or more sensors 130 may be located at a fifth location 255E on and / or in the nightstand 240 that is generally adjacent to the bed 230 and / or the user 210. Alternatively or additionally, at least one of the one or more sensors 130 may be located at a sixth location 255F such that at least one of the one or more sensors 130 is coupled to and / or positioned on the user 215 (e.g., the one or more sensors 130 are embedded in or coupled to fabric, clothing 212, and / or a smart device worn by the user 210). More generally, at least one of the one or more sensors 130 may be located in any suitable location relative to the user 210 such that the one or more sensors 130 can generate sensor data associated with the user 210.

[0087] Typically, a user prescribed respiratory therapy system 120 will tend to experience higher quality sleep and less fatigue throughout the day following use of respiratory therapy system 120 during sleep compared to not using respiratory therapy system 120 (particularly when the user suffers from sleep apnea or other sleep-related disorders). For example, user 210 may suffer from obstructive sleep apnea and rely on user interface 124 (e.g., a full-face mask) to deliver pressurized air from respiratory device 122 via conduit 126. Respiratory device 122 may be a continuous positive airway pressure (CPAP) machine, which is used to increase air pressure in the throat of user 210 to prevent the airway from closing and / or narrowing during sleep. For people with sleep apnea, their airway may narrow or collapse during sleep, thereby reducing oxygen intake and forcing them to wake up and / or otherwise disrupting their sleep. The CPAP machine prevents the airway from narrowing or collapsing, minimizing the instances where they would be woken or disturbed by reduced oxygen intake.

[0088] However, the positive pressure range prescribed for CPAP therapy may make the user feel uncomfortable when awake. Specifically, in one aspect, patients can define their comfort level in two ways of input, including active input and passive input to the system. Active indication of discomfort occurs when the patient directly responds to a survey and / or graphical user interface that they feel respiratory discomfort. Passive input as a discomfort indicator can include a single measurement and / or a set of measurements made by the system (e.g., flow data; pressure data; waveform data; tidal volume data; minute ventilation data; and leak data), where a machine learning algorithm can identify measurement values ​​that indicate that the patient may be feeling uncomfortable, causing the system to make adjustments to alleviate the discomfort. In yet another aspect, the system can receive both active and passive inputs, where the system will make adjustments based on the machine learning algorithm analysis of the active and passive inputs.

[0089] To prevent awake users from experiencing these uncomfortable pressures, one solution is to provide a ramping feature that gradually increases pressure from a starting pressure while the user is awake, then resorts to a higher, positive therapeutic pressure when the onset of sleep is detected. In yet another aspect, if the user is awake, they can provide direct, active input to the system indicating that they are experiencing discomfort, causing the ramping feature to begin adjusting. In another aspect, the system can also respond to passive input from associated sensors to implement the ramping feature even when the user is not awake or has not provided a response to an input probe.

[0090] Figure 3 3 is a graph illustrating an embodiment of a ramp feature according to some aspects of the present disclosure. The graphs show respiratory flow 301 over time and pressure over time, including a starting pressure 302, a prescribed pressure 303, and a pressure ramp 304 between the starting pressure 302 and the prescribed pressure 303. The ramp 304 can be initiated at or about the time sleep onset is detected, which can be detected by a change in respiratory flow toward smoother breathing. The ramp feature provides a gradual increase from the most comfortable starting pressure for the awake user 210 to the prescribed pressure for their therapy. If the prescribed pressure includes a minimum pressure and a maximum pressure, the ramp 304 ends at the prescribed minimum pressure 303.

[0091] The prescribed minimum pressure 303 may be, for example, 10 cm HO and may depend on the user's therapy needs. Despite the intent of this feature, the user 210 may find that the prescribed pressure 303 and / or ramp 304 actually decreases their sleep comfort rather than improving it. For example, the user 210 may find that the ramp 304 increases the pressure too quickly, making it difficult to fall asleep and / or waking the user 210. The user 210 may adjust the ramp time to provide a gentler transition from the starting pressure 302 to the prescribed pressure 303.

[0092] Additionally, some users 210 may find the ramp feature uncomfortable because they experience too much or too little air during awakening to provide the starting pressure 302. If there is a perception of too little air, one way to improve this perception is to increase the starting pressure 302 of the ramp so that once the patient puts on the user interface 124 upon awakening, a higher pressure is experienced. Alternatively, the ramp feature can be turned off completely so that once the RPT device 122 is turned on, the patient experiences a prescribed minimum pressure, which is typically higher than the prescribed starting pressure. Typically, clinicians respond to patient complaints of too little air by increasing the prescribed minimum pressure without changing the starting pressure. However, in some instances, increasing the prescribed minimum pressure can result in a mismatch between the intended pressure increase and the actual effect.

[0093] For example, a patient may receive a ramp therapy with a prescribed minimum pressure of 10 cm H2O, a prescribed maximum pressure of 15 cm H2O, and a starting pressure of 4 cm H2O. In this example, the user will experience a gradual increase from 4 cm H2O to 10 cm H2O during the ramp. If the patient indicates that they are experiencing shortness of breath, the resulting discomfort stems from the fact that the starting pressure of 4 cm H2O is too low during the start of the ramp. When the clinician adjusts the minimum pressure, this does not address the situation that caused the patient's shortness of breath, namely that the starting pressure was too low. This mismatch may be caused by the clinician confusing the difference between the starting pressure and the minimum pressure, but in any case, this may cause the patient to continue to experience shortness of breath.

[0094] To help users feel comfortable early in treatment, a survey may be offered shortly thereafter, preferably approximately three days after treatment (although other time periods may be used), to help identify any issues or difficulties the user may be experiencing and identify solutions to those issues. Data collected from users who participate in the survey may then be used to identify other current or future users who may be experiencing similar difficulties.

[0095] The survey may take the form of a prompt that is sent to the user 210 via the patient program 430 on the user device 170, according to one or more of the following embodiments: in an email (when the patient program 430 is an email client); in an SMS message; in a "Notification" in the patient program 430 (when the patient program 430 is a "Patient App"); or in a page on a website (when the patient program 430 is a web browser). In other embodiments, the prompt may be sent to the display 128 of the RPT device 122 in the respiratory therapy system 120.

[0096] Figure 4A Included is a block diagram illustrating one embodiment 400 of an RPT system in accordance with the present technology that combines a data server 410, a wide area network 420, and a patient program 430 to incorporate user 210 feedback into the RPT device 122.

[0097] Figure 4A The RPT system embodiment 400 in includes an RPT device 122 configured to provide respiratory pressure therapy to a patient 210, a data server 410, and a user device 170 associated with the patient 210. The user device 170 is co-located with the patient 210 and the RPT device 122. Figure 4A In the illustrated embodiment 400, the RPT device 122, the user device 170, and the data server 410 are connected to a wide area network 420, such as the Internet or the internet. The connection to the wide area network 420 can be wired or wireless. The user device 170 can be a personal computer, mobile phone, tablet, or other device. The user device 170 is configured to mediate between the patient 210 and the data server 410 via the wide area network 420. In one embodiment, the mediation is performed by a software application 430 running on the user device 170. The patient program 430 can be a dedicated application or "mobile app" that interacts with a supplemental process 440 hosted by the data server 410. The process 440 can be a machine learning model training and / or implementation, as described in more detail below. In another embodiment, the patient program 430 is a web browser that interacts with a website hosted by the data server 410 via a secure portal. In yet another embodiment, the patient program 430 is an email client.

[0098] Figure 4BA block diagram illustrating an alternative embodiment 400B of an RPT system in accordance with the present technology is included. In alternative embodiment 400B, the RPT device 122 communicates with the user device 170 via a local (wired or wireless) communication protocol, such as a local network protocol (e.g., Bluetooth). In alternative embodiment 400B, the local network may be identified using a local external communication network, and the user device 170 may be identified using a local external device. In alternative embodiment 400B, the user device 170 is configured via a patient program 430 to mediate between the patient 210 and the data server 410 via a wide area network 420, and also to mediate between the RPT device 122 and the data server 410 via the wide area network 420.

[0099] Hereinafter, statements regarding the RPT system 400 may be understood to apply equally to the alternative embodiment 400B unless expressly stated otherwise.

[0100] The RPT system 400 may include other RPT devices (not shown) associated with respective patients, who also have respective associated computing devices. All patients in the RPT system 400 are managed by a data server 410 .

[0101] RPT device 122 is configured to store therapy data from each RPT session delivered to patient 210 in memory 114. The therapy data for an RPT session includes settings of RPT device 122 and therapy variable data representing one or more variables of respiratory pressure therapy throughout the RPT session.

[0102] RPT device setting data may include:

[0103] Types of masks

[0104] Basic treatment pressure (P0)

[0105] Maximum and minimum treatment pressure limits (Pmax and Pmin)

[0106] Amplitude (A)

[0107] Humidity of the delivered air flow

[0108] Temperature of the delivered air flow

[0109] Treatment variables may include:

[0110] Respiratory flow (Qr)

[0111] Mask pressure (Pm)

[0112] Leakage flow (Ql)

[0113] Tidal volume (Vt)

[0114] Ventilation measurement value (Vent)

[0115] Respiratory rate

[0116] The RPT device 122 is configured to send therapy data to the data server 410. The data server 410 may receive therapy data from the RPT device 122 according to a "pull" model, whereby the RPT device 122 sends therapy data in response to a query from the data server 410. Alternatively, the data server 410 may receive therapy data according to a "push" model, whereby the RPT device 122 sends therapy data to the data server 410 as soon as possible after the RPT session.

[0117] Therapy data received from the RPT device 122 is stored and indexed by the data server 410 so that it is uniquely associated with the RPT device 122 and can therefore be distinguished from therapy data from any other RPT device participating in the RPT system 400. The data server 410 also includes information about the clinician of the user 210 so that data can be sent directly to the clinician. This can include a link to the clinician's user device, or a link to the clinician's email or program.

[0118] The data server 410 is configured to calculate usage data for each RPT session based on therapy data received from the RPT device 122. The usage data variables for the session include summary statistics derived from therapy variable data that form part of the therapy data using conventional scoring methods. The usage data may include one or more of the following usage variables:

[0119] Usage time, that is, the total duration of the RPT session

[0120] Apnea-Hypopnea Index (AHI) of the session

[0121] Average leakage traffic of a session

[0122] Average mask pressure during the session

[0123] The number of “subsessions” within an RPT session, i.e., the number of RPT therapy intervals between “mask on” and “mask off” events

[0124] Number of "mask on" and "mask off" incidents

[0125] Other statistical summaries of treatment variables, such as 95th percentile pressure, median pressure, and histograms of pressure values

[0126] Usage variables may include multi-session statistics such as the mean, median, and variance of the AHI since the start of RPT therapy.

[0127] In an alternative embodiment, the RPT device 122 calculates the usage variables at the end of each session based on therapy data stored by the RPT device 122. The RPT device 122 then sends the usage variables to the data server 410 based on the "push" or "pull" model described above.

[0128] In further embodiments, the memory 114 in which the RPT device 122 stores the therapy / usage data for each RPT session is in a removable form, such as an SD memory card. The removable memory 114 can be removed from the RPT device 122 and inserted into a card reader that communicates with the data server 410. The therapy / usage data is then copied from the removable memory 114 to the memory of the data server 410.

[0129] In yet another embodiment of an alternative embodiment 400B suitable for the RPT system, the RPT device 122 is configured to transmit therapy / usage data to the user device 170 via a wireless communication protocol, such as Bluetooth as described above. The user device 170 then transmits the therapy / usage data to the data server 410. The data server 410 may receive therapy / usage data from the user device 170 according to a "pull" model, whereby the user device 170 transmits the therapy / usage data in response to a query from the data server 410. Alternatively, the data server 410 may receive therapy / usage data according to a "push" model, whereby the user device 170 transmits the therapy / usage data to the data server 410 as soon as it is available following the RPT session.

[0130] In some implementations, data server 410 may perform some post-processing of the usage data (such as using one or more processors in communication with or included in data server 410 ).

[0131] The data server 410 may also be configured to receive data from the user device 170. This may include data entered into the patient program 430 by the patient 210, or therapy / usage data as in the alternative embodiment 400B described above.

[0132] The data server 410 is also configured to send electronic messages to the user device 170. These messages may be in the form of emails, SMS messages, automated voice messages, or notifications within the patient program 430.

[0133] The RPT device 122 may be configured such that its therapy mode or the setting of a particular therapy mode may be changed upon receiving a corresponding command via its wide area network or local area network connection. In such embodiments, the data server 410 may also be configured to transmit such commands directly to the RPT device 122 (in embodiment 400) or indirectly to the RPT device 122, relayed via the user device 170 (in embodiment 400B).

[0134] Figure 5A A graphic depiction 500A depicts a survey prompt of the patient program 430 sent to the patient's user device 170. In an exemplary embodiment, the initial prompt is sent to a mobile application downloaded by the user 210 on their user device 170, preferably between two and three days after the user 210 has begun their therapy (although other time periods may be used), and asks the user 210 to answer the initial question, "How is your therapy?" The user is provided with three response options: "Very good," "OK," and "Challenging." If the user 210 selects "OK" (button 501) or "Challenging" (button 502), the survey prompt continues to Figure 5B , and provides the user 210 with a list of possible reasons why they are not completely satisfied with the therapy under the heading "What bothers you most?" These reasons may include, but are not limited to: "Feeling it difficult to exhale" (button 503) and "Feeling there is not enough air to inhale" (button 504).

[0135] If the user 210 indicates that they have difficulty exhaling by selecting button 503, the pressure applied via the mask 124 may be too high to ensure comfort before the user 210 falls asleep. This may be alleviated by instructing the user 210 to enable Expiratory Pressure Relief (EPR) or contacting a clinician to help them enable EPR. If the user selects button 503, a possible result will be the display of a message explaining that enabling EPR may be helpful, such as Figure 5B A message such as the following appears: "When EPR is on, you may find it easier to exhale. This setting can help you adjust to therapy. Discuss adjusting this setting with your care provider."

[0136] Alternatively or additionally, this can be alleviated by turning on the ramp 304 if it is off, since the starting pressure 302 will be lower than the pressure applied during therapy. The system 100 can be configured to perform the steps of providing immediate relief in response to the user 210 selecting the button 503. For example, the system 100 can be configured to automatically turn on the ramp feature in the RPT device 122 in response to a signal from the user 210 of the user device 170 that the button 503 in the patient program 430 of the user device 170 has been selected. Alternatively, selecting "Feeling Hard to Exhale" can direct the user to view instructions on how to turn on the ramp 304 on their RPT device 122.

[0137] Figure 6 is an exemplary graphical representation 600 showing instructions on how to adjust the ramp on the RPT device, along with guidance on what changes to make based on an identified breathing challenge indicated by the user 210. These instructions may be displayed on the user device 170 via the patient program 430, or may be emailed to the user device 170. In this exemplary representation, the instructions direct the user 210 to select "My Options" from a home screen 601 of the display of the RPT device 122, which directs them to an exemplary screen 602 containing a set of customizable options including "Ramp Time." The user is directed to tap "Ramp Time" on the "My Options" menu, which directs them to a ramp time screen 603 which allows the user to select "Off," "Auto," or a specific amount of ramp time in minutes. The "Auto" feature relies on sleep detection and may trigger the ramp to minimum pressure when the user 210 has fallen asleep, such as Figure 3 If the user 210 experiences difficulty exhaling, the user will be instructed to ensure the ramp is on by selecting "auto" or a specified ramp time and / or to turn the ramp on so that the starting pressure 302 is applied during the awake time instead of the minimum pressure 303.

[0138] As discussed above, if the user 210 indicates that they are having trouble exhaling, they may also or alternatively be directed to turn on EPR (Expiratory Pressure Release), or the system may do so automatically. EPR is a feature on some RPT devices that slightly reduces the pressure delivered to the user 210 when exhaling. This makes it easier to exhale against the pressure of the air. Selecting "Feeling Hard to Exhale" may direct the user 210 to view example instructions on how to turn on and / or turn up EPR on their RPT device, or direct the user 210 to contact their clinician to request an increase in EPR. The system 100 may also be configured to automatically increase the EPR in the RPT device 122 in response to a signal from the user 210 of the user device 170 that the button 503 in the patient program 430 of the user device 170 has been selected.

[0139] Figure 7 2 is an exemplary graphical representation 700 showing instructions for turning the EPR on if it is off, as well as guidance on what changes to make based on the identified respiratory challenge indicated by the user 210. These instructions require advancing from the home screen 701 and entering the "clinical home screen" 702 to access more advanced settings typically reserved for clinicians. In the exemplary embodiment, the clinical home screen 702 is accessed by tapping and holding two fingers for 3 seconds, but it can also be accessed by other means such as a two-finger swipe. On the clinical home screen 702, tapping "Settings" will provide a more advanced settings menu 703, which includes options to turn the EPR on or off, among other things. The user 210 can turn the EPR on and off and select the EPR level. If the user 210 swipes down, screen 704 shows more options in the settings menu 703, including the EPR level. In the exemplary embodiment, as shown in screen 705, the EPR level is described as level 1, 2, or 3. Alternatively, EPR levels may be described as "low," "medium," and "high," or in specific pressure units such as 1 cmH20.

[0140] User 210 can press Figure 5B 504 to indicate that they feel like taking in more air. This may be due to a difference between the starting pressure 302 prescribed for the user 210 and a comfortable pressure during the automatic ramp feature, where the starting pressure 302 experienced by the user 210 during the awakening period before ramping up to the prescribed pressure was too low for comfort. If the user 210 selects "I feel like I need more air" at button 504, the user 210 may be directed to instructions on how to increase the pressure during that time, or the system 100 may be configured to automatically adjust the setting in response to the user selecting button 504.

[0141] One way to increase the stress experienced during the wakefulness period before falling asleep is to turn off the ramp feature. As discussed above, Figure 6 6 is an exemplary graphical representation showing instructions for adjusting the ramp on an RPT device. These instructions can be displayed on the user device 170 via the patient program 430 or can be emailed to the user device 170 in response to the user selecting "I'm having trouble breathing" (button 504) on the exemplary screen 500B. In this exemplary representation, the instructions direct the user 210 to select "My Options" from the home screen 601 of the RPT device 122's display, which directs them to the exemplary screen 602 containing a set of customizable options (including "Ramp Time"). The user is directed to tap "Ramp Time" on the "My Options" menu, which directs them to the ramp time screen 603, which allows the user to select "Off," "Auto," or a specific amount of ramp time (in minutes). If the user 210 feels they need more air, they are instructed to turn off the ramp by selecting "Off." This has the effect of applying a prescribed minimum pressure 303 during the wake period before sleep begins, rather than the typically lower starting pressure 302. The system 100 may also be configured to automatically turn off the ramping via communication between the user device 170, the RPT device 122, and / or the network 420 in response to the user 210 selecting the button 504. A signal indicating that the user 210 has selected the button 504 on the user device 170, optionally via the patient program 430, may be sent to the RPT device 122 to turn off the ramping without further input from the user 210.

[0142] As an alternative to or in conjunction with the above instructions for turning off the ramp, the user may be provided with instructions for selecting a preferred starting pressure for the ramp feature. Figure 7The feature is accessed through a more advanced settings menu described in the exemplary embodiment of FIG. These instructions require entering the "Clinical Home Screen" 702 from the home screen 701 to access more advanced settings typically reserved for clinicians. In the exemplary embodiment, the clinical home screen 702 is accessed by tapping and holding two fingers for 3 seconds, but it can also be accessed by other means such as a two-finger swipe. On the clinical home screen 702, tapping "Settings" will provide a more advanced settings menu 703, which includes options for adjusting the starting pressure 302, among other things. The starting pressure can be adjusted using terms such as "low," "medium," and "high," or using numeric values ​​from lowest to highest (such as "1" for low, "5" for high, and values ​​2 to 4 for intermediate pressures), or using precise pressure values ​​in known units (such as H2O). The user 210 can be guided through using these tools to increase the starting pressure on the ramp feature. Alternatively, an external monitor such as a clinician or server can be alerted that the patient is experiencing air starvation. Air starvation can include discomfort felt by the patient due to not receiving enough air. In response, the starting pressure associated with the system may need to be increased, thereby requiring the implementation of a setting change. Additionally, the clinician can specify predetermined thresholds for measurement settings so that the system can adjust and implement automatic setting changes (e.g., turning off ramping, increasing minimum pressure), and these changes can be pushed to the patient if air starvation is detected.

[0143] In yet another aspect, the assessment of the patient's respiratory state can be categorized into at least three categories, including: 1) the user experiences steady-state respiratory discomfort; 2) the user is not obtaining enough air during breathing; and 3) the user is not expelling enough air during breathing. The threshold for defining sufficient air will be relative to the patient based on certain biomarkers, including at least: age, height, weight and / or BMI, gender, physical fitness level, and overall health. These biomarkers, along with measurements (such as flow data; pressure data; waveform data; tidal volume data; minute ventilation data; and leak data), can be provided to a model. The results of the model can determine whether sufficient air is being obtained or expelled, allowing the system to adjust the operation of the system to alleviate the discomfort felt by the patient during inhalation and exhalation due to insufficient air.

[0144] In addition to the discomfort experienced during inhalation and exhalation, patients may also feel discomfort that is not directly related to inhalation and exhalation, but rather to steady-state discomfort. During steady-state discomfort, patients may feel a persistent sense of air hunger, resulting in an inability to get enough air. The steady-state discomfort felt by patients can be similarly assessed as discomfort related to inhalation and exhalation. Patients can identify the difference in experience by providing positive direct responses to the survey. For example, the survey questions can ask under what circumstances the patient feels that they are not getting enough air (e.g., during inhalation, during exhalation, and / or continuously feeling that there is not enough air). Similar to the treatment methods for discomfort caused by insufficient air during inhalation and exhalation, the input received from the survey associated with steady-state discomfort can be paired with passive sensor measurements and provided to the system response therapy model.

[0145] Processed by user 210 Figure 5A and Figure 5B Following the survey questions described in , subsequent self-help prompts may be provided to determine whether the information provided to the user 210 is helpful in overcoming the problem they identified. Figure 8 As shown, the prompt can take the form of a simple "yes" or "no" question, such as "Did the content we provided help you solve your problem?" sent to the interface 800 of the user device 170 or RPT device 122. This question can be sent through the patient program 430. The user's answer to the prompt can be paired with data collected from the user's system 100 to identify the problem the user experienced and the solution they attempted to overcome it. In addition, the prompt and answer will provide data regarding whether the attempted solution solved the problem identified by the user 210. As shown in screens 801 and 802, other possible solutions can also be provided. If the user 210 engages with any other potential solutions, that activity can be tracked, and subsequent self-help screens 800 can be applied again after attempting the solution to further provide data regarding activity that helped alleviate the problem identified by the user 210.

[0146] Advantageously, high-resolution data may be collected from the patient using the RPT device 122. This data may include a respiratory waveform with flow (respiratory flow) data, tidal volume data, pressure data, minute ventilation data, leak data, inspiration to expiration (IE) ratio, and other signals from sensors and transducers that may provide some indication of respiratory discomfort and its correlation to pressure settings. Figure 1 The sensor 130 described in can be used to collect this data. The measurement of ventilation can include one or both of inspiratory flow and expiratory flow (per unit time). When expressed as volume per minute, the amount is often referred to as "minute ventilation". Minute ventilation is sometimes given simply as volume, understood to be the volume per minute.

[0147] Figure 9 A typical respiratory waveform model for a person is shown, along with at least some of the data that can be used to determine if a patient may have dyspnea and / or respiratory discomfort. The horizontal axis is time, and the vertical axis is respiratory flow. Although the parameter values ​​can vary, a typical breath can have the following approximate values: tidal volume Vt 0.5 L, inhalation time Ti 1.6 seconds, peak inspiratory flow Qpeak 0.4 L / s, exhalation time Te 2.4 seconds, peak expiratory flow Qpeak -0.5 L / s. The total duration of the breath, Ttot, is approximately 4 seconds. A person typically breathes at a rate of approximately 15 breaths per minute (BPM), with a ventilation volume, Vent, of approximately 7.5 L / min. A typical duty cycle (the ratio of Ti to Ttot) is approximately 40%.

[0148] This data can be combined with user responses to surveys and Figure 1 The data collected by the sensors described in

[0045] is combined with other user data (e.g., demographic information (age, sex, weight, height, BMI, etc.), patient-reported outcome measure (PROMS) data (such as improvement in sleepiness or motivation to start therapy), the type of sleep test the user used to identify or diagnose their apnea (e.g., polysomnography (PSG) or home sleep test (HST)) to create training data for a machine learning model that can be used to identify users 210 who may be experiencing breathing problems, including users who experience breathing discomfort, such as feeling shortness of breath or a desire for more airflow. The model can be used to identify other patients who may have similar problems but have not yet participated in the survey. For example, the machine learning model can even pre-identify patients with similar problems before the first survey during therapy. In some embodiments, the machine learning model can even be able to identify patients who may experience discomfort in breathing in or out before the patient begins therapy.

[0149] Figure 10 A flow diagram depicts an exemplary process 1000 for training a machine learning model to learn associations between data obtained from one or more users 210, in accordance with certain embodiments.

[0150] As used herein, a "machine learning model" generally includes instructions, data, and / or a model that is configured to receive an input and apply one or more of weights, biases, classifications, or analyses to the input to generate an output. The output may include, for example, a classification of the input, an analysis based on the input, a design, process, prediction, or recommendation associated with the input, or any other suitable type of output. Machine learning models are typically trained using training data, such as empirical data and / or samples of input data, which are input into the model to establish, adjust, or modify one or more aspects of the model, such as weights, biases, criteria for forming classifications or clusters, etc. Aspects of a machine learning model can operate on inputs linearly, in parallel, via a network (e.g., a neural network), or via any suitable configuration.

[0151] The execution of the machine learning model may include deploying one or more machine learning techniques, such as linear regression, logistic regression, random forest, gradient boosting machine (GBM), deep learning and / or deep neural network. Supervised and / or unsupervised training may be used. For example, supervised learning may include providing training data and labels corresponding to the training data, for example, as ground truth. Unsupervised methods may include clustering, classification, etc. K-means clustering or K-nearest neighbors may also be used, which may be supervised or unsupervised. A combination of K-nearest neighbors and unsupervised clustering techniques may also be used. Any suitable type of training may be used, such as random training, gradient boosting training, random seeding training, recursive training, round-based training, batch-based training, etc.

[0152] It should be understood that the technology disclosed herein can be applied to any suitable type of activity. It should also be understood that the above examples are merely illustrative. The technology and technical means disclosed herein can be applied to any suitable activity.

[0153] Presented below are various aspects of machine learning techniques that may be suitable for identifying whether a user 210 is likely to experience discomfort during therapy. As will be discussed in greater detail below, machine learning techniques suitable for identifying a user 210 that is likely to experience discomfort may include one or more aspects of the present disclosure (e.g., a specific selection of training data, a specific training process for a machine learning model, operation of a specific device suitable for use with a trained machine learning model, operation of a machine learning model in conjunction with specific data, modification of the machine learning model to such specific data, etc.) and / or other aspects that may be apparent to one of ordinary skill in the art based on this disclosure.

[0154] As discussed in further detail below, one or more components of the exemplary environment or system 100 can generate, store, train, and / or use a machine learning model. The exemplary environment or system 100 or one of its components can include a machine learning model and / or instructions associated with the machine learning model, such as instructions for generating the machine learning model, training the machine learning model, using the machine learning model, etc. The exemplary environment or system 100 or one of its components can include instructions for retrieving data, adjusting data (e.g., based on output of the machine learning model), and / or operating a display to output data (e.g., adjusted based on the machine learning model). The exemplary environment or system 100 or one of its components can include, provide, obtain, and / or generate training data.

[0155] In some embodiments, systems or devices other than the components shown in exemplary system 100 can be used to generate and / or train a machine learning model. For example, such a system can include instructions for generating and / or obtaining a machine learning model, training data, and ground truth, and / or instructions for training a machine learning model. The resulting trained machine learning model can then be provided to exemplary system 100 or one of its components and stored, for example, in memory 114.

[0156] Typically, a machine learning model includes a set of variables, such as nodes, neurons, filters, etc., that are adjusted (e.g., weighted or biased) to different values ​​by applying training data. In supervised learning, for example, where the ground truth of the provided training data is known, training can be performed by inputting a sample of the training data into the model with the variables set to initialized values ​​(e.g., randomly, based on Gaussian noise, a pre-trained model, etc.). The output can be compared to the ground truth to determine the error, which can then be back-propagated through the model to adjust the value of the variable. Certain embodiments may utilize unsupervised learning to train a machine learning model, where, for example, the sample of training data may not include pre-assigned labels or scores to assist in the learning process; or may utilize semi-supervised learning, where a combination of training data with pre-assigned labels or scores and training data without pre-assigned labels or scores is used to train a machine learning model.

[0157] Figure 10A flow chart depicts an exemplary process 1000 for training a machine learning model to learn to identify a user 210 experiencing discomfort during therapy, according to certain embodiments. At step 1002, process 1000 may include receiving data associated with one or more users 210. For example, data server 410 may receive data from system 100, including data from control system 110, respiratory therapy system 120, sensor 130, user device 170, blood pressure device 182, and / or activity tracker 190. Data associated with user 210 may also include demographic data (such as age, gender, height, weight), PROMS data, type of sleep test, and other data that the machine may learn to factor into the identification.

[0158] The data from the user device 170 includes the user 210's Figure 8 The user's responses to these questions help to screen out a group of self-identified users 210 who experienced discomfort or other problems during their therapy.

[0159] At step 1004, process 1000 includes processing the data to extract one or more features from the data. This may include creating multiple batches of data for input into a machine learning model. Batches may include, but are not limited to:

[0160] (1) Users who identify the therapy as “okay”

[0161] (2) Identify therapy as “challenging” for users

[0162] (3) Users who identified “feeling difficulty breathing” as the most bothering issue for them

[0163] (3a) Users who respond by increasing their EPR

[0164] (3b) User responds by turning on the ramp

[0165] (4) Users who identified “feeling like there is not enough air to breathe” as the issue that bothered them most

[0166] (4a) User responds by turning off the ramp

[0167] (4b) Users who respond by reducing their EPR

[0168] (4c) A user who responds by adjusting (e.g., increasing / decreasing) the ramp feature's starting pressure, minimum pressure, EPR, etc.

[0169] (5a) Users whose therapy improved due to adjustments

[0170] (5b) Users whose therapy did not improve despite adjustments

[0171] (6) Users who identify the therapy as “very good”

[0172] Some users' data may be included in more than one batch, and these batches are not mutually exclusive. For example, a user identified as feeling "okay" would have their data included in batch (1). If they indicated difficulty breathing out, their data would also be included in batch (3). Furthermore, the machine learning model can mix and combine batches to create new training data. As just one example, the machine learning model may identify users whose therapy was "challenging," users who identified "not feeling like there was enough air to get in" as being the most bothering them, users who responded by turning off the ramp, and users who reported that adjustments improved their therapy into new batches to process data.

[0173] Data from the system 100 is then associated with the users in each batch. Advantageously, this can associate specific empirical data and sensor-based data with users 210 who have self-identified as having a specific problem or no specific problem at all. This data can include flow (respiratory flow) data, tidal volume data, pressure data, minute ventilation data, leak data, respiratory waveforms and data associated with the respiratory waveforms as described above, and / or other data and signals accessed by the sensors 130 that can provide some correlation or potential correlation with respiratory discomfort. Additional data can include the pressure setting of the RPT device 122.

[0174] At step 1006, the collected and processed data is used to train one or more machine learning models to classify one or more other users based on data from the system 100 (including sensors 130, blood pressure devices 182, and / or activity trackers 190) of the one or more other users. This can be achieved by associating the sensor data with the self-identified user as described in step 1004, and multiple models can be generated for different batches as identified above. Training can be performed in any suitable manner (e.g., in batches) and can include any suitable training method, such as stochastic or non-stochastic gradient descent, gradient boosting, random forests, etc. In some embodiments, a portion of the training data can be retained during training and / or used to validate the trained machine learning model, for example, to compare the output of the trained model to the ground truth of the portion of the training data to assess the accuracy of the trained model. The training of the machine learning model can be configured to enable the machine learning model to learn the association between the training data (e.g., user data) and the ground truth data, so that the trained machine learning model is configured to determine an output (e.g., the user feels shortness of breath) in response to the input data (e.g., sensor data associated with the user) based on the learned association.

[0175] In various embodiments, the variables of the machine learning model may be related to each other in any suitable arrangement to generate an output. For example, in some embodiments, the machine learning model may include a Figures 1 to 2 The user's breathing data and / or RPT data collected by the sensors described in FIG5 to FIG5 Figure 8

[0014] A machine learning model may be a framework for classifying users based on responses to survey prompts described in

[0014] and / or other data. For example, a machine learning model may include one or more neural networks configured to identify features in the data, and may include further frameworks (e.g., connection layers, neural networks, etc.) configured to determine relationships between the identified features in order to determine patterns in the data. In some embodiments, a machine learning model may include a single node for classification, as described elsewhere herein. For example, a trained model may determine that certain respiratory waveforms combined with specific values ​​of tidal volume data and leakage data cause a user to experience breathlessness, and identify that the user may benefit from an adjustment to the ramp start pressure or other modifications to comfort settings, such as changing the humidification level or EPR, or a combination of these and other settings. A trained model may determine that certain respiratory waveforms combined with specific values ​​of tidal volume data and leakage data cause a user to experience breathlessness, and identify that the user may benefit from an adjustment to the EPR or other modifications to comfort settings, such as changing the humidification level, temperature, or ramp parameters, or a combination of these and other settings. These are just two examples of the many classifications that a machine learning model can determine. Other comfort settings may include changing elements of the air circuit, such as mask type, mask fit, tube length, or tube diameter.

[0176] At step 1008, the trained model is incorporated into a module or other processor device for installation on the user device 170, the RPT device 122, any other suitable location within the system 100, or one or more of the RPT systems 400 / 400B. The module or other processor may be used to execute one or more machine learning models. The module may employ Figure 4A and Figure 4B The subroutine may be in the form of a mobile application program within the patient program 430 described in the foregoing. The module may be a standalone program outside of the patient program 430 or a program module incorporated into the RPT device 122. Figure 4A and Figure 4B As shown, one or more machine learning models may be stored as a process 440 on a separate data server 410 , and the module for installation may simply be an executable program for communicating with the process 440 via the wide area network 420 .

[0177] The module may be provided with a network server device for publishing the module for download and installation using a user device, or the software module may be provided directly to the user device 170 or the RPT device 122 for installation, etc. The software module may include one or more program files, electronic applications, etc. that can be installed on the user device 170 and executed by the user device 170. For example, the software module may include data for installing a virtual assistant and one or more machine learning models on a web browser of the user device 170 or within the patient program 430 on the user device 170.

[0178] Therefore, some embodiments may train one or more machine learning models to generate predictions based solely on the data of one or more users or in combination with the data of FIG. Figure 8 The above process 1000 is provided as an example only and may include the following: Figure 10 Additional, fewer, different or differently arranged steps than those depicted in .

[0179] Figure 11 18. An exemplary process 1100 is illustrated for identifying a user who may experience discomfort or other issues during therapy, for example, by utilizing a trained machine learning model, such as a machine learning model trained according to one or more embodiments discussed above. At step 1102, process 1100 may include detecting that user 210 has initiated therapy on RPT device 122. This may be accomplished by a program within system 100 (optionally within RPT device 122) that indicates when it is to be used, by an instruction from user 210 via patient program 430, by a wireless signal transmitted from RPT device 122 to a remote location (including a location with a machine learning model), or by any other suitable means. When user 210 initiates therapy, system 100 begins collecting data regarding the patient's therapy via sensor 130, blood pressure device 182, and / or activity tracker 190.

[0180] At step 1104, the collected data about the therapy is input into one or more machine learning models trained in process 1000. The data can be input into the model continuously in real time, periodically at predetermined time intervals, on demand, or at any other time interval. The data can be sent from the system 100 or the user device 170 to the data server 410 for processing in the machine learning model at process 440. When the user data collected at step 1102 is input into the trained machine learning model, the model can classify the user based on the batch used in training. For example, the trained model can identify whether the user 210 is likely to identify the therapy as "very good", "okay", or "challenging" based on the model's decision (as specified by the training data). In addition, the model can classify the user 210 as likely to have difficulty inhaling, likely to have difficulty in exhaling, and can classify the user 210 as likely to benefit from specific therapeutic interventions, such as instructions to turn on or off the ramp. As discussed above, for example, a trained model can determine that certain breathing waveforms, alone or in combination with specific values ​​of tidal volume data, leak data, and / or other signals that can indicate respiratory discomfort, can cause a user to experience breathlessness, and identify that the user could benefit from adjusting the ramp start pressure, minimum pressure, or other changes to comfort settings. Alternatively, a trained model can determine that certain breathing waveforms, in combination with specific values ​​of tidal volume data, leak data, and / or other signals that can indicate respiratory discomfort, can cause a user to experience breathlessness, and identify that the user could benefit from adjusting the EPR or other changes to comfort settings. These are just two examples of the many classifications that a machine learning model can determine and identify countermeasures to be performed. Other signals that can provide an indication of respiratory discomfort can include mask donning / docking events, which can indicate that patient 210 has removed their mask during therapy. This can be an indication that patient 210 is experiencing discomfort. Alternatively, the amount of time it takes for a patient to fall asleep (the time from mask donning to sleep onset) can also be an indicator of respiratory comfort, as if a person is experiencing discomfort, it can be expected that it may take longer to fall asleep.

[0181] At step 1106, in response to the classification performed in step 1104, process 1100 may cause the module to perform actions based on the classification. These actions may include, but are not limited to: transmitting a notification to the user that modifications to their therapy may make them more comfortable, automatically making adjustments to the RPT device 122 (including changing ramp, pressure settings, EPR, etc.) that the model identifies as beneficial based on the user's classification, transmitting a notification to the user's 210 clinician to inform the clinician of a potential identified problem with the user's therapy, etc.

[0182] Based on the collected data and information, the model can indicate that a particular mask change (whether mask size or mask type) would be beneficial for the patient 210. If a mask change is recommended, the recommendation can be communicated directly to the user 210, or to the user's clinician, indicating to the clinician that the user 210 may benefit from a mask change. Similarly, if a tube type change is recommended, the recommendation can be communicated directly to the user 210, or to the user's clinician, indicating to the clinician that the user 210 may benefit from a tube change.

[0183] For example, if the model determines that the user 210 is experiencing a breathing waveform combined with a tidal volume number and a leak number or other indication that may cause the user 210 to feel that there is not enough air to inhale, the process 1100 may cause the module to send a signal to the RPT device 122 to turn off the ramp feature. This may be independent of the user 210's participation in FIG. 5 to FIG. Figure 8 In this way, the machine learning model allows users 210 who have not or have not yet participated in the survey to benefit from data collected from users 210 who participated in the survey.

[0184] Figure 5A The survey prompts described in

[1100] can be delivered to all users 210 of the RPT device 122, regardless of the classification determined by the machine learning model. However, not all users 210 will participate in the survey process. One or more aspects of process 1100 can be performed regardless of whether a user 210 has already performed the survey process. Participating users 210 can thus provide additional training data, allowing all users to benefit from the survey prompts.

[0185] Figure 12 An alternative exemplary process 1200 for identifying users who may experience discomfort or other issues during therapy is illustrated, for example, by utilizing a trained machine learning model, such as a machine learning model trained according to one or more embodiments discussed above. At step 1202, process 1200 may include detecting that user 210 has initiated therapy on RPT device 122. This may be accomplished by a program within system 100 (optionally within RPT device 122) that indicates when therapy is being used, or by an instruction from user 210 via patient program 430. At step 1204, the process may include receiving first input data associated with the user and the therapy session. At step 1206, process 1200 may include training a machine learning model based on a plurality of pre-classified users and the first input data to determine associations between the user and a plurality of classifications. At step 1208, process 1200 may include classifying the user into one of the plurality of classifications. At step 1210, in response to classifying the user into the classification, process 1200 may include causing the user device and / or the RPT device to perform an action.

[0186] A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent Office patent file or records, but otherwise reserves all copyright rights whatsoever.

[0187] Unless the context clearly indicates otherwise and where a range of values ​​is provided, it is understood that each intervening value (to the tenth of the unit of the lower limit) between the upper and lower limits of that range, and any other stated or intervening value in that stated range, is encompassed within the present technology. The upper and lower limits of these intermediate ranges (which may independently be included in the intermediate ranges) are also encompassed within the present technology, subject to any specifically excluded limits in the stated range. Where the stated range includes one or both of these limits, ranges excluding either or both of those included limits are also encompassed within the present technology.

[0188] Furthermore, where a value or values ​​are described herein as being implemented as part of the present technology, it should be understood that such values ​​may be approximate unless otherwise indicated and that such values ​​may be used with any suitable significant figures to the extent permitted or required by the actual technical implementation.

[0189] Furthermore, "approximately," "substantially," "about," or any similar term as used herein means + / - 5-10% of the stated value.

[0190] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this technology belongs. Although any methods and materials similar or equivalent to those described herein can also be used in the practice or testing of this technology, a limited number of exemplary methods and materials are described herein.

[0191] When a specific material is identified as being used to construct a component, obvious alternative materials having similar properties may be used as substitutes. Furthermore, unless otherwise specified, any and all components described herein should be understood to be capable of being manufactured, and thus may be manufactured together or separately.

[0192] It must be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural equivalents unless the context clearly dictates otherwise.

[0193] All publications mentioned herein are incorporated by reference in their entirety to disclose and describe the methods and / or materials that are the subject of those publications. The publications discussed herein are provided solely for their disclosures prior to the filing date of the present application. This paper should not be construed as admitting that the present technology has no right to precede such publications due to prior disclosure. In addition, the publication date provided may be different from the actual publication date, which may need to be independently confirmed.

[0194] The terms “include” and “comprising” should be interpreted as referring to elements, components or steps in a non-exclusive manner, indicating that the referenced elements, components or steps may be present, utilized or combined with other elements, components or steps not explicitly referenced.

[0195] The subject headings used in the detailed description are for the convenience of the reader and should not be used to limit the subject matter found in the entire disclosure or claims. The subject headings should not be used to interpret the scope of the claims or claim limitations.

[0196] Although the technology herein has been described with reference to specific examples, it should be understood that these examples are merely illustrations of the principles and applications of the present technology. In some instances, terms and symbols may imply specific details that are not required for practicing the technology. For example, although the terms "first" and "second" may be used, unless otherwise specified, they are not intended to indicate any order, but may be used to distinguish different elements. In addition, although the process steps in the method can be described or illustrated in sequence, such order is not required. Those skilled in the art will recognize that such order can be modified and / or various aspects thereof can be performed concurrently or even synchronously.

[0197] It is therefore to be understood that numerous modifications may be made to the illustrative examples and that other arrangements may be devised without departing from the spirit and scope of the present technology.

Claims

1. A computer-implemented method for classifying users of a respiratory pressure therapy (RPT) device, the method comprising: identifying that the user has commenced a therapy session using the RPT device; receiving first input data associated with the user and the therapy session; training a machine learning model based on a plurality of pre-classified users and the first input data to determine associations between users and a plurality of classifications; classifying the user into a category among the plurality of categories; as well as In response to classifying the user into the classification, causing the user device and / or the RPT device to perform an action.

2. The method according to claim 1, further comprising: Send survey prompts to users; receiving one or more selections from the user in response to the survey prompt, wherein at least the response is an indication of user discomfort; as well as One or more of the settings of the RPT are automatically adjusted based on the indication of user discomfort.

3. The method of claim 1, wherein the first input data comprises at least one of: flow data; pressure data; waveform data; tidal volume data; minute ventilation data; and leak data.

4. The method of claim 1, wherein the plurality of categories comprises: The user experiences steady-state respiratory discomfort; The user is not getting enough air during breathing; and The user is not expelling enough air during breathing.

5. The method of claim 4, wherein the action comprises displaying instructions for alleviating the lack of adequate air obtained during breathing.

6. The method of claim 5, wherein the action comprises the RPT device automatically turning off a ramp feature.

7. The method of claim 4, wherein the action comprises displaying instructions for alleviating the user from not expelling enough air during breathing.

8. The method of claim 7, wherein the operating instructions include the RPT device automatically increasing expiratory pressure relief (EPR).

9. A non-transitory computer-readable storage medium having instructions embodied thereon, the instructions executable by one or more processors to perform a method for training a machine learning model to classify users of a respiratory pressure therapy (RPT) device, the method comprising: receiving input data associated with users and associated therapy sessions, wherein each user has one or more classifications; processing the input data to extract one or more features from the input data; training the machine learning model to classify one or more other users into the one or more categories based on the one or more features extracted from the input data; and Providing communication between the machine learning model and one or both of the user device and the RPT device, wherein the communication includes at least causing the user device and / or the RPT device to perform an action.

10. The non-transitory computer-readable storage medium of claim 9, further comprising instructions executable to perform the method: Send survey prompts to users; receiving one or more selections from the user in response to the survey prompt, wherein at least a response is an indication of user discomfort; and One or more of the settings of the RPT are automatically adjusted based on the indication of user discomfort.

11. The non-transitory computer-readable storage medium of claim 9, wherein the receiving of the input data associated with the user and the therapy session is received from the user device and / or the RPT device.

12. The non-transitory computer-readable storage medium of claim 9, wherein the input data comprises at least one of: flow data; tidal volume data; minute ventilation data; and leak data.

13. The non-transitory computer-readable storage medium of claim 9, wherein the one or more categories include: The user experiences steady-state respiratory discomfort; The user is not getting enough air during breathing; and The user is not expelling enough air during breathing.

14. The non-transitory computer-readable storage medium of claim 13, wherein the action comprises displaying instructions for alleviating a lack of air during breathing.

15. The non-transitory computer-readable storage medium of claim 14, wherein the one action comprises automatically turning off a ramp feature.

16. The non-transitory computer-readable storage medium of claim 14, wherein the action comprises displaying instructions on the RPT device for alleviating the user from not expelling enough air during breathing.

17. The non-transitory computer-readable storage medium of claim 16, wherein the operating instructions include the RPT device automatically increasing expiratory pressure relief (EPR).

18. A system for classifying users of a respiratory pressure therapy (RPT) device, the system comprising: a memory storing instructions and a machine learning model, wherein the machine learning model is trained based on pre-classified users to learn associations between the pre-classified users and a plurality of classifications, such that the machine learning model is configured to perform the classification based on the learned associations; and a processor operably connected to the memory and configured to execute the instructions to perform operations comprising: identifying that the user has begun a therapy session on the RPT device; receiving first input data associated with the user and the therapy session; classifying the user into a category among the plurality of categories by inputting the first input data into the machine learning model; as well as In response to classifying the user into the classification, causing the user device and / or the RPT device to perform an action.

19. The system of claim 18, wherein the instructions are further configured to: Send survey prompts to users; receiving one or more selections from the user in response to the survey prompt, wherein at least a response is an indication of user discomfort; and One or more of the settings of the RPT are automatically adjusted based on the indication of user discomfort.

20. The system of claim 18, wherein the plurality of categories comprises: The user experiences steady-state respiratory discomfort; The user is not getting enough air during breathing; and The user is not expelling enough air during breathing.

Images