Systems and methods for predicting alertness

Abstract

The method includes (i) receiving data related to a user during a sleep session, (ii) determining the user's alertness level using a machine learning model that uses the received data as input, and (iii) generating a response to be communicated to the user based at least in part on the determined alertness level. The data related to the user can be received from a respiratory therapy device configured to deliver pressurized air to the user's airway via a user interface, a sensor, or both the respiratory therapy device and the sensor coupled to the respiratory therapy device via a conduit.

Description

[Technical Field]

[0001] Reference to Related Applications This application claims the benefit of and priority to U.S. Provisional Patent Application No. 62 / 982,608, filed February 27, 2020, and U.S. Provisional Patent Application No. 63 / 018,206, filed April 30, 2020, each of which is incorporated by reference in its entirety.

[0002] FIELD OF THE DISCLOSURE The present disclosure relates generally to systems and methods for predicting alertness, and more particularly to systems and methods for correlating alertness with a user's sleep. [Background technology]

[0003] Many individuals suffer from sleep-related and / or breathing disorders (e.g., insomnia, periodic limb movement disorder (PLMD), obstructive sleep apnea syndrome (OSA), Shine-Stokes respiration (CSR), respiratory insufficiency, obesity hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular diseases (NMD), etc.). Individuals suffering from one or more of these sleep-related disorders can treat or manage these disorders by modifying behavioral, activity, and / or environmental parameters (e.g., bedtime, activity level, diet, etc.). Therefore, it would be advantageous to develop metrics to capture the impact of sleep on an individual. It would further be advantageous to develop approaches to calculate these metrics and communicate the results or information derived from the calculations to individuals to assist in the alleviation of one or more sleep-related disorders. The present disclosure is directed to solving these and other problems. Summary of the Invention

[0004] According to some implementations of the present disclosure, a method includes (i) receiving data related to an individual during a sleep session, (ii) determining an alertness level of the individual using a machine learning model that uses the received data as input, and (iii) generating a response to be delivered to the individual based at least in part on the determined alertness level.

[0005] According to some implementations of the present disclosure, a method for predicting a target user's alertness level includes receiving historical sleep session data associated with at least one person for a plurality of historical sleep sessions. The at least one person has used a respiratory therapy system during the plurality of past sleep sessions. Receiving historical alertness data associated with the at least one person. The alertness data includes an alertness level associated with each of the at least one person outside of the plurality of historical sleep sessions. A machine learning model is trained using the received historical sleep session data and the received historical alertness data to (i) receive as input current sleep session data associated with the target user and (ii) determine as output a predicted alertness level associated with the target user at one or more time points.

[0006] According to some implementations of the present disclosure, a method includes receiving data related to a user during a sleep session, the user being associated with a respiratory therapy device configured to deliver pressurized air to the user's airway via a user interface coupled to the respiratory therapy device via a conduit, determining a level of alertness of the user through a machine learning model that uses the received data as input, and generating a response to be communicated to the user based at least in part on the determined level of alertness.

[0007] According to some implementations of the present disclosure, a method includes initiating a test. The test includes generating a stimulus at a first time point. A response to the stimulus is received from a user at a second time point. The response includes an exhaled airflow from the user detected using a respiratory therapy device configured to deliver pressurized air to the user's airway. The pressurized air is delivered through a user interface coupled to the respiratory therapy device via a conduit. A first score is determined based at least in part on (i) the first time point and (ii) the second time point.

[0008] According to some implementations of the present disclosure, a method includes initiating a test. The test includes generating a stimulus at a first time point. A response to the stimulus is received from a user at a second time point. The response is detected using a respiratory therapy system including a respiratory therapy device, a conduit, and a user interface. The respiratory therapy device is configured to deliver pressurized air to the user's airway via the user interface coupled to the respiratory therapy device via the conduit. A first score is determined based at least in part on (i) the first time point and (ii) the second time point.

[0009] According to some implementations of the present disclosure, a method includes: (a) initiating a first test, the first test including generating a first stimulus at a first time point; (b) receiving a first response to the first stimulus from a user at a second time point, the first response being detected using a respiratory therapy system including a respiratory therapy device, a conduit, and a user interface, the respiratory therapy device being configured to deliver pressurized air to the user's airway via a user interface coupled to the respiratory therapy device via the conduit; (c) determining a first score based at least in part on (i) the first time point and (ii) the second time point; (d) delivering the pressurized air delivered to the respiratory therapy device to the user during the first therapy session; (e) initiating a second test, the second test including generating a second stimulus at a third time point; and (f) receiving a second response to the second stimulus from the user at a fourth time point, the second response being detected using the respiratory therapy system. (g) determining a second score based at least in part on (i) the third time point and (ii) the fourth time point; and (h) communicating to the user a result associated with the first score and the second score.

[0010] According to some implementations of the present disclosure, a system includes a respiratory apparatus configured to deliver pressurized air to a user's airway. The pressurized air is delivered by a user interface coupled to the respiratory apparatus via a conduit. The system further includes a memory storing machine-readable instructions. The system further includes a control system including one or more processors configured to execute the machine-readable instructions. The system (a) initiates a test, the test including generating a stimulus at a first time point; (b) receives a response to the stimulus from the user at a second time point, the response including an exhaled airflow from the user detected using the respiratory apparatus; and (c) determines a first score based at least in part on (i) the first time point and (ii) the second time point.

[0011] According to some implementations of the present disclosure, a system includes a respiratory system including a ventilator, a conduit, and a user interface. The ventilator is configured to deliver pressurized air to a user's airway via the user interface, which is coupled to the ventilator via the conduit. The system further includes a memory storing machine-readable instructions. The system further includes a control system including one or more processors configured to execute the machine-readable instructions. The control system (a) initiates a test, the test including generating a stimulus at a first time point; (b) receives a response to the stimulus from the user at a second time point, the response being detected using the respiratory system; and (c) determines a first score based at least in part on (i) the first time point and (ii) the second time point.

[0012] According to some implementations of the present disclosure, a system includes a respiratory system including a ventilator, a conduit, and a user interface. The ventilator is configured to deliver pressurized air to a user's airway via the user interface coupled to the ventilator via the conduit. The system further includes a memory storing machine-readable instructions. The system also includes a control system including one or more processors configured to execute the machine-readable instructions. The system includes: (a) initiating a first test, the first test including generating a first stimulus at a first time point; (b) receiving a first response to the first stimulus from the user at a second time point, the first response being detected using the ventilator; (c) determining a first score based at least in part on (i) the first time point and (ii) the second time point; (d) delivering the pressurized air to the ventilator; and (e) initiating a second test, the second test including generating a second stimulus at a third time point. (f) receiving a second response to the second stimulus from the user at a fourth time point, the second response being detected using the respiratory device; (g) determining a second score based at least in part on (i) the third time point and (ii) the fourth time point; and (h) communicating a result associated with the first score and the second score to the user.

[0013] The above summary is not intended to represent each implementation or every aspect of the present disclosure. Additional features and advantages of the present disclosure will be apparent from the detailed description and figures set forth below. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is a functional block diagram of a system according to some implementations of the present disclosure. [Figure 2] 2 is a perspective view illustrating at least a portion of the system of FIG. 1, the user, and the bed partner, according to some implementations of the present disclosure. [Figure 3] FIG. 3 is a diagram illustrating an example timeline of a sleep session, according to some implementations of the present disclosure. [Figure 4] FIG. 4 is a flow diagram for performing a reaction time test according to some implementations of the present disclosure. [Figure 5] FIG. 5 is a flow diagram for comparing two reaction time tests according to some implementations of the present disclosure. [Figure 6A] FIG. 6A is a diagram illustrating a user wearing a user interface having a light source, according to some implementations of the present disclosure. [Figure 6B] FIG. 6B illustrates the user of FIG. 6A receiving light stimulation via a light source, according to some implementations of the present disclosure. [Figure 6C] FIG. 6C illustrates the user of FIG. 6A responding to a light stimulus, according to some implementations of the present disclosure. [Figure 7] FIG. 7 is a flow diagram for generating a response to a user based on alertness, according to some implementations of the present disclosure. [Figure 8] FIG. 8 is a flow diagram for training a machine learning model to predict a target user's alertness level, according to some implementations of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0015] While the present disclosure is susceptible to various modifications and alternative forms, specific implementations thereof have been shown by way of example in the drawings and are herein described in detail. It is to be understood, however, that there is no intention to limit it to the particular forms disclosed, but on the contrary, the disclosure is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.

[0016] Examples of sleep-related and / or respiratory disorders include periodic limb movement disorder (PLMD), restless legs syndrome (RLS), sleep-disordered breathing (SDB), obstructive sleep apnea (OSA), Shine-Stokes respiration (CSR), respiratory failure, obesity hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular disorders (NMD), and chest wall disorders. Obstructive sleep apnea (OSA) is a type of sleep-disordered breathing (SDB) characterized by an abnormally small upper airway and loss of normal muscle tone in the tongue, soft palate, and posterior oropharynx, resulting in upper airway obstruction or events involving obstruction during sleep. Cheyne-Stokes respiration (CSR) is another type of sleep-disordered breathing. CSR is a disorder of respiratory control characterized by rhythmic alternating periods of increased and decreased ventilation, known as the CSR cycle. CSR is characterized by repeated deoxygenation and reoxygenation of arterial blood. Obesity hyperventilation syndrome (OHS) is defined as the combination of severe obesity and awake chronic hyperventilation in the absence of other causes of hypoventilation. Symptoms include dyspnea, morning headache, and excessive daytime sleepiness. Chronic obstructive pulmonary disease (COPD) refers to a group of lower airway disorders characterized by increased resistance to airflow, a prolonged expiratory phase of breathing, and loss of lung elasticity. Neuromuscular disorders (NMDs) refer to a number of conditions and disorders that impair muscle function directly through muscle pathology or indirectly through neuropathology. Chest wall disorders are a group of thoracic deformities that result in inefficient coupling between the respiratory muscles and the thoracic cage.

[0017] These disorders are characterized by specific events that occur while an individual is sleeping (e.g., snoring, apnea, hypopnea, restless legs, sleep disturbances, choking, increased heart rate, dyspnea, asthma attacks, epileptic episodes, seizures, or any combination thereof). To improve sleep and mitigate these events, a physician may prescribe or recommend the use of a respiratory therapy system. Patients using a respiratory therapy system for the first time may not immediately experience any health benefits from using the system. This lack of immediate subjective health benefits may lead some patients to discontinue use of the respiratory therapy system or to prematurely conclude that the respiratory therapy system is ineffective. While subjective improvement may be difficult to measure after the first treatment session with a respiratory therapy system, objective measures or indicators can indicate improvement. Without objective measures or metrics, some patients may discontinue use of the respiratory therapy system. Therefore, some implementations of the present disclosure provide patients with information, including objective measures, to encourage them to adhere to the prescribed or recommended use of the respiratory therapy system.

[0018] Objective measures may be obtained passively or may require active user involvement. Examples of passive objective measures include obtaining a patient's heart rate variability information or using a fitness tracker to obtain a patient's heart rate data over a period of time. A fitness tracker may passively obtain heart rate data without the patient's involvement with the fitness tracker. An example of active user involvement is having a patient perform one or more tests that indicate the user's sleep quality prior to the test. A test may be a reaction time test that measures a patient's reaction time. Tests include sustained attention tests and reaction time tests, which can engage a patient for a longer period of time than simple reaction time tests. An example of a sustained attention or reaction speed test is the psychomotor vigilance task (PVT). Some implementations of the present disclosure are described with reference to a reaction time test for illustrative purposes only. However, implementations of the present disclosure are not limited to reaction time tests.

[0019] Some implementations of the present disclosure provide an objective measure of vigilance before and after a recommended or prescribed therapy by a respiratory therapy system. Vigilance is related to alertness and watchfulness. Untreated, OSA can lead to daytime sleepiness and a corresponding decrease in alertness. Therefore, poor response on the test may indicate sleepiness or a lack of attention or concentration.

[0020] 1, a system 100 according to some implementations of the present disclosure is illustrated. System 100 includes a control system 110, a memory device 114, an electronic interface 119, one or more sensors 130, a respiratory therapy system 120, and one or more user devices 170.

[0021] Control system 110 includes one or more processors 112 (hereinafter processors 112). Control system 110 is generally used to control (e.g., operate) various components of system 100 and / or analyze data obtained and / or generated by the components of system 100. Processor 112 can be a general-purpose processor or a special-purpose processor or microprocessor. While one processor 112 is shown in FIG. 1 , control system 110 can include any suitable number of processors (e.g., 1 processor, 2 processors, 5 processors, 10 processors, etc.), which can be within a single housing or located remotely from one another. Control system 110 can be coupled to and / or located within, for example, the housing of user device 170, one or more housings of sensors 130, and / or the housing of respiratory therapy device 122 included in respiratory therapy system 120. Control system 110 can be centralized (within one such housing) or distributed (within two or more such housings that are physically separate). In implementations including two or more housings containing control system 110, they may be located proximate to and / or remote from one another. One or more of sensors 130 may be coupled to an external device separate from respiratory therapy device 122. For example, one or more of sensors 130 may be included in jewelry such as a ring, a necklace, etc. One or more of sensors 130 may be provided on or within the housing of respiratory therapy device 122.

[0022] The memory device 114 stores machine-readable instructions executable by the processor 112 of the control system 110. The memory device 114 may be any suitable computer-readable storage device or medium, such as, for example, a random-access or serial-access memory device, a hard drive, a solid-state drive, a flash memory device, etc. Although one memory device 114 is shown in FIG. 1 , the memory device 114 is shown as a single memory device 114. As shown in FIG. 1 , the system 100 may include any suitable number of memory devices 114 (e.g., one memory device, two memory devices, five memory devices, ten memory devices, etc.). The memory device 114 may be coupled to and / or located within the housing of the respiratory therapy device 122, within the housing of the user device 170, within the housing of one or more sensors 130, or any combination thereof. Like the control system 110, the memory device 114 may be centralized (within one such housing) or distributed (within two or more such housings that are physically distinct).

[0023] The electronic interface 119 is configured to receive data (e.g., physiological data) from one or more sensors 130, which can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. The electronic interface 119 can communicate with the one or more sensors 130 using a wired or wireless connection (e.g., using an RF communication protocol, a WiFi communication protocol, a Bluetooth® communication protocol, a cellular network, etc.). The electronic interface 119 can 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 can also include one or more processors and / or one or more memory devices the same as or similar to the processor 112 and memory device 114 described herein. In some implementations, the electronic interface 119 is coupled to or integrated into the user device 170. In other implementations, the electronic interface 119 is coupled to or integrated (eg, within the housing) with the control system 110 and / or the memory device 114 .

[0024] Respiratory therapy system 120 can include a respiratory pressure therapy device (e.g., respiratory therapy device 122), a user interface 124, a conduit 126 (also called a tube or air circuit), a display 128, a humidification tank 129, or any combination thereof. In some implementations, control system 110, storage device 114, display 128, one or more sensors 130, and humidification tank 129 are part of respiratory therapy device 122. Respiratory pressure therapy refers to the application of a supply of air to the entrance of a user's airway at a controlled target pressure that is nominally positive relative to the atmosphere throughout the user's respiratory cycle (as opposed to negative pressure therapy, such as a tank ventilator or cuirass). Respiratory therapy system 120 is generally used to treat individuals suffering from one or more sleep-related breathing disorders (e.g., obstructive sleep apnea, central sleep apnea, or mixed sleep apnea).

[0025] Respiratory therapy device 122 is generally used to generate pressurized air delivered to a user (e.g., using one or more motors driving one or more compressors). In some implementations, respiratory therapy device 122 generates a continuous, constant air pressure supplied to a user. In other implementations, respiratory therapy device 122 generates two or more predetermined pressures (e.g., a first predetermined air pressure and a second predetermined air pressure). In still other implementations, respiratory therapy device 122 is configured to generate a variety of different air pressures within a predetermined range. For example, respiratory therapy device 122 can deliver at least about 6 cmH2O, at least about 10 cmH2O, at least about 20 cmH2O, between about 6 cmH2O and about 10 cmH2O, between about 7 cmH2O and about 12 cmH2O, etc. Respiratory therapy device 122 can also deliver pressurized air at a predetermined flow rate, e.g., between about -20 L / min and about 150 L / min, while maintaining a positive pressure (relative to ambient pressure).

[0026] The user interface 124 engages a portion of the user's face and delivers pressurized air from the respiratory therapy device 122 to the user's airway, helping to prevent the airway from narrowing and / or collapsing during sleep. This may also increase the user's oxygen intake while sleeping. Depending on the therapy being applied, the user interface 124 may form a seal with an area or portion of the user's face to facilitate delivery of gas at a pressure sufficiently different from ambient pressure to effectively deliver the therapy, for example, approximately 10 cmH2O positive pressure above ambient pressure. For other therapies, such as oxygen delivery, the user interface may not include a seal sufficient to deliver gas to the airway at approximately 10 cmH2O positive pressure.

[0027] As shown in FIG. 2 , in some implementations, the user interface 124 is a face mask that covers the user's nose and mouth. Alternatively, the user interface 124 may be a nasal mask that delivers air to the user's nose or a nasal pillow mask that delivers air directly to the user's nostrils. The user interface 124 may include multiple straps (e.g., including hook-and-loop fasteners) for positioning and / or stabilizing the user interface 124 on a portion of the user (e.g., the face) and a conformal cushion (e.g., silicone, plastic, foam, etc.) that helps provide an airtight seal between the user interface 124 and the user. The user interface 124 may also include one or more vents to allow carbon dioxide and other gases exhaled by the user 210 to escape. In other implementations, the user interface 124 includes a mouthpiece (e.g., a night guard mouthpiece shaped to fit the user's teeth, a jaw movement device, etc.).

[0028] The conduit 126 (also called an air circuit or tubing) allows air to flow between two components of the respiratory therapy system 120, such as the respiratory therapy device 122 and the user interface 124. In some implementations, there can be separate limbs of the conduit for inhalation and exhalation. In other implementations, a single limb conduit is used for both inhalation and exhalation.

[0029] One or more of the respiratory therapy device 122, the user interface 124, the conduit 126, the display 128, and the humidification tank 129 may include one or more sensors (e.g., a pressure sensor, a flow sensor, or more generally, any of the other sensors 130 described herein). These one or more sensors may be used, for example, to measure the air pressure and / or flow rate of the pressurized air supplied by the respiratory therapy device 122.

[0030] Display device 128 is generally used to display image(s), including still images, moving images, or both, and / or information about respiratory therapy device 122. For example, display device 128 may display information about the status of respiratory therapy device 122 (e.g., whether respiratory therapy device 122 is on / off, the pressure of air delivered by respiratory therapy device 122, the temperature of air delivered by respiratory therapy device 122, etc.) and / or other information (e.g., a sleep score and / or a therapy score (also known as a myAir® score, as described in WO 2016 / 061629, which is incorporated herein by reference in its entirety), the current date / time, personal information of user 210, etc.). In some implementations, display device 128 functions as a human-machine interface (HMI) including a graphic user interface (GUI) configured to display image(s) as an input interface. Display device 128 may be an LED display, an OLED display, an LCD display, etc. The input interface may be, for example, a touch screen or touch-sensitive board, a mouse, a keyboard, or any sensor system configured to sense inputs made by a human user interacting with the respiratory therapy device 122 .

[0031] Humidification tank 129 is coupled to or integrated with respiratory therapy device 122 and includes a reservoir of water that can be used to humidify the pressurized air delivered from respiratory therapy device 122. Respiratory therapy device 122 can include a heater that heats water in humidification tank 129 to humidify the pressurized air delivered to the user. Additionally, in some implementations, conduit 126 can also include a heating element (e.g., coupled to and / or embedded in conduit 126) that heats the pressurized air delivered to the user.

[0032] The respiratory therapy system 120 can be used, for example, as a mechanical ventilator or a positive airway pressure (PAP) system, such as a continuous positive airway pressure (CPAP) system, an automatic positive airway pressure (APAP), a bi-level or variable positive airway pressure system (BPAP or VPAP), or any combination thereof. A CPAP system delivers a predetermined air pressure (e.g., determined by a sleep physician) to a user. An APAP system automatically varies the air pressure delivered to a user based, for example, on the user's breathing data. A BPAP or VPAP system is configured to deliver a first predetermined pressure (e.g., inspiratory positive airway pressure or IPAP) and a second predetermined pressure (e.g., expiratory positive airway pressure or EPAP) that is lower than the first predetermined pressure.

[0033] Referring to FIG. 2, a portion of system 100 (FIG. 1) according to some implementations is shown. A user 210 and a bed partner 220 of respiratory therapy system 120 are positioned on a bed 230, reclining on a mattress 232. A user interface 124 (e.g., a full-facial mask) can be worn by user 210 during a sleep session. User interface 124 is fluidly coupled and / or connected to respiratory therapy device 122 via conduit 126. As a result, respiratory therapy device 122 delivers pressurized air to user 210 via conduit 126 and user interface 124, increasing air pressure in the user's 210's throat and helping to prevent the airway from closing and / or narrowing during sleep. Respiratory therapy device 122 can be placed on a nightstand 240 directly adjacent to bed 230, as shown in FIG. 2, or more generally on any surface or structure generally adjacent to bed 230 and / or user 210.

[0034] 1 , the 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, an RF receiver 146, an RF transmitter 148, a camera 150, an infrared sensor 152, a photoplethysmography (PPG) sensor 154, an electrocardiogram (ECG) sensor 156, an electroencephalogram (EEG) sensor 158, a capacitance sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyogram (EMG) sensor 166, an oxygen sensor 168, an analyte sensor 174, a moisture sensor 176, a LiDAR sensor 178, a thermal imaging sensor, or any combination thereof. Generally, one or each of sensors 130 is configured to output sensor data that is received and stored in memory device 114 or one or more other memory devices.

[0035] The one or more sensors 130 are illustrated and described as including a pressure sensor 132, a flow sensor 134, a temperature sensor 136, a motion sensor 138, a microphone 140, a speaker 142, an RF receiver 146, an RF transmitter 148, a camera 150, an infrared sensor 152, a photoelectric (PPG) sensor 154, and an electrocardiogram (ECG) sensor 156, respectively, of which the pressure sensor 132, the flow sensor 134, and the temperature sensor 136 also include a photoelectric sensor 154, an electrocardiogram sensor 156, a photoelectric (ECG) sensor 157, an electrocardiogram sensor 157, and an electroencephalogram (EEG) sensor 158, respectively. The one or more sensors 130 may include an electroencephalogram (EEG) sensor 158, a capacitance sensor 160, a force sensor 162, a strain gauge sensor 164, an electromyogram (EMG) sensor 166, an oxygen sensor 168, an analyte sensor 174, a moisture sensor 176, and a LiDAR sensor 178, and more generally, any combination and number of the sensors described and / or shown herein.

[0036] The physiological data generated by one or more of the sensors 130 can be used by the control system 110 to determine a sleep-wake signal and one or more sleep-related parameters associated with the user during a sleep session. The sleep-wake signal can indicate one or more sleep states, including sleep stages such as wakefulness, relaxed wakefulness, microarousals, rapid eye movement (REM) stages, a first non-REM stage (also referred to as “N1”), a second non-REM stage (also referred to as “N2”), a third non-REM stage (also referred to as “N3”), or any combination thereof. The sleep-wake signal can also be time-stamped to determine the time the user got into bed, the time the user left bed, the time the user attempted to fall asleep, etc. The sleep-wake signal can be measured by the sensor(s) 130 during a sleep session at a predetermined sampling rate, such as, for example, one sample per second, one sample per 30 seconds, one sample per minute, etc. Methods for determining sleep states and / or sleep stages from physiological data generated by one or more sensors, such as sensor 130, are described, for example, in WO 2014 / 047310, US 2014 / 0088373, WO 2017 / 132726, WO 2019 / 12413, and WO 2019 / 12240, each of which is incorporated by reference in its entirety. Sleep stages can be discrete values ​​or continuous variables representing fine-grained transitions between states. For example, the transition from REM to slow-wave sleep (SWS) can include any number of levels, such as deep and shallow REM, N3 SWS, light sleep N1, N2, etc.

[0037] Pressure sensor 132 outputs pressure data that is stored in memory device 114 and / or analyzed by processor 112 of control system 110. In some implementations, pressure sensor 132 is an air pressure sensor (e.g., an atmospheric pressure sensor) that generates sensor data indicative of a user's breathing (e.g., inhalation and / or exhalation) and / or ambient pressure of respiratory therapy system 120. In such implementations, pressure sensor 132 may be coupled to or integrated into respiratory therapy device 122. Pressure sensor 132 may be, for example, a capacitance sensor, an electromagnetic sensor, a piezoelectric sensor, a strain gauge sensor, an optical sensor, a potentiometric sensor, or any combination thereof.

[0038] The flow sensor 134 outputs flow data that is stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some implementations, the flow sensor 134 is used to determine the airflow rate from the respiratory therapy device 122, the airflow rate through the conduit 126, the airflow rate through the user interface 124, or any combination thereof. In such implementations, the flow sensor 134 may be coupled to or integrated with the respiratory therapy device 122, the user interface 124, or the conduit 126. The flow sensor 134 may be, for example, a mass flow sensor such as a rotary flow meter (e.g., a Hall effect flow meter), a turbine flow meter, an orifice flow meter, an ultrasonic flow meter, a hot wire sensor, a vortex sensor, a film sensor, or any combination thereof.

[0039] The temperature sensor 136 outputs temperature data that is stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. In some implementations, the temperature sensor 136 generates temperature data indicative of the core body temperature of the user 210 (FIG. 2), the skin temperature of the user 210, the temperature of the air flowing from the respiratory therapy 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 can 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.

[0040] The microphone 140 outputs sound data that can be stored in the memory device 114 and / or analyzed by the processor 112 of the control system 110. The microphone 140 can be used to record sounds (e.g., sounds from the user 210) during a sleep session to determine one or more sleep-related parameters (e.g., with the control system 110), as described in further detail herein. The microphone 140 can be coupled to or integrated with the respiratory therapy device 122, the usage interface 124, the conduit 126, or the user device 170. The microphone 140 can also be combined with other microphones to perform beamforming. In some implementations, the one or more microphones 140 are electrically connected to a circuit board of the respiratory therapy device 122 and may be in acoustic communication (e.g., through small ducts and / or silicone windows, as in a stethoscope) or in fluid communication with the airflow within the respiratory therapy system 120. The microphone can be embedded in an external device such as a smart device, an Internet of Things (IoT) device, a smart speaker, a smart display, a phone, a tablet, a watch, a ring, a patch, a pendant, a security camera, a security sensor, or any combination thereof. In some cases, some of the sensors can monitor wakefulness in vehicles such as automobiles.

[0041] Speaker 142 outputs sound waves that can be heard by a user of system 100 (e.g., user 210 in FIG. 2). Speaker 142 can be used, for example, as an alarm clock or to play alerts or messages to user 210 (e.g., in response to an event). Speaker 142 can be coupled to or integrated with respiratory therapy device 122, user interface 124, conduit 126, or external device 170.

[0042] The microphone 140 and the speaker 142 can also be used as separate devices. In some implementations, the microphone 140 and the speaker 142 can be combined into an acoustic sensor 141 (e.g., a sonar sensor), as described, for example, in International (PCT) Publication Nos. WO 2018 / 050913 and WO 2020 / 104465, each of which is incorporated herein by reference in its entirety. In such implementations, the speaker 142 generates or emits sound waves at predetermined intervals, and the microphone 140 detects reflections of the sound waves emitted from the speaker 142. The sound waves generated or emitted by the speaker 142 have a frequency inaudible to the human ear (e.g., below 20 Hz or above about 18 kHz) so as not to disturb the sleep of the user 210 or their bed partner 220 (FIG. 2). Based at least in part on data from the microphone 140 and / or the speaker 142, the control system 110 can determine the location of the user 210 (FIG. 2). As used herein, the term "sonar sensor" refers to one or more sleep-related parameters, such as a respiratory signal, a respiratory rate, an inhalation amplitude, an exhalation amplitude, an inhalation-exhalation ratio, a number of events per time, a pattern of events, a sleep state, a sleep stage, a pressure setting of the breathing device 122, or any combination thereof. In this context, sonar sensors may be understood to relate to active acoustic sensing, such as by generating / transmitting ultrasonic or low-frequency ultrasonic sensing signals (e.g., in a frequency range of about 17-23 kHz, 18-22 kHz, or 17-18 kHz) through the air. Such systems may be discussed in connection with WO2018 / 050913 and WO2020 / 104465, as mentioned above.

[0043] The RF transmitter 148 generates and / or emits radio waves having a predetermined frequency and / or a predetermined amplitude (e.g., within a high frequency band, within a low frequency band, a long wave signal, a short wave signal, etc.). The RF receiver 146 detects reflections of the radio waves emitted from the RF transmitter 148, and this data can be analyzed by the control system 110 to determine the location of the user 210 (FIG. 2), including one or more sleep-related parameters described herein. The RF receiver (either the RF receiver 146 or the RF transmitter 148, or another RF pair) can also be used for wireless communication with the control system 110, the respiratory therapy device 122, one or more sensors 130, the user device 170, or any combination thereof. While the RF receiver 146 and the RF transmitter 148 are shown as separate elements in FIG. 1, in some implementations, the RF receiver 146 and the RF transmitter 148 are shown as part of an RF sensor 147 (e.g., a radar sensor). In some such implementations, the RF sensor 147 includes control circuitry. The particular form of RF communication may be WiFi, Bluetooth, or the like.

[0044] In some implementations, the RF sensor 147 is part of a mesh system. One example of a mesh system is a WiFi mesh system, which can include mesh nodes, mesh routers, and mesh gateways, each of which can be mobile / movable or fixed. In such implementations, the WiFi mesh system includes a WiFi router and / or a WiFi controller and one or more satellites (e.g., access points), each of which includes an RF sensor that is the same as or similar to the RF sensor 147. The WiFi router and the satellite are in constant communication using WiFi radio waves. The WiFi mesh system can be used to generate motion data based on changes in the WiFi signal between the router and the satellite (e.g., differences in received signal strength) due to the movement of objects or people that partially obstruct the signal. The motion data can indicate movement, breathing, heart rate, walking, falls, activity, etc., or any combination thereof.

[0045] Camera 150 outputs image data that can be reproduced as one or more images (e.g., still images, motion images, thermal images, or a combination thereof) that can be stored in memory device 114. The image data from camera 150 is used by control system 110 to determine one or more of the sleep-related parameters described herein. For example, the image data from camera 150 can be used to locate the user, determine the time that user 210 enters bed 230 (FIG. 2), and determine the time that user 210 leaves bed.

[0046] 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 memory device 114. The infrared data from the IR sensor 152 includes the temperature of the user 210 and / or the movement of the user 210 and is used to determine one or more sleep-related parameters during a sleep session. The IR sensor 152 can also be used in combination with the camera 150 in measuring the presence, location, and / or movement of the user 210. The IR sensor 152 can detect infrared light having a wavelength between about 700 nm and about 1 mm, for example, and the camera 150 can detect visible light having a wavelength between about 380 nm and about 740 nm.

[0047] The PPG sensor 154 can be used to determine one or more parameters, such as heart rate, heart rate variability, cardiac cycle, respiratory rate, inspiration amplitude, expiration amplitude, inspiration-expiration ratio, estimated blood pressure parameter(s), or a combination thereof, that output physiological data related to the user 210 ( FIG. 2 ). The PPG sensor 154 is embedded in and / or coupled to the user interface 124 and / or its associated headgear (e.g., straps, etc.), worn by the user 210, and embedded in clothing and / or fabric worn by the user 210.

[0048] The ECG sensor 156 outputs physiological data related to the electrical activity of the heart of the user 210. In some implementations, the ECG sensor 156 includes one or more electrodes that are placed on or around a portion of the user 210 during a sleep session. The physiological data from the ECG sensor 156 is used to determine, for example, some of the one or more parameters described above in connection with the PPG sensor 154.

[0049] The EEG sensor 158 outputs physiological data related to the electrical activity of the brain of the user 210. In some implementations, the EEG sensor 158 includes one or more electrodes that are placed on or around the scalp of the user 210 during a sleep session. The physiological data from the EEG sensor 158 can be used, for example, to determine the sleep state and / or sleep stage of the user 210 at any given time during the sleep session. In some implementations, the EEG sensor 158 can be integrated into the user interface 124 and / or associated headgear (e.g., straps, etc.).

[0050] The capacitive sensor 160, the force sensor 162, and the strain gauge sensor 164 output data that can be stored in the memory device 114 and used by the control system 110 to determine one or more of the parameters described herein. The EMG sensor 166 outputs physiological data related to electrical activity generated by one or more muscles. The oxygen sensor 168 outputs oxygen data indicative of the oxygen concentration of a gas (e.g., in the conduit 126 or at the user interface 124). The oxygen sensor 168 can be, for example, an ultrasonic oxygen sensor, an electrical oxygen sensor, a chemical oxygen sensor, an optical oxygen sensor, or any combination thereof. In some implementations, the one or more sensors 130 also include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiration sensor, a pulse sensor, a sphygmomanometer sensor, an oximetry sensor, or any combination thereof.

[0051] The analyte sensor 174 can be used to detect the presence of an analyte in the exhaled breath of the user 210. Data output by the analyte sensor 174 can be stored in the memory device 114 and used by the control system 110 to determine the identity and concentration of any analytes in the exhaled breath of the user 210. In some implementations, the analyte sensor 174 is placed near the mouth of the user 210 to detect analytes in breath exhaled from the user's 210 mouth. For example, if the user interface 124 is a face mask that covers the nose and mouth of the user 210, the analyte sensor 174 can be placed within the face mask to monitor the user's 210 mouth breathing. In other implementations, such as when the user interface 124 is a nasal mask or nasal pillows mask, the analyte sensor 174 can be placed near the nose of the user 210 to detect analytes in breath exhaled through the user's nose. In yet other implementations, the analyte sensor 174 is placed near the mouth of the user 210 when the user interface 124 is a nasal mask or nasal pillows mask. In this implementation, the analyte sensor 174 can be used to detect whether air is inadvertently leaking from the user's 210 mouth. In some implementations, the analyte sensor 174 is a volatile organic compound (VOC) sensor that can be used to detect carbon-based chemicals or compounds. In some implementations, the analyte sensor 174 can also be used to detect whether the user 210 is breathing through their nose or mouth. For example, if the analyte sensor 174 is located near the user's 210 mouth or within the face mask (in implementations where the user interface 124 is a face mask), and the data it outputs detects the presence of an analyte, the control system 110 can use this data as an indication that the user 210 is mouth breathing. The mask can also be part of a head-mounted PAP system, whereby the complete respiratory therapy system is worn on the head and consists of an integrated (or external) sensor as described elsewhere herein. The sensor can also be integrated into a "smart mask" that separates the respiratory therapy device from the control circuitry.

[0052] The moisture sensor 176 outputs data that is stored in the memory device 114 and used by the control system 110. The moisture sensor 176 can be used to detect moisture in various areas surrounding the user (e.g., inside the conduit 126 or the user interface 124, near the face of the user 210, near the connection between the conduit 126 and the user interface 124, near the connection between the conduit 126 and the respiratory therapy device 122, etc.). Thus, in some implementations, the moisture sensor 176 can be coupled to the user interface 124 or integrated into the conduit 126 to monitor the humidity of the pressurized air from the respiratory therapy device 122. In other implementations, the moisture sensor 176 is located near any area where humidity levels need to be monitored. The moisture sensor 176 can also be used to monitor the humidity of the air in the ambient environment surrounding the user 210, for example, in a bedroom.

[0053] The LiDAR (Light Detection and Ranging) sensor 178 can be used for depth sensing. This type of optical sensor (e.g., a laser sensor) can be used to detect objects and create a three-dimensional map of an area, such as a living space. LiDAR typically uses a pulsed laser to measure time of flight. LiDAR is also known as 3D laser scanning. In one use case, a fixed or mobile device (e.g., a smartphone) equipped with the LiDAR sensor 166 can measure and map an area more than five meters away from the sensor. LiDAR data can be fused with point cloud data, for example, estimated by a RADAR sensor using electromagnetic waves. The LiDAR sensor 178 can also automatically geofence a RADAR system by using artificial intelligence (AI) to detect and classify features in a space that may pose a problem for the RADAR system, such as glass windows (which are highly reflective to RADAR). LiDAR can also be used to estimate a person's height and detect changes in height, such as when they sit or fall. LiDAR may be used to create a 3D mesh representation of the environment. Furthermore, for solid surfaces through which radio waves pass (e.g., radio-transparent materials), LiDAR can reflect off such surfaces, allowing classification of different types of obstacles.

[0054] 1 , any combination of one or more sensors 130 may be integrated with and / or coupled to any one or more of the components of system 100, including respiratory therapy device 122, user interface 124, conduit 126, humidification tank 129, control system 110, user device 170, or any combination thereof. For example, acoustic sensor 141 and / or RF sensor 147 may be integrated with and / or coupled to user equipment 170. In such implementations, user device 170 may be considered a secondary device that generates additional or secondary data for use by system 100 (e.g., control system 110) according to some aspects of the present disclosure. In some implementations, at least one of the one or more sensors 130 is not coupled to the respiratory therapy device 122, the control system 110, or the user device 170, but is positioned generally adjacent to the user 210 during a sleep session (e.g., positioned on or in contact with a portion of the user 210, worn by the user 210, coupled or placed on a nightstand, coupled to a mattress, coupled to a ceiling, etc.).

[0055] User device 170 ( FIG. 1 ) includes a display device 172. User device 170 can be, for example, a mobile device such as a smartphone, tablet, or laptop. Alternatively, user device 170 can be an external sensing system, a television (e.g., a smart TV), or another smart home device (e.g., smart speaker(s), such as Google Home, Amazon Echo, or Alexa). In some implementations, user device 170 is a wearable device (e.g., a smart watch, a fitness tracker, etc.). Display device 172 is generally used to display image(s), including still images, moving images, or both. Display device 172 also functions as a human-machine interface (HMI), including a graphical user interface (GUI) configured to display the image(s) and an input interface. Display device 172 can be an LED display, an OLED display, a liquid crystal display, or the like. The input interface can be, for example, a touchscreen or touch-sensitive board, a mouse, a keyboard, or any sensor system configured to sense inputs made by a human user interacting with user device 170. In some implementations, one or more user devices may be used by and / or included in the system 100.

[0056] 1 illustrates control system 110 and storage 114 as separate components of system 100; in some implementations, control system 110 and / or storage 114 are integrated with user device 170 and / or respiratory therapy device 122. Alternatively, in some implementations, control system 110, or portions thereof (e.g., 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, subject to edge cloud processing, etc.), on one or more servers (e.g., remote servers, local servers, etc., or any combination thereof).

[0057] Although system 100 is shown as including all of the components described above, a system for generating physiological data and determining recommended notifications or actions for a user may include more or fewer components in accordance with implementations of the present disclosure. For example, a first alternative system includes control system 110, storage 114, and at least one of one or more sensors 130. As another example, a second alternative system includes control system 110, storage 114, at least one of one or more sensors 130, and user device 170. As yet another example, a third alternative system includes control system 110, storage 114, respiratory therapy system 120, at least one of one or more sensors 130, and user device 170. Thus, various systems can be formed using any portion or subset of the components described herein and / or in combination with one or more other components.

[0058] As used herein, a sleep session can be defined in several ways, for example, based on an initial start time and end time. Referring to FIG. 3, an exemplary timeline 300 for a sleep session is shown. The timeline 300 includes time in bed (tbed), time onset to sleep (tGTS), initial sleep time (tGTS), and sleep duration (tTBS). tsleep ), first micro-awakening MA1 and second micro-awakening MA2, final wake-up time ( twake ), and wake-up time ( trise ) is included.

[0059] As used herein, a sleep session can be defined in multiple ways. For example, a sleep session can be defined by an initial start time and an end time. In some implementations, a sleep session is a period of time during which a user is asleep, i.e., a sleep session has a start time and an end time, and during a sleep session, the user does not wake up until the end time. In other words, periods during which the user is awake are not included in a sleep session. From this initial definition of a sleep session, if a user wakes up and falls asleep multiple times in the same night, each sleep interval separated by an interval of awakening constitutes a sleep session.

[0060] Alternatively, in some implementations, a sleep session has a start time and an end time, and during a sleep session, the user can be woken up without ending the sleep session as long as the user is awake for a continuous duration that is less than a wakefulness threshold. The wakefulness threshold can be defined as a percentage of the sleep session. The wakefulness threshold can be, for example, about 20 percent of the sleep session, about 15 percent of the sleep session duration, about 10 percent of the sleep session duration, about 5 percent of the sleep session duration, about 2 percent of the sleep session duration, etc., or any other threshold percentage. In some implementations, the wakefulness threshold is defined as, for example, about 1 hour, about 30 minutes, about 15 minutes, about 10 minutes, about 5 minutes, about 2 minutes, etc., or any other amount of time.

[0061] In some implementations, a sleep session is defined as the total time from the evening when the user first went to bed to the morning after the user last left bed. In other words, a sleep session can be defined as the first time (e.g., 10 PM) that can be called the current night on a first date (e.g., Monday, January 6, 2020). If the user first goes to bed with the intention of sleeping (e.g., without the intention of watching TV or playing on their smartphone before bed), the next date (e.g., Tuesday, January 7, 2020) can be called the second day (e.g., 7 AM), and if the user wakes up and does not intend to go back to sleep, the next morning can be called the next day.

[0062] Returning to FIG. 3 , the time to bed tbed prior to sleep onset (e.g., when the user lies or sits in bed) is associated with the time the user first enters bed (e.g., bed 230 in FIG. 2 ). The time to bed tbed can be determined based on a bed threshold duration to distinguish between the time the user enters bed to sleep and the time the user enters bed for other reasons (e.g., to watch television). For example, the bed threshold duration can be at least about 10 minutes, at least about 20 minutes, at least about 30 minutes, at least about 45 minutes, at least about 1 hour, at least about 2 hours, etc. Although the time to bed tbed is described herein with reference to a bed, more generally, the time to bed tbed can refer to the time the user first enters a sleeping location (e.g., a couch, chair, sleeping bag, etc.).

[0063] The time to sleep onset (tGTS) is associated with the time (tbed) at which the user first attempts to fall asleep after getting into bed. For example, after getting into bed, the user may relax and engage in one or more activities (e.g., reading, watching television, listening to music, using the user device 170, etc.) before attempting to fall asleep. The initial sleep time (tsleep) is the time at which the user first falls asleep. For example, the initial sleep time (tsleep) may be the time at which the user first enters a non-REM sleep stage.

[0064] Last wake up time twake is the time associated with the time the user woke up without going back to sleep (e.g., the user woke up in the middle of the night, rather than going back to sleep again). After the user initially falls asleep, they may experience one or more involuntary micro-awakenings (e.g., micro-awakenings MA1 and MA2) of short duration (e.g., 5 seconds, 10 seconds, 30 seconds, 1 minute, etc.). Final Wake Time twakeConversely, the user falls asleep again after micro-arousals MA1 and MA2. Similarly, the user may experience one or more conscious awakenings (e.g., waking to go to the bathroom, accompany a child or pet, walk in their sleep, etc.) after initially falling asleep. However, since the user returns to sleep after awakening A, the final wake-up time may be determined based on, for example, an awakening threshold duration (e.g., the user must be asleep for at least 15 minutes, at least 20 minutes, at least 30 minutes, at least 1 hour, etc.). twake can be defined.

[0065] Similarly, the wake-up time trise is associated with the time the user leaves bed intending to end the sleep session (e.g., rather than waking up during the night to go to the bathroom, attend to a child or pet, sleepwalk, etc.). That is, the wake-up time trise is the last time the user leaves bed without returning until the next sleep session (e.g., the following evening). Thus, the wake-up time trise can be defined, for example, based on an elevated threshold duration (e.g., the user has left bed for at least 15 minutes, at least 20 minutes, at least 30 minutes, at least 1 hour, etc.). The bedtime tbed for the second subsequent sleep session can also be defined based on an elevated threshold duration (e.g., the user has left bed for at least 4 hours, 6 hours, 8 hours, 12 hours, etc.).

[0066] As shown above, the user can measure the time from the first time they went to bed (tbed) to the last time they woke up ( trise ) during the night to get out of bed. In some implementations, the final wake time is identified or determined based on a predetermined threshold duration of time following an event (e.g., falling asleep or getting out of bed). twake and / or final ascent time triseは , as follows. The duration of such thresholds can be customized for the user. For a typical user who goes to bed in the evening and wakes up / goes out in the morning, the last wake-up time ( twake ) or wake-up time ( trise ) to bedtime (tbed), sleep onset time (tGTS) or initial sleep time (tsleep ) can be used from about 12 hours to about 18 hours. A shorter threshold period may be used for users who spend more time in bed (e.g., between about 8 hours and about 14 hours). The threshold period can be initially selected and / or later adjusted based on the system monitoring the user's sleep behavior.

[0067] TIB (total time in bed) is the time from when you went to bed to when you woke up. trise Total sleep time (TST) is the time from the initial sleep time to the wake-up time, excluding conscious or unconscious awakenings and micro-awakenings. Generally, total sleep time (TST) is shorter than total time in bed (TIB) (e.g., 1 minute, 10 minutes, 1 hour shorter, etc.). For example, referring to the timeline 300 in FIG. 3, it is as follows: Total sleep time (TST) is the time from the initial sleep time to the wake-up time. tsleep to last wake-up time twake and excludes the duration of the first micro-awakening MA1, the second micro-awakening MA2, and the awakening A. In this example, the total sleep time (TST) is set to be shorter than the total time in bed (TIB).

[0068] In some implementations, total sleep time (TST) can be defined as continuous total sleep time (PTST). In such implementations, continuous total sleep time excludes a predetermined initial portion or period of the first non-REM stage (e.g., a light sleep stage). For example, the predetermined initial portion can be between about 30 seconds and about 20 minutes, between about 1 minute and about 10 minutes, between about 3 minutes and about 5 minutes, etc. Continuous total sleep time is an indicator of continuous sleep and smooths the sleep-wake hypnogram. For example, when a user first falls asleep, the user may be in the first non-REM stage for a very short time (e.g., about 30 seconds), then return to the wake stage for a short time (e.g., 1 minute), and then return to the first non-REM stage. In this example, continuous total sleep time excludes the first instance (e.g., about 30 seconds) of the first non-REM stage.

[0069] In some implementations, a sleep session begins at bedtime (tbed) and ends at wake-up time ( trise ), i.e., a sleep session is defined as the total time in bed (TIB). tsleep ) and the final wake-up time ( twake ) In some implementations, a sleep session is defined as total sleep time (TST). In some implementations, a sleep session is defined as starting at sleep onset time (tGTS) and ending at final wake time ( twake ) In some implementations, a sleep session is defined as starting at sleep onset time (tGTS) and ending at wake-up time ( trise ) In some implementations, a sleep session is defined as starting at bedtime (tbed) and ending at final wake-up time ( twake ) In some implementations, a sleep session is defined as ending at the initial sleep time ( tsleep ) and the rise time ( trise ) is defined as ending in

[0070] 4, a method 400 for performing a reaction time test is shown, according to some implementations of the present disclosure. One or more steps of method 400 can be performed using elements or aspects of system 100 (FIG. 1.2).

[0071] Step 402 of method 400 includes initiating a reaction time test by generating a stimulus at an initial time point. In some implementations, the stimulus may be generated by, for example, a light source. The light source may be a light emitting diode (LED) coupled to respiratory therapy device 122, electronic device 170, user interface 124, conduit 126, or a combination thereof. In some implementations, display 128 of respiratory therapy system 120 and / or display 172 of user device 170 may be used as the light source for generating the stimulus.

[0072] In some implementations, the stimulus is a sound generated, for example, by speaker 142 or a speaker coupled to the housing of user device 170. For example, user device 170 can be a smart speaker, which can generate the sound stimulus. In some implementations, the speaker that generates the sound stimulus is located at least partially within the housing of respiratory therapy device 122 and / or coupled to user interface 124.

[0073] In some implementations, the stimulus can be a vibration generated by and / or caused by the motor of the respiratory therapy device 122. For example, the revolutions per minute (RPM) of the motor of the respiratory therapy device 122 can be increased and / or decreased to vibrate the respiratory therapy device 122. For example, changing the RPM from 3000 RPM to 10000 RPM can cause the vibration to occur. The motor RPM can vibrate between two or more different levels. The user 210 (FIG. 2) can interpret the sudden vibration of the motor as receiving a vibration stimulus. The vibration stimulus can come from other sources, such as a vibration in the user device 170. For example, the user's 210 smartphone or alarm clock can vibrate to provide the vibration stimulus to the user 210.

[0074] In some implementations, the stimulus is generated by varying the pressure of the generated pressurized air supplied by the respiratory therapy device 122. For example, the user 210 wears the user interface 124, and the respiratory therapy device 122 supplies pressurized air to the user 210 at a first pressure level. The respiratory therapy device 122 can increase or decrease the pressure of the pressurized air to a second pressure level, thereby providing the stimulus to the user 210. The second pressure level is different from the first pressure level such that the user 210 can sense the change in the pressurized air being provided by the respiratory therapy device 122. In some implementations, the respiratory therapy device 122 returns the pressure of the pressurized air from the second pressure level to the first pressure level. As such, the generated stimulus includes providing pressurized air at either a temporarily increased pressure level or a temporarily decreased pressure level, interrupting the first pressure level for a period of time.

[0075] In some implementations, the stimulus includes the respiratory therapy device 122 ceasing to supply pressurized air to the user 210. In some implementations, the stimulus includes the respiratory therapy device 122 beginning to supply pressurized air to the user 210.

[0076] Step 404 of method 400 includes receiving a response to the stimulus from user 210 at a second time. In some implementations, the response is an exhaled airflow from user 210 detected using system 100. For example, flow sensor 134 and / or pressure sensor 132 may be coupled to respiratory therapy device 122, user interface 124, conduit 126, or any combination thereof. Flow sensor 134 may detect the exhaled airflow as a change in flow rate in conduit 126. Similarly, pressure sensor 132 may detect the exhaled airflow as a change in pressure in conduit 126.

[0077] In some implementations, the exhaled airflow from the user 210 is detected using the microphone 140. The microphone 140 can capture the breathing pattern of the user 210, and based on the timing of the generated stimulus of step 402 and the exhaled airflow detected by the microphone 140, the control system 110 can determine that the exhaled airflow being detected by the microphone 140 is responsive to the generated stimulus. For example, the control system 110 can determine that the exhaled airflow does not match the breathing pattern of the user 210 and therefore must be responsive to the generated stimulus of step 402.

[0078] In some implementations where exhaust airflow from the user 210 is detected in response to the generated stimulus in step 402, the timing of the generated stimulus is correlated with the breathing pattern of the user 210. For example, if the control system 110 determines that the user 210 is about to begin exhaling after inhaling, the control system 110 does not generate the stimulus. The control system 110 can provide the stimulus when the user 210 is about to begin inhaling or any time while the user 210 is inhaling. The control system 110 can analyze the breathing pattern of the user 210 under these scenarios to detect deviations from the breathing pattern and determine whether the user 210 is responding to the generated stimulus via the exhaust airflow. That is, a sudden increase in exhalation pressure or a short inhalation followed by an exhalation may indicate a response to the generated stimulus with an exhalation airflow. In some implementations, a correction factor is included to account for a delay associated with when within the breathing cycle (or breathing pattern) of the user 210 the stimulus is provided to the user 210.

[0079] In some implementations, the user 210's breathing cycle can conform to a rhythm that can be represented as a sine wave graph. The peaks of the sine wave graph represent the instants in a breathing cycle when the user 210 fully inhales, and the valleys of the sine wave graph represent the instants in a breathing cycle when the user 210 fully exhales. If a stimulus is applied to the user 210 at the valley just as the user 210 begins to inhale, the user 210 may have difficulty exhaling air without first continuing to inhale, since they have air to exhale. On the other hand, if a stimulus is applied at the peak just as the user 210 begins to exhale, the user 210 may be more likely to exhale. Therefore, a correction factor may be larger when stimulating between breathing cycles compared to when stimulating at the peak of a breathing cycle.

[0080] In some implementations, the user 210 may breathe normally using the respiratory therapy system 120, and the pressure and / or flow rate of the pressurized air delivered to the user 210 using the respiratory therapy system 120 may be monitored prior to delivery in step 402. The pressure and / or flow rate may be monitored for 5 seconds, 10 seconds, 20 seconds, etc. By monitoring the pressure and / or flow rate, the control system 110 may determine fluctuations in the pressure and / or flow rate that are attributable to the normal breathing pattern of the user 210. By determining fluctuations in the pressure and / or flow rate that are attributable to the normal breathing pattern of the user 210, the control system 110 may detect deviations from the normal breathing pattern in response to a stimulus.

[0081] In some implementations, in step 404, the response from user 210 is a tap, a touch, or more generally, an intentional physical contact or movement to user device 170, respiratory therapy device 122, user interface 124, and / or conduit 126. The intentional physical contact may be detected by display device 172 of user device 170 or display device 128 of respiratory therapy system 120 (e.g., display device 172 or display device 128 is a touch-sensitive display configured to receive touch input from user 210). The sensed intentional physical contact may be due to movement of user 210's head.

[0082] In some implementations, the intended physical contact is detected by one or more sensors 130. For example, the conduit 126 or the user interface 124 may include a force sensor 162 to detect an external force or disturbance on either the conduit 126 or the user interface 124. For example, the force sensor 162 may include an acceleration sensor to detect movement of the conduit 126 or the user interface 124. In another example, a strain gauge sensor 164 or a capacitance sensor 160 may be included on the user interface 124 to detect a tap or touch on the user interface 124. The one or more sensors 130 may be used to determine whether the user 210 moves position in response to the generated stimulus of step 402, whether the user 210 moves their head in response to the generated stimulus, or whether the user 210 makes a gesture that disturbs or is detected on the user interface 124 or the conduit 126. In some implementations, the intended physical contact may include pressing a button coupled to the user interface 124.

[0083] In some implementations, responses from the user 210 include gestures that may not be classified as intentional physical contact. Gestures may include hand movements (e.g., waving, thumbs up, peace sign, etc.), head movements (e.g., nodding, shaking head, etc.), facial movements (e.g., smiling, raising eyebrows, etc.), etc. The gestures are detected by one or more sensors 130 integrated into the smart device and / or respiratory therapy system 120. For example, the motion sensor 138, the IR sensor 152, and / or the camera 150 may be used to capture video and / or sequential images to detect the gestures.

[0084] In some implementations, the response from the user 210 is verified by multiple sensors in the one or more sensors 130. For example, the control system 110 can use any of the motion sensor 138, the acoustic sensor 141, the RF sensor 147, or a combination thereof to increase confidence in the intended physical contact and / or non-physical contact gesture detected by the one or more sensors 130. For example, the motion sensor 138 can sense movement of the user 210 before a tap is detected by the force sensor 162 on the user interface 124 or on the conduit 126. Combining the movement sensed by the motion sensor 138 with the movement of the force sensor 162 can increase confidence that the user 210 responded to the generated stimulus of step 402. In some implementations, audio from the microphone 140 can be combined with image capture from the camera 150 and / or the IR sensor 152 to verify the non-physical contact gesture.

[0085] In some implementations, in step 404, the response from user 210 is the voice of user 210 captured by microphone 140. Microphone 140 may include an array of microphones so that the voice captured by microphone 140 can be localized. In that way, other sensors in one or more sensors 130 can be used to verify that the voice captured by microphone 140 comes from user 210 and not someone else (e.g., bed partner 220).

[0086] Step 406 of method 400 includes determining a first score based at least in part on the first time point and the second time point. In some implementations, control system 110 generates a first timestamp when the generated stimulus of step 402 is presented to user 210 and a second timestamp when the response of step 404 is received from user 210. Control system 110 can then calculate the first score, which is the difference between the first timestamp and the second timestamp.

[0087] In some implementations, the difference between the first and second timestamps is adjusted for different variables. For example, one or more delays related to the dynamics of the user's 210 response are taken into account. As an example, the user 210 may see an LED light up on the user interface 124 and may quickly tap on the user interface 124 to register a response. Depending on where the user's 210 palm is located, the user 210 may experience either a long or short delay before their palm reaches the user interface 124. This delay may be taken into account when determining the initial score.

[0088] The user 210 may be at the beginning of inspiration when the stimulus is given, and therefore the user 210 decides to take a breath in enough to reach minimum vital capacity before expelling air from their lungs. The delay until the patient reaches a comfortable minimum vital capacity sufficient to expel air can be taken into account in determining the initial score.

[0089] Another example takes into account the dynamics of the delay associated with the generation of a light stimulus or a sound stimulus. For example, there may be a finite delay between the time when the control system 110 decides to provide a light stimulus and the time when the light source actually provides the light signal. Similarly, there may be a finite delay between the time when the control system 110 decides to provide a sound stimulus and the time when the sound stimulus is actually generated. This delay dynamics can be used to determine a correction factor when determining the initial score.

[0090] In some implementations, the effects of noise are taken into account when determining the initial score, for example, bounce effects such as switch bounce and multiple consecutive registrations in the received response of step 404 are smoothed with a high-pass signal filter.

[0091] In some implementations, steps 402 and 404 are repeated multiple times to provide multiple pairs of timestamps for each stimulus-response pair. The multiple pairs of timestamps are used with various statistical models to determine an initial score. For example, for multiple pairs of timestamps, the duration between each pair of timestamps is calculated. Each duration can be included in a set to determine a median, mode, mean, or weighted average as the first score. In some implementations, each of the durations is adjusted for different variables, as described above, before applying the statistical model to determine the first score.

[0092] In some implementations, steps 402 and 404 are repeated multiple times to obtain multiple sets of timestamps over a period of time, which may be at least 30 seconds. In some examples, if the user 210 fails to respond within a threshold period of time (e.g., does not respond within 0.5 seconds), the control system 110 determines that the generated stimulus was ignored by the user 210 and does not include the timestamp of the ignored stimulus when determining the first score. In some implementations, steps 402 and 404 are performed only once over the period of time.

[0093] In some implementations, if the response in step 404 is exhaust airflow from the user 210, steps 402 and 404 are repeated multiple times. Each of the stimuli generated in step 402 is provided at a different point in time during the user's 210 breathing pattern. For example, the stimuli can occur multiple times during inhalation, exhalation, or a combination of both. By receiving a response to each of the generated stimuli, multiple stimulus-response paired data can be obtained. The multiple stimulus-response paired data can be averaged, regressed, or filtered to reduce effects associated with catching the user 210 with a stimulus at an inappropriate time (e.g., presenting a stimulus to the user 210 at the end of exhalation and having the user quickly inhale to respond to the stimulus).

[0094] In some implementations, the first score is determined based on receiving user feedback provided by the user 210. The user feedback may include an analog assessment of the user 210's subjective energy level. The user device 170 may receive the user feedback (e.g., via alphanumeric text, audio text, etc.). In some implementations, the user 210 is prompted to provide the user feedback. For example, the control system 110 may cause one or more prompts to be displayed on the display device 172 of the user device 170 that provides an interface for the user 210 to provide the user feedback (e.g., the user clicks or taps to enter the feedback, the user enters the feedback using an alphanumeric keyboard, etc.). The received user feedback may be stored, for example, in the storage device 114.

[0095] Optionally, step 408 of method 400 includes communicating results related to the first score to the user, such as via user device 170. For example, the communicated results may include the initial score and the data collected to generate the initial score. The collected data may be provided in a comma-separated values ​​file to enable user device 170 to graph the data collected during the reaction time test. The results are communicated to the user, such as via user device 170, to help user 210 gauge their baseline performance on the reaction time test.

[0096] In some implementations, method 400 is performed multiple times throughout a day or week of user 210. For example, user 210 wakes up in the morning while still coupled to user interface 124. Control system 110 determines a sleep-wake signal associated with user 210 indicating that user 210 has changed sleep state to a wakeful sleep state. Control system 110 can then initiate a first test by generating stimulation in step 402, receiving a response using respiratory therapy system 120 in step 404, and determining a first score. During the day, control system 110 can cause user device 170 to initiate a second test in which user 210 engages user device 170 and determines a second score. In some implementations, the second test is performed based on a time of day, such as during user 210's lunch break. Before going to bed, the user 210 can engage the respiratory therapy system 120 and the control system 110 can cause the respiratory therapy system 120 to perform a third test and obtain a third score.

[0097] In some implementations, before generating the stimulus in step 402, the control system 110 determines whether the user 210 is ready to receive the stimulus. The control system 110 can provide an alert to the user informing them when the reaction time test exemplified by the method 400 will begin, for example, that the reaction time test will begin within an indicated time period, for example, within 30-60 seconds or within 1-2 minutes of the alert. The alert provides the user 210 with a warning to prevent them from disengaging from the user interface 124 or performing another task that may distract them. The warning can include a prompt displayed on the display 172 of the user device 170 or the display 128 of the respiratory therapy system 120. The warning can include a sound emitted by a speaker partially disposed within or coupled to the housing of the user device 170. The warning can include a noise generated by a motor of the respiratory therapy device 122 or a motor of the user device 170. The alert can include a light generated by a light source coupled to respiratory therapy system 120 or a light source coupled to user device 170. The alert can include a vibration of a motor of respiratory therapy device 122 or a motor of user device 170.

[0098] In some implementations, user 210 provides an acknowledgment to the provided alert. This acknowledgment indicates that user 210 is ready to begin the reaction time test. The acknowledgment may include a touch signal generated by display device 172 or display device 128 in response to user 210 touching display device 172 or display device 128, respectively. The acknowledgment may include a button press signal coupled to the housing of respiratory therapy device 122 or a button press signal coupled to the housing of user device 170. The acknowledgment may include audio data received via microphone 140.

[0099] In some implementations, when method 400 is performed using different systems (e.g., using user device 170 to generate stimuli and receive responses, using respiratory therapy system 120 to generate stimuli and receive responses, etc.), control system 110 is configured to determine a normalization relationship to relate scores obtained from one system to scores obtained from another system. For example, a touch input as a response on respiratory therapy system 120 or user device 170 may be detected more quickly than detecting the exhaled airflow of user 210. Thus, when scores are determined throughout the day using different stimuli and different responses, the determined scores may be normalized to remove inconsistencies related to the mode of obtaining responses from user 210.

[0100] In some implementations, the control system 110 is configured to determine the normalized relationship over a period of time. The control system 110 can track and associate each of the determined scores with a respective mode for obtaining a response from the user 210. In that way, before performing any reaction time test, the control system 110 can predict the score for a particular mode for obtaining a response. The predicted score is used to assess the accuracy of the determined normalized relationship. As more scores are determined from each mode, the normalized relationship becomes more accurate. In some implementations, a predicted score within a percentage (e.g., 1%, 2%, 5%, etc.) of the determined score is considered accurate.

[0101] 5, a method 500 according to some implementations of the present disclosure is shown. Method 500 can be implemented using any combination of elements or aspects of system 100 described herein.

[0102] Step 502 of method 500 may be the same as or similar to step 402 of method 400 (FIG. 4) and may include generating a first stimulus at a first time point. The generation of the first stimulus may indicate the start of a first test.

[0103] Step 504 of method 500 is the same as or similar to step 404 of method 400 (FIG. 4) and includes receiving an initial response to a first stimulus from a user (e.g., user 210 of FIG. 2). At a first time point, the response to the initial stimulus can be detected using respiratory therapy system 120.

[0104] Step 506 of method 500 is the same as or similar to step 406 of method 400 (FIG. 4) and includes determining a first score based at least in part on the first time point and the second time point. One or more of steps 502, 504, or 506 can be performed multiple times.

[0105] Step 508 of method 500 includes delivering pressurized air to user 210 during a first sleep session. For example, a first score is determined before user 210 goes to bed. During sleep, respiratory therapy system 120 provides pressurized air to user 210, as shown in FIG. 2 .

[0106] Step 510 of method 500 is the same as or similar to step 402 of method 400 (FIG. 4) and includes generating a second stimulus at a third time point. The generation of the second stimulus may indicate the start of a second test. Step 510 is performed after the first sleep session while user 210 is awake.

[0107] Step 512 of method 500 is the same as or similar to step 404 of method 400 (FIG. 4) and includes receiving a second response to the second stimulus from user 210 at a fourth time. The response to the second stimulus can be detected using respiratory therapy system 120.

[0108] Step 514 of method 500 is the same as or similar to step 406 of method 400 (FIG. 4) and includes determining a second score based at least in part on the third and fourth time points. One or more of steps 510, 512, or 514 may be performed multiple times.

[0109] Step 516 of method 500 is similar to step 408 of method 400 (FIG. 4) and includes communicating results associated with the first score and the second score to a user, such as via user device 170. The results may include a statistical analysis between the first score and the second score.

[0110] In some implementations, the results communicated to the user device 170 may include physiological data (e.g., heart rate, respiration rate, EEG, EMG, electrooculography (EOG), pleuropygiography, etc.) and / or demographic data (e.g., age, gender, etc.). One or more sensors 130 may collect physiological data of the user 210 before or during a first test and after or during a second test. The physiological data may provide additional insight into treatment with the respiratory therapy system 120. For example, resting heart rate and heart rate variability (HRV) are expected to decrease over time with sustained use of the respiratory therapy system 120.

[0111] In some implementations, collected physiological and / or demographic data of the user 210 can be used to make inferences or predictions. For example, changes in heart rate, such as HRV, can be captured at different times during a reaction time test (e.g., during the first test, the second test, and other subsequent tests). The captured HRV can be used as a baseline (or can be used to determine a baseline) for typical changes in heart rate associated with a particular level of vigilance (e.g., alertness, drowsiness, etc.). Thus, by correlating the collected physiological data of the user 210 with reaction time, future monitored changes in HRV can be associated with estimated reaction time and / or with the effectiveness of a treatment. In some implementations, tests can be classified according to the mode of stimulus used in the test (e.g., auditory stimulus, light stimulus, pressure change, etc.) and the mode of response in the test. This classification allows for different calibration coefficients to be applied between different modes.

[0112] In some implementations, control system 110 can trigger changes in settings of respiratory therapy system 120 based at least in part on results associated with the first score and the second score. For example, the results can indicate that the second score is objectively worse than the first score, so that for the next sleep session, respiratory therapy system 120 can trigger adjustments to (i) the pressure setting of the supply of pressurized air provided by respiratory therapy device 122, (ii) the humidity setting of the supply of pressurized air provided by respiratory therapy device 122, or (iii) both (i) and (ii).

[0113] In some implementations, the steps of method 500 are repeated over a period of time to obtain a trend in scores relative to the total number of tests administered. The control system 110 can make adjustments to the pressure or humidity settings of the supplied pressurized air based at least in part on the trend in scores that indicate the user 210 is objectively performing better or worse over time.

[0114] Referring to FIGS. 6A-6C, a sequence for performing a reaction time test is shown. FIG. 6A illustrates a user 610 wearing a user interface 624 according to some implementations of the present disclosure. The user interface 624 may be the same as or similar to the user interface 124 described herein. The user interface 624 may include a cushion, a frame, a connector (for connecting the frame to a conduit), multiple straps, or any combination thereof. FIG. 6A illustrates a cross-sectional cutaway view of the user interface 624. The user interface 624 is connected to a conduit 626 (which may be the same as or similar to the conduit 126) and connected to a respiratory therapy device (e.g., the respiratory therapy device 122 in FIG. 1). The user interface 624 includes a light source 611 (e.g., one or more LED lights) capable of emitting light of one or more colors.

[0115] In FIG. 6B, according to some implementations of the present disclosure, the user 610 receives a light stimulus via the light source 611. The illumination of the light source 611 is a visual indicator (i.e., a light stimulus) for the user 610 to respond. In FIGS. 6A and 6B, before the visual indicator is provided, the user 610 is in a normal breathing pattern or normal breathing cycle. That is, depending on where the user 610 is in the breathing cycle, the user 610 can inhale or exhale. The user can breathe through the nose and / or mouth in FIGS. 6A and 6B.

[0116] FIG. 6C illustrates a user 610 intentionally responding to a light stimulus, according to some implementations of the present disclosure. In FIG. 6C, the user 610 blows into the user interface 624, as indicated by the arrow from the user's lips / mouth. The arrow indicates that the user 610 is expelling airflow (e.g., blowing, puffing, etc.) at a rate higher than the user's 610's normal breathing pattern. In some implementations, a flow sensor 134 and / or a pressure sensor 132 integrated into the respiratory therapy system 120 can be used to determine that the user 610 has expelled airflow. In some implementations, a sensor external to the respiratory therapy system 120 is used to determine that the user 610 has expelled airflow. The sensor may be communicatively coupled to the respiratory therapy system 120 and / or the respiratory therapy device 122.

[0117] 6A-6C are one illustrative example of the concepts of the present disclosure, where a light source 611 provides a stimulus and air exhaled by a user 610 provides a response to the stimulus. As described herein, the time between the stimulus and the response can be used to measure the user's 610 current psychomotor reaction time (or the like).

[0118] In some implementations, reaction time tests need not be captured for a specific individual. A machine learning model can be trained with data from one or more individuals and used to predict how a specific individual will perform on a reaction time test. Advantages of using a trained machine learning model for reaction time estimation or prediction include: (a) eliminating the need for a specific individual to undergo reaction time tests over an extended period of time; (b) reducing the data requirements for estimating reaction time tests by leveraging data from multiple individuals; (c) estimating reaction times from passive data, i.e., data for which a specific individual does not provide input; and (d) predicting predicted reaction times further in time. The present disclosure provides a reliable method for estimating reaction times and using these estimates to suggest treatment changes to an individual.

[0119] 7 is a flow diagram for generating a response to a user based on the user's alertness level, according to some implementations of the present disclosure. Method 700 can be implemented using any combination of elements or aspects of system 100 described herein.

[0120] Step 702 includes receiving data related to a user (e.g., user 210) during a sleep session. In some implementations, control system 110 receives data from respiratory therapy system 120, sensor 130, user device 170, or any combination thereof. The received data may include a flow signal, a respiratory signal, a respiratory rate, respiratory rate variability, inspiratory amplitude, expiratory amplitude, an inspiratory-expiratory ratio, or any combination thereof. The flow signal from flow sensor 134 may be used to derive a respiratory flow signal indicative of the volumetric flow of air inhaled and exhaled by user 210. The respiratory rate is the number of breaths the user 210 takes per unit time (e.g., 15 breaths per minute, 20 breaths per minute, etc.), and a breath consists of an inhale and an exhale. The inspiratory amplitude and expiratory amplitude are volumetric measurements of air during the inhalation and exhalation cycles while the user 210 is breathing.

[0121] The flow sensor 134, the pressure sensor 132, the temperature sensor 136, or any combination thereof, can be used to measure some of these respiratory measures. The control system 110 can derive some of these respiratory measures (e.g., the inspiratory-to-expiratory ratio can be derived by dividing the inspiratory amplitude by the expiratory amplitude). In some implementations, the inspiratory-to-expiratory ratio can be determined as the ratio of time spent by inhalation to the ratio of time spent by exhalation.

[0122] In step 702, the data received may include flow and / or pressure settings of respiratory therapy system 120, the heart rate of user 210, heart rate variability of user 210, blood pressure of user 210, blood pressure variability of user 210, movement of user 210, or any combination thereof. Measuring these parameters using system 100 has been previously described in connection with FIG. 1.

[0123] The data received in step 702 may include sleep stages, sleep states, the time the user spends in a sleep state, the time the user spends in a sleep state, the ratio of the time the user spends in a sleep state to the time of the sleep session, the ratio of the time the user spends in a sleep state to the time of the sleep session, the ratio of the time the user spends in a sleep state to the time of the sleep session, the ratio of a first sleep state to a second sleep state, the ratio of a first sleep stage to a second sleep stage, or any combination thereof. As described in connection with FIG. 1 , the control system 110 can determine the sleep states and / or sleep stages of the user 210 using physiological data generated by the sensors 130. Once the sleep states and / or sleep stages are determined for the sleep session, other parameters can be determined, such as the ratio of the duration of one sleep state (and / or stage) to the duration of another sleep state (and / or stage). Example ratios include the ratio of light sleep, deep sleep, REM sleep, etc.

[0124] The data received in step 702 may include the number of events per time, the pattern of events, the duration of each event, or any combination thereof. Examples of events include central apnea, obstructive apnea, mixed apnea, hypopnea, snoring (e.g., simple or complex), periodic limb movements, arousals, choking, epileptic episodes, seizures, or any combination thereof. The flow sensor 134 may be used to measure snoring vibrations. The received data may include an apnea-hypopnea index (AHI), which is an index of sleep apnea severity determined as the average number of apneas and hypopneas occurring per unit of time (e.g., per hour, per day, etc.). The received data may include a residual AHI, a ratio of the residual AHI during treatment to the AHI off treatment, or both. A residual AHI may be defined as residual events detected (and not effectively treated) by the respiratory therapy device 122 operating in a continuous pressure mode or an auto-adjusting mode. Preferably, this residual AHI is as low as possible, e.g., an AHI of 5 or less. An AHI above 0 (or even 5 or 10) may discourage users from continuing treatment due to perceived ineffectiveness and reduced alertness relative to desired levels. Even with a low residual AHI, apneas and hypopneas occurring during REM sleep shortly before wakefulness may signal potential wakefulness issues, such as anxiety, drowsiness, and feelings of tension due to stress and sympathetic activation caused by untreated apneas and hypopneas. Similarly, frequent mask leaks or mouth leaks near wakefulness time can negatively impact short-term alertness and well-being (or lack thereof). Sympathetic activation, exemplified via galvanic skin response (GSR) or heart rate variability (HRV) metrics, along with residual apnea detection by respiratory therapy device 122, can help clarify these links between perceived anger and estimated short-term alertness. On the other hand, a balanced amount of restorative sleep, with the right proportion and duration of REM and deep sleep, can help you feel refreshed and ready for the day, with vagal or parasympathetic activation predominating when you first wake up.

[0125] With respect to a sleep session, "on therapy" describes when user 210 is asleep and engaged with respiratory therapy system 120 during the sleep session, and "off therapy" describes when user 210 is asleep and not engaged with respiratory therapy system 120 during the sleep session. For example, during a sleep session, respiratory therapy system 120 may generate sleep-related data for user 210, and external sensors in sensors 130 may also generate sleep-related data for user 210. If control system 110 receives sleep-related data for user 210 only from the external sensors and not from respiratory therapy system 120, control system 110 may determine that user 210 is off therapy. The period during which sleep-related data is received from respiratory therapy system 120 may be determined by timestamps of when respiratory therapy system 120 begins providing sleep-related data and when respiratory therapy system 120 stops providing sleep-related data.

[0126] The data received in step 702 may include therapy effectiveness, sleep efficiency, the user's 210 time in bed, the ratio of on-therapy sleep efficiency to off-therapy sleep efficiency, the ratio of on-therapy sleep time to sleep session duration, the ratio of on-therapy sleep time to off-therapy sleep time, or any combination thereof. Therapy effectiveness includes whether an unintentional leak associated with the respiratory therapy system 120 during the sleep session was below a threshold. Sleep efficiency provides an indication of how well the user 210 slept during the sleep session and may be measured as the ratio of the time the user 210 spent asleep to the time the user 210 was in bed. For example, if the user 210 slept for 6 hours but spent 8 hours in bed, the sleep efficiency may be provided as 75%.

[0127] The received data in step 702 may include a sleep score, a mind charge score, a body charge score, or any combination thereof. Examples of such scores and methods for calculating such scores are described, for example, in WO2015 / 006364, which is incorporated herein by reference in its entirety. The sleep score may be calculated using one or more sleep parameters previously described herein. In some implementations, the sleep score includes weighting of different parameters. The mind charge score may be based on the user's 210 percentage of REM sleep in the sleep session relative to the average user's REM sleep percentage in the same demographic as the user 210. The body charge score may be based on the user's 210 percentage of deep sleep in the sleep session relative to the average user's deep sleep percentage in the same demographic as the user 210. Demographic information may include age, gender, region, etc.

[0128] In some implementations, the control system 110 determines a sleep score based on measurement data representing the user's 210 movements, total sleep time, deep sleep time, REM sleep time, light sleep time, wake time after sleep onset, and sleep onset time. In some cases, the characteristics may include time-domain statistics and / or frequency-domain statistics. The sleep score includes a sum having multiple component values, each determined as a function of a measured sleep factor and a predetermined normative value for the sleep factor. The function may include a weighting variable that varies between 0 and 1. The weighting may be multiplied by the predetermined normative value. The function of at least one sleep factor for determining the component value may be an increasing function of the measured sleep factor, such as when the at least one sleep factor is total sleep time, deep sleep time, REM sleep time, or light sleep time. In some cases, the function of at least one sleep factor for determining the component value may be an initially increasing and then decreasing function of the measured sleep factor, such as when the at least one sleep factor is REM sleep time. The function of the at least one sleep factor for determining the component value may be, for example, a decreasing function of the measured sleep factor if the at least one sleep factor is one of time to fall asleep and time to wake after sleep onset.

[0129] In some implementations, the control system 110 communicates with a clinician / healthcare professional (HCP) if reduced alertness or vigilance is detected or estimated for the day. As an example, the user may be in a safety-critical role (e.g., a heavy machinery or public transportation operator) where reduced alertness could pose a risk or hazard. This may include the HCP recommending or configuring changes to the respiratory therapy device 122 (e.g., program adaptations or changes), changing medications, and / or recommending that the user refrain from certain high-risk activities pending further on-site evaluation.

[0130] In some implementations, the control system 110 obtains other information from the user 210 that can affect sleep. For example, the control system 110 may prompt the user 210 to input one or more of their daily caffeine consumption, daily alcohol consumption, daily stress level, and daily exercise amount. The sleep score may capture one or more of the following aspects: effectiveness of the user interface 124 (e.g., low leak and / or good seal), time using the respiratory therapy device 122, reduced awakenings or arousals, percentage of deep sleep, percentage of REM sleep, apneas effectively treated without disturbing the user 210, residual AHI, subject input obtained from the user 210 (e.g., based on how the user 210 feels), sleep cycle sufficiency, snoring, residual snoring after treatment, sleep efficiency, sleep quality, sleep latency, sleep fragmentation, comparison with people of a similar age, comparison with people of a similar gender, etc.

[0131] Step 704 includes determining a level of alertness for the user 210 using a machine learning model that uses the received data from step 702 as input. The determined level of alertness may be the level of alertness immediately after the user 210 awakens from sleep. The determined level of alertness may be the level of alertness at a future time after the user 210 awakens from sleep. For example, the user 210 awakens at 7:00 AM, and a determined level of alertness is provided at 3:00 PM. The attention level determination for a future time period can be windowed (e.g., 2 hours ahead, 12 hours ahead, 16 hours ahead, 24 hours ahead, etc.). The future attention level determination can be obtained approximately simultaneously after the user 210 awakens from sleep. In some implementations, the determined level of alertness tends to provide multiple levels of alertness. For example, the user 210 awakens at 7:00 AM, and the determined levels of alertness include multiple levels of alertness at 10:00 AM, 2:00 PM, 5:00 PM, 7:00 PM, and 9:00 PM. In some implementations, the control system 110 determines the alertness of the user 210 as an alertness score, as described further herein. Such a score may be based, for example, on an evaluation of reaction times measured after a stimulus and a comparison to expected reaction times, which may be derived from an individual's historical reaction time data, population-level reaction time data (optionally matched based on individual demographic and / or medical parameters), or a combination thereof. The alertness score may also be related to a circadian rhythm-based model of sleepiness. Other factors, such as diagnosed insomnia, OSA, CSA, delayed sleep phase syndrome (e.g., "social jet lag"), sleep deprivation syndrome (e.g., excess sleep debt), and / or depression, may be used in calculating the alertness score.

[0132] Step 706 includes generating a response to be communicated to user 210, optionally via a third party such as a physician, based at least in part on the determined alertness level. In some implementations, the generated response is a message including the determined alertness level, and control system 110 causes the message to be provided to user 210 via speaker 142, display device 128, display device 172, or any combination thereof. In some implementations, the generated response is an alarm, such as a visual alarm provided by a light source coupled to respiratory therapy system 120, an auditory alarm provided by speaker 142, and / or a vibration alarm provided by vibrating user device 170 and / or respiratory therapy device 122.

[0133] In step 706, in some implementations, the predicted length of the remaining duration of the sleep session is taken into consideration when generating a response. For example, if the user 210 is expected to wake up in 20 minutes, the control system 110 does not generate a response. On the other hand, if the user 210 is expected to wake up in 45 minutes or more, the control system 110 generates a response. For example, if the user 210 wakes up for a bathroom break, the response can be an alarm or message instructing the user 210 to engage with the respiratory therapy system 120 before returning to sleep. Thus, the control system 110 can utilize the user 210's regular wake-up time or regular bedtime to determine the remaining duration of the sleep session. That is, the user 210's typical sleep time is used to predict the remaining duration of the sleep session.

[0134] In some implementations, the control system 110 generates a response based on the user interface 124 not being safely engaged with the user 210 and the remaining duration of the sleep session being greater than a sleep duration threshold. For example, the user 210 may engage the user interface 124 such that an excess of supplied pressurized air leaks out of the user interface 124. Excessive leakage refers to air leaking out of the user interface 124 in excess of the user's 210 exhaled carbon dioxide (CO2)-containing breath. The microphone 140 and / or pressure sensor 132 may be used to determine excessive leakage at the user interface 124. If the user 210 sleeps with the user interface 124 not safely engaged, the control system 110 may estimate the remaining duration of the current sleep session. If the remaining duration is greater than or equal to the sleep duration threshold, the control system 110 generates a response. The sleep duration threshold may be 45 minutes, 1 hour, etc. The response may be an alarm to wake the user 210 to properly engage with the respiratory therapy system 120. The response may include a message instructing the user 210 to properly engage with the respiratory therapy system 120 .

[0135] In some implementations, the sleep duration threshold is determined based on the likelihood that the determined alertness level will improve with therapy for the remaining duration of the sleep session. The likelihood of improvement of the determined alertness level can be calculated from historical data, for example, as the number of apnea events the user 210 experienced per unit time when the user interface 124 was not firmly engaged by the user 210 multiplied by the remaining duration of the current sleep session. The likelihood of improvement can also be determined by probing various on-therapy periods for the remaining duration of the sleep session using a machine learning model. The determined likelihood can be compared to a threshold to determine whether to generate a response. For example, if the determined likelihood is greater than 0.90, the control system 110 generates a response. Furthermore, the response can be generated based on the magnitude of the potential improvement in the determined alertness level being equal to or greater than an improvement threshold. That is, if the determined level of attention is an attention score of 80 / 100 and the magnitude of improvement is determined to be 10 such that the user 210 can potentially reach 90 / 100, the control system 110 can determine that 10 is greater than 5 (which is the improvement threshold in this example) and generate a response.

[0136] In some implementations, in step 706, the generated response is further based at least in part on the duration of the sleep session. The control system 110 can determine the likelihood that extending the duration of the sleep session will improve the determined alertness level. A likelihood can be calculated based on the machine learning model by probing the machine learning model to predict the likelihood of longer sleep time. The control system 110 can generate a response based on the likelihood being above a threshold, the magnitude of the potential improvement to the determined alertness level being above an improvement threshold, or both. The generated response can include a message to the user instructing them to return to bed to extend the sleep session by 10 minutes, 30 minutes, 1 hour, 2 hours, etc. The generated response can include a message to the user 210 instructing them to sleep 10 minutes longer, 20 minutes longer, 1 hour longer, etc. in a future sleep session. For example, if the user 210 slept for 5 hours, the control system 110 can instruct the user 210 to sleep for 7 hours next time.

[0137] In some implementations, in step 706, the generated response is based at least in part on the duration of the portion of the sleep session in which the user is not engaged with the user interface 124. That is, after the user 210 awakens from sleep, the control system 110 determines the duration of the sleep session in which the user 210 was on therapy and the duration of the sleep session in which the user 210 was off therapy. The control system 110 determines whether to generate a response based on the duration of the sleep session in which the user 210 was on therapy or off therapy. In some implementations, the control system 110 determines the likelihood that the determined level of alertness can be improved during a future sleep session by increasing the duration of on therapy sleep or decreasing the duration of off therapy sleep. In some implementations, the likelihood is determined by using a machine learning model to determine whether the determined level of alertness has improved using different durations of off therapy and on therapy sleep for the same total number of sleep hours. In some implementations, the total number of sleep hours is increased or decreased when determining whether the determined level of alertness has improved. The control system 110 can generate a response based on the likelihood of exceeding the threshold, the magnitude of potential improvement in the determined alertness level above the improvement threshold, or both. The generated response is a message instructing the user 210 to wear the user interface 124 before a future sleep session. The generated response is a message instructing the user 210 to shorten the duration of future sleep sessions if the user interface 124 is being worn. For example, the control system 110 may determine that the user 210 slept for eight hours, but that the user 210 did not engage with the user interface 124 for five of those eight hours. The control system 110 may then recommend that the user 210 sleep for six and a half hours, seven hours, seven and a half hours, etc., for the next sleep session. In some implementations, the user 210 may have a severe AHI and be in bed for 12 to 14 hours, with some of that time not engaging with the user interface 124.The control system 110 can recommend that the user 210, through the user interface 124, reduce their bedtime to a healthier 7-9 hours of sleep. Thus, reducing their off-therapy time can reduce the total length of future sleep sessions required to achieve the same or greater level of alertness. The reduction recommended by the control system 110 can be based, at least in part, on the age of the user 210.

[0138] In some implementations, in step 706, the control system 110 generates a response based at least in part on the determined alertness level of step 704 satisfying a condition. The condition may include the determined alertness level being (i) less than or equal to the user's average alertness level, (ii) less than or equal to a threshold, or (iii) greater than or equal to a threshold. For example, the determined alertness level may be an alertness score of 75, which may be compared to a threshold of 80, and a response may be generated because the alertness score is less than the threshold of 80. In some implementations, the condition may include the determined alertness level at a future time being (i) less than the user's average alertness level, (ii) less than the threshold, or (iii) greater than or equal to the threshold. For example, the determined alertness level may be an alertness score of 75 at 3:00 PM, which may be compared to a threshold of 70, and a response may be generated because the alertness score at 3:00 PM is greater than the threshold of 70. The response may be a message informing the user 210 that the threshold has been exceeded in the determined alertness level (for a future time or the current time) and that the user 210 had a good sleep. The response is a message to the user 210 informing them that the determined alertness level (for a future time point or for the current time point) is below a threshold and that they should use more therapy or implement bedtime habits to get a better night's sleep so that future alertness levels can be improved.

[0139] In some implementations, the generated response is an encouraging message. An example message might be, "Your current alertness score is 50. When you wake up at 6:00 AM, remember to use your respiratory therapy device to raise your alertness score to 70." Another example might be, "Yesterday at 2:00 PM, your alertness score was 55. Use your respiratory therapy device for at least 5 hours tomorrow afternoon to improve your alertness score." Another example might be, "Just one more hour of sleep and your alertness will increase."

[0140] In some implementations, the generated response is further based in part on the effectiveness of the therapy during the sleep session, the effectiveness of the therapy during past sleep sessions, or both. The therapy effectiveness may be related to excessive leakage, as discussed above. Thus, the generated response may be a message instructing the user to improve the therapy effectiveness for a future sleep session or for the current sleep session by: (i) increasing the upper pressure limit of the supply of pressurized air provided by the respiratory therapy device 122 or decreasing the upper pressure limit of the supply of pressurized air; (ii) increasing the lower pressure limit of the supply of pressurized air or decreasing the lower pressure limit of the supply of pressurized air; (iii) replacing the user interface 124 coupled to the respiratory therapy device 122; (iv) adjusting the humidity of the supply of pressurized air; or (v) any combination of (i)-(iv).

[0141] Various implementations of the present disclosure described in connection with FIG. 7 utilized a machine learning model to determine alertness. Referring to FIG. 8, some implementations of the present disclosure provide a flow diagram for training a machine learning model to predict the alertness level of a target user (e.g., user 210). Method 800 can be implemented using any combination of elements or aspects of system 100 described herein.

[0142] Step 802 includes receiving historical sleep session data associated with at least one person for a plurality of historical sleep sessions. The at least one person may include (i) one or more people associated with or using a respiratory therapy system, (ii) one or more people not using a respiratory therapy system, or (iii) both (i) and (ii). For each sleep session in the plurality of historical sleep sessions, the historical sleep session data associated with each of the at least one person may include a sleep score, a cardiac charge score, a body charge score, a flow signal, a respiratory signal, a respiration rate, a respiration rate variability, an inspiratory amplitude, an expiratory amplitude, an inspiratory-expiratory ratio, a number of events per hour, an event pattern, a duration of each event, sleep states and / or sleep stages, time spent in sleep states and / or sleep stages, a sleep score, a respiratory signal, a respiration rate variability, an inspiratory amplitude, and a respiration rate variability. The parameters may include the inhalation-exhalation ratio, the number of events per hour, the pattern of events, the duration of each of the events, the sleep states and / or sleep stages, the time the person spends in the sleep states and / or sleep stages, the ratio of the time the person spends in the sleep states and / or sleep stages to the duration of the respective sleep session, the ratio of the first sleep state to the second sleep state, the ratio of the first sleep stage to the second sleep stage, the person's time in bed, the residual AHI, the pressure setting of the respiratory therapy system, the heart rate, the heart rate variability, the blood pressure, the blood pressure variability, the person's movement, sleep efficiency, the effectiveness of the treatment, the ratio of on-the-job time in the sleep states and / or sleep stages to the treatment effect, the ratio of on-therapy sleep time to off-therapy sleep time, the ratio of on-therapy sleep time to the duration of the respective sleep session, the ratio of on-therapy residual AHI to off-therapy AHI, the ratio of on-therapy sleep efficiency to off-therapy sleep efficiency, or any combination thereof. Each of these parameters is described above in connection with step 702 of FIG. 7 . The parameters may be received from sensors, user equipment, respiratory therapy equipment, and / or a respiratory therapy system associated with the at least one person. In some implementations, the historical sleep session data includes subjective feedback from the at least one person.The subjective feedback is one or more ratings of how at least one person rates one or more past sleep sessions in the plurality of past sleep sessions.

[0143] In some implementations, the at least one person is 1 person, 2 people, 5 people, 100 people, 1000 people, 10,000 people, 1 million people, 1 billion people, etc. In some implementations, the at least one person includes a user 210, such that the historical sleep session data includes historical sleep session data of the user 210. In some implementations, the at least one person consists of only one person who is a user 210. In some implementations, the at least one person does not include the user 210.

[0144] In some implementations, at least one person is a person in a cohort. A cohort can be based, at least in part, on a health condition shared by at least one person. For example, individuals with diabetes can be grouped in a cohort, individuals with high blood pressure can be grouped in a cohort, individuals with insomnia can be grouped in a cohort, etc. A cohort can be based on demographic information. For example, individuals between the ages of 18 and 25 can be grouped in a cohort, individuals between the ages of 40 and 50 can be grouped in a cohort, individuals of the same ethnic group or individuals with particular genetic markers can be grouped in a cohort, individuals in the same geographic location can be grouped in a cohort because they may be affected by similar environmental factors, etc. A target user (e.g., user 210) can share the same health condition(s) and / or demographic information as the cohort.

[0145] Step 804 includes receiving historical attention data associated with at least one person. The alertness data includes alertness levels associated with at least one person outside of multiple historical sleep sessions. Outside of a sleep session includes immediately after a sleep session, or one hour, one day, one week, etc. after a sleep session. The attention data can include results from sustained attention and reaction time tests (e.g., psychomotor vigilance task tests), such as those described above in connection with some implementations of the present disclosure. Reaction time test results can be measured in milliseconds and can be time-stamped for different time periods. Reaction time test results can be trimmed or cleaned to remove missed responses to stimuli, false starts, etc. Reaction time test results can be referenced as mean reaction time, median reaction time, etc.

[0146] The alertness data may be associated with a timestamp indicating a time period. For example, the alertness data may include a reaction time test performed by at least one person in the morning, afternoon, or evening hours, or any combination thereof. In some implementations, the alertness data may be accompanied by one or more characteristics associated with at least one user. For example, each of the at least one user may perform a reaction time test at 3:00 p.m., and the results of the reaction time test may be included in the alertness data along with physiological data associated with each person. The physiological data may include average heart rate values, heart rate variability, spectral analysis of exhaled breath, etc. The physiological data may be obtained from one or more sensors 130, as discussed in connection with some implementations of the present disclosure.

[0147] In some implementations, the physiological data included in the wakefulness data can be windowed based on the type of physiological data. For example, one minute of data collection can yield a heart rate of 60 beats, and one minute of data collection can yield a respiratory rate of approximately 15 beats. Thus, physiological data can be obtained in 30-second windows, 5-minute windows, etc., to obtain a representative sample of physiological data around the time each person attempted the reaction time test. In some implementations, physiological data from the most recent sleep session prior to the reaction time test is linked and tagged to the physiological data results included in the wakefulness data.

[0148] Step 806 includes training a machine learning model using the received historical sleep session data of step 802 and the received historical wakefulness data of step 804. Once trained, the machine learning model is configured to (i) receive as input current sleep session data associated with user 210 and (ii) determine as output a predicted wakefulness level associated with user 210 at one or more time points.

[0149] In some implementations, in step 806, the control system 110 correlates the received historical sleep session data with the received historical wakefulness data to determine characteristic or features of parameters within the historical sleep session data that are indicative of a level of wakefulness and that are indicative of good or poor reaction times. The control system 110 can determine thresholds for good and poor reaction times for at least one person.

[0150] In some implementations, in step 806, the control system 110 correlates on-therapy data for at least one person present in the historical sleep session data with physiological data present in the historical wake data to determine how respiratory therapy device use during multiple historical sleep sessions affects physiological data outside of the multiple historical sleep sessions. The control system 110 can align periods of poor reaction time in the historical attention data with the past sleep session data to indicate that changes in sleep (e.g., sleep efficiency, on-therapy to off-therapy ratio, etc.) affect the attention data. One or more techniques can be used for the analysis. For example, decision trees, bootstrap aggregation, log-linear fitting, support vector machines, or any combination thereof can be used to align the sleep data and develop relationships between the sleep data and the wake data.

[0151] In some implementations, the machine learning model is trained in successive iterations, such that past sleep session data associated with a first one of the at least one human and past wakefulness data associated with a first one of the at least one human are used to train the machine learning model in a first iteration. After the first iteration, the machine learning model is tuned specifically to the first one of the at least one human. For successive iterations, past sleep session data associated with subsequent human beings and past wakefulness data associated with subsequent human beings are used to update the machine learning model in subsequent iterations. After each iteration, the machine learning model reduces an error associated with each one of the at least one human when predicting a wakefulness level associated with each one of the at least one human.

[0152] Successive learning iterations result in updates to the machine learning model. For example, the control system 110 may store in memory a trained machine learning model for predicting alertness levels. The machine learning model is trained using past sleep session data and past alertness data from multiple individuals, not including the user 210. The user 210 may then provide the control system 110 with past sleep session data associated with the user 210 for at least one previous sleep session. The user 210 may also provide past alertness data associated with the user 210 other than the at least one previous sleep session. The control system 110 may then update the machine learning model by further training the trained machine learning model using past sleep session data and past alertness data associated with the user 210. Before updating the trained machine learning model, when the user 210 obtained an attentiveness level using the trained machine learning model, the trained machine learning model had an error level (or error rate) e1 associated with the user 210. After updating the trained machine learning model, the trained machine learning model has an error level e2 associated with the user 210, where e2 is less than e1.

[0153] In some implementations, the arousal level predicted by a trained machine learning algorithm is provided as an arousal score. The arousal score takes into account not only the raw arousal data but also health and demographic information. For example, a 70-year-old might be ranked as 70 on the arousal scale, even though the 25-year-old has a faster reaction time than a 70-year-old. The 70-point scale takes into account the individual's age and therefore incorporates a comparison of the 25-year-old's expected performance with that of others in the same cohort. Similarly, health can be factored in to adjust the arousal score.

[0154] The following are some example steps for training a machine learning model. The historical sleep session data and alertness data used for training can be conditioned by filtering outliers. Short sleep data can be removed from the historical sleep session data. Short sleep data includes sleep durations of less than 10 minutes, less than 15 minutes, less than 30 minutes, and less than 1 hour. After conditioning, a regression algorithm can be applied to the conditioned data. In some implementations, ensemble learning with bagging using decision trees is used for training. At each split of the decision tree, several parameters or variables are randomly selected from the historical sleep session data. Empirical feature importance is estimated for features that contributed to specific reaction time results in the historical alertness data. In one implementation, six to eight features are identified for each specific reaction time test result. Considering empirical feature importance can reduce the dimensionality of the historical data for the target sleep session. In some implementations, AHI and respiration rate are important or control features for predicting alertness using sleep data.

[0155] One or more elements or aspects or steps from any of the following claims 1-168, or any portion(s) thereof, may be combined with one or more elements or aspects or steps from any of the other claims 1-168, or combinations thereof, to form one or more additional implementations and / or claims of the present disclosure.

[0156] While the present disclosure has been described with reference to one or more particular implementations or implementations, those skilled in the art will recognize that many modifications may be made thereto without departing from the spirit and scope of the present disclosure. Each of these implementations and obvious variations thereof is contemplated as falling within the spirit and scope of the present disclosure. It is also contemplated that additional implementations according to aspects of the present disclosure may combine any number of features from any of the implementations described herein.

Claims

1. receiving data associated with the individual while sleeping; determining an alertness level of the individual using a machine learning model that uses the received data as input; and generating a response to be delivered to the individual based at least in part on the determined arousal level; The method includes:

2. The method, wherein the received data includes a sleep score, a cardiac charge score, a physical charge score, a flow signal, a respiratory signal, a respiratory rate, a respiratory rate variability, an inhalation amplitude, an exhalation amplitude, an inhalation-exhalation ratio, a number of events, a number of events per unit time, a pattern of events, a duration of each event, a sleep stage, a period the individual spends in a sleep stage, a ratio of a period the individual spends in a sleep stage to a time of a sleep session ... ratio, individual's bed time, residual apnea-hypopnea index (AHI), pressure of pressurized air delivered during treatment, flow rate of pressurized air delivered during treatment, heart rate, heart rate variability, blood pressure, blood pressure variability, individual's movement, sleep efficiency, efficacy of treatment, pressure of pressurized air delivered during treatment, flow rate of pressurized air delivered during treatment, individual's movement, sleep efficiency, efficacy of treatment, ratio of sleep time during treatment to sleep time outside of treatment, ratio of sleep time during treatment to duration of sleep session, ratio of residual AHI during treatment to AHI outside of treatment, sleep efficiency during treatment to sleep efficiency outside of treatment, or any combination thereof. The method of claim 1.

3. The received data includes the therapeutic effect, the therapeutic effect being based at least in part on an unintentional leakage of pressurized air delivered during a sleep session being below a threshold. The method of claim 2.

4. The alertness level is determined during an initial period of a sleep session, and the generated response is based at least in part on a remaining duration of the sleep session. The method according to any one of claims 1 to 3.

5. the generated response is based at least in part on the individual not engaging with a user interface of the respiratory therapy system and the predicted remaining duration of the sleep session being above or below a sleep duration threshold. The method according to claim 4.

6. determining a likelihood that the determined alertness level will be improved by treatment during the remainder of the sleep session; wherein the generated response is based, at least in part, on: (i) the likelihood exceeds a threshold; (ii) a magnitude of the potential improvement to the determined level of attention exceeds an improvement threshold; or (iii) both (i) and (ii). The method according to claim 4 or claim 5.

7. The generated response includes an alarm to wake the individual up and put on the user interface; or the generated response includes a message instructing the individual to wear the user interface before returning to sleep. The method according to claim 5 or claim 6.

8. the generated response is based at least in part on a duration of the sleep session.

4. The method according to any one of claims 1 to 3.

9. determining a likelihood that the determined alertness level will be improved by extending the duration of the sleep session, wherein: The generated response is based, at least in part, on: (i) the likelihood exceeds a threshold; (ii) a magnitude of the potential improvement to the determined level of attention exceeds an improvement threshold; or (iii) both (i) and (ii). The method according to claim 8.

10. the generated response is a message instructing the individual to extend the duration of a sleep session or future sleep sessions. The method according to claim 8 or claim 9.

11. the generated response is based at least in part on a duration of a portion of a sleep session during which the individual is not engaged with a user interface of the respiratory therapy system.

4. The method according to any one of claims 1 to 3.

12. determining a possibility that the determined alertness level can be improved by reducing a period of a portion of a sleep session during which the individual is not engaged with the user interface; wherein the generated response is based, at least in part, on: (i) the likelihood exceeds a threshold; (ii) a magnitude of the potential improvement to the determined level of attention exceeds an improvement threshold; or (iii) both (i) and (ii). The method of claim 11.

13. The generated response includes a message instructing the individual to wear the user interface prior to a future sleep session.

13. The method according to claim 11 or claim 12.

14. the message instructing the individual to shorten a duration of future sleep sessions while the user interface is being worn. The method of claim 13.

15. the determined arousal level is or includes an arousal score, and the response is generated based on the arousal score satisfying a condition; The satisfied condition may include (i) the determined arousal score being below an average arousal score for the individual, (ii) the determined arousal score being below a threshold, or (iii) the determined arousal score being above a threshold.

15. The method according to any one of claims 1 to 14.

16. the generated response is based at least in part on the determined arousal level satisfying a condition; The satisfied condition may include (i) the determined arousal level being below an average arousal level for the individual, (ii) the determined arousal level being below a threshold, or (iii) the determined arousal level being above a threshold.

15. The method according to any one of claims 1 to 14.

17. The determined alertness level is a predicted alertness level for a future time period following the sleep session.

17. The method according to any one of claims 1 to 16.

18. The data relating to the individual is received from (i) a respiratory therapy device configured to deliver pressurized air to the individual's airway via a user interface coupled to the respiratory therapy device via a conduit, (ii) a sensor, or (iii) both (i) and (ii); 18. The method of any one of claims 1 to 4, 8 to 13, or 15 to 17.

19. determining that the individual was not receiving treatment based at least in part on receiving first data from the sensor during at least a portion of the sleep session and not simultaneously receiving second data from the respiratory therapy device during the portion of the sleep session; Further comprising: The data relating to the individual is composed of first data and second data.

20. The method of claim 18.

20. determining a period of time during which the individual did not receive medical treatment based at least in part on a timestamp associated with failure to receive the second data; Further comprising:

20. The method of claim 19.

21. the generated response is based at least in part on (i) the effectiveness of the treatment during the sleep session, (ii) the effectiveness of the treatment during a previous sleep session, or (iii) both (i) and (ii); 20. The method of claim 18 or 19.

22. The generated response may provide the individual with the following instructions: (i) Raising the upper limit of the pressure of the pressurized air supplied; or Lowering the upper limit pressure of the pressurized air supplied; (ii) increasing the lower limit pressure of the pressurized air supplied; or Lowering the lower limit pressure of the pressurized air to be supplied; (iii) replacing a user interface coupled to the respiratory therapy device; (iv) adjusting the humidity of the supplied pressurized air; (v) any combination of (i) to (iv); 22. The method of claim 18, further comprising a message to

23. the data includes measurements of air pressure, airflow, or both air pressure and airflow within a respiratory therapy device, a conduit, a user interface, or any combination thereof; 23. The method according to any one of claims 18 to 22.

24. The data relating to the individual is received from the sensors, the sensors including a microphone, a video camera, an acoustic sensor, a radio frequency (RF) sensor, a photoelectric (PPG) sensor, a piezoelectric sensor, a pressure sensor, a capacitive sensor, a force sensor, a strain gauge sensor, a galvanic sensor, a temperature sensor, a pulse sensor, an oxygen concentration sensor, an electroencephalogram (EEG), an electromyogram (EMG), an electroencephalogram (EOG) sensor, or any combination thereof.

24. The method according to any one of claims 18 to 23.

25. The generated response includes relaying a message to the individual including the determined arousal level.

25. The method of any one of claims 18 to 24.

26. The message may be displayed on a screen on the housing of the respiratory therapy device, or relayed to the individual by displaying a message on a screen provided on an external device associated with the individual; The external device includes a mobile phone, a tablet, a personal computer, a smart display, a television, an in-vehicle infotainment display, or smart glasses; 26. The method of claim 25.

27. The message is relayed to the individual by a speaker.

27. The method of claim 25 or claim 26.

28. The speaker is provided on or within a housing of an external device associated with the individual, or the speaker is provided on or within a housing of a respiratory therapy device.

28. The method of claim 27.

29. The machine learning model is trained using (i) past sleep session data associated with at least one person during one or more past sleep sessions, and (ii) historical wake data associated with at least one person outside of the one or more past sleep sessions.

29. The method of any one of claims 1 to 28.

30. 30. The method of claim 29, wherein the at least one person comprises an individual.

31. the historical arousal data includes results of a reaction time test from at least one person, subjective input from at least one person, or any combination thereof; A method according to claim 29 or claim 30.

32. The machine learning model is trained in successive iterations such that (i) past sleep session data associated with a first one of the at least one person and past wake data associated with a first one of the at least one person are used to train the machine learning model in a first iteration, and (ii) past sleep session data associated with a subsequent person and past wake data associated with a subsequent person are used to update the machine learning model in subsequent iterations.

32. The method of any one of claims 29 to 31.

33. The machine learning model is trained with one or more techniques including decision trees, bootstrap aggregation, log-linear fitting, support vector machines, or any combination thereof; 33. The method of any one of claims 29 to 32.

34. the at least one person is a person in a cohort; The cohort is based, at least in part, on the health status of at least one person, on demographic information of at least one person, or on both; 34. The method of any one of claims 29 to 33.

35. a control system including one or more processors; a memory storing machine-readable instructions; A system comprising: The control system is coupled to a memory, the machine-executable instructions in the memory being executed by at least one of the one or more processors of the control system to: Receive personally relevant data during your sleep session; determining the individual's arousal level using a machine learning model that takes the received data as input; The system is capable of performing a process that generates a response to be delivered to the individual based at least in part on the determined arousal level.

Images