User Interface Auto-Identification

Abstract

Airflow parameters (e.g., flow rate and airflow pressure) of the airflow generated by the flow generator of the respiratory treatment system can be measured and processed during use to automatically identify user interface and / or conduit identification information. The user interface and / or conduit identification information can be used to adjust settings on the respiratory treatment device, generate notifications (e.g., notification of a detected change in the user interface without an expected adjustment of settings on the respiratory treatment device), or otherwise facilitate respiratory treatment for the user or other users. The user interface and / or conduit identification information can indicate particular characteristics of the user interface and / or conduit (e.g., resonant frequency, impedance, etc.), a pattern of the user interface (e.g., mask, nasal mask, or nasal pillows) and / or a pattern of the conduit, a particular manufacturer, a particular model, or other such identifying information.

Description

Technical Field

[0001] The present disclosure generally relates to respiratory therapy devices, and more specifically, to the automatic identification of user interfaces and conduits of respiratory devices.

Background Art

[0002] Many people suffer from sleep-related breathing disorders associated with one or more events that occur during sleep, such as snoring, apnea, hypopnea, restless legs, sleep disorders, choking, increased heart rate, labored breathing, asthma attacks, seizure attacks, convulsions, or any combination thereof. These people are often treated using a respiratory therapy system (e.g., a continuous positive airway pressure (CPAP) system) that delivers pressurized air to assist in preventing the airway from closing or narrowing during a sleep session. The pressurized air is supplied to the user via a user interface such as a mask, nasal mask, nasal pillow mask, etc. Different user interfaces can be used in the same respiratory device. Depending on the characteristics of the user interface, the respiratory device may need to be programmed or set to achieve optimal results. Generally, one or more doctor visits may be required to fit the respiratory system to the user.

Summary of the Invention

Means for Solving the Problems

[0003] According to some embodiments of the present disclosure, a method for automatically identifying a user interface including generating an airflow through the user interface is disclosed. The method further includes measuring one or more airflow parameters including at least one of a flow rate signal of the generated airflow over time and a pressure signal of the generated airflow over time associated with the generated airflow. The method further includes identifying user interface identification information that can be used to identify the characteristics of the user interface based on the measured one or more airflow parameters.

[0004] The above summary is not intended to illustrate any or any embodiment of the present disclosure. Additional features and benefits of the present disclosure are evident from the detailed description and drawings below. [Brief explanation of the drawing]

[0005] [Figure 1] Figure 1 is a functional block diagram of a system for generating user-related physiological data during a sleep session, relating to several implementations of the present disclosure. [Figure 2] Figure 2 is a perspective view of the system, user, and cohabitant in Figure 1, relating to several implementations of the present disclosure. [Figure 3] Figure 3 is a flowchart of the process for analyzing airflow parameters to determine user interface and / or conduit identification information, relating to several implementations of this disclosure. [Figure 4] Figure 4 is a graph that can be used to identify exemplary flow signals of user interface identification information in several implementations of the present disclosure. [Figure 5] Figure 5 is a flowchart of the process for analyzing pressure data and flow rate data to determine user interface and / or conduit identification information, relating to several implementations of the present disclosure. [Figure 6] Figure 6 is an illustrative graph of data points compared to a template curve for several implementations of the present disclosure. [Figure 7] Figure 7 is a graph showing examples of experimental data on the identification distance of user interfaces across multiple patterns related to several implementations of the present disclosure. [Modes for carrying out the invention]

[0006] While various modifications and alternative forms are possible for this disclosure, specific implementations and embodiments of this disclosure are shown as examples in the drawings and are described in detail herein. However, it should be understood that this disclosure is not intended to be limited to any particular form disclosed, but rather encompasses all modifications, equivalents, and alternatives that fall within the spirit and scope of this disclosure as defined by the appended claims.

[0007] Some aspects and features of this disclosure relate to the automatic detection of user interfaces of respiratory therapy systems. Airflow parameters (e.g., flow rate and airflow pressure) of the airflow generated by a flow generator are measured and processed during use to identify user interface identification and / or conduit information. This user interface and / or conduit identification information can be used to adjust the settings of the respiratory therapy device, generate notifications (e.g., notifications of changes in the user interface detected without the expected adjustment of the settings of the respiratory therapy device), or otherwise facilitate respiratory therapy for this user or other users. The user interface identification information may indicate specific characteristics of the user interface (e.g., resonant frequency, impedance, etc.), the pattern of the user interface (e.g., mask, nasal mask, or nasal pillow), the specific manufacturer of the user interface, the specific model of the user interface, or other such identifiable information.

[0008] A respiratory therapy device can benefit from knowledge of the user interface and / or the conduit attached thereto. Information about the user interface and / or conduit can be used to set the internal parameters of the respiratory therapy device and to ensure accurate data reporting. By utilizing knowledge of the downstream system (e.g., the user interface and / or the conduit connecting the user interface to the respiratory therapy device), the respiratory therapy device can apply corrections to ensure that the correct therapeutic pressure is supplied to the user. User interface and / or conduit information may include information such as the user interface and / or conduit manufacturer (e.g., brand), user interface and / or conduit model, user interface and / or conduit size, and the presence and type of user interface vents.

[0009] While users, or more likely medical professionals, can configure respiratory therapy devices to operate efficiently using specific user interfaces and conduits, this configuration process is prone to errors. In addition, even when properly configured, user interfaces and / or conduits may be closed or replaced shortly afterward, or may begin operating differently due to normal wear and tear. If a respiratory therapy device is not updated to reflect appropriate user interface and conduit information, it will be unable to provide appropriate respiratory therapy to the user. Therefore, a respiratory therapy system is needed that can automatically detect information regarding user interfaces and / or conduits attached to the respiratory therapy device. Furthermore, some aspects of this disclosure enable the detection of user interfaces and / or conduits without relying on external sensors or input from users or medical professionals.

[0010] Some aspects of this disclosure relate to varying airflow parameters (e.g., flow rate and pressure) over time as incoming data (e.g., airflow parameter data). This incoming data may be processed, for example, by digital signal processing techniques to generate a set of features that can be fed into a machine learning model. The output of the machine learning model may be user interface identifier information. This user interface identifier information may be a specific user interface (e.g., the user interface of a particular model), a general manufacturer of the user interface, a pattern of the user interface (e.g., a mask, nasal mask, or nasal pillow), or other characteristics of the user interface. In some implementations, the incoming data may include additional information such as a speed signal of a flow generator fan (e.g., revolutions per minute) or other characteristics of the flow generator or respiratory therapy device.

[0011] The features that can be determined from incoming data can vary depending on the embodiment. In some implementations, the user interface pattern can be determined from the airflow parameter data. Other examples of features include the presence of vents, the number of vents, the type of vents, the occurrence of intentional leaks (e.g., vent flow rate), the normal shape of the user interface, the normal size of the user interface, breathing rate, inhalation volume, inhalation duration, exhalation volume, exhalation duration, occurrence of transient events, occurrence of unintended air leaks, classification of unintended air leaks, indication of whether the user interface is being worn, and frequency components (e.g., high-frequency, intermediate-frequency, and / or low-frequency components of the airflow parameter data). Any combination of these features can be used as input to a machine learning model to identify user interface identifiers.

[0012] For example, the presence of air leakage from the user's mouth can indicate that the user interface being used is a nasal mask or nasal pillow, rather than a mask. In another example, the presence of both nasal and oral breathing can indicate that a mask is being used. In some implementations, spectral components of airflow parameters (whether normal or during some stage of breathing, e.g., during inhalation or exhalation) can be used to indicate different shape and size characteristics of the user interface. In yet another example, detection of intentional ventilation (e.g., through vents in the user interface) can be used to determine user interface identification information, such as when intentional ventilation is detected from two vents and then from a single vent, and the positions of the two vents can be determined based on the ability of one vent to temporarily block (e.g., when the user turns over on one side during sleep). In yet another example, the system can calculate the relative vent flow rate by comparing the measured flow rate to a desired flow rate and taking into account any unintentional leakage (e.g., around the user interface seal). This relative vent flow rate can represent the vent's contribution to the flow rate, which may differ between user interfaces. For example, some vents exhibit a flow rate that changes with pressure, while others exhibit a constant flow rate regardless of pressure changes.

[0013] Any suitable machine learning model can be used. In some implementations, a machine learning model that is a deep neural network is used. In some implementations, the deep neural network is a recurrent neural network that can favorably analyze time-dependent airflow parameter data. In some implementations, the recurrent neural network is a long- and short-term memory recurrent neural network. In some implementations, the deep neural network is a convolutional neural network that is particularly useful when analyzing graphical representations of airflow parameter data (e.g., graphs of time-dependent flow rate and / or pressure, contours of the shape of one or more breaths, or spectral maps of airflow parameter data).

[0014] In some implementations, this system can utilize an expiratory pressure release (EPR) mechanism. EPR can automatically reduce expiratory pressure to facilitate exhalation by the user. In some implementations, automatic identification of user interface identification information can use EPR information, such as whether EPR is activated, how much the pressure is reduced, and when it is reduced. In some implementations, EPR information may be determined directly from airflow parameters. However, in some implementations, EPR information is obtained from one or more settings of the respiratory therapy device itself. In some implementations, since several aspects of airflow parameters can be modified by EPR, using EPR information can be useful in analyzing airflow parameters. Therefore, knowledge of EPR information can improve the identification of user interface identification information by allowing its changes to be filtered, weighted elimination, or processed in other ways.

[0015] In some implementations, preprocessing can be performed on the airflow parameter signal to determine the signal-to-noise ratio, thereby ensuring proper identification of user interface identifiers. In some implementations, the signal-to-noise ratio can affect the confidence level of the identified user interface identifier. For example, a low signal-to-noise ratio may result in a low confidence level. In such implementations, if the confidence level is below a threshold, no further action may be taken, or a notification may be provided indicating that user interface identifiers cannot be obtained.

[0016] In some implementations, the respiratory therapy device may induce known noise to calibrate the system. In some implementations, the respiratory therapy device may induce known changes in airflow generation to trigger detectable events in airflow parameters. In some implementations, existing detectable events may exist in the airflow parameters (e.g., from user-based actions such as attaching or detaching a user interface). These detectable events (whether intentionally created by the respiratory therapy device or spontaneously created by user actions) can be used to facilitate the identification of user interface identifiers by analyzing the airflow parameter data associated with the events. The airflow parameter data associated with an event may include airflow parameter data generated during the event and airflow parameter data generated after the event that indicates the system's response to the event.

[0017] Based on the detected user interface identification information, various actions can be performed. In some implementations, actions may include adjusting the airflow generation of the respiratory therapy device, such as adjusting settings to improve the efficiency of the respiratory therapy device or ensuring that the respiratory therapy device delivers the correct therapeutic pressure to the user. In some implementations, actions may include providing notifications to the user or other people (e.g., medical professionals or caregivers). In some implementations, actions may include automatically shutting down the respiratory therapy device if an unexpected, unauthorized, or dangerous user interface (e.g., to implement a product recall) is detected.

[0018] In some implementations, the settings of the respiratory therapy device can be dynamically adjusted based on the identified characteristics of the identified user interface. In one example, the identified characteristic may be that one of the two vents of the user interface is blocked (e.g., the user sleeps on one side with one vent blocked). In such an example, the system automatically detects user interface identification information indicating that the user interface has two vents. However, if it is also detected that one of the vents is blocked, the system can dynamically update the settings of the respiratory therapy device so that the user can receive the desired treatment despite one of the vents being blocked. And if the system later detects that the vent is not blocked, the settings of the respiratory therapy device can be restored.

[0019] Various aspects of the present disclosure are described primarily with reference to the user interface, such as the automatic detection of the user interface and the adjustment of the respiratory therapy device based on a particular user interface. However, similar automatic detection and adjustment can be performed with reference to other elements of the fluid transport system, such as a flow generator that generates an airflow and a conduit that transports the airflow to the user interface. The flow generator, the conduit, and the user interface may include a fluid transport path from the flow generator to the user airway. In some implementations, additional elements may be included within the fluid transport path. For the purposes of the present disclosure, where various aspects are described with reference to the automatic detection of the user interface (e.g., the identification of user interface identification information) and / or the use of knowledge of the attached user interface (e.g., using the user interface identification information), the same aspects can be used to appropriately and automatically detect and utilize any single element or combination of elements that make up the fluid transport path.

[0020] In some implementations, automatic detection (e.g., automatic detection of a user interface and / or conduit) occurs continuously during use of the respiratory therapy device. In some implementations, automatic detection occurs frequently (e.g., once per hour, once every few hours, once per day, once every few days, once per week, once every few weeks, once per month, once every few months, once per year, or once every few years). In some implementations, automatic detection occurs only once per sleep session or once each time the respiratory therapy device is activated. In some implementations, automatic detection occurs only after being manually turned on by pressing a button or control associated with activating automatic detection of the user interface. In some implementations, automatic detection occurs when it is detected that one or more components within the fluid transport path have been removed, attached, or replaced.

[0021] These illustrative examples are for introducing the general themes discussed herein to the reader and are not intended to limit the scope of the disclosed concepts. The following sections describe various additional features and examples with reference to the drawings, where like numerals in the figures indicate like elements, and the directional descriptions are for explaining the illustrative examples but, like the illustrative examples, do not limit the present disclosure. The elements included in the illustrations herein may be plotted out of proportion.

[0022] Referring to FIG. 1, system 100 includes a control system 110, a respiratory therapy system 120, one or more sensors 130, and an external device 170. As described herein, system 100 can generally be used to provide respiratory therapy to a user and automatically detect user interface identification information regarding user interface 124 used in system 100.

[0023] The control system 110 includes one or more processors 112 (hereinafter referred to as processor 112). The control system 110 is generally used to control (e.g., operate) various components of system 100 and / or to analyze data acquired and / or generated by the components of system 100. The processors 112 may be general-purpose or special-purpose processors or microprocessors. Although one processor 112 is shown in Figure 1, the control system 110 may include any appropriate number of processors (e.g., one processor, two processors, five processors, ten processors, etc.) that may reside in a single housing or be located apart from one another. The control system 110 can be connected to and / or located inside, for example, the housing of the external device 170, part of the respiratory system 120 (e.g., housing), and / or one or more housings of the sensor 130. The control system 110 can be centralized (in one such housing) or distributed (in two or more physically separate such housings). In such an implementation configuration, which includes two or more housings for the control system 110, the housings may be located close to and / or far apart from one another.

[0024] The storage device 114 stores machine-readable instructions that can be executed by the processor 112 of the control system 110. The storage device 114 may be any suitable computer-readable storage device or medium, such as a random access memory device or a serial access memory device, a hard drive, a solid-state drive, or a flash memory device. Although one storage device 114 is shown in Figure 1, the system 100 may include any suitable number of storage devices 114 (e.g., one, two, five, or ten). The storage devices 114 may be connected to and / or located inside the housing of the respiratory device 122, the housing of the external device 170, the housing of one or more sensors 130, or any combination thereof. Similar to the control system 110, the storage devices 114 may be centralized (in one such housing) or distributed (in two or more physically separate such housings).

[0025] The electronic interface 119 is configured to receive data (e.g., physiological data, environmental data, airflow data, and / or audio data) from one or more sensors 130 so that the data can be stored in a storage device 114 and / or analyzed by a processor 112 of the control system 110. The electronic interface 119 can communicate with one or more sensors 130 using a wired or wireless connection (e.g., RF communication protocol, WiFi communication protocol, Bluetooth® communication protocol, 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 further include one or more processors and / or one or more storage devices that are identical or similar to the processor 112 and storage device 114 described herein. In some embodiments, the electronic interface 119 is connected to or integrated with an external device 170. In other embodiments, the electronic interface 119 is connected to or integrated with the control system 110 and / or the storage device 114 (for example, within the housing).

[0026] The respiratory system 120 (also called a respiratory therapy system) may include a respiratory pressure therapy device 122 (hereinafter also called the respiratory device 122), a user interface 124, a conduit 126 (also called a tube or air circuit), a display device 128, and a selectable humidification tank 129. In some embodiments, one or more of the control system 110, memory device 114, display device 128, sensor 130, and humidification tank 129 are part of the respiratory device 122. Respiratory pressure therapy refers to applying an air supply to the inlet of the user's airway at a controlled target pressure that is nominally positive to the atmosphere throughout the user's entire respiratory cycle (unlike negative pressure therapy, such as tank ventilators or positive / negative pressure external ventilators). The respiratory system 120 is commonly used to treat individuals suffering from one or more sleep-related breathing disorders (e.g., obstructive sleep apnea, central sleep apnea, mixed sleep apnea).

[0027] The breathing apparatus 122 is generally used to generate pressurized air to be delivered to the user. The breathing apparatus 122 may include a flow generator designed to generate pressurized air (for example, using one or more motors that drive one or more compressors or fans). In some embodiments, the breathing apparatus 122 generates a continuous, constant air pressure to be delivered to the user. In other embodiments, the breathing apparatus 122 generates two or more predetermined pressures (for example, a first predetermined air pressure and a second predetermined air pressure). In yet another embodiment, the breathing apparatus 122 is configured to generate a variety of different air pressures within a predetermined range. For example, the breathing apparatus 122 can deliver at least about 6 cm H2O, at least about 10 cm H2O, at least about 20 cm H2O, about 6 cm H2O to about 10 cm H2O, about 7 cm H2O to about 12 cm H2O, etc. The breathing apparatus 122 can also deliver pressurized air at a predetermined flow rate, for example, about -20 L / min to about 150 L / min, while maintaining positive pressure (relative to ambient pressure).

[0028] The user interface 124 engages with a portion of the user's face and helps deliver pressurized air from the respiratory device 122 to the user's airway, thereby preventing airway narrowing and / or obstruction during the sleep session. This can also increase the user's oxygen intake during the sleep session. Depending on the therapy applied, the user interface 124 can, for example, form a seal with an area or portion of the user's face to facilitate the delivery of gas at a pressure sufficiently different from the ambient pressure, e.g., a positive pressure of approximately 10 cmH2O relative to the ambient pressure, in order to activate the therapy. In other forms of therapy, such as oxygen delivery, the user interface may not include a seal sufficient to facilitate the delivery of gas to the airway at a positive pressure of approximately 10 cmH2O.

[0029] As shown in Figure 2, in some embodiments, the user interface 124 is a face mask that covers the user's nose and mouth. Other patterns of user interfaces may be used. For example, in some implementations, the user interface 124 may be a nasal mask that provides air to the user's nose, or a nasal pillow mask that delivers air directly to the user's nostrils. The user interface 124 may include a number of straps (e.g., including hook-and-loop fasteners) for positioning and / or stabilizing the interface on a part of the user (e.g., the face), and a shape-conforming cushion (e.g., silicone, plastic, foam, etc.) that helps to provide an airtight seal between the user interface 124 and the user. The user interface 124 may also be a tubular mask (also called a “crown” tube or mask), and optionally, one or more belts of a head-mounted device associated with the user interface may be configured to function as one or more conduits for delivering pressurized air to a full-face user interface or nasal user interface, and the user interface may be called a “conduit mask”. The user interface 124 may also include one or more vents to allow carbon dioxide and other gases exhaled by the user 210 to escape. In other embodiments, the user interface 124 includes a mouthpiece (e.g., a night guard mouthpiece molded to fit the user's teeth, a mandibular repositioning device, etc.).

[0030] The user interface 124 shown in Figure 2 is a mask-type user interface, but other user interfaces may be used as part of the respiratory device 120. User interfaces from different models, patterns, and manufacturers can be coupled to any given respiratory system 120 according to the user's needs or desires. Different user interfaces may have different characteristics regarding how they handle and respond to airflow. For example, user interfaces of different shapes may result in different impedances and different resonant frequencies within the respiratory airflow system 120. Therefore, the respiratory device 122 (e.g., the fan or flow generator of the respiratory device 122) may require different drives to generate a prescribed or desired airflow to the user's airway for different user interfaces. As used herein, the term “pattern” as used with respect to user interfaces is intended to describe types of user interfaces such as full-face masks, nasal masks, nasal pillows, and mouthpieces. As used herein, the terms “model” and “manufacturer” as used with respect to user interfaces are intended to indicate a common understanding of the model and manufacturer of any given user interface. An example of a user interface model is ResMed. TM F10 full face mask, ResMed TM P10 nose pillow mask, ResMed TM Examples include the N20 nasal mask. User interfaces can be obtained from multiple manufacturers. A single manufacturer may create and distribute multiple different user interfaces for various models. Each model may have a specific pattern.

[0031] The conduit 126 (also called an air circuit or tube) allows air to flow between two components of the breathing system 120, for example, the breathing apparatus 122 and the user interface 124. In some embodiments, this conduit may have separate branch tubes for inhalation and exhalation. In other embodiments, a single branch conduit is used for both inhalation and exhalation.

[0032] Similar to the user interface, conduits of different patterns, manufacturers, and models can be used in any given breathing system 120. In some implementations, conduits of different patterns, manufacturers, and / or models may have different characteristics regarding how the conduits respond to airflow. Therefore, in some implementations, it is advantageous to understand the conduit patterns, manufacturers, and / or models to ensure that the breathing system 120 uses the appropriate settings.

[0033] One or more of the breathing apparatus 122, user interface 124, conduit 126, display device 128, and humidification tank 129 may include one or more sensors (e.g., pressure sensors, flow sensors, or more generally, any of the other sensors 130 described herein). These one or more sensors can be used, for example, to measure airflow parameters such as the air pressure and / or flow rate of the pressurized air supplied by the breathing apparatus 122.

[0034] The display device 128 is generally used to display images and / or information relating to the respiratory device 122, including still images, moving images, or both. For example, the display device 128 may display information about the status of the respiratory device 122 (e.g., whether the respiratory device 122 is on / off, the pressure of the air being transported by the respiratory device 122, the temperature of the air being transported by the respiratory device 122, etc.), information about the user interface 124 (e.g., patterns, manufacturers, models, or characteristics of the user interface 124), information about the conduit 126 (e.g., patterns, manufacturers, models, or characteristics of the conduit 126), and / or other information (e.g., myAir TMIt can provide information such as a score, the current date / time, and personal information of user 210. In some embodiments, the display device 128 functions as a human-machine interface (HMI) that includes a graphical user interface (GUI) configured to display images as an input interface. The display device 128 may be an LED display, an OLED display, an LCD display, etc. The input interface may be, for example, a touchscreen or touch-sensitive board, a mouse, a keyboard, or any sensor system configured to sense input made by a human user interacting with the respiratory device 122.

[0035] The humidifying tank 129 includes a reservoir that is coupled to or integrated with the breathing apparatus 122 and can be used to humidify the pressurized air supplied from the breathing apparatus 122. The breathing apparatus 122 may include a heater that heats the water in the humidifying tank 129 in order to humidify the pressurized air supplied to the user. Furthermore, in some embodiments, the conduit 126 may also include a heating element (e.g., coupled to and / or embedded in the conduit 126) that heats the pressurized air supplied to the user.

[0036] The respiratory system 120 can be used as, for example, a ventilator, or a positive airway pressure (PAP) system such as a continuous positive airway pressure (CPAP) system, an automated positive airway pressure (APAP) system, a bilevel or variable positive airway pressure (BPAP or VPAP) system, or any combination thereof. A CPAP system delivers a predetermined air pressure to the user (determined, for example, by a sleep physician). An APAP system automatically changes the air pressure delivered to the user based, for example, on respiratory data related to the user. A BPAP or VPAP system is configured to deliver a first predetermined pressure (e.g., inspiratory positive airway pressure or IPAP) and a second predetermined pressure lower than the first predetermined pressure (e.g., expiratory positive airway pressure or EPAP).

[0037] Referring to Figure 2, some parts of the system 100 (Figure 1) according to several embodiments are shown. The user 210 and bedmate 220 of the breathing system 120 are positioned in the bed 230 and lying on the mattress 232. A user interface 124 (e.g., a face mask) may be worn by the user 210 during the sleep session. The user interface 124 is fluidically connected to and / or connected to the breathing apparatus 122 via a conduit 126. The breathing apparatus 122 also delivers pressurized air to the user 210 via the conduit 126 and the user interface 124 to increase the air pressure in the user 210's throat, helping to prevent the airway from closing and / or becoming narrowed during the sleep session. The breathing apparatus 122 may be placed on a nightstand 240 directly adjacent to the bed 230, as shown in Figure 2, or more generally, on any surface or structure adjacent to the bed 230 and / or the user 210.

[0038] Returning to Figure 1, 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 photoplethysmogram (PPG) sensor 154, an electrocardiogram (ECG) sensor 156, an electroencephalogram (EEG) sensor 158, a volume sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyogram (EMG) sensor 166, an oxygen sensor 168, a sample sensor 174, a moisture sensor 176, a LiDAR sensor 178, or a combination thereof. Generally, each of the one or more sensors 130 is configured to output sensor data received and stored by the storage device 114 or one or more other storage devices.

[0039] One or more sensors 130 are illustrated and described as including each of the following: pressure sensor 132, flow sensor 134, temperature sensor 136, motion sensor 138, microphone 140, speaker 142, RF receiver 146, RF transmitter 148, camera 150, infrared sensor 152, photoplethysmogram (PPG) sensor 154, electrocardiogram (ECG) sensor 156, electroencephalogram (EEG) sensor 158, volume sensor 160, force sensor 162, strain gauge sensor 164, electromyogram (EMG) sensor 166, oxygen sensor 168, specimen sensor 174, moisture sensor 176, and LidAR sensor 178, but more generally, one or more sensors 130 may include any combination and any number of each sensor described and / or illustrated herein.

[0040] One or more sensors 130 can be used to generate, for example, airflow data (e.g., data relating to airflow parameters such as flow rate and pressure), physiological data, audio data, image data, other data, or any combination thereof. The airflow data can be used to determine user interface identification information and / or conduit identification information, as further disclosed herein. In some implementations, audio data, image data, and / or other data can be used to determine or facilitate the determination of user interface identification information and / or conduit identification information. For example, audio data or image data that shows a particular shape or feature of the user interface can be used to facilitate the determination of user interface identification information after it has been reduced by analyzing airflow parameters. The control system 110 can use the physiological data generated by one or more of the sensors 130 to determine sleep-wake signals and one or more sleep-related parameters relevant to the user during a sleep session. The sleep-wake signal can indicate one or more sleep states, including wakefulness, relaxed wakefulness, micro-wakefulness, rapid eye movement (REM) stage, first non-REM stage (often referred to as "N1"), second non-REM stage (often referred to as "N2"), third non-REM stage (often referred to as "N3"), or any combination thereof. The sleep-wake signal can also be time-stamped to indicate the time the user goes to bed, gets out of bed, or attempts to fall asleep. The sleep-wake signal can be measured during a sleep session by sensor 130 at a predetermined sampling rate, such as one sample per second, one sample per 30 seconds, or one sample per minute. One or more sleep-related parameters that can be determined for the user during a sleep session based on the sleep-wake signal include total bedtime, total sleep duration, sleep latency, wake-up parameters, sleep efficiency, fragmentation index, or any combination thereof.

[0041] Physiological data and / or audio data generated by one or more sensors 130 can be used to determine respiratory signals associated with a user during a sleep session. Respiratory signals generally indicate the user's respiration / breathing during a sleep session. Respiratory signals may indicate, for example, respiratory rate, respiratory rate variability, inspiratory amplitude, expiratory amplitude, inspiratory-to-expiratory ratio, number of events per hour, event patterns, pressure settings of the respiratory device 122, or any combination thereof. Events may include snoring, apnea, central apnea, obstructive apnea, mixed apnea, respiratory depression, mask leakage (e.g., leakage from the user interface 124), lower limb immobility, sleep disturbance, suffocation, increased heart rate, labored breathing, asthma attacks, epileptic seizures, convulsions, or any combination thereof. In some implementations, these respiratory signals can be used to facilitate the determination of user interface identification information and / or conduit identification information.

[0042] The pressure sensor 132 outputs pressure data (e.g., a pressure signal) 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 indicating the user's breathing (e.g., inhalation and / or exhalation) and / or ambient pressure of the breathing system 120. In such embodiments, the pressure sensor 132 can be connected to or integrated with the breathing device 122. The pressure sensor 132 may be, for example, a capacitive sensor, an electromagnetic sensor, a piezoelectric sensor, a strain gauge sensor, an optical sensor, a potentiometric sensor, or any combination thereof. In one example, the pressure sensor 132 can be used to determine the user's blood pressure.

[0043] The flow sensor 134 outputs flow data (e.g., a flow signal) 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 airflow from the breathing apparatus 122, the airflow through the conduit 126, the airflow through the user interface 124, or any combination thereof. In such embodiments, the flow sensor 134 can be connected to or integrated with the breathing apparatus 122, the user interface 124, or the conduit 126. The flow sensor 134 may be a mass flow sensor such as a rotary flow meter (e.g., a Hall effect flow meter), a turbine flow meter, an orifice flow meter, an ultrasonic flow meter, a hot-wire sensor, an eddy current sensor, a membrane sensor, or any combination thereof.

[0044] 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 temperature data indicating the core body temperature of the user 210 (Figure 2), the skin temperature of the user 210, the temperature of the air flowing from the respiratory device 122 and / or through the conduit 126, the temperature within the user interface 124, the ambient temperature, or any combination thereof. The temperature sensor 136 may be, for example, a thermocouple sensor, a thermistor sensor, a silicon bandgap temperature sensor or semiconductor-based sensor, a resistance temperature detector, or any combination thereof.

[0045] The microphone 140 outputs audio data that is stored in the storage device 114 and / or can be 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 during a sleep session (e.g., sounds from user 210). As further described herein, the audio data from the microphone 140 can also be used to identify events experienced by the user during a sleep session (e.g., using the control system 110). The microphone 140 can be connected to or integrated with the breathing apparatus 122, user interface 124, conduit 126, or external device 170.

[0046] The speaker 142 can output sound waves audible to the user of the system 100 (for example, user 210 in Figure 2). The speaker 142 can be used, for example, as an alarm clock or to play a warning or message to user 210 (for example, in response to an event). In some embodiments, the speaker 142 can be used to transmit audio data generated by the microphone 140 to the user. The speaker 142 can be connected to or integrated with the breathing apparatus 122, user interface 124, conduit 126, or external device 170.

[0047] The microphone 140 and speaker 142 can be used as independent devices. In some embodiments, the microphone 140 and speaker 142 can be combined with an acoustic sensor 141, for example, as described in WO 2018 / 050913, which is incorporated herein by reference in its entirety. In such embodiments, the speaker 142 generates or emits sound waves at predetermined intervals, and the microphone 140 detects reflections of the sound waves emitted from the speaker 142. The sound waves generated or emitted by the speaker 142 have frequencies inaudible to the human ear (e.g., less than 20 Hz or greater than about 18 kHz) so as not to disturb the sleep of the user 210 or the person sharing a bed 220 (Figure 2). The control system 110 can determine the position of the user 210 (Figure 2) and / or one or more of the sleep-related parameters described herein, at least in part, based on data from the microphone 140 and / or speaker 142.

[0048] In some embodiments, the sensor 130 includes (i) a first microphone which is the same as or similar to microphone 140 and integrated into acoustic sensor 141, and (ii) a second microphone which is the same as or similar to microphone 140 but is independent of and separate from the first microphone integrated into acoustic sensor 141.

[0049] The RF transmitter 148 generates and / or emits radio waves having a predetermined frequency and / or amplitude (e.g., within the high frequency band, within the low frequency band, long wave signal, short wave signal, etc.). The RF receiver 146 detects the reflection of the radio waves emitted from the RF transmitter 148, and this data can be analyzed by the control system 110 to determine the location of the user 210 (Figure 2) and / or one or more of the sleep-related parameters described herein. The RF receiver (either the RF receiver 146 and the RF transmitter 148 or another RF pair) can also be used for wireless communication between the control system 110, the respiratory device 122, one or more sensors 130, external devices 170, or any combination thereof. The RF receiver 146 and the RF transmitter 148 are shown in Figure 1 as separate, independent elements, but in some embodiments, the RF receiver 146 and the RF transmitter 148 are combined as part of an RF sensor 147. In some such embodiments, the RF sensor 147 includes a control circuit. Specific forms of RF communication can include WiFi, Bluetooth (registered trademark), and others.

[0050] In some embodiments, the RF sensor 147 is part of a mesh system. An example of a mesh system is a WiFi mesh system, which may include mesh nodes, mesh routers, and mesh gateways, each of which may be mobile / movable or fixed. In such embodiments, the WiFi mesh system includes WiFi routers and / or WiFi controllers, each of which includes an RF sensor identical or similar to the RF sensor 147, as well as one or more satellites (e.g., access points). The WiFi routers and satellites communicate with each other continuously using WiFi signals. The WiFi mesh system can be used to generate motion data based on changes in the WiFi signal between the routers and satellites (e.g., differences in received signal strength) due to the movement of objects or people partially interfering with the signal. This motion data may represent exercise, respiration, heart rate, walking, falls, behavior, or any combination thereof.

[0051] Camera 150 outputs image data that can be reproduced as one or more images (e.g., still images, moving images, thermal images, or a combination thereof) that can be stored in the storage device 114. Image data from camera 150 can be used by the control system 110 to determine one or more sleep-related parameters described herein. For example, image data from camera 150 can be used to identify the user's location, determine the time when user 210 goes to bed 230 (Figure 2), and determine the time when user 210 gets out of bed 230. In some implementations, image data from camera 150 can be used by the control system 110 to determine or facilitate the determination of user interface identification information and / or conduit identification information. For example, after reducing possible user interface identification information by analysis of airflow parameters to a few possibilities, image data (e.g., a photograph of the user interface can be requested) can be requested and used to determine or facilitate the determination of user interface identification information.

[0052] The infrared (IR) sensor 152 outputs infrared image data that can be reproduced as one or more infrared images (e.g., still images, moving images, or both) that can be stored in the storage device 114. The infrared data from the IR sensor 152 can be used to determine one or more sleep-related parameters during a sleep session, including the user 210's temperature and / or movement. The IR sensor 152 can also be used in combination with the camera 150 to measure the user 210's presence, location, and / or movement. In some implementations, the infrared data from the IR sensor 152 can be used to determine or facilitate the determination of user interface identification information and / or conduit identification information. The IR sensor 152 can detect infrared light having wavelengths between approximately 700 nm and 1 mm, for example, while the camera 150 can detect visible light having wavelengths between approximately 380 nm and 740 nm.

[0053] The PPG sensor 154 outputs physiological data related to user 210 (Figure 2) that can be used to determine one or more sleep-related parameters, such as heart rate, heart rate variability, cardiac cycle, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-to-expiratory ratio, estimated blood pressure parameters, or any combination thereof. The PPG sensor 154 can be worn by user 210 and embedded in clothing and / or fabric worn by user 210, or embedded and / or connected to user interface 124 and / or its associated headgear (e.g., straps).

[0054] The ECG sensor 156 outputs physiological data associated with the electrical activity of the user 210's heart. In some embodiments, the ECG sensor 156 includes one or more electrodes placed on or around a part of the user 210 during a sleep session. The physiological data from the ECG sensor 156 can be used to determine, for example, one or more sleep-related parameters as described herein.

[0055] The EEG sensor 158 outputs physiological data associated with the electrical activity of the user 210's brain. In some embodiments, the EEG sensor 158 includes one or more electrodes placed on or around the user 210's scalp during a sleep session. The physiological data from the EEG sensor 158 can be used, for example, to determine the user 210's sleep state 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 its associated headgear (e.g., a strap).

[0056] The capacity sensor 160, force sensor 162, and 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 sleep-related parameters as described herein. The EMG sensor 166 outputs physiological data associated with electrical activity produced by one or more muscles. The oxygen sensor 168 outputs oxygen data indicating the oxygen concentration of a gas (e.g., in the conduit 126 or in the user interface 124). The oxygen sensor 168 may be, for example, an ultrasonic oxygen sensor, an electro-oxygen sensor, a chemical oxygen sensor, an optical oxygen sensor, or any combination thereof. In some embodiments, one or more sensors 130 also include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a blood pressure sensor, an oxygen measurement sensor, or any combination thereof.

[0057] The sample sensor 174 can be used to detect the presence of a sample in the user 210's exhaled breath. The data output by the sample sensor 174 is stored in the storage device 114 and can be used by the control system 110 to determine the identity and concentration of any sample in the user 210's breath. In some embodiments, the sample sensor 174 is positioned near the user 210's mouth to detect a sample in the breath exhaled from the user 210's mouth. For example, if the user interface 124 is a face mask that covers the user 210's nose and mouth, the sample sensor 174 can be positioned inside the face mask to monitor the user 210's breathing. In other embodiments, for example, if the user interface 124 is a nasal mask or nasal pillow mask, the sample sensor 174 can be positioned near the user 210's nose to detect a sample in the exhaled breath from the user's nose. In yet another embodiment, if the user interface 124 is a nasal mask or nasal pillow mask, the sample sensor 174 can be positioned near the user 210's mouth. In this embodiment, the sample sensor 174 can be used to detect whether air is inadvertently leaking from the user 210's mouth. In some embodiments, the sample sensor 174 is a volatile organic compound (VOC) sensor that can be used to detect carbonaceous chemicals or carbonaceous compounds. In some embodiments, the sample sensor 174 can also be used to detect whether the user 210 is breathing through their nose or mouth. For example, if the presence of a sample is detected by data output from the sample sensor 174 located near the user 210's mouth or (in embodiments where the user interface 124 is a face mask) inside the face mask, the control system 110 can use this data as an indicator that the user 210 is breathing through their mouth.

[0058] The moisture sensor 176 outputs data that is stored in the storage device 114 and can be used by the control system 110. The moisture sensor 176 can be used to detect moisture in various areas surrounding the user (e.g., inside the conduit 126 or user interface 124, near the user 210's face, near the connection point between the conduit 126 and the user interface 124, near the connection point between the conduit 126 and the breathing device 122, etc.). Thus, in some embodiments, the moisture sensor 176 can be placed inside the user interface 124 or conduit 126 to monitor the humidity of the pressurized air from the breathing device 122. In other embodiments, the moisture sensor 176 can be placed near any area where the moisture level needs to be monitored. The moisture sensor 176 can also be used to monitor, for example, the moisture in the air in a bedroom, or the surrounding environment surrounding the user 210.

[0059] The LiDAR (Light Detection and Ranging) sensor 178 can be used for depth sensing. Such optical sensors (e.g., laser sensors) can be used to detect objects and create three-dimensional (3D) maps of the surrounding environment, such as living spaces. LiDAR generally uses pulsed lasers to measure time of flight. LiDAR is also called 3D laser scanning. In one use case of such a sensor, a stationary or mobile device (such as a smartphone) having the LiDAR sensor 178 can measure and map an area more than 5 meters away from the sensor. LiDAR data can be fused with point cloud data estimated by, for example, an electromagnetic RADAR sensor. The LiDAR sensor 178 can also use artificial intelligence (AI) to automatically create geofencing for a RADAR system by detecting and classifying features in 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 estimate a person's height, as well as changes in height that occur when a person is sitting, falling, etc. LiDAR can be used to form a 3D mesh representation of the environment. In further applications, LiDAR can be reflected off solid surfaces (e.g., radio wave-transparent materials) through which radio waves pass, enabling the classification of different types of obstacles. In some implementations, LiDAR data from the LiDAR sensor 178 can be used to determine or facilitate the determination of user interface identification information and / or conduit identification information.

[0060] Although shown separately in Figure 1, any combination of one or more sensors 130 can be integrated and / or coupled to any one or more components of system 100, including the breathing apparatus 122, user interface 124, conduit 126, humidifier tank 129, control system 110, external device 170, or any combination thereof. For example, the microphone 140 and speaker 142 are integrated and / or coupled to the external device 170, while the pressure sensor 130 and / or flow sensor 132 are integrated and / or coupled to the breathing apparatus 122. In some embodiments, at least one of the one or more sensors 130 is not connected to the breathing apparatus 122, control system 110, or external device 170, but is positioned generally adjacent to the user 210 during a sleep session (e.g., positioned on or in contact with part of the user 210, worn by the user 210, connected to or positioned on a nightstand, connected to a mattress, connected to the ceiling, etc.).

[0061] For example, as shown in Figure 2, one or more of the sensors 130 can be placed at a first position 250A on the nightstand 240 adjacent to the bed 230 and user 210. Alternatively, one or more of the sensors 130 can be placed at a second position 250B on and / or within the mattress 232 (e.g., the sensors are coupled and / or integrated with the mattress 232). Another option is to place one or more of the sensors 130 at a third position 250C on the bed 230 (e.g., the auxiliary sensor 140 is coupled and / or integrated on the headboard, footboard, or other position on the frame of the bed 230). Finally, one or more of the sensors 130 can generally be placed at a fourth position 250D on the wall or ceiling adjacent to the bed 230 and / or user 210. One or more of the sensors 130 can be positioned at a fifth position 250E such that one or more of the sensors 130 are coupled to the housing of the respiratory device 122 of the respiratory system 120 and / or are located on and / or inside the housing. Alternatively, one or more of the sensors 130 can be positioned at a sixth position 250F such that they are coupled to and / or positioned on the user 210 (for example, the sensors are embedded in or coupled to the fabric, clothing worn by the user 210 during a sleep session). More generally, one or more of the sensors 130 can be positioned at any suitable location relative to the user 210 so that one or more sensors 140 can generate physiological data related to the user 210 and / or the person sharing the bed 220 during one or more sleep sessions.

[0062] Returning to Figure 1, the external device 170 includes a processor 172, a memory 174, and a display device 176. The external device 170 may be, for example, a mobile device such as a smartphone, tablet, or laptop computer. The processor 172 is the same as or similar to the processor 112 of the control system 110. Similarly, the memory 174 is the same as or similar to the storage device 114 of the control system 110. The display device 176 is generally used to display images, including still images, moving images, or both. In some embodiments, the display device 176 functions as a human-machine interface (HMI) including a graphical user interface (GUI) and an input interface configured to display images. The display device 176 may be an LED display, an OLED display, an LCD display, etc. The input interface may be, for example, a touchscreen or touch sensor board, a mouse, a keyboard, or any sensor system configured to sense input made by a human user interacting with the external device 170.

[0063] The control system 110 and the storage device 114 are described and shown in Figure 1 as separate components of system 100, but in some embodiments, the control system 110 and / or the storage device 114 are integrated into the external device 170 and / or the respiratory device 122. Alternatively, in some embodiments, the control system 110 or a part thereof (e.g., the processor 112) may be located in the cloud (e.g., integrated into a server, integrated into an Internet of Things (IoT) device, connected to the cloud, and subjected to edge cloud processing), or on one or more servers (e.g., remote servers, local servers, etc., or any combination thereof).

[0064] System 100 is shown as including all of the above components, but a system for automatically determining user interface identification information may include more or fewer components. For example, a first alternative system includes a control system 110, a breathing system 120, and at least one of one or more sensors 130. Another example is a second alternative system which includes a breathing system 120, one or more sensors 130, and an external device 170. Yet another example is a third alternative system which includes a control system 110 and one or more auxiliary sensors 140. Thus, any part of the components shown and described herein can be used and / or combined with one or more other components to form a variety of systems for determining sleep-related parameters associated with a sleep session.

[0065] Figure 3 is a flowchart of a process 300 for analyzing airflow parameters according to some aspects of the present disclosure to determine a user interface and / or conduit identification information. The process 300 can be performed on any suitable system, such as the control system 110 of the system 100 in Figure 1.

[0066] In block 302, airflow can be generated through a user interface (e.g., user interface 124 in Figure 1). The airflow can be generated by a breathing apparatus, or more specifically, by a flow generator in the breathing apparatus. In some implementations, the flow generator can operate with a specific set of settings or parameters. For example, the flow generator may include a fan driven at a certain speed or speed mode.

[0067] In some implementations, generating airflow in block 302 may involve generating known adjustments to the airflow (e.g., outside the normal operating process of respiratory therapy) and returning the known adjustments to the airflow. The airflow parameters measured before, during, and / or after the adjustment can be used to determine the user interface and / or conduit identification information. For example, in some implementations, generating airflow in block 302 may involve causing a transient increase in airflow rate to facilitate the determination of the user interface and / or conduit identification information by detecting the adjustment of the measured airflow parameters and / or the response to the adjustment of the measured airflow parameters. For example, fluctuations due to flow rate and / or pressure can be generated, and the response to the generated fluctuations can be used to facilitate the determination of the user interface and / or conduit identification information.

[0068] In block 304, sensor data can be received. Sensor data can be received from one or more sensors (for example, one or more sensors 130 in Figure 1). Receiving sensor data may include measuring airflow parameters of the airflow generated in block 302, such as flow rate, pressure, or both flow rate and pressure. In some implementations, other parameters of the airflow can be measured in block 304. Measuring airflow parameters may include generating signals that indicate the airflow parameters corresponding to changes over time by measuring the time-dependent airflow parameters. For example, a flow rate signal may indicate the time-dependent flow rate of the airflow generated from block 302. In another example, a pressure signal may indicate the time-dependent pressure of the airflow generated from block 302.

[0069] In some implementations, receiving sensor data in block 304 may further include receiving other sensor data such as audio data, image data, and physiological data. In some implementations, receiving such other sensor data may be performed in response to user prompts via a graphical user interface that requests additional data, as described later with reference to block 314. In some implementations, receiving sensor data in block 304 may further include receiving detected flow generator information, such as the fan speed of the flow generator fan.

[0070] In some implementations, receiving sensor data in block 304 can occur in real time or near real time relative to when the sensor data is acquired. For example, in such an implementation, process 300 can be used to automatically determine user interface and / or conduit identification information (e.g., identifying the user interface, user interface characteristics, conduit, conduit characteristics, or any combination thereof) in real time or near real time. However, in other implementations, receiving sensor data in block 304 may be asynchronous (e.g., asynchronous with the acquisition of sensor data). In such implementations, the sensor data acquired by the system may be stored in memory or elsewhere until such time is used to determine the user interface and / or conduit identification information. For example, in such an implementation, the airflow generated in block 302 can occur when the user is sleeping and using the system, at which time sensor data can be acquired and stored. A little later, such as after the sleep session has ended, the system can receive the sensor data in block 304 and continue processing the sensor data to determine the user interface and / or conduit identification information.

[0071] In some implementations, receiving sensor data in block 304 includes receiving a first set of sensor data when the user is wearing the user interface and receiving a second set of sensor data when the user is not wearing the user interface. In such implementations, this sensor data (e.g., the first set of sensor data and the second set of sensor data) can be used to identify the user interface and / or conduit identification information. Since different user interfaces may show different sensor data changes between when the user interface is being worn and when it is not, such data is useful in facilitating the identification of the user interface and / or conduit identification information.

[0072] In some implementations, an optional block 326 may receive and supply supplemental parameters that can be used while block 306 identifies the user interface and / or conduit identification information. Such supplemental parameters may include flow generator parameters and physiological data related to the system. Flow generator parameters may include any parameters or other information related to the flow generator or other parts of the respiratory system. Specific examples of flow generator parameters include the presence of a humidifier, information about the humidifier (e.g., model or operating characteristics), inlet filter information (e.g., type, shape or other characteristics), inlet baffle information (e.g., type, shape or other characteristics), motor information (e.g., type, shape or other characteristics of the flow generator motor), outlet baffle information (e.g., type, shape or other characteristics), and expiratory pressure release settings. Physiological data related to the system may be any appropriate physiological data determined individually by the system, such as central apnea detection information.

[0073] In block 306, user interface and / or conduit identification information can be identified using sensor data received from block 304. Identifying user interface and / or conduit identification information may include identifying user interface identification information, identifying conduit identification information, or identifying both user interface and conduit identification information. Identifying user interface identification information may include identifying a specific user interface, a model of the user interface, a manufacturer of the user interface, a pattern of the user interface, or several other characteristics of the user interface. Identifying conduit identification information may include identifying a specific conduit, a model of the conduit, a manufacturer of the conduit, a pattern of the conduit (e.g., shape of the conduit, diameter of the conduit (e.g., conduit with an inner diameter of 12 mm, 15 mm, or 19 mm), length of the conduit, etc.), or several other characteristics of the conduit. Identification of user interface and / or conduit identification information can be achieved by different techniques.

[0074] In some implementations, identifying user interface and / or conduit identification information may include identifying the user interface and / or conduit pattern from possible user interface and / or conduit pattern cells. In some implementations, a broad determination of the user interface and / or conduit pattern can be made quickly and easily from sensor data. After determining the user interface and / or conduit pattern, other characteristics can be more easily determined from the sensor data. For example, after determining the user interface and / or conduit pattern, the system can more easily determine the model and / or manufacturer of the user interface and / or conduit. For example, a different algorithm or model can be applied to sensor data from a nose pillow user interface than the algorithm or model applied to sensor data from a mask user interface. However, in some implementations, the user interface and / or conduit pattern does not need to be determined beforehand or individually.

[0075] In some implementations, identifying user interface and / or conduit identification information may involve applying a machine learning model, such as sensor data received from block 304, to incoming data in block 312. Any suitable machine learning model or algorithm can be used. In some implementations, using a machine learning model (e.g., a deep neural network) as the neural network model may be particularly useful. In some implementations, a recurrent neural network model can be used to effectively identify user interface and / or conduit identification information from input data such as airflow parameter signals (e.g., flow rate signals and pressure signals). When using a recurrent neural network, the recurrent neural network may be a long-short-term memory recurrent neural network. In some implementations, a convolutional neural network model can be used to effectively identify user interface and / or conduit identification information from input data such as diagrams of airflow parameters (e.g., flow rate maps and pressure maps). In some implementations, a combination of multiple neural networks can be used.

[0076] In some implementations, identifying the user interface and / or conduit identification information in block 306 may involve generating a spectral map using airflow parameters and applying that spectral map to a deep neural network (e.g., a convolutional neural network).

[0077] The machine learning model used in block 312 may be pre-trained. The machine learning model can be trained using appropriate training data for the input data used with the model. For example, in some implementations, a machine learning model that receives flow and pressure signals and generates user interface and / or conduit identification information can be trained using a corpus containing data for flow signals, associated pressure signals, and associated user interface and / or conduit identification information. In some implementations, the machine learning model is trained using a corpus of flow signal data and pressure signal data across multiple different user interfaces and / or conduits. Any appropriate training program can be used.

[0078] In some implementations, applying a machine learning model in block 312 may involve directly providing the machine learning model with received data (e.g., sensor data such as flow and pressure signals). For example, the input to the machine learning model may include flow and pressure signals. However, in some implementations, applying a machine learning model in block 312 may involve providing features extracted from the received data. In such implementations, identifying the user interface and / or conduit identification information may involve determining features in block 310. Features can be determined in any suitable way, for example, by analyzing sensor data using an algorithm or machine learning model.

[0079] In some implementations, characterization in block 310 may include determining one or more resonant frequencies associated with a fluid system including a flow generator, conduits, and a user interface. The determination of resonant frequencies, including applying cepstrum analysis to airflow parameters (e.g., flow signal and / or pressure signal), may be performed in any suitable manner. Since different user interfaces and / or conduits may have different characteristics that result in different resonant frequencies in the fluid system, one or more resonant frequencies associated with the fluid system may be useful features for identifying user interface and / or conduit identification information.

[0080] In some implementations, defining features in block 310 may include determining leakage signals, such as unintended leakage signals. Unintended leakage signals may be prompts for the presence and / or intensity of any unintended leakage that changes over time during use of the user interface. Unintended leakage can occur through inadequate sealing portions of the user interface and / or conduit (e.g., between the user interface and the user or other location, e.g., between the user interface and the conduit). The presence and / or other information related to unintended leakage may indicate the type of user interface and / or conduit or other user interface and / or conduit identification information. For example, the type of unintended leakage that occurs when the user interface is removed may differ for a full-face user interface and a nose pillow user interface. In some implementations, other information related to the user's sleep session, such as sleeping position (e.g., supine, prone, left side, or right side), may be used in conjunction with unintended leakage signals to facilitate the determination of user interface and / or conduit identification information. For example, some user interfaces and / or conduits are likely to exhibit unintended leakage in some sleeping positions. As another example, certain user interfaces and / or conduits can make it less likely that a user will enter a particular sleeping position. For example, if no unintended leak is detected, but it is detected that the user is sleeping in a prone position, the user can be informed that a particular user interface (e.g., a full-face user interface) is not being used. Unintended leaks do not include intentionally diverting air through one or more vents in the user interface and / or conduits.

[0081] In some implementations, determining a leak signal may include determining an intentional leak signal. An intentional leak signal may be a prompt indicating the presence and / or intensity of an intentional leak of any temporal change during use of the user interface. An intentional leak may include, during the application of respiratory therapy, airflow passing through one or more vents of the user interface and / or conduit, or otherwise intentionally moving away from the user interface and / or conduit. The presence and / or other information related to an intentional leak may indicate the type of user interface and / or conduit or other user interface and / or conduit identification information. In some implementations, other information related to the user's sleep session, such as sleeping position (e.g., supine, prone, left side, or right side), may be used in conjunction with the intentional leak signal to facilitate the determination of user interface and / or conduit identification information. For example, for different user interfaces (e.g., due to the location and design of the vents, as well as other features of the user interface) and / or conduit, some sleeping positions may have different effects on intentional leaks. For example, a top-down or overhead user interface may include vents that can be blocked in several sleeping positions, and such a user interface may be able to show intentional leakage signals that differ from those of a nose pillow user interface.

[0082] In some implementations, intentional leak signals (e.g., airflow through one or more vents in a user interface) can be characterized by different airflow parameters (e.g., under one or more therapeutic pressures). Changes in intentional leak signals at these different airflow parameters can be used to identify user interfaces and / or conduits. For example, different user interfaces and / or conduits may exhibit different characteristics regarding how they respond to changes in airflow parameters (e.g., changes in flow rate or therapeutic pressure). As an example, a particular conduit may exhibit different pressure drops along its length depending on the total flow rate, or in other words, the exhibited pressure drop is a function of the total flow rate through the conduit. This function may differ in different conduits and may therefore be a characteristic that can be used to distinguish conduits from others (e.g., to identify the conduit pattern, model, and / or manufacturer). Similarly, characteristic responses associated with a user interface (e.g., a vent in the user interface) in response to changes in airflow parameters can be used to distinguish this user interface from other user interfaces (e.g., to identify the pattern, model, and / or manufacturer of the user interface).

[0083] In some implementations, defining features in block 310 may include determining a nasal-mouth breathing signal. The nasal-mouth breathing signal may be a prompt for a change over time in whether the user is breathing through their nose (e.g., nasal breathing), their mouth (e.g., mouth breathing), or a combination thereof. Since different user interfaces and / or conduits may respond differently to the presence of nasal breathing and / or mouth breathing or to changes between nasal and mouth breathing, the nasal-mouth breathing signal may be a useful feature for identifying user interface and / or conduit identification information. For example, characteristic flattening of a flow signal (e.g., flow waveform) during the exhalation phase of breathing may indicate air leaking from the mouth, indicating the presence of a nasal mask or nasal pillow pattern user interface.

[0084] In some implementations, defining features in block 310 may include determining a volumetric breathing signal. The volumetric breathing signal may be a prompt for changes in inspiratory and / or expiratory volume over time. In some implementations, the volumetric breathing signal may be a useful feature for identifying a user interface and / or conduit identification information. For example, a volumetric breathing signal indicating that the inspiratory volume is greater than the expiratory volume may indicate air leaking from the mouth, indicating the presence of a nasal mask or nasal pillow pattern user interface.

[0085] In some implementations, defining features in block 310 may include determining a sustained breathing signal. The sustained breathing signal may also be a prompt for changes in inhalation duration and / or expiratory duration over time. In some implementations, the sustained breathing signal may be a useful feature for identifying the user interface and / or conduit identification information. The sustained breathing signal can serve as a useful feature for a machine learning model trained on training data containing the sustained breathing signal.

[0086] In some implementations, defining features in block 310 may involve determining one or more packets of frequency components of airflow parameters (e.g., flow rate signals and / or pressure signals). These frequency component packets may contain signal components below or above a threshold frequency. The frequency components can be represented as frequency and intensity, such as through a time-domain to frequency-domain transformation (e.g., Fast Fourier Transform). One or more frequency component packets can be used as input to a machine learning model or to filter out unwanted data from one or more signals.

[0087] In some implementations, determining one or more packets of frequency components includes determining high-frequency components that may include components above a high-frequency threshold frequency. In some implementations, high-frequency components include components higher than the baseline respiratory rate or other respiratory rate thresholds (e.g., the maximum respiratory rate identified in current and / or historical sensor data, or a percentage higher than the baseline respiratory rate). Such high-frequency components are also called "AC" components in the same sense as alternating current electricity, and may include rapidly occurring effects such as fluctuations due to the rotation of a flow generator fan. In some implementations, if the analyzed signal identifies user interface and / or conduit identification information, it is desirable to remove high-frequency components from the signal (e.g., flow signal or pressure signal) because the characteristics of the user interface and / or conduit often do not affect signals at high frequencies. In some implementations, determining one or more packets of frequency components may include determining non-high-frequency components, or all non-high-frequency components (e.g., all frequency components below the baseline respiratory rate).

[0088] In some implementations, determining one or more packets of frequency components involves determining low-frequency components that may include components below a low-frequency threshold frequency. In some implementations, the low-frequency components include components lower than a baseline respiratory rate or other respiratory rate threshold (e.g., the minimum respiratory rate identified in current and / or historical sensor data, or a percentage lower than such a respiratory rate). For example, the low-frequency threshold may be 0.5 Hz, 0.25 Hz, 0.125 Hz, 0.0625 Hz, etc. Such low-frequency components are also called "DC" components in the same sense as direct current, and may include the effects of gradual changes and / or steady states, such as the characteristics of the user interface and / or conduit (e.g., the fluid impedance of the user interface and / or conduit). In some implementations, the impedance signal can be determined from the low-frequency components. In some implementations, since the characteristics of the user interface and / or conduit tend to have the greatest influence at low frequencies, it is desirable to use such low-frequency components to identify user interface and / or conduit identification information.

[0089] In some implementations, determining one or more packets of frequency components involves determining a mid-frequency component that may include components between a low-frequency threshold frequency (e.g., the low-frequency threshold frequency described above) and a high-frequency threshold frequency (e.g., baseline breathing rate). Such a mid-frequency component may include signals modified at mid-frequency, which may include user influences related to the use of the user interface and / or conduit. For example, when a user uses the user interface, the user's breathing and movements, and the user interface and / or conduit's response to such breathing and movements, may generate a mid-frequency component. In some implementations, the mid-frequency component may indicate unintended leakage within the user interface and / or conduit, and in some cases, an unintended leakage signal can be determined from the mid-frequency component. In some implementations, since the characteristics of the user interface and / or conduit tend to affect such mid-frequency components, it is desirable to use such mid-frequency components to identify user interface and / or conduit identifiers.

[0090] In some implementations, identifying user interface and / or conduit identification information in block 306 may include identifying transient events in airflow parameters. Transient events may include removal and / or adjustment of the user interface and / or conduit, changes in user position during sleep (e.g., movement between sleeping positions or movement on the bed), changes in therapeutic pressure (e.g., changes in automatic positive airway pressure), or other such actions that result in transients in the airflow parameter signal. The transient itself and / or the response to the transient can be used to facilitate the identification of user interface and / or conduit identification information. For example, different user interfaces and / or conduits may respond to users wearing the user interface and / or connecting to the conduit in different identifiable ways, such as detected in the airflow parameters. As another example, different user interfaces and / or conduits may respond differently to users changing position on the bed. For example, a user interface with more substantial fastening features (e.g., a belt) and / or better seal than other user interfaces may represent differently before, during, and / or after a detected transient event (e.g., a detected change in user position on the bed). Such discrepancies associated with detected transient events are useful for identifying user interface and / or conduit identification information.

[0091] In some implementations, identifying user interface and / or conduit identification information in block 306 may include identifying breathing shapes associated with user breathing using airflow parameters. Breathing shapes may be provided to a machine learning model as input data (e.g., as image files provided to a convolutional neural network) or compared to template breathing shapes. In some implementations, a machine learning model can be trained on template breathing shapes. One or more template breathing shapes may be acquired for multiple different user interfaces and / or conduits, so as to facilitate the identification of user interfaces and / or conduits based on the identified breathing shapes using identifiable features of the breathing shapes.

[0092] In some implementations, identifying user interface and / or conduit identification information in block 306 may include requesting and receiving additional data in block 314. In some implementations, if it is determined that additional data is necessary to select the correct user interface and / or conduit identification information from user interface and / or conduit cells, additional data may be requested in block 314. For example, if applying a machine learning model in block 312 results in determining only the pattern and / or manufacturer of the user interface and / or conduit, the system may request additional information from the user to facilitate further identification of the user interface and / or conduit model from user interface and / or conduit cells that match the identified pattern and / or manufacturer. In some implementations, if user interface and / or conduit identification information is identified with a confidence level below a threshold level, additional data may be requested in block 314. For example, if applying a machine learning model in block 312 results in identifying user interface and / or conduit identification information with a relatively low level of confidence, an attempt can be made to improve the confidence level and / or to request additional data from the user to confirm that only the identified user interface and / or conduit identification information is correct. Additional data may be requested by the user of the respiratory therapy system or another user (e.g., a medical professional or caregiver).

[0093] In some implementations, requesting and receiving additional data in block 314 may include generating and presenting a confirmation request indicating the most possible user interface and / or conduit identification information, and receiving a response to the confirmation request indicating whether the most possible user interface and / or conduit identification information is correct or incorrect.

[0094] In some implementations, requesting and receiving additional data in block 314 may include generating and presenting a request for purchase history information. In some implementations, after receiving authorization to access the purchase history information, such purchase history information can be used to facilitate the identification of user interfaces and / or conduit identification information. For example, if three possible user interfaces are identified but only one exists in the purchase history, the system can select this user interface as the identified user interface. In other implementations, in response to a request for purchase history information, other information related to the purchase history of the user interface and / or conduit (e.g., a receipt or photograph of the resale package) may be provided. In such implementations, the purchase history information can be used to facilitate the identification of user interfaces and / or conduit identification information.

[0095] In some implementations, requesting and receiving additional data in block 314 may include generating and presenting a request for additional sensor data, receiving additional sensor data, and using the additional sensor data (similar to the sensor data received from block 304) to identify the user interface and / or conduit identification information. This additional sensor data may include audio data (e.g., audio recordings of the air passing through the user interface and / or conduit), imaging data (e.g., photographs, videos, infrared images, LiDAR scans, thermal images, or other images of the user interface and / or conduit).

[0096] In some implementations, requesting and receiving additional data in block 314 may involve generating one or more questions, presenting these questions to the user, receiving responses to these questions, and using these responses to facilitate the identification of the user interface and / or conduit identification information. For example, the system may present the user with a series of questions such as, "Is your user interface being used?", "Was your user interface worn from 11:00 p.m. to 11:30 p.m. last night?", or other such questions. The user can provide answers to these questions. Based on these answers, process 300 can identify the user interface and / or conduit identification information. For example, an answer to a later question about whether the user interface was used within a given time period can help the system know how to analyze the sensor data, since sensor data acquired when the user interface was not being worn may be processed or interpreted differently from sensor data acquired when the user interface was being worn. Responses to such questions may be used in other ways.

[0097] In some implementations, identifying the user interface and / or conduit identification information in block 306 may include receiving historical data in block 316. The received historical data may include sensor data received in previous examples in block 304, such as sensor data from the previous night, the previous week, or other times. The historical data received in block 316 may include the same user associated with the sensor data received from block 304. The historical data may include airflow parameters such as flow rate and pressure, and other data. The historical data can be used to facilitate the processing and / or analysis of the sensor data received from block 304. For example, the historical data can be used to identify changes in baseline respiratory rate by comparing it with the sensor data received in block 304, and / or to identify a baseline respiratory rate that can normalize the received sensor data based on the baseline respiratory rate identified from the historical data. In some implementations, the historical data may include sensor data received in previous sleep sessions (e.g., sleep sessions started the previous day). In some implementations, the historical data may include sensor data received in at least 24 hours prior to acquiring the sensor data received in block 304.

[0098] Identifying user interface identification information in block 306 can yield information that can be used to identify the characteristics of the user interface. In some implementations, the user interface identification information is the pattern, model, or manufacturer of the user interface. This information can be used to identify one or more other characteristics of the user interface. For example, a particular model of a user interface may indicate a particular airflow impedance. In another example, a user interface of a particular pattern (e.g., a nose pillow) may indicate a resonant frequency that is different or absent in user interfaces of other patterns (e.g., a mask), which can affect the airflow through the user interface. Examples of characteristics that can be identified for a particular user interface include the pattern of the user interface, the model of the user interface, the manufacturer of the user interface, one or more resonant frequencies of the user interface, the fluid impedance of the user interface, the fluid resistance of the user interface, the presence, number, and / or pattern of vents in the user interface, and / or other features or characteristics of the user interface.

[0099] Identifying conduit identification information in block 306 can generate information usable to identify the characteristics of conduits connecting the user interface to the respiratory therapy device. In some implementations, conduit identification information is the conduit pattern, model, or manufacturer. This information can be used to identify one or more other characteristics of the conduit. For example, a particular type of conduit may exhibit a specific resistance to airflow. In another example, a conduit with a particular pattern (e.g., a heated conduit) may exhibit a resonant frequency that is different or absent in other conduit patterns (e.g., an unheated conduit) that can affect the airflow through the conduit. Examples of characteristics that can be identified for a particular conduit include the conduit pattern, conduit model, conduit manufacturer, one or more resonant frequencies of the conduit, conduit fluid impedance, conduit fluid resistance, and / or other features or characteristics of the conduit.

[0100] In some implementations, identifying user interface and / or conduit identification information in block 306 may include determining a confidence level associated with the identified user interface and / or conduit identification information. Such a confidence level can be expressed as a number or percentage indicating how the system determines the accuracy of the identified user interface and / or conduit identification information. In some implementations, one or more confidence thresholds may be set to determine when some of the actions described herein are taken. For example, as described above, in block 314, a confidence level below a certain threshold may present the request and reception of additional data. In another example, a confidence level above a certain threshold may be required before adjusting the airflow generation in block 320, as will be further detailed below.

[0101] In some implementations, flow generator identification information can be determined separately in a selective block 308, along with, or in addition to, determining the user interface and / or conduit identification information in block 306. Flow generator identification information can be determined in block 308 in the same or similar manner as how the user interface and / or conduit identification information is determined in block 306. For example, flow generator identification information can be identified from sensor data received in block 304 by using the same or different machine learning models. It should be understood that the explanations and examples of how the user interface and / or conduit identification is determined, as described herein, can be applied to flow generator identification information.

[0102] Identifying flow generator identification information in block 308 can generate information that can be used to identify the characteristics of the flow generator supplying airflow to the user interface. In some implementations, the flow generator identification information is the flow generator pattern, model, or manufacturer. This information can be used to identify one or more other characteristics of the flow generator. For example, a particular type of flow generator may represent a particular pattern of high-frequency components in the airflow parameter signal. Examples of characteristics that can be identified for a particular flow generator include the flow generator pattern, the flow generator type, the flow generator manufacturer, one or more resonant frequencies of the flow generator, and / or other features or characteristics of the flow generator. As described above with reference to identifying user interface and / or conduit identification information in block 306, identifying flow generator identification information in block 308 may include determining features, similar to determining features in block 310 and applying a machine learning model in block 312; requesting and receiving additional data, similar to requesting and receiving additional data in block 314; receiving historical data, similar to receiving historical data in block 316; or any combination thereof.

[0103] In block 318, user interface and / or conduit identification information from block 306, and optionally flow generator identification information from block 308, can be used. This identification information can be used to perform one or more actions, such as adjusting airflow generation in block 320, presenting the user interface and / or conduit identification in block 322, and / or generating notifications in block 324.

[0104] In block 320, the generation of airflow through the user interface may be adjusted based on identified user interface and / or conduit identification information from block 320. Adjusting airflow generation in block 320 may include adjusting one or more settings of the breathing apparatus so that future airflow is generated in a different way than in block 302. For example, adjusting airflow generation may include driving the motor of the flow generator at a different speed or in a different speed mode. In some implementations, adjusting airflow generation in block 320 may use the identification of user interface and / or conduit identification information obtained from airflow parameters, or, in addition to using user interface and / or conduit identification information, use airflow parameters. In some implementations, adjusting airflow generation in block 320 includes determining that the identified user interface and / or conduit identification information is different from existing user interface and / or conduit identification information (e.g., previously stored or previously set user interface and / or conduit identification information stored in the system).

[0105] In block 322, user interface and / or conduit identification information can be presented to the user, caregiver, or other person. Presenting user interface and / or conduit identification information may include transmitting a transmission to an external device so that, upon receiving the transmission, the external device generates a display on a graphical user interface based on the user interface and / or conduit identification information. For example, the system may transmit a transmission containing a model of a user interface and / or conduit, such as the one identified in block 306. Upon receiving the transmission, the external device can generate a display showing the model of the user interface and / or conduit. In some implementations, this display may be inherently message-oriented, such as graphically displaying the correct model of the user interface and / or conduit, showing the correct wearing command for wearing this user interface based on this model of the user interface, showing the correct connection command for connecting this conduit based on this model of the conduit, or warning the user or caregiver that the detected user interface and / or conduit is different from the expected user interface and / or conduit (e.g., compared to the existing settings of the respiratory device). In some implementations, this display may be a prompt requesting confirmation from the user, which can be used to implement other actions (e.g., adjusting airflow generation) and / or to further train a machine learning model.

[0106] In block 324, a notification can be generated based on user interface and / or conduit identification information (and / or other identification information). This notification may be any appropriate notification, such as a notification that the detected user interface and / or conduit does not align with the expected user interface and / or conduit. For example, the system can access a setting stored in the system (e.g., existing user interface and / or conduit identification information) that indicates the user interface and / or conduit to be used with the system (e.g., one that has been previously determined or previously configured), and compare this stored setting with the user interface and / or conduit identification information identified in block 306. If this comparison determines that the user interface and / or conduit do not match, a notification can be generated to inform the user, thereby allowing the user to take any necessary action, such as switching the settings on the system or switching the user interface and / or conduit.

[0107] In process 300, the blocks are shown in one configuration, but in other cases, these blocks may be executed in a different order, with additional blocks and / or some blocks being removed.

[0108] Figure 4 is a graph 400 showing exemplary flow signals 410 that can be used to identify user interface and / or conduit identification information according to some aspects of the present disclosure. The flow signal 410 is a representation of flow rate (y-axis) as a function of time (x-axis) during a sleep session when a user is using a respiratory therapy system. The flow signal 410 can be acquired by one or more sensors, such as the flow sensor 134 in Figure 1.

[0109] The flow signal 410 indicates a repetitive mode representing a repetitive breathing cycle 402. Line 404 can represent nominal flow rate or zero flow rate. When the user breathes, the flow signal 410 is on line 404. When the user exhales, the flow signal 410 is lower than line 404. Therefore, within each breathing period 402, a single exhalation can extend from the end of the inspiratory point 406 to the end of the expiratory point 408. Similarly, a single inspiratory can extend from the end of the expiratory point 408 to the end of the inspiratory point 406. Therefore, the volume of a single inspiratory may be the area between line 404 and the flow signal 410 between the expiratory point 408 and the inspiratory point 406. Similarly, the volume of a single exhalation may be the area between line 404 and the flow signal 410 between the inspiratory point 406 and the expiratory point 408.

[0110] Various features can be extracted from the flow signal 410, as illustrated by referring to the feature determination in block 310 of Figure 3. For example, the flow signal 410 may include minimum flow rate, maximum flow rate, area of ​​one or two respiratory stages (e.g., inspiration and expiration), rise time (e.g., time from minimum flow rate to zero and / or time from zero to peak flow rate), fall time (e.g., time from maximum flow rate to zero and / or time from zero to minimum flow rate), ratios between other features (ratio of rise time to fall time or ratio of inspiration area to expiration area), skewness present in the flow signal 410, kurtosis of any part of the flow signal 410, etc. In some implementations, features can be extracted from the flow signal 410 to more easily analyze the rate of change of the signal by analyzing the first and / or second derivatives of the flow signal 410.

[0111] As disclosed herein, for example, referring to Figure 3, the flow signal 410 can be used to identify the user interface and / or conduit identification information. In some implementations, data from the flow signal 410 may be applied directly to a machine learning algorithm or used to extract features that can be used as input to a machine learning algorithm. For example, some graphic drawings and / or spectrograms of the flow signal 410 can serve as input to a convolutional neural network to facilitate the identification of the user interface and / or conduit identification information.

[0112] Figure 5 is a flowchart of a process 500 for analyzing pressure and flow rate data to determine a user interface and / or conduit identification information, relating to several implementations of the present disclosure. Process 500 can be executed on any suitable system, as it is executed on the control system 110 of system 100 in Figure 1. In some implementations, process 500 can be executed as part of process 300 in Figure 3, as it is incorporated as part of block 306 in Figure 3. In some implementations, process 500 can be executed in real time, although this is not always the case.

[0113] In block 502, pressure data and flow rate data are received. The pressure data and flow rate data may be pressure data and flow rate data acquired by a flow rate generator (e.g., blower pressure and blower flow rate, respectively), and may be presented in any appropriate unit (e.g., cmH2O for pressure data and L / min for flow rate data). In some implementations, the pressure data and / or flow rate (e.g., flow rate) data may be received as time-dependent data streams (e.g., pressure signal and flow rate signal).

[0114] In block 504, pressure data and flow rate data are processed to generate one or more data points. Each data point may include a pressure value and a corresponding flow rate value at a given time point. The number of data points generated may depend at least in part on the duration of the ongoing treatment course and the sampling rate. For example, a 10-minute session with a sampling rate of 10 Hz may generate 6000 data points. The one or more data points generated in block 504 may be a point cloud. If necessary, such a point cloud can be visualized on a two-dimensional histogram (e.g., a 2D histogram with flow rate on the X axis and pressure on the Y axis). As used herein, a point cloud may include a set of data points (e.g., each data point includes a pressure value and a corresponding flow rate value at a given time point).

[0115] In some implementations, processing the received pressure and flow rate data in block 506 may include identifying and removing data (e.g., pressure and flow rate data) related to unintended leaks and / or the user interface not being worn by the user. Identifying data related to unintended leaks may include identifying one or more durations during which the unintended leaks occurred. Removing data related to unintended leaks may include excluding any pressure and flow rate data, or excluding data points related to each identified duration during which the unintended leaks occurred. Identifying data related to the user interface not being worn by the user may include identifying one or more durations during which it was determined that the user interface was not being worn by the user. Removing data related to the user interface not being worn by the user may include excluding any pressure and flow rate data, or excluding data points related to durations during which it was determined that the user interface was not being worn by the user.

[0116] In some implementations, processing the received pressure and flow rate data may include removing respiratory artifacts in block 508. Removing respiratory artifacts may include filtering the received pressure and flow rate data to remove information or artifacts that may be attributable to the user's breathing. In some implementations, removing respiratory artifacts may include applying a low-pass filter to each of the received pressure and flow rate data (e.g., applying the filter to the pressure signal and the flow rate signal). This low-pass filter may include applying an averaging filter over a duration of, for example, 30 seconds to 1 minute. In some implementations, removing respiratory artifacts may include filtering the received pressure and flow rate data based on respiratory stage analysis. For example, in some implementations, respiratory artifacts can be removed by selectively removing all data points related to transitional stages of user breathing (e.g., during inspiration or expiration). Thus, only the remaining data points are related to steady-state stages of user breathing (e.g., the steady state between inspiration and expiration). In some implementations, removing respiratory artifacts may include removing artifacts resulting from intentional leaks. Any suitable techniques for detecting unintended leaks, intentional leaks, and / or respiratory stages, as described herein and / or as described with reference to WO 2021 / 176426, may be used.

[0117] In some implementations, processing the received pressure and flow rate data may include removing outlier data points in block 510. Removing outlier data points may include identifying and removing data points that have an occurrence frequency lower than a threshold occurrence frequency within the duration. In some implementations, the duration may be the session in which the received pressure and flow rate data was received (e.g., a complete sleep session, all data collected since the respiratory device was turned on, or all data collected since the user interface was connected to the respiratory device). In some implementations, the duration may be a previous duration, such as the last two minutes, as if process 500 is run in real time. In some implementations, the duration may span multiple sessions in which the pressure and flow rate data was received (e.g., multiple different sessions representing multiple uses of respiratory therapy over multiple nights). In some implementations, removing outlier data points may include identifying and removing data points that have an occurrence frequency lower than a threshold occurrence frequency in a predetermined number of previous data points. Any appropriate threshold occurrence frequency, such as 1% of the session duration, can be used.

[0118] In some implementations, for each of the pressure data (e.g., pressure signal) and flow rate data (e.g., flow rate signal), block 504 may first generate a pre-filtered signal by executing block 506 on the received signal and transmitting it to block 508 to generate a filtered signal. The filtered signal can then be used to generate a set of data points, which can be transmitted to block 510 to remove outliers from this set of data points, thereby generating one or more sets of data points. In some implementations, one or more of blocks 506, 508, and 510 may be removed or executed in a different order.

[0119] In block 512, the template curve database is accessed. The template curve database may be stored locally or remotely (e.g., on the cloud or on a remote server). The template curve database may be a set of one or more template curves used to compare pressure data with flow rate data. Some implementations use a single template curve. Some implementations may use multiple template curves, such as different template curves used for various different patterns of user interfaces (e.g., full face, nose, nose pillow).

[0120] Each template curve may be a pressure-to-flow curve that shows some relationship between pressure and flow rate in a fluid system. In some implementations, the template curve may be a predictive template curve, in which the template curve is specifically generated to ensure high identifiability between different types of user interface identifiers and / or conduit identifiers. For example, the predictive template curve may be a curve that has been found to be particularly effective in distinguishing different patterns of user interfaces. In another example, the predictive template curve may be a curve that has been found to be particularly effective in distinguishing different models of user interfaces (e.g., several common models).

[0121] However, in some implementations, template curves can be based on practical, controlled measurements from different user interfaces and / or conduits. For example, a database of template curves can be generated for multiple user interfaces with different patterns, different models, or other differences. Such a database can be generated by acquiring pressure and flow rate data during controlled experiments (e.g., by coupling a user interface to a face model and measuring pressure and flow rate data while controlling a flow rate generator).

[0122] In some implementations, each template curve in the template curve database can be associated with a unique user interface (e.g., a unique user interface pattern and / or a unique user interface model), a unique conduit (e.g., a unique conduit pattern and / or a conduit model), or a unique combination of a user interface and a conduit (e.g., a unique user interface pattern and / or a unique user interface model is combined with (e.g., joined to) a unique conduit pattern and / or a unique conduit model).

[0123] In block 514, the identification distance can be calculated based at least in part on one or more data points from block 504 and the template curve database in block 512. The identification distance is a comparison of one or more data points with one or more template curves from the template curve database. As will be further detailed herein, the identification distance can be a useful calculation for identifying user interfaces and / or conduits, as it can generate identification distances that distinguish different user interfaces and different conduits. In some implementations, a single template curve can be used, and different user interfaces and / or conduits can be distinguished by their different identification distances. In some implementations, multiple unique template curves can be used, and different user interfaces and / or conduits can be distinguished by identifying which unique template curve yields the smallest identification distance.

[0124] In some implementations, block 514 calculates the discrimination distance using a single template curve, although this is not always the case. Calculating the discrimination distance may involve calculating one or more distances from each data point to the template curve.

[0125] The flow rate-based distance (ΔQ) may be the distance between a data point and a template curve at a given pressure level, for example, ΔQ = Q - Q0, where Q is the flow rate at the data point and Q0 is the flow rate of the template curve at the pressure value of the data point.

[0126] The pressure-based distance (ΔP) may be the distance between a data point and a template curve at a given flow rate, for example ΔP = P - P0, where P is the pressure at the data point and P0 is the pressure of the template curve at the flow rate of the data point (for example

number

[0127] curve( The minimum distance to the curve (JPEG0007865953000002.jpg74) can be calculated. The minimum distance to the curve can take into account the deviation of pressure and flow rate. Nondimensionalization of pressure and flow rate values ​​may be performed first, as the pressure and flow rate have different values ​​and the minimum distance can be tilted towards curve measurement. Reference pressure value (P R ) and standard flow rate (Q R )(for example, 10 cmH2O and 0.5 L / s respectively) may be set in advance. The dimensionless flow rate value

number

number

number

[0128] In some implementations, the discrimination distance can be based on flow rate-based distance, pressure-based distance, minimum distance to a curve, or any combination thereof. When analyzing a single data point, the discrimination distance may be the distance to this data point (e.g., flow rate-based distance, pressure-based distance, minimum distance to a curve, or any combination thereof). However, when multiple data points are used, the distance to each data point can be used to calculate the discrimination distance in an equal and / or weighted manner.

[0129] In some implementations, the calculated distance of each data point can be weighted and added based on the frequency of occurrence of that data point. In some implementations, the calculated distance of each data point can be weighted and added based on pressure level, for example, by giving greater weight to higher pressures and / or to the pressure of a more reliable approximation template curve that represents known system behavior. In some implementations, since conduit blockage can result in a negative flow deviation from the template curve, the calculated distance of each data point can be weighted and added based on flow rate, so that greater weight is given for higher flow rates in a given pressure tank (e.g., a given pressure level or pressure level range). In some implementations, comparing multiple data points may involve any suitable combination and variations thereof of the techniques described above.

[0130] In some implementations, calculating the discrimination distance in block 514 may further include generating a confidence score associated with the discrimination distance. Generating the confidence score may include calculating a quantity of variance (e.g., variability or variance) associated with the data points. The confidence score can be based on at least the variance. For example, if data points that vary greatly along the flow rate and pressure axes are collected, it may be assumed that the discrimination distance and the discrimination thus obtained will have a relatively low confidence score. However, if the data points vary only slightly along the flow rate and pressure axes, it may be assumed that the discrimination distance and the discrimination thus obtained will have a relatively high confidence score.

[0131] In block 516, the user interface and / or conduit identification information can be identified using the identification distance calculated in block 514. The identification distance may be compared to a lookup table, applied to an expression, or classified in other ways (e.g., fed to a pre-trained machine learning classifier) ​​to generate the user interface and / or conduit identification information. The user interface and conduit identification information may be the same as the user interface and conduit identification information identified in block 306 of Figure 3.

[0132] Some aspects and features of this disclosure will be described with reference to pressure and flow rate data, such as data points including pressure and flow rate values, and template curves for comparing pressure and flow rate data. However, the other of the pressure and flow rate data can be revealed using knowledge of impedance (i.e., Z, which can be calculated as P / Q) and one of the pressure and flow rate data. Thus, as used herein, for example with reference to process 500, the pressure data or the flow rate data can be replaced with impedance data to achieve suitable similar embodiments. For example, instead of receiving pressure and flow rate data in block 502, pressure and impedance data may be received. In such an example, any template curve for calculating the identification distance may be a pressure-impedance curve instead of a pressure-flow rate curve. Similarly, if flow rate data and impedance data are received, the template curve may be a flow rate-impedance curve.

[0133] Process 500 is shown in a certain arrangement of blocks, but in other implementations, these blocks may be executed in a different order, with additional blocks and / or some blocks removed. For example, in some implementations, similar to block 302 in Figure 3, process 500 is initiated by generating airflow through the user interface before receiving pressure and flow rate data in block 502. As another example, in some implementations, similar to block 318 in Figure 3, process 500 is continued by utilizing the user interface and / or conduit identification information after identifying the user interface and / or conduit identification information in block 516.

[0134] Figure 6 is an exemplary graph 600 showing data points 602 compared to a template curve 604, according to some aspects of the present disclosure. The data points 602 may be any one or more data points generated in block 504 of Figure 5. The template curve 604 may be any suitable template curve, such as a template curve database accessed in block 512 of Figure 5.

[0135] The flow rate-based distance 608 is the distance between data point 602 and template curve 604 at a given pressure level (e.g., pressure level 616 at data point 602). The template flow rate at a given pressure level can be expressed as Q0614.

[0136] The pressure-based distance 606 is the distance between data point 602 and template curve 604 at a given flow rate (e.g., flow rate 618 at data point 602). The template pressure level at a given flow rate can be represented as P0612.

[0137] The minimum distance to curve 610 is the distance between data point 602 and the point on template curve 604 closest to data point 602.

[0138] Figure 7 is an exemplary graph 700 showing experimental data of discrimination distances for various patterns of user interfaces according to several embodiments of the present disclosure. The discrimination distances in Figure 7 may be dimensionless. In some cases, the discrimination distance may be symbolized, but the discrimination distance may be symbolless, or it may indicate whether the data point is to the left or right of the template curve (for example, a negative discrimination distance may indicate that the data point is to the left of the template curve).

[0139] The data in Graph 700 was obtained from 53 different patients, each spanning 7 nights. Each patient used either a full-face user interface, a nasal user interface, or a nasal pillow user interface. The resulting discrimination distances associated with the full-face user interface, nasal user interface, and nasal pillow user interface are easily distinguishable from one another. In other words, Graph 700 demonstrates that good separation exists between the full-face user interface, the nasal user interface, and the nasal pillow user interface.

[0140] One or more further implementations and / or claims of the present disclosure can be formed by combining one or more elements, aspects, or steps or any part thereof from any one or more of the following claims 1 to 128 with one or more elements, aspects, or steps or any part thereof from any one or more of the other claims 1 to 128 or any combination thereof.

[0141] While this disclosure has been described with reference to one or more specific embodiments or implementations, those skilled in the art will recognize that many modifications are possible without departing from the spirit and scope of this disclosure. Each of these implementations and its explicit modifications is considered to be within the spirit and scope of this disclosure. Additional implementations according to aspects of this disclosure may also be constructed by combining any number of features from any of the implementations described herein.

[0142] [Cross-reference of related applications] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 090,002, filed on 9 October 2020, entitled "Automatic User Interface Identification," which is incorporated herein by reference in its entirety.

Claims

1. Generating an airflow through a user interface, wherein generating the airflow includes generating the airflow using a flow generator, Measuring one or more airflow parameters related to the generated airflow, including at least one of the flow rate signal and the pressure signal of the generated airflow, Identifying user interface identification information that can be used to identify the characteristics of the user interface based on one or more measured airflow parameters, Receiving existing user interface identification information related to the flow generator, Determining that the identified user interface identification information is different from the existing user interface identification information, If it is determined that the identified user interface identifier is different from the existing user interface identifier, a notification is generated. including, The method used by computers.

2. The method further includes determining the adjustment of the generation of the airflow through the user interface based on identified user interface identification information. The adjustment of the generation of the airflow through the user interface is further based on one or more airflow parameters. The method according to claim 1.

3. The method according to claim 1 or 2, wherein generating an airflow through the user interface includes powering a flow generator fan at a certain speed, the method further includes determining the speed of the flow generator fan, and identifying the user interface identification information is further based on the speed of the flow generator fan.

4. Identifying the aforementioned user interface identification information means that (i) Inputting one or more airflow parameters as input to a machine learning model having user interface identification information output, wherein the machine learning model is trained using a corpus containing data of the airflow parameters across multiple different user interfaces, and the machine learning model includes at least one selected from the group consisting of recurrent neural network models and convolutional neural network models. (ii) Identifying at least one of the manufacturer of the user interface, the model of the user interface, and the pattern of the user interface, and / or, (iii) Identifying the user interface pattern from a user interface pattern cell that includes a full-face interface, a nose interface, and a nose pillow interface, including, The method according to any one of claims 1 to 3.

5. Identifying the user interface identification information includes identifying the user interface pattern from user interface pattern cells, including a full-face interface, a nose interface, and a nose pillow interface. Identifying the user interface identification information further includes identifying the manufacturer of the user interface, the model of the user interface, or both, based on at least one airflow parameter or both of the at least one airflow parameter and the identified user interface pattern. The method according to any one of claims 1 to 4.

6. The method according to any one of claims 1 to 5, wherein the one or more airflow parameters include a flow signal that includes first flow data captured when the user interface is not being worn by the user and second flow data captured when the user interface is being worn by the user, and the identification of the user interface identification information is based on the first flow data and the second flow data.

7. The method according to any one of claims 1 to 6, wherein generating an airflow through the user interface includes passing the airflow through a conduit, and the method further includes identifying conduit identification information based on one or more measured airflow parameters, the conduit identification information can be used to identify the characteristics of the conduit.

8. The further includes determining the adjustment of the generation of the airflow through the user interface based on identified conduit identification information, The conduit identification information includes at least one of the manufacturer of the conduit, the model of the conduit, and the pattern of the conduit. The method according to claim 7.

9. The determination of the need for additional data related to the user interface, The aforementioned additional data is (i) Audio data related to the airflow passing through the user interface, (ii) Image data related to the image of the user interface, (iii) One or more responses to one or more questions relating to the user interface, or, (iv) Any combination of (i) to (iii), including, To make a decision, To generate a prompt requesting the user for the additional data, The further includes receiving additional data in response to the aforementioned prompt, Identifying the user interface identification information is further based on additional data, according to any one of claims 1 to 8.

10. The method according to any one of claims 1 to 9, further comprising receiving historical airflow parameter data related to the use of the user interface during a past period, wherein the historical airflow parameter data includes at least one of historical flow rate data and historical pressure data, and identifying the user interface identification information is further based on the historical airflow parameter data.

11. The method of claim 10, further comprising identifying a baseline breathing rate using the historical airflow parameter data, and identifying the user interface identification information based on the historical airflow parameter data, comprising using the baseline breathing rate.

12. Identifying user interface identification information is Determining one or more characteristics based on the measured one or more airflow parameters, The method according to any one of claims 1 to 11, comprising inputting one or more features determined based on one or more measured airflow parameters as input to a machine learning model, wherein the output of the machine learning model can be used to determine the user interface identification information.

13. Determining one or more of the above features means The method of generating one or more data points based at least partially on one or more airflow parameters, wherein each of the one or more data points includes a pressure value and a corresponding flow rate value. Accessing one or more template curves, The method of claim 12, comprising generating a comparison between one or more data points and one or more template curves, wherein one or more features include the comparison.

14. The method according to claim 13, wherein generating the comparison includes calculating an identification distance between one or more data points and one or more template curves, the calculation of the identification distance includes i) calculating the minimum distance between one or more data points and one or more template curves, ii) calculating a flow rate-based distance between one or more data points and one or more template curves, iii) calculating a pressure-based distance between one or more data points and one or more template curves, or iv) any combination of i to iii.

15. The method according to any one of claims 13 to 14, wherein the machine learning model is a long- and short-term memory recurrent neural network.

16. The one or more of the above features are, (i) including a resonant frequency signal related to the user interface, wherein the resonant frequency signal indicates one or more resonant frequencies of changes over time related to the user interface, (ii) including unintended leak signals related to the user interface, the unintended leak signals indicating one or more unintended leaks of changes over time related to the user interface, (iii) Includes a nasal-mouth breathing signal related to the user interface, wherein the nasal-mouth breathing signal indicates nasal or oral breathing as it changes over time related to the user interface. (iv) A volume breathing signal associated with the user interface, the volume breathing signal indicating at least one of the inspiratory volume and expiratory volume as they change over time, (v) A continuous breathing signal relating to the user interface, the continuous breathing signal indicating at least one of the inspiratory duration and expiratory duration as they change over time, or, (vi) Any combination of (i) to (v), including, The method according to any one of claims 12 to 15.

17. Determining one or more of the aforementioned features includes determining the resonant frequency signal by performing cepstrum analysis on the airflow parameters. The method according to claim 16.

18. Determining the one or more features involves using the high-frequency components of the measured airflow parameters, Identifying a baseline breathing rate based on one or more measured airflow parameters, The method according to any one of claims 12 to 17, comprising identifying the high-frequency component of one or more measured airflow parameters, wherein the high-frequency component occurs at a frequency higher than the baseline breathing rate.

19. Determining the one or more features involves using the non-high frequency components of the measured airflow parameters, Identifying a baseline breathing rate based on one or more measured airflow parameters, The method according to any one of claims 12 to 18, comprising identifying the non-high frequency component of one or more measured airflow parameters, wherein the non-high frequency component occurs at a frequency lower than the baseline breathing rate.

20. Determining one or more features involves using the medium-frequency components of the measured one or more airflow parameters, Identifying a baseline breathing rate based on one or more measured airflow parameters, The method according to any one of claims 12 to 19, comprising identifying the mid-frequency components of one or more measured airflow parameters, wherein the mid-frequency components occur at a frequency lower than the baseline breathing rate and higher than the low-frequency threshold frequency.

21. The method according to claim 20, wherein determining one or more of the features further comprises using the medium-frequency components to determine an unintended leakage signal related to the user interface, the unintended leakage signal indicating one or more unintended leakages of temporal changes related to the user interface.

22. The method according to any one of claims 12 to 21, wherein determining the one or more features involves using the low-frequency components of the one or more measured airflow parameters, and determining the one or more features involves identifying the low-frequency components of the one or more measured airflow parameters, wherein the low-frequency components occur at a frequency lower than a low-frequency threshold frequency.

23. The method according to claim 22, wherein determining one or more of the features further includes using the low-frequency components to determine an impedance signal associated with the user interface, the impedance signal representing the impedance of the user interface.

24. Identifying the aforementioned user interface identification information means that Using one or more of the measured airflow parameters, identify breathing patterns related to respiration, The method according to any one of claims 1 to 23, comprising comparing an identified respiratory shape with a template respiratory shape.

25. Identifying the aforementioned user interface identification information means that A spectrogram is generated using one or more of the measured airflow parameters, The method according to any one of claims 1 to 24, comprising inputting the spectrogram as input to a deep neural network having user interface identification information as output, and determining the user interface identification information.

26. The method according to any one of claims 1 to 25, wherein generating the airflow includes generating a known adjustment of the airflow and returning the known adjustment to the airflow, measuring one or more airflow parameters occurring before and after the known adjustment, and identifying user interface identification information based on the measured changes in one or more airflow parameters related to the known adjustment.

27. The method according to any one of claims 1 to 26, wherein measuring one or more airflow parameters occurs during a transient event, and the transient event includes removing or wearing the user interface.

28. The method according to any one of claims 1 to 27, further comprising updating the settings of the flow generator in response to the determination that the identified user interface identifier is different from the existing user interface identifier.

29. A control system including one or more processors, A system including a memory that stores machine-readable instructions, The control system is coupled to the memory, and the method according to any one of claims 1 to 28 is carried out when a machine-executable instruction in the memory is executed by at least one of the one or more processors of the control system.

30. A computer program product comprising a computer-readable medium that, when executed by a computer, records an instruction causing the computer to perform the method according to any one of claims 1 to 28.

Images