Prediction of usage or compliance

Abstract

Systems and methods have been developed that increase user compliance and persistence with various devices and services, including respiratory therapy devices, exercise equipment, and online or other software services. For example, in some examples, the disclosed techniques may monitor usage data output from a respiratory therapy device, exercise equipment, or a computer software program to determine when a user may terminate or reduce usage within a specified time window based on usage trends. Tagging the user may also trigger further actions to automatically intervene before the user terminates participation in the service.

Description

Technical Background 1.1 Technical Field

[0001] The present technology relates to one or more of screening, diagnosing, monitoring, treating, preventing, and improving respiratory-related disorders. The present technology also relates to medical devices or equipment and their uses. The present technology also relates to predicting compliance, use, or use withdrawal of respiratory treatment devices, websites and other software, exercise equipment, drivers of on-demand taxi services, or other applications.

[0002] 1.2 Description of Related Technologies

[0003] 1.2.1 Human Respiratory System and Its Disorders

[0004] The respiratory system of the body facilitates gas exchange. The nose and mouth form the entrance to the patient's airway.

[0005] The airway contains a series of branching tubes that become narrower, shorter, and more numerous as the bronchial tubes penetrate deeper into the lungs. The primary function of the lungs is gas exchange, which allows oxygen to enter venous blood from inhaled air and expel carbon dioxide in the opposite direction. The trachea divides into the left and right main bronchi, which ultimately divide further into terminal bronchioles. The bronchi constitute the conducting airways and do not participate in gas exchange. Further airway division leads to respiratory bronchioles and ultimately to alveoli. The alveolar region of the lungs is where gas exchange occurs and is referred to as the respiratory zone. See "Respiratory Physiology", 9th Edition, published by John B. West, Lippincott Williams & Wilkins in 2012.

[0006] There is a series of respiratory system disorders. Some disorders can be characterized by specific events, such as apnea, hypopnea, and hyperventilation.

[0007] Examples of respiratory disorders include obstructive sleep apnea (OSA), Cheyne-Stokes respiration (CSR), respiratory insufficiency, obesity hypoventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular disease (NMD), and chest wall disorders.

[0008] Obstructive sleep apnea (OSA) is a form of sleep-disordered breathing (SDB) characterized by events that involve occlusion or obstruction of the upper airway during sleep. This is caused by an abnormally small upper airway in the regions of the tongue, soft palate, and posterior oropharyngeal wall during sleep, combined with a normal loss of muscle tone. The condition causes affected patients to stop breathing, typically for periods of 30 seconds to 120 seconds, sometimes 200 to 300 times per night. It often results in excessive daytime sleepiness and can lead to cardiovascular disease and brain damage. Although affected individuals may not be aware of the problem, the syndrome is a disorder that is particularly common in middle-aged overweight men. See U.S. Patent US4,944,310 (Sullivan).

[0009] Cheyne-Stokes respiration (CSR) is another form of sleep-disordered breathing. CSR is a disorder of the patient's respiratory controller in which there are rhythmic waxing and waning cycles of ventilation. CSR is characterized by repeated deoxygenation and reoxygenation of arterial blood. Due to repeated hypoxia, CSR can be harmful. In some patients, CSR is associated with repeated arousals from sleep, which results in severe sleep disruption, increased sympathetic activity, and increased afterload. See U.S. Patent US6,532,959 (Berthon-Jones).

[0010] Respiratory failure is an umbrella term for breathing disorders in which the lungs are unable to inhale sufficient oxygen or exhale sufficient CO2 to meet the needs of the patient. Respiratory failure can encompass some or all of the following disorders.

[0011] Patients with respiratory insufficiency, a form of respiratory failure, may experience abnormal shortness of breath during exercise.

[0012] Obesity hypoventilation syndrome (OHS) is defined as the combination of severe obesity and chronic hypercapnia while awake, in the absence of other known causes of hypoventilation. Symptoms include dyspnea, morning headache, and daytime sleepiness.

[0013] Chronic obstructive pulmonary disease (COPD) includes any of a group of lower airway diseases that share certain common characteristics. These include increased resistance to air movement, prolonged expiratory phase of respiration, and loss of normal elasticity of the lungs. Examples of COPD are emphysema and chronic bronchitis. COPD is caused by chronic smoking (the main risk factor), occupational exposure, air pollution, and genetic factors. Symptoms include exertional dyspnea, chronic cough, and sputum production.

[0014] Neuromuscular diseases (NMDs) are a broad term that encompasses many diseases and afflictions that directly or indirectly impair muscle function via intrinsic muscle pathology or neuropathology. Some NMD patients are characterized by progressive muscle damage, leading to loss of walking ability, wheelchair confinement, difficulty swallowing, respiratory muscle weakness, and ultimately death due to respiratory failure. Neuromuscular disorders can be classified into rapidly progressive and slowly progressive types: (i) rapidly progressive disorders: characterized by muscle damage that worsens within months and leads to death within a few years (e.g., juvenile amyotrophic lateral sclerosis (ALS) and Duchenne muscular dystrophy (DMD)); (ii) variable or slowly progressive disorders: characterized by muscle damage that worsens over the years and only slightly reduces life expectancy (e.g., limb-girdle, scapulohumeral, and myotonic dystrophy). The symptoms of NMD respiratory failure include increased overall weakness, difficulty swallowing, dyspnea on exertion and at rest, fatigue, lethargy, morning headache, and difficulty with concentration and mood changes.

[0015] Thoracic wall disorders are a group of chest deformities that result in inefficient coupling between the respiratory muscles and the thoracic cavity. These disorders are typically characterized by restrictive defects and have the potential for chronic hypercapnic respiratory failure. Scoliosis and / or kyphosis can lead to severe respiratory failure. The symptoms of respiratory failure include dyspnea on exertion, peripheral edema, orthopnea, recurrent chest infections, morning headache, fatigue, poor sleep quality, and loss of appetite.

[0016] A range of therapies have been used to treat or improve such conditions. In addition, other healthy individuals may utilize such treatments to prevent the development of respiratory disorders. However, these have numerous drawbacks.

[0017] 1.2.2 Therapies

[0018] Various therapies, such as continuous positive airway pressure (CPAP) therapy, non-invasive ventilation (NIV), and invasive ventilation (IV), have been used to treat one or more of the above respiratory disorders.

[0019] 1.2.2.1 Respiratory pressure therapy

[0020] Continuous positive airway pressure (CPAP) has been used to treat obstructive sleep apnea (OSA). Its mechanism of action is that CPAP acts as a pneumatic splint and can prevent upper airway obstruction, such as by pushing the soft palate and tongue forward and away from the posterior oropharyngeal wall. Treatment of OSA by CPAP therapy can be voluntary, so if patients find the device used to provide this therapy uncomfortable, difficult to use, expensive, and / or unaesthetic, they can choose not to comply with the therapy.

[0021] Non-invasive ventilation (NIV) provides ventilatory support to a patient via the upper airway to assist the patient in breathing and / or maintaining adequate oxygen levels in the body by performing some or all of the work of breathing. This ventilatory support is provided via a non-invasive patient interface. NIV has been used to treat CSR and respiratory failure in forms such as OHS, COPD, NMD, and chest wall disorders. In some forms, the comfort and effectiveness of these therapies can be improved.

[0022] Invasive ventilation (IV) provides ventilatory support to a patient who is no longer able to breathe effectively on their own and can be provided using a tracheostomy tube. In some forms, the comfort and effectiveness of these therapies can be improved.

[0023] 1.2.2.2 Flow therapies

[0024] Not all respiratory therapies are aimed at delivering a prescribed therapeutic pressure. Some respiratory therapies aim to deliver a prescribed respiratory volume, perhaps by targeting a flow profile over a target duration. In other cases, the interface to the patient's airway is "open" (unsealed), and the respiratory therapy may only supplement the patient's own spontaneous breathing. In one example, high-flow therapy (HFT) provides a continuous, heated, humidified airflow to the airway inlet via an unsealed or open patient interface at a "therapy flow" that is generally constant throughout the respiratory cycle. This therapy flow is nominally set to exceed the patient's peak inspiratory flow. HFT has been used to treat OSA, CSR, COPD, and other respiratory disorders. One mechanism of action is that the high-flow air at the airway inlet improves ventilatory efficiency by flushing or washing out exhaled CO2 from the patient's anatomic dead space. Thus, HFT is sometimes referred to as dead space therapy (DST). In other flow therapies, the therapeutic flow rate can follow a curve that varies with the respiratory cycle.

[0025] Another form of flow therapy is long-term oxygen therapy (LTOT) or supplemental oxygen therapy. A doctor may prescribe a continuous flow of oxygen-enriched gas at a specific flow rate (e.g., 1 liter per minute (LPM), 2 LPM, 3 LPM, etc.) and a specific oxygen concentration (ranging from 21%, the fraction of oxygen in ambient air, to 100%) to the patient's airway.

[0026] 1.2.2.3 Supplemental oxygen

[0027] For some patients, oxygen therapy can be combined with respiratory pressure therapy or HFT by adding supplemental oxygen to a pressurized air stream. When oxygen is added to respiratory pressure therapy, this is called RPT with supplemental oxygen. When oxygen is added to HFT, the resulting therapy is called HFT with supplemental oxygen.

[0028] 1.2.3 Treatment systems

[0029] These respiratory therapies can be provided by a treatment system or device. Such systems and devices can also be used to screen, diagnose, or monitor a condition without treating it.

[0030] A respiratory treatment system can include a respiratory pressure treatment device (RPT device), an air circuit, a humidifier, a patient interface, an oxygen source, and data management.

[0031] Another form of treatment system is a mandibular repositioning device.

[0032] 1.2.3.1 Patient Interface

[0033] The patient interface can be used to connect a breathing device to its wearer, for example, by providing an air flow to the entrance of the airway. The air flow can be provided to the patient's nose and / or mouth via a face mask, to the mouth via a tube, or to the patient's trachea via a tracheostomy tube. Depending on the treatment to be applied, the patient interface can form a seal (e.g., a tight seal) with an area of the patient's face in order to facilitate the delivery of gas at a pressure that varies sufficiently with respect to ambient pressure at a positive pressure of about 10 cmH2O, thereby achieving the treatment. For other forms of treatment, such as oxygen delivery, the patient interface may not include a seal sufficient to facilitate the delivery of a gas supply at a positive pressure of about 10 cmH2O to the airway.

[0034] Some other face mask systems may not be functionally suitable for the present field. For example, a purely decorative face mask may not be able to maintain an appropriate pressure. A face mask system for underwater swimming or diving can be configured to prevent water from a higher external pressure from entering, but will not maintain the internal air at a pressure above ambient pressure.

[0035] Some face masks may not be clinically beneficial for the present technology, for example, if they block the air flow through the nose and only allow air flow through the mouth.

[0036] If some face masks require the patient to insert a portion of the face mask structure into their mouth to create and maintain a seal via their lips, it may be uncomfortable or impractical for the present technology.

[0037] Some face masks may not be achievable for use during sleep, for example, when sleeping on one's side in bed with the head on a pillow.

[0038] The design of the patient interface presents many challenges. The face has a complex three-dimensional shape. The size and shape of the nose vary significantly from person to person. Since the head contains bone, cartilage, and soft tissue, different regions of the face respond differently to mechanical forces. The jawbone or mandible can move relative to other bones of the skull. The entire head can move during respiratory treatment.

[0039] Due to these challenges, some face masks suffer from one or more of the following problems: obtrusiveness, unaesthetic appearance, expense, disproportion, difficulty of use, and discomfort especially when worn for a long period of time or when the patient is not familiar with the system. A face mask of incorrect size may result in reduced compliance, reduced comfort, and poor patient outcomes. Face masks designed only for pilots, face masks designed as part of personal protective equipment (such as filter masks), SCUBA masks, or face masks designed to administer anesthetic agents are acceptable for their original applications, but are not as comfortable as desired for long-term (such as several hours) wear. This discomfort may lead to reduced patient compliance with treatment. This is especially true if the face mask is worn during sleep.

[0040] Assuming patient compliance with treatment, CPAP therapy is very effective in treating certain respiratory disorders. If the face mask is uncomfortable or difficult to use, the patient may not comply with treatment. Since patients are often advised to clean their face masks regularly, if the face mask is difficult to clean (e.g., difficult to assemble or disassemble), the patient may not clean their face mask, which may affect patient compliance.

[0041] While face masks for other applications (such as navigators) may not be suitable for treating sleep apnea, face masks designed for treating sleep apnea may be suitable for other applications.

[0042] For these reasons, patient interfaces for delivering CPAP during sleep form a distinct field.

[0043] 1.2.3.1.1 Seal-forming structure

[0044] The patient interface may include a seal-forming structure. Since the seal-forming structure is in direct contact with the patient's face, the shape and configuration of the seal-forming structure can directly affect the effectiveness and comfort of the patient interface.

[0045] The patient interface can be characterized in part by the design intent of the seal-forming structure to engage with the face during use. In one form of patient interface, the seal-forming structure can include a first sub-part that forms a seal around the left nostril and a second sub-part that forms a seal around the right nostril. In one form of patient interface, the seal-forming structure can include a single element that surrounds both nostrils during use. Such a single element can be designed to cover, for example, the upper lip area and the bridge of the nose area of the face. In one form of patient interface, the seal-forming structure can include an element that surrounds the mouth area during use, for example, by forming a seal over the lower lip area of the face. In one form of patient interface, the seal-forming structure can include a single element that surrounds both nostrils and the mouth area during use. These different types of patient interfaces can be given various names by their manufacturers, including nasal masks, full face masks, nasal pillows, nasal sprays, and oro-nasal masks.

[0046] A seal-forming structure that is effective in one area of the patient's face may not be suitable in another area, for example, because of differences in the shape, structure, variability, and sensitive areas of the patient's face. For example, a seal on a swimming goggle that covers the patient's forehead may not be suitable for use on the patient's nose.

[0047] Certain seal-forming structures can be designed for mass production such that one design is suitable and comfortable and effective for a wide range of different face shapes and sizes. To the extent that there is a mismatch between the shape of the patient's face and the seal-forming structure of a mass-produced patient interface, one or both must be adapted to form a seal.

[0048] One type of seal-forming structure extends around the periphery of the patient interface and is designed to seal against the patient's face when a force is applied to the patient interface while the seal-forming portion is in face-to-face engagement with the patient's face. The seal-forming structure can include an air or fluid-filled pad, or a molded or formed surface of a resilient seal element made of an elastomer such as rubber. For this type of seal-forming structure, if the fit is inadequate, there will be a gap between the seal-forming structure and the face, and additional force will be required to force the patient interface against the face to achieve a seal.

[0049] Another type of seal-forming structure incorporates a sheet-like seal of thin material positioned around the perimeter of the face mask to provide a self-sealing action against the patient's face when positive pressure is applied within the face mask. Similar to the previously described form of seal-forming portion, if the match between the face and the face mask is poor, additional force may be required to achieve a seal, or the face mask may leak. Additionally, if the shape of the seal-forming structure does not match the shape of the patient, it may wrinkle or bend during use, resulting in leakage.

[0050] Another type of seal-forming structure may include friction fit elements, such as for insertion into the nostrils, however some patients find these uncomfortable.

[0051] Another form of seal-forming structure may use an adhesive to effect the seal. Some patients may find it inconvenient to apply and remove the adhesive to and from their face frequently.

[0052] A series of patient interface seal-forming structure techniques are disclosed in the following patent applications assigned to ResMed Limited: WO 1998 / 004,310; WO 2006 / 074,513; WO 2010 / 135,785.

[0053] One form of nasal pillow is found in the Adam Circuit manufactured by Puritan Bennett. Another nasal pillow or nasal cannula is the subject of US Patent No. 4,782,832 (Trimble et al.) assigned to the Puritan-Bennett Corporation.

[0054] 1.2.3.1.2 Positioning and stabilization

[0055] The seal-forming structure of a patient interface for positive pressure therapy is subject to corresponding forces from the air pressure that would break the seal. Accordingly, various techniques have been used to position the seal-forming structure and maintain its sealing relationship with the appropriate portion of the face.

[0056] One technique is to use an adhesive. See for example the US patent application with publication number US2010 / 0000534. However, some people may feel discomfort with the use of an adhesive.

[0057] Another technique is to use one or more straps and / or stabilizing harnesses. Many such harnesses suffer from one or more of ill-fitting, bulky, uncomfortable, and awkward to use.

[0058] 1.2.3.2 Respiratory pressure therapy (RPT) devices

[0059] Respiratory pressure therapy (RPT) devices may be used alone or as part of a system to deliver one or more of the various therapies described above, such as by operating the device to generate an air flow for delivery to an airway interface. The air flow may be pressure-controlled (for respiratory pressure therapy) or flow-controlled (for flow therapy, such as HFT). Accordingly, RPT devices may also be used as flow therapy devices. Examples of RPT devices include CPAP devices and ventilators. Examples of RPT devices include CPAP devices and ventilators.

[0060] Air pressure generators are known within the scope of applications such as industrial-scale ventilation systems. However, air pressure generators for medical applications have specific requirements that are not met by more general air pressure generators, such as the reliability, size, and weight requirements of medical devices. In addition, even devices designed for medical use can have drawbacks regarding one or more of the following: comfort, noise, ease of use, efficacy, size, weight, manufacturability, cost, and reliability.

[0061] An example of a special requirement for some RPT devices is noise.

[0062] Table of noise output levels of existing RPT devices (only one sample, measured in CPAP mode at 10 cmH2O using the test method specified in ISO3744).

[0063] RPT device name A-weighted sound pressure level dB(A) Year (approx.) <![CDATA[C series Tango TM > 31.9 2007 <![CDATA[Tango with humidifier in series C TM > 33.1 2007 <![CDATA[S8 Escape TM II]]> 30.5 2005 <![CDATA[With H4i TM S8 Escape of the humidifier TM II]]> 31.1 2005 <![CDATA[S9 AutoSet TM > 26.5 2010 <![CDATA[S9 AutoSet with H5i Humidifier TM > 28.6 2010

[0064] A known RPT device for treating sleep apnea is the S9 Sleep Therapy System manufactured by ResMed Limited. Another example of an RPT device is a ventilator. ResMed Stellar TM series of ventilators can provide support for invasive and non-invasive non-dependent ventilation for a range of patients being treated for a variety of conditions such as, but not limited to, NMD, OHS, and COPD.

[0065] ResMed Elisée TM 150 ventilator and ResMed VS III TM Ventilators can provide support for invasive and non-invasive dependent ventilation suitable for adult or pediatric patients for treating a variety of disorders. These ventilators provide volume ventilation and pressure ventilation modes with single-limb or double-limb circuits. RPT devices typically include a pressure generator, such as a motor-driven blower or a compressed gas reservoir, and are configured to supply an air flow to the patient's airway. In some cases, the air flow can be provided to the patient's airway at positive pressure. The outlet of the RPT device is connected via an air circuit to a patient interface such as those described above.

[0066] The device designer may be presented with an infinite number of choices. Design criteria often conflict, meaning that certain design choices are far from conventional or inevitable. In addition, comfort and efficacy in certain aspects can be highly sensitive to small and subtle changes in one or more parameter aspects.

[0067] 1.2.3.3 Humidifier

[0068] Delivering an airstream without humidification can lead to airway dryness. A humidifier with an RPT device and a patient interface is used to generate humidified gas, minimizing dryness of the nasal mucosa and increasing patient airway comfort. Additionally, in colder climates, warm air typically applied to the facial area in and around the patient interface is more comfortable than cold air.

[0069] A series of artificial humidification devices and systems are known, however they may not meet the specific requirements of a medical humidifier.

[0070] When needed, a medical humidifier is used to increase the humidity and / or temperature of an airstream relative to ambient air, typically where a patient is sleeping or resting (e.g., in a hospital). A medical humidifier for bedside placement can be small. A medical humidifier can be configured to only humidify and / or heat the airstream delivered to the patient, without humidifying and / or heating the patient's surrounding environment. Room-based systems (such as saunas, air conditioners or evaporative coolers), for example, can also humidify the air a patient breathes, however these systems also humidify and / or heat the entire room, which can cause discomfort to the occupants. Additionally, medical humidifiers can have more stringent safety constraints than industrial humidifiers

[0071] Although many medical humidifiers are known, they may have one or more drawbacks. Some medical humidifiers may provide inadequate humidification, and some are difficult or inconvenient for patients to use.

[0072] 1.2.3.4 Data Management

[0073] There may be clinical reasons for obtaining data to determine whether a patient prescribed respiratory therapy has been "compliant", e.g., the patient has used their RPT device in accordance with one or more "compliance rules". An example of a compliance rule for CPAP therapy is that, to be considered compliant, a patient is required to use a respiratory pressure therapy device for at least twenty-one (21) days out of thirty (30) consecutive days, for at least four hours each night. To determine a patient's compliance, a provider of the RPT device (such as a healthcare provider) may manually obtain data describing the patient's treatment using the RPT device, calculate the usage over a predetermined period, and compare it with the compliance rule. Once the healthcare provider has determined that the patient has used their RPT device in accordance with the compliance rule, the healthcare provider can notify a third party that the patient is compliant.

[0074] There may be other aspects of patient treatment that would benefit from communication of treatment data to a third party or external system.

[0075] Existing processes for communicating and managing such data can be one or more of expensive, time-consuming and error-prone.

[0076] 1.2.3.5 Ventilation port technology

[0077] Some forms of treatment systems can include an exhaust port to allow the expulsion of exhaled carbon dioxide. The ventilation port can allow gas to flow from the internal space of the patient interface (such as an inflatable chamber) to the outside of the patient interface (such as to the surrounding environment).

[0078] The ventilation port can include a vent and during use of the mask the gas can flow through the vent. Many such vents are noisy. Others may become blocked during use, thus providing inadequate flushing. Some vents can, for example, disturb the sleep of the patient 1000's bed partner 1100 through noise or a concentrated airflow.

[0079] ResMed Limited has developed a number of improved mask ventilation technologies. See the international patent application with publication number WO1998 / 034,665; the international patent application with publication number WO2000 / 078,381; US Patent US6,581,594; the US patent application with publication number US2009 / 0050156; the US patent application with publication number US2009 / 0044808.

[0080] Noise table of existing masks (ISO 17510-2:2007, 10 cmH2O pressure at 1 m)

[0081]

[0082] (*Only one sample, measured at 10 cmH2O in CPAP mode using the test method specified in ISO 3744)

[0083] The sound pressure values of various objects are listed below

[0084]

[0085] 1.2.4 Screening, diagnosis and monitoring systems

[0086] Polysomnography (PSG) is a conventional system for diagnosing and monitoring cardiorespiratory disorders and usually involves clinical experts to apply the system. PSG usually involves placing 15 to 20 contact sensors on the patient to record various body signals such as electroencephalogram (EEG), electrocardiogram (ECG), electrooculogram (EOG), electromyogram (EMG), etc. PSG for sleep disordered breathing involves observing the patient in the clinic for two nights, one night for pure diagnosis and another night for a clinician to titrate treatment parameters. Therefore, PSG is expensive and inconvenient. In particular, it is not suitable for home screening / diagnosis / monitoring of sleep disordered breathing.

[0087] Screening and diagnosis generally describe identifying a condition from the signs and symptoms of the condition. Screening typically gives a true / false result indicating whether the patient's SDB is severe enough to warrant further study, while diagnosis can yield clinically actionable information. Screening and diagnosis tend to be one-time processes, while monitoring the progression of the condition can continue indefinitely. Some screening / diagnosis systems are only suitable for screening / diagnosis, while some can also be used for monitoring.

[0088] Clinical experts can adequately screen, diagnose, or monitor patients based on visual observation of PSG signals. However, there are situations where clinical experts may not be available or may not be affordable. Different clinical experts may have different opinions on a patient's condition. Additionally, a given clinical expert may apply different criteria at different times. Summary of the Invention

[0089] The present technology relates to providing medical devices for screening, diagnosing, monitoring, improving, treating, or preventing respiratory disorders, having one or more of improved comfort, cost, efficacy, ease of use, and manufacturability.

[0090] A first aspect of the present technology relates to devices for screening, diagnosing, monitoring, improving, treating, or preventing respiratory disorders.

[0091] Another aspect of the present technology relates to methods used in website or computer software usage and monitoring, as well as usage monitoring including other applications for drivers of on-demand taxi services and exercise equipment.

[0092] One aspect of certain forms of the present technology provides methods and / or devices for improving patient compliance with respiratory therapy, websites, and other software programs that require user participation, exercise equipment, drivers for on-demand taxi services, or other applications.

[0093] One form of the present technology includes a respiratory therapy device, a computer system, exercise equipment, or other systems that output usage data, and a controller that processes the usage data to determine whether a user or patient will reduce the use of the respiratory therapy device, exercise equipment, computer system, software, or other applications within a time window.

[0094] Another aspect of one form of the present technology is to determine the likelihood that a user of a respiratory therapy device, computer system, exercise equipment, or other system will discontinue within a specified time window.

[0095] Another aspect of one form of the present technology is to identify weekly trends in non-usage days, average number of uses per day, and usage standard deviation for users of a respiratory therapy device, computer system, exercise equipment, or other systems to determine whether the user will discontinue or reduce use.

[0096] Another aspect of one form of the present technology is to use random forest and logistic regression algorithms to process usage data output from a respiratory therapy device computer system, exercise equipment, or other systems to determine whether a user will drop out within a specified time window (e.g., two weeks, one week, or three weeks).

[0097] The methods, systems, devices, and apparatuses described can be implemented to improve the functionality of a processor, such as a processor of a dedicated computer, a respiratory monitor, and / or a respiratory therapy device. Additionally, the methods, systems, devices, and apparatuses described can provide improvements in the technical field of the automatic management, monitoring, and / or treatment of respiratory conditions, including, for example, sleep apnea.

[0098] Of course, some of these aspects can form sub - aspects of the present technology. The various aspects within the sub - aspects and / or aspects can be combined in various ways and also constitute other aspects or sub - aspects of the present technology.

[0099] Other features of the present technology will become apparent in view of the information contained in the following detailed description, the abstract, the drawings, and the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] The present technology is illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like reference numerals refer to like elements and include:

[0101] 3.1 Treatment System

[0102] Figure 1A A system is shown in which a patient 1000 wearing a patient interface 3000 in the form of a nasal pillow receives a supply of air under positive pressure from an RPT device 4000. The air from the RPT device 4000 is humidified in a humidifier 5000 and flows along an air circuit 4170 to the patient 1000. A bed partner 1100 is also shown. The patient sleeps in a supine sleeping position.

[0103] Figure 1B A system is shown in which a patient 1000 wearing a patient interface 3000 in the form of a nasal mask receives a supply of air under positive pressure from an RPT device 4000. The air from the RPT device is humidified in a humidifier 5000 and flows along an air circuit 4170 to the patient 1000.

[0104] Figure 1C A system is shown in which a patient 1000 wearing a patient interface 3000 in the form of a full face mask receives a supply of air under positive pressure from an RPT device 4000. The air from the RPT device is humidified in a humidifier 5000 and flows along an air circuit 4170 to the patient 1000. The patient sleeps in a lateral sleeping position.

[0105] 3.2 Respiratory System and Facial Anatomy

[0106] Figure 2A A general overview of the human respiratory system is shown, which includes the nasal and oral cavities, larynx, vocal cords, esophagus, trachea, bronchi, lungs, alveolar sacs, heart, and diaphragm.

[0107] 3.3 Patient Interface

[0108] Figure 3A A patient interface in the form of a nasal mask according to one form of the present technology is shown.

[0109] 3.4 RPT Device

[0110] Figure 4A An exploded view of an RPT device according to one form of the present technology is shown.

[0111] Figure 4B It is a schematic diagram of the pneumatic path of an RPT device according to one form of the present technology. The upstream and downstream directions are indicated with reference to the blower and the patient interface. The blower is defined as upstream of the patient interface and the patient interface is defined as downstream of the blower, regardless of the actual flow direction at any particular moment. Items within the pneumatic path between the blower and the patient interface are downstream of the blower and upstream of the patient interface.

[0112] Figure 4C It is a schematic diagram of the electrical components of an RPT device according to one form of the present technology.

[0113] Figure 4D It is a schematic diagram of an algorithm implemented in an RPT device according to one form of the present technology.

[0114] Figure 4E It is shown by Figure 4D a flowchart of a method executed by the treatment engine module according to one form of the present technology.

[0115] 3.5 Humidifier

[0116] Figure 5A It is an isometric view of a humidifier according to one form of the present technology.

[0117] Figure 5B An isometric view of a humidifier according to one form of the present technology is shown, which shows the humidifier reservoir 5110 removed from the humidifier reservoir base 5130.

[0118] Figure 5C A schematic diagram of a humidifier according to one form of the present technology is shown.

[0119] 3.6 Respiratory Waveform

[0120] Figure 6A Shows a typical respiratory waveform of a human model during sleep.

[0121] Figure 6B Shows selected polysomnogram channels (pulse oximetry, flow, thoracic movement, and abdominal movement) of a patient that typically exceed about 90 seconds during non-REM sleep breathing.

[0122] 3.7 Screening, Diagnosis, and Monitoring Systems

[0123] Figure 7A Shows a patient undergoing polysomnogram (PSG). The patient is sleeping in a supine position.

[0124] Figure 7B Shows a monitoring device for monitoring a patient's condition. The patient is sleeping in a supine position.

[0125] 3.8 Data Transmission

[0126] Figure 8A Is a block diagram of a system that receives usage data and other data from a respiratory therapy device.

[0127] Figure 8B Is a block diagram of an alternative system that receives usage data and other data from a respiratory therapy device.

[0128] 3.9 Predicting Reduction or Termination of Treatment

[0129] Figure 9 Shows a flowchart illustrating a method for predicting patient compliance based on usage data output from a respiratory therapy device.

[0130] Figure 10 Shows a schematic diagram of an example of a time window of usage data considered in an algorithm applied with the disclosed technology. Detailed Description

[0131] Before describing the present technology in further detail, it should be understood that the present technology is not limited to the specific examples described herein, and the specific examples described herein may be changed. It should also be understood that the terms used in this disclosure are only for the purpose of describing the specific examples described herein and are not intended to be limiting.

[0132] The following description is provided with respect to various examples that may share one or more common characteristics and / or features. It should be understood that one or more features of any example may be combined with one or more features of other examples. Additionally, in any of the examples, any single feature or combination of features may form additional examples.

[0133] 4.1 Treatment

[0134] In one form, the present technology includes a method for treating a respiratory disorder, the method including the step of applying positive pressure to the airway inlet of a patient 1000.

[0135] In certain examples of the present technology, an air supply under positive pressure is provided to the nasal passages of the patient via one or both nostrils.

[0136] In certain examples of the present technology, mouth breathing is restricted, constrained, or blocked.

[0137] 4.2 Treatment System

[0138] In one form, the present technology includes an apparatus or device for treating a respiratory disorder. The apparatus or device may include an RPT device 4000 for supplying pressurized air to a patient 1000 via an air circuit 4170 to a patient interface 3000 or 3800.

[0139] 4.3 Patient Interface

[0140] The non-invasive patient interface 3000 according to one aspect of the present technology includes the following functional aspects: a seal-forming structure 3100, a pressurization chamber 3200, a positioning and stabilization structure 3300, a vent 3400, a connection port 3600 in one form for connection to the air circuit 4170, and a forehead support 3700. In some forms, the functional aspects may be provided by one or more physical components. In some forms, a single entity component may provide one or more functional aspects. In use, the seal-forming structure 3100 is arranged to surround the inlet of the patient's airway to facilitate the supply of positive pressure air to the airway.

[0141] The unsealed patient interface 3800 in the form of a nasal cannula includes nasal forks 3810a, 3810b which can deliver air to the respective nostrils of a patient 1000. Such nasal forks generally do not form a seal with the inner or outer skin surface of the nostrils. Air can be delivered to these nasal forks through one or more air supply lumens 3820a, 3820b coupled to the nasal cannula 3800. The lumens 3820a, 3820b lead from the nasal cannula 3800 to an RT device which generates an air flow at high flow rate. The "vent" at the unsealed patient interface 3800 is the passage from between the ends of the nasal forks 3810a and 3810b of the cannula 3800, through the patient's nostrils, to the atmosphere, through which excess air flow escapes to the surrounding environment.

[0142] If the patient interface cannot comfortably deliver a minimum level of positive pressure to the airway, the patient interface may not be suitable for respiratory pressure therapy.

[0143] 4.3.1 Seal-Forming Structure

[0144] In one form of the present technology, the seal forming structure 3100 provides a target seal forming area and may additionally provide a cushioning function. The target seal forming area is the area on the seal forming structure 3100 where sealing may occur. The area where actual sealing occurs - the actual sealing surface - can vary from day to day and from patient to patient during a given treatment session, depending on a series of factors, including for example the position on the face where the patient interface is placed, the tension in the positioning and stabilization structure, and the shape of the patient's face.

[0145] In one form, the target seal forming area is located on the outer surface of the seal forming structure 3100.

[0146] In certain forms of the present technology, the seal forming structure 3100 is composed of a biocompatible material such as silicone rubber.

[0147] The seal forming structure 3100 according to the present technology can be composed of a soft, flexible, elastic material such as silicone.

[0148] In certain forms of the present technology, a system is provided that includes more than one seal forming structure 3100, each seal forming structure being configured to correspond to a different range of sizes and / or shapes. For example, the system can include one form of the seal forming structure 3100 that is suitable for large-sized heads but not for small-sized heads, while another is suitable for small-sized heads but not for large-sized heads.

[0149] 4.3.1.1 Sealing mechanism

[0150] In one form, the seal forming structure includes a seal flange that utilizes a pressure-assisted sealing mechanism. In use, the seal flange can readily respond to the system positive pressure inside the inflatable chamber 3200 acting on its underside, thereby forming a tight sealing engagement with the face. This pressure-assisted mechanism can act together with the elastic tension in the positioning and stabilization structure.

[0151] In one form, the seal forming structure 3100 includes a seal flange and a support flange. The seal flange includes a relatively thin member having a thickness less than about 1 mm, for example about 0.25 mm to about 0.45 mm, that extends around the perimeter of the inflatable chamber 3200. The support flange can be relatively thicker than the seal flange. The support flange is disposed between the seal flange and the edge of the inflatable chamber 3200 and extends at least a portion of the route around the perimeter. The support flange is or includes a spring-like element and is used to support the seal flange from buckling in use.

[0152] In one form, the seal-forming structure may include a compression seal portion or a gasket seal portion. In use, the compression seal portion or the gasket seal portion is configured and arranged to be in a compressed state, such as as a result of elastic tension in the positioning and stabilizing structure.

[0153] In one form, the seal-forming structure includes a tensioning portion. In use, the tensioning portion is held in tension, for example, by adjacent regions of a sealing flange.

[0154] In one form, the seal-forming structure includes a region having a sticky or adhesive surface.

[0155] In certain forms of the present technology, the seal-forming structure may include one or more of a pressure-assisted sealing flange, a compression seal portion, a gasket seal portion, a tensioning portion, and a portion having a sticky or adhesive surface.

[0156] 4.3.1.2 Nose bridge or nasal ridge region

[0157] In one form, the non-invasive patient interface 3000 includes a seal-forming structure that forms a seal on the nose bridge region or nasal ridge region of the patient's face in use.

[0158] In one form, the seal-forming structure includes a saddle-shaped region configured to form a seal on the nose bridge region or nasal ridge region of the patient's face.

[0159] 4.3.1.3 Upper lip region

[0160] In one form, the non-invasive patient interface 3000 includes a seal-forming structure that forms a seal when used on the upper lip region (i.e., the upper part of the lip) of the patient's face.

[0161] In one form, the seal-forming structure includes a saddle-shaped region configured to form a seal on the upper lip region of the patient's face in use.

[0162] 4.3.1.4 Chin region

[0163] In one form, the non-invasive patient interface 3000 includes a seal-forming structure that forms a seal when used on the chin region of the patient's face.

[0164] In one form, the seal-forming structure includes a saddle-shaped region configured to form a seal when used on the chin region of the patient's face.

[0165] 4.3.1.5 Forehead region

[0166] In one form, the seal-forming structure forms a seal on the forehead region of the patient's face in use. In this form, the inflatable chamber can cover the eyes in use.

[0167] 4.3.1.6 Nasal Pillow

[0168] In one form, the seal-forming structure of the non-invasive patient interface 3000 includes a pair of nasal masks or nasal pillows, each nasal mask or nasal pillow being configured and arranged to form a seal with a respective nostril of the patient's nose.

[0169] The nasal pillow according to one aspect of the present technology includes: a frustum of a cone that forms a seal on at least a portion of the bottom surface of the patient's nose; a stem; a flexible region on the bottom surface of the frustum of the cone that connects the frustum of the cone to the stem. In addition, the structure to which the nasal pillow of the present technology is connected includes a flexible region adjacent to the bottom of the stem. The flexible regions can cooperate to facilitate a universal engagement structure that is capable of accommodating relative movement both in displacement and in angle between the frustum of the cone and the structure to which the nasal pillow is connected. For example, the position of the frustum of the cone can be axially moved towards the structure to which the stem is connected.

[0170] 4.3.2 Inflatable Chamber

[0171] The inflatable chamber 3200 has a perimeter that is shaped to be complementary to the surface profile of an average person's face in the region where the seal will be formed in use. In use, the edge of the inflatable chamber 3200 is positioned adjacent to an adjacent surface of the face. The seal-forming structure 3100 provides the actual contact with the face. The seal-forming structure 3100 can extend around the entire perimeter of the inflatable chamber 3200 in use. In some forms, the inflatable chamber 3200 and the seal-forming structure 3100 are formed from a single homogeneous sheet of material.

[0172] In certain forms of the present technology, the inflatable chamber 3200 does not cover the patient's eyes in use. In other words, these apertures are outside the pressurized volume defined by the inflatable chamber. Such forms tend to be less invasive and / or more comfortable for the wearer, which can improve compliance with the treatment.

[0173] In certain forms of the present technology, the inflatable chamber 3200 is made of a transparent material such as transparent polycarbonate. Using a transparent material can reduce the prominence of the patient interface and help improve compliance with the treatment. Using a transparent material can help the clinician observe how the patient interface is positioned and functions.

[0174] In certain forms of the present technology, the inflatable chamber 3200 is made of a translucent material. Using a transparent material can reduce the prominence of the patient interface and help improve compliance with the treatment.

[0175] 4.3.3 Positioning and Stabilizing Structure

[0176] The sealing formation structure 3100 of the patient interface 3000 of the present technology can be maintained in a sealed state during use by the positioning and stabilizing structure 3300.

[0177] In one form, the positioning and stabilizing structure 3300 provides a holding force that is at least sufficient to overcome the effect of the positive pressure in the inflatable chamber 3200 to lift away from the face.

[0178] In one form, the positioning and stabilizing structure 3300 provides a holding force to overcome the effect of gravity on the patient interface 3000.

[0179] In one form, the positioning and stabilizing structure 3300 provides a holding force as a safety margin to overcome the potential impact of destructive forces on the patient interface 3000, such as from tube drag or accidental interference with the patient interface.

[0180] In one form of the present technology, a positioning and stabilizing structure 3300 is provided, which is configured in a manner consistent with being worn by a patient while sleeping. In one example, the positioning and stabilizing structure 3300 has a low profile or cross-sectional thickness to reduce the perceived or actual volume of the device. In one example, the positioning and stabilizing structure 3300 includes at least one band with a rectangular cross-section. In one example, the positioning and stabilizing structure 3300 includes at least one flat band.

[0181] In one form of the present technology, a positioning and stabilizing structure 3300 is provided that is configured to not be so large and bulky as to prevent the patient from lying in a supine sleeping position, where the back region of the patient's head is on the pillow.

[0182] In one form of the present technology, a positioning and stabilizing structure 3300 is provided that is configured to not be so large and bulky as to prevent the patient from lying in a lateral sleeping position, where the side region of the patient's head is on the pillow.

[0183] In one form of the present technology, the positioning and stabilizing structure 3300 is provided with a decoupling portion located between the front portion of the positioning and stabilizing structure 3300 and the rear portion of the positioning and stabilizing structure 3300. The decoupling portion does not resist compression and can be, for example, a flexible band or a soft band. The decoupling portion is constructed and arranged such that when the patient lies their head on the pillow, the presence of the decoupling portion prevents the force acting on the rear portion from being transmitted along the positioning and stabilizing structure 3300 and breaking the seal.

[0184] In one form of the present technology, the positioning and stabilizing structure 3300 includes a strap configured as a laminate of a fabric patient contact layer, a foam inner layer, and a fabric outer layer. In one form, the foam is porous such that moisture (e.g., sweat) can pass through the strap. In one form, the fabric outer layer includes loop material for engaging with a hook material portion.

[0185] In certain forms of the present technology, the positioning and stabilizing structure 3300 includes a strap that is extendable, such as elastically extendable. For example, the strap can be configured to be in a tensioned state during use and direct a force to cause the seal forming structure to make sealing contact with a portion of the patient's face. In one example, the strap can be configured as a tie.

[0186] In one form of the present technology, the positioning and stabilizing structure includes a first tie configured and arranged such that at least a portion of the lower edge of the first tie passes over the supra-aural reference point of the patient's head and covers a portion of the parietal bone without covering the occipital bone during use.

[0187] In one form of the present technology applicable to a nasal mask only or a full face mask, the positioning and stabilizing structure includes a second tie configured and arranged such that at least a portion of the upper edge of the second tie passes below the infra-aural reference point of the patient's head and covers or is located below the occipital bone of the patient's head during use.

[0188] In one form of the present technology applicable to a nasal mask only or a full face mask, the positioning and stabilizing structure includes a third tie configured and arranged to interconnect the first tie and the second tie to reduce the tendency of the first tie and the second tie to separate from each other.

[0189] In certain forms of the present technology, the positioning and stabilizing structure 3300 includes a strap that is bendable and, for example, non-rigid. The advantage of this aspect is that the strap makes it more comfortable for the patient to lie on while sleeping.

[0190] In certain forms of the present technology, the positioning and stabilizing structure 3300 includes a strap configured to be breathable to allow moisture to be transmitted through the strap.

[0191] In certain forms of the present technology, a system is provided that includes more than one positioning and stabilizing structure 3300, each positioning and stabilizing structure being configured to provide a holding force corresponding to a different range of sizes and / or shapes. For example, the system can include one form of the positioning and stabilizing structure 3300 that is suitable for a large-sized head but not for a small-sized head, while another form of the positioning and stabilizing structure is suitable for a small-sized head but not for a large-sized head.

[0192] In certain forms of the present technology, the stabilization structure 3300 includes sensors configured to output data related to tensile or other relevant forces, stresses, or mechanical values along the longitudinal axis of these strips. In other examples, the stabilization structure 3300 may include pressure sensors on the side that senses the pressure of the sensing band against the patient's head.

[0193] 4.3.4 Ventilation port

[0194] In one form, the patient interface 3000 includes a ventilation port 3400 constructed and arranged to allow flushing of exhaled gases such as carbon dioxide.

[0195] In certain forms, the ventilation port 3400 is configured to allow continuous ventilation flow from the interior of the inflation chamber 3200 to the surrounding environment while the pressure in the inflation chamber is positive relative to the surrounding environment. The ventilation port 3400 is configured such that the ventilation port flow has an amplitude sufficient to reduce the patient's rebreathing of exhaled CO2 while maintaining the therapeutic pressure in the inflation chamber during use.

[0196] One form of the ventilation port 3400 according to the present technology includes a plurality of holes, for example, from about 20 to about 80 holes, or from about 40 to about 60 holes, or from about 45 to about 55 holes.

[0197] The ventilation port 3400 may be located in the inflation chamber 3200. Alternatively, the ventilation port 3400 is located in a decoupling structure (e.g., a rotary joint).

[0198] In one form of the present technology, the ventilation port 3400 may include an acoustic sensor to determine whether ventilation port noise is emitted from the ventilation port 3400. For example, the acoustic sensor on the ventilation port 3400 may be compared with the noise output of a sensor on another component of a remote sensor or the RPT device 4000 to determine the noise associated with the ventilation port 3400 as opposed to other components of the RPT device 4000.

[0199] 4.3.5 Forehead support

[0200] In one form, the patient interface 3000 includes a forehead support 3700.

[0201] 4.3.6 Ports

[0202] In one form of the present technology, the patient interface 3000 includes one or more ports that allow access to the volume within the inflation chamber 3200. In one form, this allows a clinician to supply supplemental oxygen. In one form, this enables direct measurement of the properties of the gas within the inflation chamber 3200, such as pressure.

[0203] 4.4 RPT device

[0204] The RPT device 4000 according to one aspect of the present technology includes mechanical, pneumatic, and / or electrical components and is configured to execute one or more algorithms 4300, such as any of the methods described in whole or in part herein. The RPT device 4000 can be configured to generate an air flow for delivery to a patient's airway, such as for treating one or more respiratory conditions described elsewhere in this document.

[0205] In one form, the RPT device 4000 is configured and arranged to be able to deliver an air flow in the range of -20 L / min to +150 L / min while maintaining a positive pressure of at least 6 cmH2O, or at least 10 cmH2O, or at least 20 cmH2O.

[0206] 4.4.1 Mechanical and Pneumatic Components of the RPT Device

[0207] The RPT device may include one or more of the following components in an integral unit. In an alternative form, one or more of the following components may be provided as separate units.

[0208] 4.4.1.1 Transducer

[0209] The transducer can be inside the RPT device or outside the RPT device. An external transducer can be located, for example, on an air circuit (e.g., patient interface) or form part of an air circuit (e.g., patient interface). The external transducer can be in the form of a non-contact sensor, such as a Doppler radar motion sensor that transmits or transfers data to the RPT device.

[0210] In one form of the present technology, one or more transducers 4270 are located upstream and / or downstream of the pressure generator 4140. The one or more transducers 4270 can be configured and arranged to generate a signal representing a characteristic of the air flow (such as flow rate, pressure, or temperature) at that point in the pneumatic path.

[0211] In one form of the present technology, one or more transducers 4270 can be located near the patient interface 3000 or 3800 and include one or more acoustic sensors.

[0212] In one form, the signal from the transducer 4270 can be filtered, such as by low-pass, high-pass, or band-pass filtering.

[0213] 4.4.1.1.1 Flow Sensor

[0214] The flow sensor 4274 according to the present technology can be based on a differential pressure transducer, such as the SDP600 series differential pressure transducers from SENSIRION.

[0215] In one form, the central controller 4230 receives a signal representative of the flow rate from the flow sensor 4274.

[0216] 4.4.1.1.2 Pressure Sensor

[0217] The pressure sensor 4272 according to the present technology is in fluid communication with the pneumatic path. Examples of suitable pressure transducers are sensors of the HONEYWELL ASDX series. Another suitable pressure transducer is a sensor of the NPA series of GENERAL ELECTRIC.

[0218] In one form, the signal from the pressure sensor 4272 is received by the central controller 4230.

[0219] 4.4.1.1.3 Motor Speed Transducer

[0220] In one form of the present technology, a motor speed transducer 4276 is used to determine the rotational speed of the motor 4144 and / or the blower 4142. The motor speed signal from the motor speed transducer 4276 can be provided to the therapy device controller 4240. The motor speed transducer 4276 can be, for example, a speed sensor such as a Hall effect sensor.

[0221] 4.4.2 CPG Device Electrical Components

[0222] 4.4.2.1 Power Supply

[0223] The power supply 4210 can be located inside or outside the housing 4010 of the RPT device 4000.

[0224] In one form of the present technology, the power supply 4210 supplies power only to the RPT device 4000. In another form of the present technology, the power supply 4210 supplies power to both the RPT device 4000 and the humidifier 5000.

[0225] 4.4.2.2 Input Device

[0226] In one form of the present technology, the RPT device 4000 includes one or more input devices 4220 in the form of buttons, switches, or dials to allow a person to interact with the device. The buttons, switches, or dials can be physical devices or software devices accessible via a touch screen. In one form, these buttons, switches, or dials can be physically connected to the external housing 4010, or in another form, can be in wireless communication with a receiver electrically connected to the central controller 4230.

[0227] In one form, the input device 4220 can be constructed and arranged to allow a person to select values and / or menu options.

[0228] 4.4.2.3 Central Controller

[0229] In one form of the present technology, the central controller 4230 is a processor or processors adapted to control the RPT device 4000.

[0230] Suitable processors may include x86 INTEL processors, processors based on the -M processors from ARM Holdings, such as the STM32 series microcontrollers from STMICROELECTRONICS. In certain alternative forms of the present technology, 32-bit RISC CPUs (such as the STR9 series microcontrollers from STMICROELECTRONICS) or 16-bit RISC CPUs (such as processors from the MSP430 series microcontrollers) manufactured by TEXAS INSTRMENTS may also be suitable. -M processors, such as the STM32 series microcontrollers from STMICROELECTRONICS. In certain alternative forms of the present technology, 32-bit RISC CPUs (such as the STR9 series microcontrollers from STMICROELECTRONICS) or 16-bit RISC CPUs (such as processors from the MSP430 series microcontrollers) manufactured by TEXAS INSTRMENTS may also be suitable.

[0231] In one form of the present technology, the central controller 4230 is a dedicated electronic circuit.

[0232] In one form, the central controller 4230 is an application specific integrated circuit. In another form, the central controller 4230 includes discrete electronic components.

[0233] The central controller 4230 may be configured to receive one or more input signals from one or more converters 4270, one or more input devices 4220, and the humidifier 5000.

[0234] The central controller 4230 may be configured to provide output signals to one or more of the output device 4290, the therapy device controller 4240, the data communication interface 4280, and the humidifier 5000.

[0235] In some forms of the present technology, the central controller 4230 is configured to implement one or more of the methods described herein, such as one or more algorithms 4300 represented as a computer program stored on a non-transitory computer-readable storage medium (such as the memory 4260). In some forms of the present technology, the central controller 4230 may be integrated with the RPT device 4000. However, in some forms of the present technology, some of the methods may be performed by a remotely located device. For example, the remotely located device may determine control settings for a ventilator or detect respiratory-related events by analyzing the stored data (such as data from any of the sensors described herein).

[0236] 4.4.2.4 Clock

[0237] The RPT device 4000 may include a clock 4232 connected to the central controller 4230.

[0238] 4.4.2.5 Treatment Device Controller

[0239] In one form of the present technology, the treatment device controller 4240 is a treatment control module 4330, which forms part of an algorithm 4300 executed by a central controller 4230.

[0240] In one form of the present technology, the treatment device controller 4240 is a dedicated motor control integrated circuit. For example, in one form, an MC33035 brushless DC motor controller manufactured by ONSEMI is used.

[0241] 4.4.2.6 Protection Circuit

[0242] One or more protection circuits 4250 according to the present technology may include an electrical protection circuit, a temperature and / or pressure safety circuit.

[0243] 4.4.2.7 Memory

[0244] In one form according to the present technology, the RPT device 4000 includes a memory 4260, such as a non-volatile memory. In some forms, the memory 4260 may include a battery-powered static RAM. In some forms, the memory 4260 may include a volatile RAM.

[0245] The memory 4260 may be located on the PCBA 4202. The memory 4260 may be in the form of an EEPROM or a NAND flash memory.

[0246] Additionally, the RPT device 4000 includes a removable form of memory 4260, such as a memory card manufactured according to the Secure Digital (SD) standard.

[0247] In one form of the present technology, the memory 4260 acts as a non-transitory computer-readable storage medium on which computer program instructions are stored, and these computer program instructions express one or more methods described herein, such as one or more algorithms 4300.

[0248] 4.4.2.8 Data Communication System

[0249] In one form of the present technology, a data communication interface 4280 is provided, and the data communication interface 4280 is connected to a central controller 4230 or other processor or control system depending on the system (e.g., a computer system, exercise equipment, or other system). The data communication interface 4280 may be connected to a remote external communication network 4282 and / or a local external communication network 4284. The remote external communication network 4282 may be connected to a remote external device 4286. The local external communication network 4284 may be connected to a local external device 4288.

[0250] In one form, the data communication interface 4280 is part of the central controller 4230. In another form, the data communication interface 4280 is separate from the central controller 4230 and may include an integrated circuit or a processor.

[0251] In one form, the remote external communication network 4282 is the Internet. The data communication interface 4280 may use wired communication (e.g., via Ethernet or fiber optic) or a wireless protocol (e.g., CDMA, GSM, LTE) to connect to the Internet.

[0252] In one form, the local external communication network 4284 utilizes one or more communication standards, such as Bluetooth or the consumer infrared protocol.

[0253] In one form, the remote external device 4286 is one or more computers, such as a cluster of networked computers. In one form, the remote external device 4286 may be a virtual computer rather than a physical computer. In either case, such a remote external device 4286 may be accessed by a properly authorized person (such as a clinician).

[0254] The local external device 4288 may be a personal computer, a mobile phone, a tablet, or a remote control.

[0255] In certain forms of the present technology, the central controller 4230 will record usage data 9045 in the memory 4260, which may include outputs from a treatment device controller 4240, a computer system, exercise equipment, or other systems. The usage data 9045 may include several blocks or data portions, including: (1) date and time stamps, (2) start and stop times of use, (3) usage time of a session, (4) dates and times of turning on and off the RPT device 4000, computer system, exercise equipment, or other systems, and (5) treatment or other settings and sensor data, including readings from sensors 4270, including flow 4274, pressure 4272, speed 4276 (in the case of exercise equipment, it may be the speed or intensity of exercise (e.g., treadmill speed)).

[0256] In certain forms of the present technology, usage data 9045 will be stored in the local memory 4260. The usage data 9045 can also be sent over a network via the data communication interface 4280 to a remote external device 4286 or a local external device 4288.

[0257] In some examples, the central controller 4230 will send the usage data 9085 via the data communication interface 4280 one hour, two hours, three hours, or other suitable time range after a treatment session or other session (e.g., exercise session, driving session, website usage session) has ended. In other examples, the usage data 9045 will be sent weekly. In some examples, if no usage sessions are active on a particular day, the controller 4230 can send the usage data 9045 via the data communication interface 4280 at 1:00 am or other suitable time on the next day or weekend. The usage data 9045 will indicate that the particular day or time period contains a non - usage day. In some examples, the usage data 9045 can distinguish between: (1) turning on and not using the device (e.g., RPT device 4000, not turning on the device or system at all). In some examples, the RPT device 4000 or other device or system will not send usage data 9045 until it is turned on again, and will determine the amount of non - usage days since the last session recognized and stored in the memory 4260 by the controller 4230.

[0258] Data sent via the data communication interface 4280 can be raw data, or can be pre - processed data to save bandwidth, especially in areas with poor cellular signals or other remote external communication network 4282 bandwidth. For example, the usage data 9045 can be pre - processed to output relevant features for usage reduction or termination prediction. This can include the number of non - usage days, average usage (e.g., hours), and usage standard deviation. Then, the relevant features can be processed by an algorithm 4300 on the remote external device 4286 or server.

[0259] In certain forms of the present technology, a full usage prediction algorithm can reside in the local memory 4260, and the controller 4230 can process the usage data 9045 to determine the likelihood that the patient 1000 or other user (depending on the application) will discontinue or reduce the use of the device itself. In these cases, the controller 4230 can send a signal to send the output to the display 4294, and / or send data to a local or remote external device, e.g., if the percentage likelihood exceeds a threshold.

[0260] 4.4.2.9 Output devices, including an optional display, siren

[0261] The output device 4290 according to the present technology can take the form of one or more of a visual, audio, and tactile unit. [000170] The visual display can be a liquid crystal display (LCD) or a light emitting diode (LED) display.

[0262] 4.4.2.9.1 Display Driver

[0263] It is shown that the driver 4292 receives characters, symbols, or images to be shown on the display 4294 as input and converts them into commands to cause the display 4294 to show these characters, symbols, or images.

[0264] 4.4.2.9.2 Display

[0265] The display 4294 is configured to visually show characters, symbols, or images in response to commands received from the display driver 4292. For example, the display 4294 can be an eight-segment display, in which case the display driver 4292 converts each character or symbol such as the digit "0" into eight logic signals indicating whether to activate the eight corresponding segments to show a specific character or symbol.

[0266] In some examples, the display can include a touch screen or a remote interface, such as a smart phone that receives input from a user or patient 1000.

[0267] 4.4.3 Algorithms

[0268] As described above, in some forms of the present technology, the central controller 4230 or other processors can be configured to implement one or more algorithms represented as a computer program stored in a non-transitory computer-readable storage medium (such as the memory 4260). The algorithms are generally grouped into multiple groups called modules. These algorithms can include feature detection algorithms and machine learning algorithms for predicting the reduction or termination of treatment, the use of exercise equipment, or the participation in the use of on-demand services, such as a taxi service that can track usage (e.g., by a user or employee - such as a driver) using a mobile application.

[0269] 4.4.3.1 Preprocessing Module

[0270] The preprocessing module 4310 according to one form of the present technology receives signals from the converter 4270 (e.g., the flow sensor 4274 or the pressure sensor 4272) as input and performs one or more process steps to calculate one or more output values that will be used as input to another module (e.g., the treatment engine module 4320).

[0271] In one form of the present technology, the output values include the interface pressure Pm, the respiratory flow Qr, and the leakage flow Ql.

[0272] In various forms of the present technology, the preprocessing module 4310 includes one or more of the following algorithms: interface pressure estimation 4312, ventilation flow estimation 4314, leak flow estimation 4316, and respiratory flow estimation 4318.

[0273] 4.4.3.1.1 Interface Pressure Estimation

[0274] In one form of the present technology, the interface pressure estimation algorithm 4312 receives as inputs a signal from the pressure sensor 4272 indicating the pressure (device pressure Pd) in the pneumatic path near the outlet of the pneumatic block and a signal from the flow sensor 4274 representing the flow rate (device flow rate Qd) of the air stream leaving the RPT device 4000. The device flow rate Qd without any supplementary gas 4180 can be used as the total flow rate Qt. The interface pressure algorithm 4312 estimates the pressure drop ΔP across the air circuit 4170. The dependence of the pressure drop ΔP on the total flow rate Qt can be modeled for a specific air circuit 4170 by the pressure drop characteristic ΔP(Q). The interface pressure estimation algorithm 4312 provides an estimated pressure Pm in the patient interface 3000 or 3800 as an output. The pressure Pm in the patient interface 3000 or 3800 can be estimated as the device pressure Pd minus the air circuit pressure drop ΔP.

[0275] 4.4.3.1.2 Ventilation Flow Estimation

[0276] In one form of the present technology, the ventilation flow estimation algorithm 4314 receives as an input the estimated pressure Pm in the patient interface 3000 or 3800 from the interface pressure estimation algorithm 4312 and estimates the ventilation flow rate Qv of the air from the ventilation port 3400 in the patient interface 3000 or 3800. For a particular ventilation orifice 3400 in use, the dependence of the orifice flow rate Qv on the interface pressure Pm can be modeled by the orifice characteristic Qv(Pm).

[0277] 4.4.3.1.3 Leak Flow Estimation

[0278] In one form of the present technology, the leak flow estimation algorithm 4316 receives the total flow rate Qt and the ventilation flow rate Qv as inputs and provides an estimate of the leak flow rate Ql as an output. In one form, the leak flow estimation algorithm estimates the leak flow rate Ql by calculating the average value of the difference between the total flow rate Qt and the ventilation flow rate Qv over a sufficiently long time period (e.g., about 10 seconds).

[0279] In one form, the leak flow estimation algorithm 4316 receives as inputs the total flow Qt, the ventilation flow Qv, and the estimated pressure Pm in the patient interface 3000 or 3800, and provides as output the leak flow Ql by calculating the leak conductance and determining the leak flow Ql as a function of the leak conductance and the pressure Pm. The leak conductance is calculated as the quotient of the low-pass filtered non-ventilation flow equal to the difference between the total flow Qt and the ventilation flow Qv, and the square root of the low-pass filtered pressure Pm, where the low-pass filter time constant has a value long enough to encompass several respiratory cycles, e.g., about 10 seconds. The leak flow Ql can be estimated as the product of the leak conductivity and a function of the pressure Pm.

[0280] 4.4.3.1.4 Respiratory Flow Estimation

[0281] In one form of the present technique, the respiratory flow estimation algorithm 4318 receives the total flow Qt, the ventilation flow Qv, and the leak flow Ql as inputs, and estimates the respiratory flow Qr of air to the patient by subtracting the ventilation flow Qv and the leak flow Ql from the total flow Qt.

[0282] 4.4.3.2 Treatment Engine Module

[0283] In one form of the present technique, the treatment engine module 4320 receives as inputs one or more of the pressure Pm in the patient interface 3000 or 3800 and the respiratory flow Qr of air to the patient, and provides one or more treatment parameters as output.

[0284] In one form of the present technique, the treatment parameter is the treatment pressure Pt.

[0285] In one form of the present technique, the treatment parameter is one or more of the pressure change amplitude, the base pressure, and the target ventilation volume.

[0286] In various forms, the treatment engine module 4320 includes one or more of the following algorithms: phase determination 4321, waveform determination 4322, ventilation determination 4323, inspiratory flow limit determination 4324, apnea / hypopnea determination 4325, snoring determination 4326, airway patency determination 4327, target ventilation volume determination 4328, and treatment parameter determination 4329.

[0287] 4.4.3.2.1 Phase Determination

[0288] In one form of the present technique, the RPT device 4000 does not determine the phase.

[0289] In one form of the present technique, the phase determination algorithm 4321 receives as input a signal indicative of the respiratory flow Qr and provides as output the phase Φ of the current respiratory cycle of the patient 1000.

[0290] In some forms known as discrete phase determination, the phase output Φ is a discrete variable. In one implementation of discrete phase determination, a binary-valued phase output Φ with an inspiration or expiration value is provided when the start of spontaneous inspiration and expiration are detected separately, for example values represented as 0 and 0.5 revolutions respectively. The RPT device 4000 that effectively performs discrete phase determination for "trigger" and "cycle" since the trigger point and cycle point are respectively the moments when the phase changes from expiration to inspiration and from inspiration to expiration. In one implementation of binary-valued phase determination, when the respiratory flow rate Qr has a value exceeding a positive threshold, the phase output Φ is determined to have the discrete value 0 (thus "triggering" the RPT device 4000), and when the respiratory flow rate Qr has a value more negative than a negative threshold, the phase output Φ is determined to have the discrete value 0.5 revolutions (thus "cycling" the RPT device 4000). The inspiratory time Ti and expiratory time Te can be estimated as typical values over many respiratory cycles of the time taken for the phase Φ to be equal to 0 (indicating inspiration) and 0.5 (indicating expiration) respectively.

[0291] Another implementation of discrete phase determination provides a ternary-valued phase output Φ with a value of one of inspiration, mid-inspiratory pause, and expiration.

[0292] In other forms known as continuous phase determination, the phase output Φ is a continuous variable, for example varying from 0 to 1 revolution or 0 to 2 radians. The RPT device 4000 that performs continuous phase determination can be triggered and cycled when the continuous phase reaches 0 and 0.5 revolutions respectively. In one implementation of continuous phase determination, a fuzzy logic analysis of the respiratory flow rate Qr is used to determine the continuous phase value Φ. The continuous value of the phase determined in this implementation is typically referred to as "fuzzy phase". In one implementation of the fuzzy phase determination algorithm 4321, the following rules are applied to the respiratory flow Qr:

[0293] 1. If the respiratory flow is zero and rapidly increasing, the phase is 0 revolutions.

[0294] 2. If the respiratory flow is large, positive, and stable, the phase is 0.25 revolutions.

[0295] 3. If the respiratory flow is zero and rapidly decreasing, the phase is 0.5 revolutions.

[0296] 4. If the respiratory flow is negative and stable, the phase is 0.75 revolutions.

[0297] 5. If the respiratory flow is zero and stable, and the absolute value of the 5-second low-pass filtered respiratory flow is large, the phase is 0.9 revolutions.

[0298] 6. If the respiratory flow is positive and the phase is expiration, the phase is 0 revolutions.

[0299] 7. If the respiratory flow is negative and the phase is inhalation, the phase is 0.5 turns.

[0300] 8. If the absolute value of the 5 - second low - pass filtered respiratory flow is large, the phase increases at a steady rate equal to the patient's respiratory rate, low - pass filtered with a time constant of 20 seconds.

[0301] The output of each rule can be represented as a vector, where the phase of the vector is the result of the rule and its magnitude is the degree of fuzziness for which the rule is true. The degree of fuzziness of "large", "steady", etc. for the respiratory flow is determined using appropriate membership functions. The results of the rules are represented as vectors and then combined through some function such as taking the centroid. In such a combination, the rules can be weighted equally or differently.

[0302] In another embodiment of continuous phase determination, as described above, the phase Φ, the inspiratory time Ti, and the expiratory time Te are also discretely estimated from the respiratory flow Qr. The continuous phase Φ at any moment can be determined as half of the proportion of the inspiratory time Ti that has elapsed since the previous trigger moment, or 0.5 turns plus half of the proportion of the expiratory time Te that has elapsed since the previous cycle moment (whichever moment is closer).

[0303] 4.4.3.2.2 Waveform determination

[0304] In one form of the present technology, the treatment parameter determination algorithm 4329 provides a substantially constant treatment pressure throughout the patient's respiratory cycle.

[0305] In other forms of the present technology, the treatment control module 4330 controls the pressure generator 4140 to provide a treatment pressure Pt that varies as a function of the phase Φ of the patient's respiratory cycle according to the waveform template Π(Φ).

[0306] In one form of the present technology, the waveform determination algorithm 4322 provides a waveform template Π(Φ) with values in the range [0, 1] over the domain of the phase value Φ provided by the phase determination algorithm 4321 for use by the treatment parameter determination algorithm 4329.

[0307] In one form, suitable for discrete or continuous value phase, the waveform template Π(Φ) is a square wave template that has a value of 1 for phase values up to and including 0.5 revolutions and a value of 0 for phase values above 0.5 revolutions. In one form, suitable for continuous value phase, the waveform template Π(Φ) comprises two smoothly curved portions, i.e., for phase values up to 0.5 revolutions, the smooth curve (e.g., a raised cosine) rises from 0 to 1, and for phase values above 0.5 revolutions, the smooth curve (e.g., exponential) falls from 1 to 0. In one form, suitable for continuous value phase, the waveform template Π(Φ) is based on a square wave, but has a smooth rise from 0 to 1 for phase values until a "rise time" less than 0.5 revolutions and a smooth fall from 1 to 0 for phase values within a "fall time" after 0.5 revolutions, with a "fall time" less than 0.5 revolutions.

[0308] In some forms of the present technology, the waveform determination algorithm 4322 selects the waveform template Π(Φ) from a waveform template library according to the settings of the RPT device. Each waveform template Π(Φ) in the library can be provided as a look-up table of values for phase values. In other forms, the waveform determination algorithm 4322 uses a predetermined functional form that may be parameterized by one or more parameters (e.g., the time constant of an exponential curve portion) to calculate the waveform template Π(Φ) "on the fly". The parameters of the functional form can be predetermined or depend on the current state of the patient 1000.

[0309] In some forms of the present technology, for a discrete two-valued phase of inspiration (Φ = 0 revolutions) or expiration (Φ = 0.5 revolutions), the waveform determination algorithm 4322 calculates the "on-the-fly" waveform template Π(Φ,t) as a function of the discrete phase Φ and the time t measured since the most recent trigger event. In one such form, the waveform determination algorithm 4322 calculates the two-part (inspiration and expiration) waveform template Π(Φ,t) as follows:

[0310]

[0311] where Π i (t) and Π e (t) are the inspiration and expiration portions of the waveform template Π(Φ,t). In one such form, the inspiration portion Π i (t) of the waveform template is a smooth rise from 0 to 1 parameterized by the rise time, and the expiration portion Π e (t) of the waveform template is a smooth fall from 1 to 0 parameterized by the fall time.

[0312] 4.4.3.2.3 Ventilation measurement

[0313] In one form of the present technology, the ventilation measurement algorithm 4323 receives an input of respiratory flow Qr and determines a measurement Vent indicative of current patient ventilation.

[0314] In some embodiments, the ventilation determination algorithm 4323 determines a measure of ventilation that is an estimate of the actual patient ventilation. One such embodiment is to take half of the absolute value of the respiratory flow Qr, optionally filtered by a low-pass filter (such as a second-order Bessel low-pass filter with a corner frequency of 0.11 Hz).

[0315] In other embodiments, the ventilation determination algorithm 4323 determines a measure of ventilation that is approximately proportional to the actual patient ventilation. One such embodiment estimates the peak respiratory flow Qpeak on the inspiratory portion of the cycle. This process and many other processes involving sampling the respiratory flow rate Qr produce measurements that are approximately proportional to ventilation, as long as the flow rate waveform shape does not vary greatly (herein, two breaths are considered to have similar shapes when the flow rate waveforms of the breaths are similar when normalized in time and amplitude). Some simple examples include the mean respiratory flow, the median of the absolute value of the respiratory flow, and the standard deviation of the flow. Any linear combination of any order statistics of the absolute value of the respiratory flow using positive coefficients, and even some arbitrary linear combinations of any order statistics using both positive and negative coefficients, are approximately proportional to the ventilation volume. Another example is the average of the respiratory flow in the middle K proportion (by time) of the inspiratory portion, where 0 < K < 1. If the flow shape is constant, there are any number of measurements that are exactly proportional to ventilation.

[0316] 4.4.3.2.4 Determine Inspiratory Flow Limitation

[0317] In one form of the present technology, the central controller 4230 executes an inspiratory flow limitation determination algorithm 4324 to determine the degree of inspiratory flow limitation.

[0318] In one form, the inspiratory flow limitation determination algorithm 4324 receives the respiratory flow signal Qr as an input and provides as an output a measure of the degree to which the inspiratory portion of the breath exhibits inspiratory flow limitation.

[0319] In one form of the present technology, the inspiratory portion of each breath is identified by a zero-crossing detector. An interpolator interpolates a plurality of uniformly spaced points (e.g., sixty-five) representing time points along the inspiratory flow velocity-time curve of each breath. The curve described by the points is then scaled by a scalar to have unit length (duration / cycle) and unit area to remove the effects of changing respiratory rate and depth. The scaled breath is then compared in a comparator to a pre-stored template representing a normal unobstructed breath, similar to Figure 6AThe inspiratory portion of the respiration shown. Respirations that deviate from this template by more than a specified threshold (usually 1 unit of scale) at any time during inspiration, such as those due to coughing, sighing, swallowing, and hiccupping as determined by the test element, are rejected. For data that is not rejected, the central controller 4230 calculates the moving average of the first such scaled point for several previous inspiratory events. For the second such point, this is repeated for the same inspiratory event, and so on. Thus, for example, sixty-five scaled data points are generated by the central controller 4230 and represent the moving average of several previous inspiratory events, such as three events. The moving average of the successive updated values of these (e.g., 65) points is hereinafter referred to as the "scaled flow" and is designated Qs(t). Alternatively, a single inspiratory event may be used instead of the moving average.

[0320] Based on the scaled flow, two shape factors related to the determination of partial obstruction can be calculated.

[0321] Shape factor 1 is the ratio of the average of the middle (e.g., 32) scaled flow points to the overall average (e.g., 65) scaled flow points. In the case where this ratio exceeds unity, the respiration will be considered normal. In the case where this ratio is unity or less, the respiration will be obstructed. A ratio of approximately 1.17 is considered the threshold between partially obstructed and unobstructed respirations and is equal to the degree of obstruction that allows for adequate oxygenation to be maintained in a typical patient.

[0322] Shape factor 2 is calculated as the RMS deviation of the unit scaled flow taken from the middle (e.g., 32) points. An RMS deviation of approximately 0.2 units is considered normal. An RMS deviation of 0 is taken as a completely flow-limited respiration. The closer the RMS deviation is to zero, the more flow-limited the respiration.

[0323] Shape factors 1 and 2 can be used as alternatives or in combination. In other forms of this technology, the number of sampling points, respirations, and midpoints may be different from those described above. Additionally, the thresholds may be different from those described.

[0324] 4.4.3.2.5 Determination of Apnea and Hypopnea

[0325] In one form of this technology, the central controller 4230 executes an apnea / hypopnea determination algorithm 4325 for determining the presence of apnea and / or hypopnea.

[0326] In one form, the apnea / hypopnea determination algorithm 4325 receives the respiratory flow signal Qr as an input and provides a flag indicating that apnea or hypopnea has been detected as an output.

[0327] In one form, an apnea is considered detected when a function of the respiratory flow Qr drops below a flow threshold for a predetermined period of time. The function can determine peak flow, relative short-term average flow, or the flow between relative short-term average and peak flow, such as RMS flow. The flow threshold can be a relatively long-term measure of flow.

[0328] In one form, a hypopnea is considered detected when a function of the respiratory flow Qr drops below a second flow threshold within a predetermined period of time. The function can determine peak flow, relative short-term average flow, or the flow between relative short-term average flow and peak flow, such as RMS flow. The second flow threshold can be a relatively long-term measure of flow. The second flow threshold is greater than the flow threshold used to detect apnea.

[0329] 4.4.3.2.6 Determination of snoring

[0330] In one form of the present technology, the central controller 4230 executes one or more snoring determination algorithms 4326 for determining the degree of snoring.

[0331] In one form, the snoring determination algorithm 4326 receives the respiratory flow signal Qr as an input and provides a measure of the presence of snoring as an output.

[0332] The snoring determination algorithm 4326 can include steps of determining the intensity of the flow signal in the range of 30 - 300 Hz. Additionally, the snoring determination algorithm 4326 can include steps of filtering the respiratory flow signal Qr to reduce background noise (e.g., the sound of air flow in a system with a blower).

[0333] 4.4.3.2.7 Determination of airway patency

[0334] In one form of the present technology, the central controller 4230 executes one or more airway patency determination algorithms 4327 for determining the degree of airway patency.

[0335] In one form, the airway patency determination algorithm 4327 receives the respiratory flow signal Qr as an input and determines the signal power in the frequency range of approximately 0.75 Hz and approximately 3 Hz. The presence of a peak in this frequency range is used to indicate an open airway. The absence of a peak is considered an indication of a closed airway.

[0336] In one form, the frequency range in which the peak is sought is the frequency of small forced oscillations in the processing pressure Pt. In one embodiment, the frequency of the forced oscillation is 2 Hz and the amplitude is approximately 1 cmH2O.

[0337] In one form, the airway patency determination algorithm 4327 receives the respiratory flow signal Qr as an input and determines the presence or absence of a cardiogenic signal. The absence of a cardiogenic signal is considered an indication of an occluded airway.

[0338] 4.4.3.2.8 Determining the target ventilation volume

[0339] In one form of the present technology, the central controller 4230 takes the current ventilation volume Vent as an input and executes one or more target ventilation volume determination algorithms 4328 for determining the target value Vtgt of the ventilation volume.

[0340] In some forms of the present technology, there is no target ventilation volume determination algorithm 4328, and the target value Vtgt is predetermined, for example, by hard coding during the configuration of the RPT device 4000 or by manual input via the input device 4220.

[0341] In other forms of the present technology, such as adaptive servo ventilation (ASV), the target ventilation volume determination algorithm 4328 calculates the target value Vtgt based on a value Vtyp representing the typical recent ventilation volume of the patient.

[0342] In some forms of adaptive servo ventilation, the target ventilation volume Vtgt is calculated as a high proportion of the typical recent ventilation volume Vtyp, but less than the typical recent ventilation volume Vtyp. The high proportion in these forms can be in the range of (80%, 100%) or (85%, 95%) or (87%, 92%).

[0343] In other forms of adaptive servo ventilation, the target ventilation volume Vtgt is calculated as an integer multiple slightly greater than the typical recent ventilation volume Vtyp.

[0344] The typical recent ventilation volume Vtyp is a value around which the measured values of the current ventilation volume Vent tend to cluster at multiple moments on a certain predetermined time scale, that is, the measured value of the central tendency of the measured values of the current ventilation volume in the recent history. In one implementation of the target ventilation volume determination algorithm 4328, the recent history is on the order of several minutes, but in any case should be longer than the time scale of the Cheyne - Stokes waxing and waning cycle. The target ventilation volume determination algorithm 4328 can use any of a variety of well - known measures of central tendency to determine the typical recent ventilation volume Vtyp based on the measure of the current ventilation volume Vent. One such measure is to output a low - pass filter on the measurement of the current ventilation, with a time constant equal to one hundred seconds.

[0345] 4.4.3.2.9 Determination of treatment parameters

[0346] In some forms of the present technology, the central controller 4230 executes one or more treatment parameter determination algorithms 4329 for determining one or more treatment parameters using values returned by one or more other algorithms in the treatment engine module 4320. This can include an algorithm 4300 for changing treatment parameters in the case where the patient 1000 is flagged for reducing or terminating treatment.

[0347] In one form of the present technology, the treatment parameter is the instantaneous treatment pressure Pt. In one implementation of this form, the treatment parameter determination algorithm 4329 determines the treatment pressure Pt using the following equation:

[0348] Pt = AΠ(Φ,t) + P0 (1)

[0349] Where:

[0350] A is the amplitude,

[0351] Π(Φt) is the waveform template value at the current value Φ of the phase and time t (in the range of 0 to 1), and

[0352] P0 is the base pressure.

[0353] If the waveform determination algorithm 4322 provides the waveform template Π(Φ, t) as a look-up table of values Π indexed by the phase Φ, the treatment parameter determination algorithm 4329 applies equation (1) by locating the nearest look-up table entry to the current value Φ of the phase returned by the phase determination algorithm 4321, or by interpolating between two entries straddling the current value Φ of the phase.

[0354] The values of the amplitude A and the base pressure P0 can be set by the treatment parameter determination algorithm 4329 in the manner described below according to the selected respiratory pressure treatment mode.

[0355] 4.4.3.3 Treatment control module

[0356] The treatment control module 4330 according to one aspect of the present technology receives the treatment parameters from the treatment parameter determination algorithm 4329 of the treatment engine module 4320 as input and controls the pressure generator 4140 to deliver an air flow according to the treatment parameters.

[0357] In one form of the present technology, the treatment parameter is the treatment pressure Pt, and the treatment control module 4330 controls the pressure generator 4140 to deliver an air flow such that the interface pressure Pm at the patient interface 3000 or 3800 is equal to the treatment pressure Pt.

[0358] 4.4.3.4 Detecting fault conditions

[0359] In one form of the technology, the central controller 4230 executes one or more methods 4340 for detecting fault conditions. Fault conditions detected by the one or more methods 4340 can include at least one of the following:

[0360] · Power failure (no power or insufficient power)

[0361] · Converter fault detection

[0362] · Failure to detect the presence of a component

[0363] · Operating parameters outside the recommended range (e.g., pressure, flow rate, temperature, PaO2).

[0364] · Test alarm fails to generate a detectable alarm signal.

[0365] When a fault condition is detected, the corresponding algorithm 4340 signals the presence of the fault by one or more of the following:

[0366] · Activating an audible, visual, and / or dynamic (e.g., vibration) alarm

[0367] · Sending a message to an external device

[0368] · Logging of events

[0369] 4.5 Humidifier

[0370] 4.5.1 Humidifier Overview

[0371] In one form of the technology, a humidifier 5000 is provided (e.g., as shown in Figure 5A ) to change the absolute humidity of air or gas delivered to a patient relative to the surrounding air. Generally, the humidifier 5000 is used to increase the absolute humidity and increase the temperature of the air flow (relative to ambient air) before delivery to the patient's airway.

[0372] The humidifier 5000 can include a humidifier reservoir 5110, a humidifier inlet 5002 for receiving the air flow, and a humidifier outlet 5004 for delivering the humidified air flow. In some forms, as shown in Figure 5A and 5B , the inlet and outlet of the humidifier reservoir 5110 can be the humidifier inlet 5002 and the humidifier outlet 5004, respectively. The humidifier 5000 can also include a humidifier base 5006, which can be adapted to receive the humidifier reservoir 5110 and includes a heating element 5240.

[0373] 4.6 Respiratory Waveform

[0374] Figure 6AA model showing the typical respiratory waveform of a person during sleep is presented. The horizontal axis represents time, and the vertical axis represents respiratory flow. While the parameter values can vary, a typical breath can have the following approximate values: tidal volume Vt of 0.5 L, inspiratory time Ti of 1.6 s, peak inspiratory flow Qpeak of 0.4 L / s, expiratory time Te of 2.4 s, peak expiratory flow Qpeak -0.5 L / s. The total duration of a breath Ttot is approximately 4 s. A person typically breathes at a rate of approximately 15 breaths per minute (BPM), and the ventilation outlet is approximately 7.5 L / min. The typical duty cycle, the ratio of Ti to Ttot, is approximately 40%.

[0375] Figure 6B Shows selected polysomnography channels (pulse oximetry, flow rate, chest movement, and abdominal movement) of a patient during non-REM sleep breathing over a period of approximately ninety seconds under normal conditions, where approximately 34 breaths are being treated with automatic PAP therapy and the interface pressure is approximately 11 cmH2O. The top channel shows pulse oximetry (oxygen saturation or SpO2), with a saturation range on the vertical scale from 90% to 99%. The patient maintains a saturation of approximately 95% during the shown period. The second channel shows the quantitative respiratory airflow, with a scale on the vertical from -1 LPS to +1 LPS, and inspiration is positive. Chest and abdominal movements are shown in the third and fourth channels.

[0376] 4.7 Screening, Diagnosis, Monitoring System

[0377] 4.7.1 Polysomnogram

[0378] Figure 7A Shows patient 1000 undergoing a polysomnogram (PSG). The PSG system includes a headbox 2000 that receives and records signals from the following sensors: EOG electrodes 2015; EEG electrodes 2020; ECG electrodes 2025; submental EMG electrodes 2030; snore sensor 2035; respiratory inductive plethysmogram on the chest strap (respiratory effort sensor) 2040; respiratory inductive plethysmogram on the abdominal strap (respiratory effort sensor) 2045; nose and mouth cannula with an oral thermistor 2050; photoplethysmograph (pulse oximeter) 2055; and body position sensor 2060. The electrical signals are referenced to a ground electrode (ISOG) 2010 located at the center of the forehead.

[0379] 4.7.2 Non-invasive Monitoring System

[0380] Figure 7BShows an example of a monitoring device 7100 for monitoring the respiration of a sleeping patient 1000. The monitoring device 7100 includes a non-contact motion sensor generally directed at the patient 1000. The motion sensor is configured to generate one or more signals representative of the body movement of the patient 1000, from which signals a signal representative of the respiratory movement of the patient can be obtained. In other examples, the system may include environmental and other acoustic sensors to sense the environment, vents, and noise of the patient 1000.

[0381] 4.7.3 Respiratory polysomnography

[0382] Respiratory polygraph (RPG) is a term for a simplified form of PSG that does not have electrical signals (EOG, EEG, EMG), snoring, or body position sensors. The RPG includes at least a thoracic motion signal from a respiratory inductive plethysmogram (motion sensor) on a chest strap, such as motion sensor 2040, a nasal pressure signal sensed via a nasal cannula, and an oxygen saturation signal from a pulse oximeter (such as pulse oximeter 2055). These three RPG signals or channels are received by an RPG headbox similar to the PSG headbox 2000.

[0383] In some configurations, the nasal pressure signal is a satisfactory proxy for the nasal flow signal generated by a flow transducer in line with a sealed nasal mask because the nasal pressure signal is comparable in shape to the nasal flow signal. If the patient's mouth remains closed, i.e., there is no mouth leak, then the nasal flow is equal to the respiratory flow.

[0384] The screening / diagnosis / monitoring device receives the above three RPG channels (a signal indicating thoracic motion, a signal indicating nasal flow, and a signal indicating oxygen saturation) at a data input interface. The screening / diagnosis / monitoring device also includes a processor configured to execute encoded instructions. The screening / diagnosis / monitoring device also includes a non-transitory computer-readable memory / storage medium.

[0385] The memory can be the internal memory of the screening / diagnosis / monitoring device, such as RAM, flash memory, or ROM. In some embodiments, the memory can also be a removable or external memory linked to the screening / diagnosis / monitoring device, such as, for example, an SD card, a server, a USB flash drive, or an optical disc. In other embodiments, the memory can be a combination of external and internal memory. The memory contains stored data and processor control instructions (code) adapted to configure the processor to perform specific tasks. The stored data can include RPG channel data received by the data input interface, as well as other data provided as part of an application. The processor control instructions can also be provided as part of an application. The processor is configured to read the code from the memory and execute the encoded instructions. Specifically, the code can include instructions adapted to configure the processor to perform a method of processing RPG channel data provided by the interface. One such method can be storing the RPG channel data as data in the memory. Another such method can be analyzing the stored RPG data to extract features. The processor can store the result of such analysis as data in the memory.

[0386] The screening / diagnosis / monitoring device can also include a communication interface. The code can include instructions configured to allow the processor to communicate with an external computing device (not shown) via the communication interface. The communication mode can be wired or wireless. In one such embodiment, the processor can transfer the stored RPG channel data from the data to a remote computing device. In such an embodiment, the remote computing device can be configured to analyze the received RPG data to extract features. In another such embodiment, the processor can transfer the result of the analysis from the data to a remote computing device.

[0387] Alternatively, if the memory is removable from the screening / diagnosis / monitoring device, the remote computing device can be configured to connect to the removable memory. In such an embodiment, the remote computing device can be configured to analyze the RPG data retrieved from the removable memory to extract features.

[0388] 4.8 Respiratory Therapy Modes

[0389] The RPT device 4000 can implement various respiratory therapy modes.

[0390] 4.8.1 CPAP Therapy

[0391] In some embodiments of respiratory pressure therapy, the central controller 4230 sets the therapy pressure Pt according to a therapy pressure equation (1) that is part of a therapy parameter determination algorithm 4329. In one such embodiment, the amplitude A is equal to zero, and thus the therapy pressure Pt, which represents the target value achieved by the interface pressure Pm at the current moment, is equal to zero throughout the respiratory cycle. Such embodiments are typically classified under the heading of CPAP therapy. In these embodiments, there is no need for the therapy engine module 4320 to determine the phase Φ or the waveform template Π(Φ).

[0392] In CPAP therapy, the baseline pressure P0 can be a constant value that is hard-coded or manually input into the RPT device 4000. Alternatively, the central controller 4230 can repeatedly calculate the baseline pressure P0 based on metrics or measurements of sleep disordered breathing (such as one or more of flow limitation, apnea, hypopnea, arousal, and snoring) returned by corresponding algorithms in the therapy engine module 4320. This alternative approach is sometimes referred to as APAP therapy.

[0393] Figure 4E is a flowchart of a method 4500 performed by the central controller 4230 to continuously calculate the baseline pressure P0 as part of an APAP therapy implementation of the therapy parameter determination algorithm 4329 when the pressure support A is equal to zero.

[0394] Method 4500 begins at step 4520, where the central controller 4230 compares a measurement of the presence of apnea / hypopnea with a first threshold and determines whether the measurement of the presence of apnea / hypopnea has exceeded the first threshold for a predetermined period of time, indicating that apnea / hypopnea is occurring. If so, method 4500 proceeds to step 4540; otherwise, method 4500 proceeds to step 4530. At step 4540, the central controller 4230 compares a measurement of airway patency with a second threshold. If the measure of airway patency exceeds the second threshold, indicating that the airway is patent, the detected apnea / hypopnea is considered central, and method 4500 proceeds to step 4560; otherwise, the apnea / hypopnea is considered obstructive, and method 4500 proceeds to step 4550.

[0395] At step 4530, the central controller 4230 compares a measurement of flow limitation with a third threshold. If the measure of flow limitation exceeds the third threshold, indicating that the inspiratory flow is limited, method 4500 proceeds to step 4550; otherwise, method 4500 proceeds to step 4560.

[0396] In step 4550, if the resulting treatment pressure Pt does not exceed the maximum treatment pressure P max, the central controller 4230 increases the base pressure P0 by a predetermined pressure increment P. In one embodiment, the predetermined pressure increment P and the maximum treatment pressure P max are 1 cmH20 and 25 cmH20 respectively. In other embodiments, the pressure increment P can be as low as 0.1 cmH2O and as high as 3 cmH2O, or as low as 0.5 cmH2O and as high as 2 cmH2O. In other embodiments, the maximum treatment pressure P max can be as low as 15 cmH2O and as high as 35 cmH2O, or as low as 20 cmH2O and as high as 30 cmH2O. The method 4500 can then return to step 4520.

[0397] At step 4560, the central controller 4230 decreases the base pressure P0 by a decrement as long as the decreased base pressure P0 does not drop below the minimum treatment pressure P min below. The method 4500 can then return to step 4520. In one embodiment, the decrement is proportional to the value of P0 - P min such that in the absence of any detected events, the decrease of P0 to the minimum treatment pressure P min is exponential. In one embodiment, the proportionality constant is set such that the time constant for the exponential decrease of P0 is 60 minutes, and the minimum treatment pressure P min is 4 cmH2O. In other embodiments, the time constant can be as low as 1 minute and as high as 300 minutes, or as low as 5 minutes and as high as 180 minutes. In other embodiments, the minimum treatment pressure P min can be as low as 0 cmH2O and as high as 8 cmH2O, or as low as 2 cmH2O and as high as 6 cmH2O. Alternatively, the decrement of P0 can be preset such that in the absence of any detected events, the decrease of P0 to the minimum treatment pressure P min is linear.

[0398] 4.8.2 Bilevel Therapy

[0399] In other embodiments of this form of the present technology, the value of the amplitude A in equation (1) can be positive. Such embodiments are referred to as bilevel therapy because when determining the treatment pressure Pt using equation (1) with a positive amplitude A, the treatment parameter determination algorithm 4329 oscillates the treatment pressure Pt between two values or levels synchronized with the patient 1000's spontaneous breathing effort. That is, based on the above typical waveform template Π(Φ, t), the treatment parameter determination algorithm 4329 increases the treatment pressure Pt to P0 + A (referred to as IPAP) at the start of exhalation or during inhalation, and decreases the treatment pressure Pt to the base pressure P0 (referred to as EPAP) at the start of exhalation or during exhalation.

[0400] In some forms of bi-level therapy, the IPAP is a therapy pressure with the same purpose as the therapy pressure in the CPAP therapy mode, and the EPAP is the IPAP minus the amplitude A, which has a "small" value (a few cmH2O) and is sometimes referred to as expiratory pressure relief (EPR). This form is sometimes called CPAP therapy with EPR, which is generally considered more comfortable than direct CPAP therapy. In CPAP therapy using EPR, one or both of the IPAP and EPAP can be constant values that are hard-coded or manually entered into the RPT device 4000. Alternatively, the therapy parameter determination algorithm 4329 can repeatedly calculate the IPAP and / or EPAP during CPAP and EPR. In this alternative, the therapy parameter determination algorithm 4329 repeatedly calculates the EPAP and / or IPAP based on the indicators or measurements of sleep disordered breathing returned by the corresponding algorithms in the therapy engine module 4320 in a manner similar to the calculation of the base pressure P0 in the above-mentioned APAP therapy.

[0401] In other forms of bi-level therapy, the amplitude A is large enough such that the RPT device 4000 performs some or all of the patient 1000's breathing work. In this form, which is called pressure support ventilation therapy, the amplitude A is called the pressure support or swing. In pressure support ventilation therapy, the IPAP is the base pressure P0 plus the pressure support A, and the EPAP is the base pressure P0.

[0402] In some forms of pressure support ventilation therapy called fixed pressure support ventilation therapy, the pressure support A is fixed at a predetermined value, such as 10 cmH2O. This predetermined pressure support value is a setting of the RPT device 4000 and can be set, for example, by hard-coding during the configuration of the RPT device 4000 or by manual input via the input device 4220.

[0403] In other forms of pressure support ventilation therapy, widely called servo ventilation, the therapy parameter determination algorithm 4329 takes as inputs some currently measured or estimated parameters of the respiratory cycle (e.g., the current measured value Vent of the ventilation volume) and the target value of this respiratory parameter (e.g., the target value Vtgt of the ventilation volume), and repeatedly adjusts the parameters of equation (1) to bring the currently measured value of the respiratory parameter to the target value. In one form of servo ventilation called adaptive servo ventilation (ASV), which has been used to treat CSR, the respiratory parameter is ventilation, and the target ventilation volume value Vtgt is calculated by the target ventilation volume value determination algorithm 4328 based on the typical recent ventilation volume value Vtyp, as described above.

[0404] In some forms of servo ventilation, the treatment parameter determination algorithm 4329 applies a control method to repeatedly calculate the pressure support A in order to bring the current measured values of the respiratory parameters to the target values. One such control method is proportional-integral (PI) control. In one implementation of PI control, applicable to the ASV mode, where the target ventilation volume Vtgt is set to be slightly less than the typical recent ventilation volume Vtyp, the pressure support A is repeatedly calculated as:

[0405] A = G∫(Vent - Vtgt)dt (2)

[0406] where G is the gain of the PI control. A larger gain value G can result in positive feedback in the treatment engine module 4320. A smaller gain G value can allow some residual untreated CSR or central sleep apnea. In some embodiments, the gain G is fixed at a predetermined value, such as -0.4 cmH2O / (L / min) / sec. Alternatively, the gain G can vary between treatment sessions, starting small and increasing from one session to another until a value is reached that substantially eliminates CSR. Conventional means for retrospectively analyzing the parameters of the treatment period can be employed in this embodiment to evaluate the severity of CSR during the treatment period. In other embodiments, the gain G can vary according to the difference between the current ventilation volume measurement Vent and the target ventilation volume Vtgt.

[0407] Other servo ventilation control methods that can be applied by the treatment parameter determination algorithm 4329 include proportional (P), proportional-derivative (PD), and proportional-integral-derivative (PID).

[0408] Pressure support limit A min and A max are settings of the RPT device 4000, for example, set by hard coding during the configuration of the RPT device 4000 or by manual input via the input device 4220.

[0409] In the pressure support ventilation treatment mode, EPAP is the baseline pressure P0. Similar to the baseline pressure P0 in CPAP therapy, EPAP can be a constant value specified or determined during titration. Such a constant EPAP can be set, for example, by hard coding during the configuration of the RPT device 4000 or by manual input via the input device 4220. This alternative method is sometimes referred to as fixed EPAP pressure support ventilation therapy. The clinician can perform the titration of EPAP for a given patient during the titration period with the aid of a PSG, with the aim of preventing obstructive apnea, thus maintaining an open airway for pressure support ventilation treatment in a manner similar to the titration of the baseline pressure P0 in constant CPAP therapy.

[0410] Alternatively, the treatment parameter determination algorithm 4329 can repeatedly calculate the baseline pressure P0 during pressure support ventilation therapy. In such an embodiment, the treatment parameter determination algorithm 4329 repeatedly calculates EPAP based on an indicator or metric of sleep disordered breathing returned by a corresponding algorithm in the treatment engine module 4320, such as one or more of flow limitation, apnea, hypopnea, airway opening, and snoring. Because the continuous calculation of EPAP is similar to the clinician's manual adjustment of EPAP during EPAP titration, this process is sometimes also referred to as the auto-titration of EPAP, and the treatment mode is called auto-titrating EPAP pressure support ventilation therapy or auto-EPAP pressure support ventilation therapy.

[0411] 4.8.3 High Flow Therapy

[0412] In other forms of respiratory therapy, the pressure of the air flow is not controlled because it is used for respiratory pressure therapy. Instead, the central controller 4230 controls the pressure generator 4140 to deliver an air flow whose device flow rate Qd is controlled to a therapeutic or target flow rate Qtgt. Such forms are typically categorized under the heading of flow therapy. In flow therapy, the therapeutic flow rate Qtgt can be a constant value that is hard-coded or manually entered into the RPT device 4000. If the therapeutic flow rate Qtgt is sufficient to exceed the patient's peak inspiratory flow rate, then this therapy is typically referred to as high flow therapy (HFT). Alternatively, the therapeutic flow rate can be a curve Qtgt(t) that varies with the respiratory cycle.

[0413] 4.9 Data Transmission and Collection

[0414] Such as Figure 4A the connection device of the RPT 4000 in [reference] or other devices such as exercise equipment (treadmill or stationary exercise bike) are capable of storing and sending different levels of data. For example, Figure 4C the central controller 4230 in [reference] or the applicable device processor can send data to an external source 4286. Such data can include data collected by the sensors of the RPT 4000, such as the flow rate sensor 4272 or the pressure sensor 4272, data collected by the exercise equipment sensors, such as the speed and length of the exercise, data collected by the computer system, such as the frequency and type of user interaction with the user interface; data generated by the algorithms of the preprocessing module 4310 or other algorithms; or data generated by the algorithms of the treatment engine module 4320. Such data can be used for analysis through the combination of algorithms that generate more data.

[0415] Figure 8AFIG. 7000 is a block diagram showing an embodiment of a system according to the present technology, which can be an RPT system, an exercise system, a computer hardware and software usage system, an on-demand service used by employees and customers, a digital health online service, or other suitable services or systems. Thus, in addition to the RPT system, the system and apparatus may also include:

[0416] Exercise and healthcare system

[0417] · Electronic exercise equipment that includes a treadmill and outputs usage data;

[0418] · Stationary bicycles, digital weights;

[0419] · Fitness trackers, such as wearables that detect movement, exercise, and other factors; and

[0420] · Other exercise and health care systems

[0421] Computer system, software and interface

[0422] · Websites and software programs that track usage data, including health care software for monitoring compliance with CBT programs and other online or software programs;

[0423] · Weight loss monitoring applications that monitor things such as eating, exercise, food types, and other things that can track usage and other data;

[0424] · Computer hardware and software for coordinating on-demand services such as on-demand taxi services, where the software and / or hardware can track usage data;

[0425] And

[0426] · Other software and services.

[0427] System 7000 may include a device 4000 configured to provide respiratory pressure therapy to patient 1000 or other services to a user, a data server 7010, and a computing device 7050 associated with patient 1000 or the user. The computing device 7050 may be placed with the user 1000 and the device 4000 (such as an RPT device). In Figure 7A the illustrated embodiment 7000, the device 4000, the computing device 7050, and the data server 7010 are connected to a wide area network 7090, such as the Internet, the cloud, or the Internet.

[0428] The connection to the wide area network may be wired or wireless. The wide area network may be identified by Figure 4C a remote external communication network 4282, and the data server 7010 may be identified by Figure 4Cidentified by the remote external device 4286. The computing device 7050 can be a personal computer, a mobile phone, a tablet computer, or other device, and can incorporate various devices disclosed herein. The computing device 7050 can be configured to be intermediated between a user (e.g., patient 1000) and the data server 7010 via the wide area network 7090. In one embodiment, this intermediation is performed by a software application 7060 running on the computing device 7050. The user program 7060 can be a dedicated application referred to as a "user app" that interacts with a complementary process hosted by the data server 7010. In another embodiment, the user program 7060 is a web browser that interacts with a website hosted by the data server 7010 via a secure portal. In yet another embodiment, the user program 7060 is an email client.

[0429] Figure 8B includes a block diagram showing an alternative embodiment 7000B of the system according to the present technology. In the alternative embodiment 7000B, the device 4000 communicates with the computing device 7050 via a local (wired or wireless) communication protocol, such as a local network protocol (e.g., Bluetooth). In the alternative embodiment 7000B, the local network can be identified by Figure 4C the local external communication network 4284, and the user computing device 110 can be identified by Figure 4C the local external device 4288. In the alternative embodiment 7000B, the user patient computing device 7050 is configured via the user program 7060 to be intermediated between the user (e.g., patient 1000) and the data server 7010 on the wide area network 7090, and also between the device 4000 and the data server 7010 on the wide area network 7090.

[0430] Hereinafter, statements regarding the system 7000 can be understood to apply equivalently to the alternative embodiment 7000B, unless otherwise explicitly stated.

[0431] The system 7000 can include other devices (not shown) associated with the respective user or patient, who also has a corresponding associated computing device. Additionally, the system 7000 can include other monitoring or treatment devices that can interface with the controller 4230 or the user computing device 7050.

[0432] The device 4000 may be configured to store data for each usage period delivered to a user (e.g., patient 1000) in the memory 4260. For example, treatment data for an RPT period includes settings of the RPT device 4000 and treatment variable data representing one or more variables of the respiratory pressure treatment for the entire RPT period. In other examples, data for a usage period may include speed or other intensity settings on exercise equipment, length of the usage or exercise period, length of website usage, number of clicks, or other suitable usage and interaction data.

[0433] The device 4000 may be configured to send data to the data server 7010. As described above, the transmission of data is modulated based on different situations. In normal operation, only low-resolution data is transmitted. High-resolution data may be transmitted under different circumstances, as will be explained below. The data server 7010 may receive data from the device 4000 according to a "pull" model, whereby the device 4000 sends data in response to a query from the data server 7010. Alternatively, the data server 7010 may receive data according to a "push" model, whereby the device 4000 sends data to the data server 7010 as soon as possible after a period.

[0434] Data received from the device 4000 may be stored and indexed by the data server 7010 so as to be uniquely associated with the device 4000 and thus distinguishable from data of any other device participating in the system 7000.

[0435] In this example, the data server 7010 is configured to calculate different types of analytical data available for a clinician or system administrator. For example, usage data for each period may be determined based on data received from the device 4000. Usage data variables for a period include summary statistics derived from variable data that forms part of the data by a conventional scoring device.

[0436] The usage data may include one or more of the following usage variables:

[0437] · Usage time, i.e., the total duration of the period;

[0438] · Apnea-Hypopnea Index (AHI) for the period;

[0439] · Average leak flow for the period

[0440] · Average mask pressure for the period;

[0441] · Number of "sub-periods" in an RPT period, i.e., the number of intervals of RPT treatment between "mask on" and "mask off" events;

[0442] · Other statistical summaries of treatment variables, such as the 95th percentile pressure, median pressure, pressure value histogram;

[0443] · Average speed of running, cycling, or other exercise system metrics;

[0444] · Length of the exercise session;

[0445] · Heart rate or other physiological metrics tracked by the wearable during exercise or other use, for example;

[0446] · Repetition frequency;

[0447] · Power (speed multiplied by weight)

[0448] · Acceleration;

[0449] · Average exercise session per week;

[0450] · Calories burned;

[0451] · Length of time using the software program;

[0452] · Number of mouse clicks per session;

[0453] · Number of times the software program, RPT device, on-demand service, or other system is used per time period (e.g., day, week, month); and

[0454] · Multiple session statistics, such as the mean, median, and variance of AHI since the start of RPT treatment, trends in exercise duration, calories burned, speed, or other metrics; and

[0455] · Others.

[0456] Other servers can be coupled to network 7090 and obtain data based on the above "push" or "pull" model. For example, a data server 7100 operated by the payee can receive data for different purposes, such as determining compliance or predicting compliance, for determining payment for the treatment of patient 1000 or other services for the user. A machine learning server 7200 can also receive data for learning or refining baselines for anomalies that require high-resolution data, as follows. Alternatively, the machine learning server 7200 can learn the optimal response when an anomaly is detected, or learn the correct prediction data to be included in the high-resolution data in response to certain anomalies.

[0457] In an alternative embodiment, device 4000 calculates usage variables at the end of each session based on the data stored by device 4000. Then, device 4000 sends the usage variables to data server 7010 according to the above "push" or "pull" model.

[0458] In another embodiment, the memory 4260 of the device 4000 that stores the treatment / usage data for each period is in a removable form, such as an SD memory card. The removable memory 4260 can be removed from the device 4000 and inserted into a card reader that communicates with the data server 7010. The treatment / usage data is then copied from the removable memory 4260 to the memory of the data server 7010.

[0459] In yet another embodiment of an alternative implementation 7000B of the system, the device 4000 is configured to send the treatment / usage data to the user computing device 7050 via a wireless communication protocol such as Bluetooth described above. The user computing device 7050 then sends the treatment / usage data to the data server 7010. The data server 7010 can receive the treatment / usage data from the user computing device 7050 according to a "pull" model, whereby the user computing device 7050 sends the treatment / usage data in response to a query from the data server 7010. Alternatively, the data server 7010 can receive the treatment / usage data according to a "push" model, whereby the user computing device 7050 sends the treatment / usage data to the data server 7010 as soon as it is available after a period.

[0460] In some embodiments, the data server 7010 can perform some post-processing of the usage data, such as with one or more processors that communicate with or are included in the data server 7010. An example of such post-processing is determining whether the most recent period is an "adherence period". Some adherence rules specify the required RPT device usage within an adherence period (such as 30 days) based on a minimum duration of device use (such as four hours) for each period within a certain minimum number of days (such as 21 days) within the adherence period.

[0461] If the duration of the period exceeds the minimum duration, the period is considered to be adherent. The usage data post-processing can determine whether the most recent period is an adherence period by comparing the usage duration with the minimum duration from the adherence rules. The result of such post-processing is adherence data that forms part of the usage data, such as a Boolean adherence variable. Another example of multi-period usage data is the count of adherence periods since the start of an RPT treatment or other type of period.

[0462] The data server 7010 can also be configured to receive data from the user computing device 7050. This can include data input by the user or patient 1000 to the user program 7060, or the treatment / usage data in the alternative implementation 7000B described above.

[0463] The data server 7010 is also configured to send electronic messages to the user computing device 7050. The messages can be in the form of e-mails, SMS messages, automated voice messages, or notifications within the user program 7060.

[0464] The device 4000 can be configured such that its treatment mode or settings for a particular treatment mode can be changed when a corresponding command is received via its wide area or local area network connection. In such an embodiment, the data server 7010 can also be configured to send such a command directly to the device 4000 (in embodiment 7000) or indirectly to the device 4000, relayed via the user computing device 7050 (in embodiment 7000B).

[0465] The data server 7010 hosts a process 7020, which, as described in detail below, is configured to increase or maintain the user's motivation to continue treatment or continue with other services. Broadly speaking, the process 7020 analyzes data from the user computing device 4000 and / or the user computing device 7050 or the user computing device 7050 to calculate a quality indicator that indicates the quality of a recent treatment session or other type of user session as disclosed herein. The process 7020 then conveys the quality indicator to the user or patient 1000, for example, via the user program 7060 running on the user computing device 7050. The need to increase motivation can be detected by analyzing low-resolution data, and high-resolution data can be obtained to optimize the method of increasing or maintaining patient motivation.

[0466] The patient 1000 or user perceives the treatment or other usage quality indicator as a concise indicator of how their treatment, exercise, or other session is progressing. This thereby motivates the user or patient 1000 to adhere to their treatment. It is known that tracking and measuring performance can be a strong motivator for a person to achieve their goals, and treatment quality metrics are used as such a performance measurement in the case of respiratory pressure treatment.

[0467] 4.9.1 Predicting User Adherence or Dropout

[0468] Studies have shown that up to 90% of patients prescribed respiratory pressure therapy have at least some problems meeting compliance rules. Examples of these problems include difficulty setting up the RPT device 4000, discomfort due to a poorly fitting or maladjusted patient interface 3000, lack of tolerance for the prescribed level of airway positive pressure sensation, excessive leakage causing noise or disruption to the patient or a caregiver, and lack of improvement in subjective health. This results in low compliance, lower reimbursement, and suboptimal health outcomes for the patient 1000, as well as higher overall long-term healthcare costs and additional healthcare costs for the deteriorating related conditions form for non-compliant patients 100. For example, in some countries, patients must meet a minimum level of compliance to be reimbursed. Accordingly, the inventors have developed techniques to predict whether a patient 1000 will comply with treatment and automatically intervene to improve compliance and ongoing treatment adherence and utilization.

[0469] For other systems and services, maintaining user engagement is also key to their success, and identifying patients who may stop using or drop out of the service can be crucial for intervening before they drop out or significantly reduce use.

[0470] Specifically, the disclosed techniques and related devices 4000 can implement an automated system that monitors usage to identify patients 1000 or other users who may reduce use and automatically intervenes (including by notifying a provider or the patient 1000 or user). This provides the opportunity to adjust treatment, exercise, or other related settings, switch to a more appropriate device, correct any problems with the treatment or service the patient 1000 or user may have, or provide other recommendations to help increase patient 1000 or user compliance and long-term adherence outcomes or service enrollment.

[0471] For example, it has been determined that trends in usage data can specifically predict future compliance and continuous usage rates. Accordingly, in certain forms of the present technology, usage data 9045 output from a device (e.g., the RPT device 4000) can be monitored to determine when a patient 1000 or user may terminate treatment or reduce usage by a specific amount.

[0472] Figure 9 An example of a process for predicting whether a patient or user will reduce or stop using the device 4000 is shown. First, the patient 1000 can start a session or service (e.g., an RPT treatment session, an exercise session) by turning on the device 4000, using the device (e.g., wearing the device for a treatment period), and then turning off the device (e.g., and / or removing the mask once complete).

[0473] After completion of the usage period 9000, the device 4000 can output usage data 9010 to an external source, such as outputting it to a server and database via a network. In other examples, for instance, the device 4000 can locally store the usage data 9045 and send the data to an external source after storing the usage data 9045 for a week. In further examples, the device 4000 can store data and locally process the usage data on the processor 4230 and the memory 4360. The usage data 9045 can include various types of information, including those disclosed above.

[0474] In some examples, demographic data, profile data, healthcare providers, machine types, and other data can be used in the model. This data can be locally stored on the device 4000 or separately stored in a database referenced by a patient ID for efficient retrieval and updating of the algorithm. This data may not need to be updated each time the model or algorithm is updated and can thus be stored separately in some examples. This can also save bandwidth used to send usage data from the device 4000.

[0475] Additionally, after outputting and storing the usage data 9045, the disclosed techniques can identify a time window of previously stored usage data 9020. For example, the disclosed techniques can use an algorithm to identify previously stored usage data 9020 recorded in the previous week, two weeks, three weeks, or other suitable time frames to identify usage trends.

[0476] Next, the disclosed techniques can process the data to determine the likelihood that patient 1000 or the user will reduce (or maintain) the usage level within a future time window 9030. For example, the disclosed techniques can determine the percentage likelihood that patient 1000 or the user will reduce from four hours to two hours within two weeks, or reduce from three exercise sessions to one exercise session within two weeks. In other examples, the disclosed techniques can determine the percentage likelihood that patient 1000 or the user will stop using within two weeks, three weeks, one week, or other predictive time frames. In some examples, the disclosed techniques will process the data and predict the amount of usage of the device 4000, system, and / or service by patient 1000 or the user within a future time window (e.g., average number of hours per night) without necessarily predicting whether patient 1000 or the user will reduce usage.

[0477] The disclosed technology can utilize various algorithms to determine the percentage chance that patient 1000 or a user will reduce or stop usage (or maintain the current usage level) within a specific time window. The platform can utilize various data sources, including: (1) usage data 9045 (including recent periods and historical usage data, as well as other types of data disclosed above), (2) demographic data 9035 (including the age of the patient), and (3) device type 9055 (including device type, model, and manufacturer, including RPT devices, exercise devices, computing devices, or other devices), as well as other suitable data. In some examples, a healthcare provider can also be input data. As described above, usage data 9045 can be output from device 4000, and other data sources can be stored on a separate database. In other examples, all data can be stored on the memory of device 4000.

[0478] Next, the disclosed technology can first calculate various features based on data that includes data on usage periods from within a previous time window. For example, the disclosed technology can determine patterns of non-usage days, average usage hours, average weekly usage hours, age, engagement with an associated online platform, and other factors. In some examples, these features can be calculated weekly to determine the weekly trends for each of these features.

[0479] In certain forms of the technology, these features are then input into various algorithms to output the percentage likelihood that patient 1000 will reduce usage by a certain amount within a certain time window 9030. For example, the system can use logistic regression, linear regression, and / or random forest algorithms to analyze the features. In some examples, where the output is a binary classification—logistic regression, decision tree, random forest, Bayesian network, support vector machine, neural network, or probability model can be used to output the probability that the input features result in patient 1000 terminating treatment. In other examples, machine learning algorithms and combinations of algorithms can be used to classify the input into usage categories. This can include linear classifiers (logistic regression, bayes classifier), support vector machines, decision trees, boosting trees, random forests, neural networks, stochastic gradient descent, nearest neighbors, etc.

[0480] In addition, other machine learning algorithms can be used. In some examples, a decision tree can be utilized to determine which pre-trained machine learning algorithm to apply. For example, different algorithms can be used based on the age cohort to which patient 1000 or the user belongs. In other examples, for instance, different vendors or different types of devices 4000 can have different algorithms trained with data from those vendors. In other examples, the algorithm can output a binary determination of whether patient 1000 or the user is likely to drop out, or the amount of usage range (such as 4 - 2 hours, 2 - 0 hours, or cessation of use) that patient 1000 or the user will likely be suitable for.

[0481] Next, if the output percentage of the algorithm exceeds threshold 9040, the disclosed technique can output an indication that patient 1000 or the user is likely to drop out or reduce usage within a certain time window. This can include marking patient 1000 or the user on the internal database of the medical record and sending a notification to the display 4294 of the associated computing device, server, or device 4000. This will allow the healthcare provider to contact patient 1000 or the user or initiate various action steps discussed below.

[0482] 4.9.2 If the predicted usage rate is low, perform the action steps for intervention

[0483] In some forms of this technique, the notification can trigger actions to improve treatment 9050 or reduce the likelihood that patient 1000 or the user will terminate or reduce treatment or other services. For example, patient 1000 or the user terminates or reduces their use for many reasons, which include treatment adaptation challenges, problems related to equipment management, environmental factors, and incentive issues. Some of the following reasons: (1) The size or fit of patient interface 3000 is inappropriate, (2) Patient 1000 is not accustomed to wearing RPT device 4000 while sleeping, (3) Patient 1000 has difficulty breathing forced air, (4) Leaky patient interface 3000, which dries the nose or mouth of patient 1000, (5) Excessive noise, (6) Loud exercise equipment, (7) Pain or discomfort, (8) Or others.

[0484] Therefore, the action steps will best address the reasons why patient 1000 or the user wants to reduce or terminate treatment or other services. Thus, the disclosed technique can first apply various workflows or algorithms to determine the reasons why patient 1000 or the user can reduce or terminate use. For example, the disclosed technique can send a notification or request to the display 4294 on device 4000 that provides a menu or options and requests patient 1000 or the user to indicate which aspects of the treatment or other services patient 1000 or the user does not like or find ineffective.

[0485] The notification can also be text, an email, a pop-up notification on a mobile device, or other types of notifications. In some examples, depending on the probability of termination of a treatment or other service, or the classification used, the notification frequency or content can be changed to increase the incentive. In some examples, a menu can provide options for patients 1000 or users for common questions. Then, based on the selection of the patient 1000 or user, further remedial options can be provided to the patient 1000 or user, which will attempt to overcome the difficulties of the patient or user with the treatments or other services disclosed herein. In some examples, this can include displaying a video to the patient 1000, user, or other content to assist the patient 1000 or other user in using the device 4000 in cases where the patient 1000 or other user has difficulty using the device 4000.

[0486] In some examples, current techniques can use machine learning or other algorithms to estimate the reasons why patient 1000 or user may drop out. This can include monitoring periods or certain aspects of the device 400 that are known to potentially increase the chance that the patient 1000 or user may terminate the treatment. In some examples, the determination that the patient 1000 or user may terminate the treatment or reduce usage will trigger an analysis of other metrics that can be analyzed to determine the most probable reasons why the patient 1000 or user may drop out. For example, leak flow, noise, respiratory events, sleep score, and other variables can be analyzed to determine which has the highest deviation from a normal, successful patient 1000 or user. Then, the disclosed techniques can ask the patient 1000 or user questions starting with the most probable identified reasons for reducing the service (e.g., respiratory treatment), and perform appropriate interventions, as detailed below. In some examples, the determination of the possible reasons can consider demographic information (knowing that a particular age group has difficulty using the device or its features). The following is a list of action steps that can be taken, and the monitoring or other algorithms that can automatically determine when to take these steps.

[0487] Change service settings

[0488] In response to a prompt on the RPT device 4000 or an associated application or software program on a computing device, the patient or clinician 1000 or user can enter a selection on a display or via the cloud management system 4294, the selection indicating that there is a high leak from the patient interface, trouble with the patient falling asleep or waking up repeatedly at night, their sleep apnea not being effectively treated, or other treatment-related problems that are causing ineffective treatment. Thus, current techniques can prompt the patient 1000 with options to change the treatment settings 9065 on the RPT device 4000. Once those options are selected, the device receiving the patient input can send instructions to the controller of the RPT device 4000 to effect the change.

[0489] Tilt pressure when the patient is asleep

[0490] Some patients 1000 marked for reduced use may indicate that they are uncomfortable under high pressure and have difficulty falling asleep (e.g., in response to a notification with a query about their use). The current technology can then present the patient 1000 with the option to select the "RAMP" feature, which implements a protocol on the RPT device 4000 to slowly increase the baseline pressure until the patient 1000 falls asleep at the start of treatment.

[0491] In some examples, the usage data 9045 can indicate that the patient 1000 is removing the device within the first hour of turning on the device, or some other threshold indicating that the patient 1000 has difficulty falling asleep. Thus, if the processing of the usage data 2045 indicates that the patient 1000 stops using within a short time window of, for example, 30 minutes or within an hour, the current technology can automatically suggest the RAMP feature. Additionally, if the processed usage data 9045 identifies an early stop in use (or, for example, a low number of hours of use per session), the current technology can adjust the ramp feature to have an even lower initial pressure to help the patient 1000 fall asleep.

[0492] Pressure, expiratory pressure release and treatment mode adjustment

[0493] In some examples, the patient 1000 may wake up frequently, potentially indicating that the treatment settings are not optimal once the patient 1000 falls asleep. In this example, patient notifications and inputs may be of less value because the patient 1000 may not be consciously aware of the treatment settings while they are asleep. Thus, certain algorithms (such as those disclosed herein) can be utilized to identify disrupted sleep, breathing, or other sleep problems and automatically adjust the treatment and respiratory comfort settings. This can also include other adjustments to the treatment mode, including APAP to CPAP, etc.

[0494] Bi-level positive airway pressure

[0495] In some examples, if the patient 1000 indicates that they are uncomfortable with the inspiratory pressure, the current technology can change the inspiratory pressure delivered to the patient 1000. In other examples, this can be offered as an attempt at the patient 1000's mode, perhaps if the patient 1000 does not know why their treatment is uncomfortable.

[0496] Humidification

[0497] In some examples, the patient 1000 can select an input indicating that their mouth or nose is too wet or too dry. Once the current technology receives this input from the patient 1000, it can automatically recommend increasing or decreasing the humidification level.

[0498] In other examples, if patient 1000 provides an input that they have dry mouth or dry nose, the current technology can automatically determine whether the leakage flow rate QV exceeds a threshold indicating that the humidity should be increased. For example, once the current technology receives an input from patient 1000 indicating that they have a dry mouth, the current technology or the RTP device 4000 can automatically query or initiate a leakage flow rate estimate 4316 to determine whether it exceeds the threshold.

[0499] Patient interface fit or device type

[0500] In response to a prompt on the RPT device 4000 or an associated application or software program on a computing device, the patient or clinician 1000 can enter a selection on the display 4294 indicating that their mouth is dry, and the fit of the patient interface 3000 is not optimal (e.g., their facial injury). For example, patient 1000 can indicate that they feel a leak between the skin and the patient interface 3000, or other problems with the assembly of the device 9075, as described herein. As described above, the leakage flow rate estimate 4316 module can determine that there is a problem with leakage through the patient interface 3000.

[0501] Therefore, the current technology can prompt patient 1000 to determine whether they feel that the fit of the patient interface 3000 is incorrect, and specifically, whether it feels too small or too large. Therefore, the current technology can then recommend a replacement patient interface 3000 for patient 1000 based on the data profile of the current patient interface 3000 of patient 1000 and the fit problem.

[0502] In some examples, the current technology can prompt patient 1000 to indicate the uncomfortable parts of the face in contact with the patent interface 3000. For example, the current technology can request patient 1000 to click on a diagram of the face to indicate immovable positions around the seal formation structure 3100, the positioning and stabilization structure 3300, or other parts of the patient interface 3000. Then, based on the uncomfortable positions, the platform can recommend an alternative patient interface 3000.

[0503] In some examples, the patient interface 3000 can include sensors on the positioning and stabilization structure 3300 to determine, for example, how tight the straps are. In some examples, this can include a simple tension assessment or pressure between the straps and the head of patient 1000. This information can be compared with the average tension and pressure to provide patient 1000 with suggestions to relax or tighten the positioning and stabilization structure 3300 or change the size.

[0504] Noise

[0505] Noise is a frequent reason for Patient 1000 to discontinue treatment, including at the request of their sleep partner. In response to a prompt on the RPT device 4000 or an associated application or software program on a computing device, Patient 1000 or a clinician can enter a selection on a display or cloud software 4294 indicating that the noise is excessive or that their partner perceives the noise to be excessive. In this example, current technology can perform diagnostic checks to determine whether the RPT device 4000 itself and all of its channels and vents are generating more noise than a standard amount.

[0506] For example, current technology can evaluate whether ambient noise is deviating from an average or expected noise level from the RPT device 4000.

[0507] Accordingly, current technology and / or the RPT device 4000 can include an acoustic sensor that senses ambient noise, noise associated with the RPT device 4000, and other forms of noise. In some cases, machine learning algorithms can be used to classify the type of noise and identify the level of noise associated with the RPT device 4000 (or “bleed” noise and separate it from Patient 1000's snoring and other ambient noise) and compare it to a standard value. If those values exceed a threshold, current technology can recommend maintenance, resupply, or other remedial actions for components.

[0508] In other examples, if Patient 1000 indicates that noise is the primary issue, current technology can automatically change treatment settings within a range and optimize the settings to reduce noise.

[0509] Type of treatment

[0510] In response to a prompt on the RPT device 4000 or an associated application or software program on a computing device, Patient 1000 or a clinician can enter a selection on a display 4294 or cloud software indicating that they are generally dissatisfied with treatment based on the RPT device 4000 and would prefer to have a different type of treatment 9085. In other examples, usage data 9045 may be so low that current technology recommends a different type of treatment, or Patient 1000 may fail to engage in treatment using the RPT device 4000 after current technology has taken many different recommendations and actions. In such cases, current technology can recommend that Patient 1000 use an additional or complementary form of treatment. For example, the system can ask Patient 1000 whether he or she would prefer a mandibular repositioning device or cognitive behavioral therapy.

[0511] 4.9.3 Example 1: Treatment termination predictor

[0512] The disclosed technology has been used on anonymized data sets from patient data to test whether specific logistic regression and random forest algorithms can predict when patient 1000 may accurately terminate treatment. It has been found that the current technology can use these algorithms to predict with 90% accuracy (on average) whether patient 1000 will reduce or terminate the use of a respiratory treatment device (e.g., CPAP) within a two-week time window. This has been confirmed by testing the current technology on 20 different patient cohorts, each with an installed base of 4,000 - 26,000. In one example, the current technology identifies more than 40 patients per week as potentially terminating treatment from a group of approximately 16,000 patients.

[0513] Function set

[0514] In this example, usage data 9045 is first preprocessed to identify target features for processing by the random forest and logistic regression algorithms. First, the current technology determines the time window and prediction window of the data to be considered. As Figure 10 shown, the current technology identifies usage periods that occurred three weeks before the current time / date. Each usage period data set may already contain some combination or permutation of the following data information:

[0515] · Date / time stamp;

[0516] · Start treatment time, stop treatment time;

[0517] · Total treatment time

[0518] · Treatment and sensor data (e.g., identified respiratory events, treatment settings, etc.); and

[0519] · Patient ID.

[0520] This data can be output from the RPT device 4000 (e.g., usage data and treatment data), and other parts of this data can come from the provider database). Next, each identified usage period data is processed to identify usage features that can be input into the algorithms. For example, the following table shows an example set of usage features determined based on the usage period data used in the study:

[0521]

[0522] Additionally, the features can include whether the user is registered in a patient engagement or treatment management software platform (or app). These features are then extracted from the sample data set and output as features for different patients 1000.

[0523]

[0524] Process the data using a logistic regression algorithm that is trained using prior data with actual droplet data (regardless of patient 1000) for treatments that were actually discarded. Through model operation, the study reveals that some predictive features include: (1) non-zero use days (period) (“NZD”), (2) average non-zero use (“NZUse”), and (3) non-zero use standard deviation (“NZSD”). Thus, in some examples, a logistic regression algorithm that exploits these three features or other combinations of features can be developed.

[0525] Processing algorithm

[0526] In this study, use random forest and logistic regression algorithms to process the usage trends based on these features to output the probability that each patient 1000 will discontinue use within a two-week period. This involves examining the trends of the features on a weekly basis (comparing the features for the entire week with the subsequent week to identify trends). Additionally, in this example, a logistic regression model is created for each day in the prediction window. Each of these models is trained using a three-week window of data prior to the day predicted by the model. Thus, for the training data, for patients 1000 who end treatment, a separate model can be trained using a three-week window of prior usage data that ends: (a) 1 day before termination, (b) 2 days before termination, and so on, such that in this case 14 models are trained because the termination prediction window is two weeks in this case.

[0527] Next, 14 models are trained using data from patients 1000 who did not end treatment. These 14 models are trained using different time windows of usage data (as in the termination data) starting from the last day the device was used by patient 1000 (rather than the day of termination) until 14 days before the last day. Thus, after training the 14 models with terminating and non-terminating patients, they can be used to predict the termination probability for new patients 1000.

[0528] Thus, in this case, 14 models are created such that they can be applied to the usage data and determine the probability of termination each day. Then, by combining the probabilities for the 14-day period, the total probability of termination can be determined for each patient 1000 within a future two-week window.

[0529] The following are examples of some raw data, indicating the probabilities for each patient 1000 (one anonymous patient per column) and whether they actually terminated within two weeks (“true drop”):

[0530] Scoring True 0.0716 0 0.3418 0 0.0865 0 0.2484 0 0.3817 0 0.3045 0 0.6334 1 0.9748 1 0.9827 1 0.9788 1 0.9269 1 0.97 1

[0531] The study provides evidence that the disclosed platform can predict treatment termination for Patient 1000 with an accuracy of 88%-93% within a two-week window. These surprising results will be extremely beneficial to healthcare providers, enabling them to intervene before Patient 1000 stops treatment. For example, once the patient has actually made the decision to terminate treatment, intervention becomes more difficult. Thus, some of the advantages of this technology stem from the fact that it predicts rather than monitors or detects termination. The platform has the potential to predict future low adherence and termination, rather than low usage or adherence warnings. This will likely result in much higher adherence and retention rates, as well as greatly improved outcomes for Patient 1000 with sleep disorders.

[0532] 4.9.4 Example 2: Treatment Adherence Predictor

[0533] The disclosed technology has also been used on datasets from healthcare providers to test whether specific linear and logistic regression algorithms can predict whether a patient will remain adherent within a future time window. This is advantageous because in some countries, reimbursement depends on past adherence. For example, reimbursement for the next month can depend on the level of adherence that meets the threshold for the previous month (e.g., adherence during the past 28-day period can determine reimbursement for the next 28-day period). In some countries, reimbursement may be based only on adherence after an initial ramp-up period (e.g., 10, 13, 14, or 15 weeks).

[0534] Therefore, for some countries, it may be advantageous to predict whether Patient 1000 will be adherent in the next week, two weeks, three weeks, four weeks, eight weeks, or other time periods according to local regulations. In this example, the disclosed technology is used to determine whether adherence in the next 28-day cycle can be predicted based on usage data from the past 28 days. Specifically, the disclosed technology predicts whether the average usage of Patient 1000 in the next 28-day cycle will be:

[0535] · 0 - 2 hours per day "[0, 2]"

[0536] · 2 - 4 hours per day "[0, 4]"

[0537] · > 4 hours per day "[4, 24]"

[0538] It has been found that the correlation between usage between consecutive four-week intervals is very high (0.9). Therefore, the average usage in the first four weeks can be used to estimate the usage in the next four-week interval. For example, the following equation is an example of how it is determined:

[0539] Usage(t + 1) = a + b * Usage(t) + error

[0540] Specifically, in this example, the following features are processed from the data to estimate adherence within 28 days:

[0541] (1) U1: Average usage in the first three weeks of the first 28-day interval

[0542] (2) U2: Average usage in the last week of the first 28-day interval

[0543] (3) Non-zero days: Number of non-zero usage days in the first 28-day interval

[0544] (4) SD_NZ: Standard deviation of non-zero usage in the first 28-day interval

[0545] (5) Interval: Number of 28-day intervals counted from the start of treatment

[0546] (6) Age

[0547] These features are identified from various data sources as disclosed herein. Next, these features are processed using the following multiple linear regression model in the first model:

[0548] U = a + b*U1 + c*U2 + d*NOZERO_DAYS + e*SD_NZ + F*Age + g*Interval + error

[0549] In some examples, the interval feature can be discarded, and the model should be trained for each interval (every 28-day cycle after initiation). The interval data can be obtained from the setup data output from the RTP device 4000.

[0550] The data output from the RPT device 4000, profile data, and other patient 1000 data can be used to train the above model (or additional models). This includes real historical usage data and other data from various 28-day intervals (in this example). The model can be trained by, for example, feeding training data from two consecutive 28-day intervals from real historical data.

[0551] In this example, the model performs well, but it is determined that the accuracy can be improved between 28-day intervals for some classes:

[0552] T / P [0,2) [2,4) [4,24] [0,2) 312 189 47 [2,4) 86 497 325 [4,24] 18 247 4385

[0553] Therefore, a second model is developed to train a logistic regression algorithm to classify the data into [0.2] and [2, 24] classes. Then, the model can be applied to predict patients falling into [0, 2] and [2, 4] from the first model and re-classify them using the second model. The second model uses a logistic regression equation with the same features as above. Using this method increases the accuracy of the prediction, and the following results are shown for the 28-day interval from week 3 to week 4:

[0554] T / P [0,2) [2,4) [4,24] [0,2) 486 15 47 [2,4) 86 497 325 [4,24] 18 247 4385

[0555] This greatly improves the prediction accuracy for the [0, 2] class. Therefore, continuous improvements can be made to increase the accuracy for each class, such that the disclosed technology can reliably classify a patient's usage predictors with an accuracy approaching 90%.

[0556] The most important features determined for compliance prediction include U1, U2, NOZERO_DAYS, SD_NZ, age, and time intervals. Less important features (at least in this model) include AHI (apnea-hypopnea index), LEAK (leak flow rate), and patient App metrics.

[0557] Example 3 Exercise Compliance Predictor

[0558] The disclosed technology can also be implemented in exercise equipment or other wearable appliances that measure an exercise, movement, or other procedure that requires a patient's adherence or participation. The hardware can include exercise equipment (such as a treadmill, stationary bike, or other exercise equipment) and a control system and processor as disclosed herein.

[0559] The system can monitor usage data as disclosed herein and provide a notification regarding when a user may discontinue or reduce their use of a device or digital service. For example, when usage data drops or a usage trend is identified as determined, it can be determined that the user may discontinue exercise, or participate in a physical or other treatment program. In some examples, the data can indicate that the user will reduce use of a wearable device.

[0560] Accordingly, appropriate interventions can be initiated, including notifying a user of an exercise equipment or other motivators disclosed herein. For example, a notification can be sent to the user's mobile device, or other interventions can be initiated. A variety of other interventions can be utilized, including notifications regarding an application associated with a software program that communicates with a device including exercise equipment.

[0561] A variety of machine learning algorithms can be used to identify users who may quit or reduce participation or compliance, including [additional example algorithms] random forest and logistic regression algorithms. This includes trends in exercise frequency, duration, intensity, and other appropriate metrics.

[0562] Example 4 Website Usage / Participation Predictor

[0563] The disclosed technology can also be implemented to monitor a user's interaction with a website or software program to predict participation or compliance with a service or program. The system can include a server, control system, and user device as disclosed herein, and can additionally include a user interface that includes a touch screen, mouse, keyboard, or other.

[0564] Accordingly, the system can monitor various usage data output from a user's interaction with the user interface of a particular software program, website, or other application. For example, the usage data that can be monitored can include: (1) the amount of time spent browsing a particular site, (2) using a particular software program (e.g., a CBT-based online therapy session), (3) the level of interaction with the user interface (mouse clicks, clicking on links, engaging with various features), and (4) other aspects.

[0565] Various machine learning algorithms can be used to identify users who may be equivalent or reduce participation or compliance, including [additional example algorithms] random forest and logistic regression algorithms. This includes analyzing usage trends and determining whether a user is likely to reduce participation or terminate their use of a website or software program.

[0566] Example 5 On-Demand Service / Labor Prediction

[0567] The disclosed technology can also be implemented to monitor a user's interaction with a software program, such as on a mobile device, computer system, or other device, to determine whether they are likely to terminate their employment or service based on the interaction of an employee or independent contractor and the usage of one or more user interfaces of various devices.

[0568] For example, various on-demand services utilize the mobile phones of employees or independent contractors to coordinate their services. These include on-demand taxi services, food delivery, etc. Many employees or independent contractors can flexibly log in to the service and be available for rides, deliveries, or other services. Accordingly, the user's mobile phone and associated software can output usage data that includes the frequency of logging in / making themselves available, the length of the time period or service availability, the number of service requests fulfilled, customer ratings, and other usage data.

[0569] Various machine learning algorithms can be utilized to identify users who may be equivalent or reduce their employment or availability for the service, including [add example algorithms] random forest and logistic regression algorithms. This includes analyzing usage trends and determining whether a user is likely to reduce participation or terminate their use of a website or software program associated with the service.

[0570] 4.10 Glossary

[0571] For the purposes of implementing the present technology disclosure, one or more of the following definitions may be applied in certain forms of the present technology. In other forms of the present technology, alternative definitions may be applied.

[0572] 4.10.1 General

[0573] Air: In certain forms of the present technology, air can be considered to refer to atmospheric air, and in other forms of the present technology, air can be considered to refer to some other combination of breathable gases, such as oxygen-rich atmospheric air.

[0574] Environment: In certain forms of the present technology, the term "environment" refers to (i) outside of the treatment system or the patient, and (ii) directly surrounding the treatment system or the patient.

[0575] For example, the ambient humidity with respect to a humidifier can be the humidity of the air directly surrounding the humidifier, such as the humidity in the room where the patient is sleeping. This ambient humidity can be different from the humidity outside the room where the patient is sleeping.

[0576] In another example, the ambient pressure can be the pressure directly surrounding the body or outside the body.

[0577] In certain forms, the ambient (e.g., acoustic) noise can be considered to be the background noise level in the room where the patient is located, in addition to, for example, the noise generated by an RPT device or from a mask or patient interface. The ambient noise can be generated by sources outside the room.

[0578] Auto positive airway pressure (APAP) therapy: CPAP therapy in which the therapy pressure is automatically adjustable, e.g., from breath to breath, between a minimum and a maximum, depending on the presence or absence of an indication of an SDB event.

[0579] Continuous positive airway pressure (CPAP) therapy: A respiratory pressure therapy in which the therapy pressure is substantially constant during the patient's respiratory cycle. In some forms, the pressure at the airway inlet will be slightly higher during exhalation and slightly lower during inhalation. In some forms, the pressure will vary between different respiratory cycles of the patient, e.g., increasing in response to detection of an indication of a partial upper airway obstruction and decreasing in the absence of an indication of a partial upper airway obstruction.

[0580] Flow: The volume (or mass) of air delivered per unit time. Flow can refer to an instantaneous quantity. In some cases, a reference to flow will be a reference to a scalar, i.e., a quantity having only magnitude. In other cases, a reference to flow will be a reference to a vector, i.e., a quantity having both magnitude and direction. Flow can be given the symbol Q. "Flow" is sometimes shortened to simply "flow" or "airflow".

[0581] In an example of patient breathing, the flow can be nominally positive for the inspiratory part of the patient's breathing cycle and thus negative for the expiratory part of the patient's breathing cycle. The device flow Qd is the flow of air leaving the RPT device. The total flow Qt is the flow of air and any supplemental gas reaching the patient interface via the air circuit. The ventilation flow Qv is the flow of air leaving the vent to allow flushing of exhaled gas. The leak flow Ql is the leak flow from the patient interface system or elsewhere. The breathing flow Qr is the flow of air received into the patient's respiratory system.

[0582] Humidifier: The term humidifier will be considered to refer to a humidifying device that is constructed and arranged or configured with a physical structure that is capable of delivering a therapeutically beneficial amount of water (H2O) vapor to an air stream to improve the patient's medical breathing condition.

[0583] Leak: The term leak refers to an unwanted air flow. In one example, a leak may occur due to an imperfect seal between the mask and the patient's face. In another example, a leak may occur in the return elbow to the surrounding environment.

[0584] Noise, conducted (acoustic): Conducted noise in this document refers to noise brought to the patient through the pneumatic path (such as the air circuit and the patient interface and the air therein). In one form, the conducted noise can be quantified by measuring the sound pressure level at the end of the air circuit.

[0585] Noise, radiated (acoustic): Radiated noise in this document refers to noise carried to the patient by the ambient air. In one form, the radiated noise can be quantified by measuring the sound power / pressure level of the object in question according to ISO 3744.

[0586] Noise, ventilated (acoustic): Ventilated noise in this document refers to noise generated by the flow of air through any vent (such as the vent hole of the patient interface).

[0587] Patient: A person, whether or not they have a respiratory condition.

[0588] Pressure: Force per unit area. Pressure can be measured in units including cmH2O, g-f / cm 2 and hectopascals. 1 cmH20 is equal to 1 g-f / cm2 and is approximately 0.98 hectopascals (1 hectopascal = 100 Pa = 100 N / m 2 = 1 millibar - 0.001 atm). In this specification, unless otherwise stated, pressure is given in units of cmH2O.

[0589] The pressure in the patient interface is given the symbol Pm, while the therapeutic pressure representing the target value achieved by the interface pressure Pm at the current moment is given the symbol Pt.

[0590] Respiratory Pressure Therapy (RPT): The supply of air is applied to the entrance of the airway at a treatment pressure that is typically positive relative to the atmosphere.

[0591] Ventilator: A mechanical device that provides pressure support to a patient to perform some or all of the work of breathing.

[0592] 4.10.1.1 Materials

[0593] Silicone or silicone elastomer: A synthetic rubber. In this specification, reference to silicone resin refers to liquid silicone rubber (LSR) or compression molded silicone rubber (CMSR). One form of commercially available LSR is SILASTIC (included in the range of products sold under this trademark), which is manufactured by Dow Corning. Another manufacturer of LSR is the Wacker Group. Unless otherwise specified to the contrary, an exemplary form of LSR has a Shore A (or type A) indentation hardness in the range of approximately 35 to approximately 45 as measured using ASTM D2240.

[0594] Polycarbonate: A transparent thermoplastic polymer of bisphenol A carbonate.

[0595] 4.10.2 Respiratory Cycle

[0596] Apnea: According to some definitions, apnea is said to have occurred when the flow drops below a predetermined threshold for a duration, for example, of 10 seconds. Obstructive apnea is said to have occurred when some obstruction of the airway does not allow air flow despite the patient's efforts. Central apnea is considered to have occurred when apnea is detected despite the airway being patent, due to a reduction or absence of respiratory effort. Mixed apnea is considered to have occurred when a reduction or absence of respiratory effort occurs simultaneously with an obstructed airway.

[0597] Respiratory rate: The rate of a patient's spontaneous breathing, typically measured in breaths per minute.

[0598] Duty cycle: The ratio of the inhalation time Ti to the total respiratory time Ttot.

[0599] Effort (respiratory): The work done by a person breathing spontaneously in attempting to breathe.

[0600] The expiratory part of the respiratory cycle: The time period from the start of the expiratory flow to the start of the inspiratory flow.

[0601] Flow limitation: Flow limitation will be considered a condition in a patient's breathing where an increase in the patient's effort does not result in a corresponding increase in flow. In the case where flow limitation occurs during the inspiratory portion of the respiratory cycle, it may be described as inspiratory flow limitation. In the case where flow limitation occurs during the expiratory portion of the respiratory cycle, it may be described as expiratory flow limitation.

[0602] Flow-limited inspiratory waveform types:

[0603] (i) Flat type: Having a rising portion, followed by a relatively flat portion, followed by a descending portion.

[0604] (ii) M-shaped: Having two local peaks, one at the leading edge and one at the trailing edge, and a relatively flat portion between the two peaks.

[0605] (iii) Chair type: Having a single local peak that is at the leading edge, followed by a relatively flat portion.

[0606] (iv) Inverted chair type: Having a relatively flat portion, followed by a single local peak that is at the trailing edge.

[0607] Hypopnea: By some definitions, hypopnea is considered a reduction in flow rather than a cessation of flow. In one form, hypopnea can be said to have occurred when the flow is below a threshold rate for a period of time. When hypopnea is detected due to a reduction in respiratory effort, central hypopnea will be considered to have occurred. In one form in adults, any of the following can be considered hypopnea:

[0608] (i) A 30% reduction in the patient's breathing for at least 10 seconds plus a related 4% desaturation; or

[0609] (ii) A reduction (but less than 50%) in the patient's breathing for at least 10 seconds, accompanied by at least a 3% related desaturation or arousal.

[0610] Hyperpnea: Flow increases to above normal levels.

[0611] Inspiratory portion of the respiratory cycle: The time period from the start of inspiratory flow to the start of expiratory flow will be considered the inspiratory portion of the respiratory cycle.

[0612] Patency (airway): The degree to which the airway is open, or the extent of airway opening. The patient's airway is open. Airway patency can be quantified, for example, a value of one (1) is open and a value of zero (0) is closed (obstructed).

[0613] Positive end-expiratory pressure (PEEP): The pressure above atmospheric pressure that exists in the lungs at the end of expiration.

[0614] Peak flow (Qpeak): The maximum value of the flow during the inspiratory portion of the respiratory flow waveform.

[0615] Respiratory flow, patient gas flow rate, respiratory gas flow rate (Qr): These terms may be understood to refer to an estimate of the respiratory flow rate of the RPT device, as opposed to the "true respiratory flow rate" or "actual respiratory flow rate", which is the actual respiratory flow rate experienced by the patient, typically expressed in liters per minute.

[0616] Tidal volume (Vt): The volume of air inhaled or exhaled during normal breathing when no additional effort is applied. In principle, the inspiratory volume Vi (the volume of inhaled air) is equal to the expiratory volume Ve (the volume of exhaled air), so a single tidal volume Vt can be defined as equal to either quantity. In practice, the tidal volume Vt is estimated as some combination of the inspiratory volume Vi and the expiratory volume Ve, such as an average.

[0617] (Inspiratory) time (Ti): The duration of the inspiratory portion of the respiratory flow waveform.

[0618] (Expiratory) time (Te): The duration of the expiratory portion of the respiratory flow waveform.

[0619] (Total) time (Ttot): The total duration between the start of one inspiratory portion of a respiratory flow waveform and the start of the next inspiratory portion of that respiratory flow waveform.

[0620] Typical recent ventilation volume: The ventilation value around which the most recent values of ventilation Vent tend to cluster on a certain predetermined time scale, i.e., a measure of the central tendency of the most recent values of ventilation.

[0621] Upper airway obstruction (UAO): Includes partial and complete upper airway obstruction. This may be associated with a state of flow limitation, where the flow rate only increases slightly or may even decrease when the pressure difference across the upper airway increases (Starling resistor behavior).

[0622] Ventilation volume (vent port): A measure of the rate at which the patient's respiratory system exchanges gases. The measurement of ventilation may include one or both of the inspiratory and expiratory flows per unit time. When expressed as a volume per minute, this quantity is commonly referred to as "minute ventilation". Minute ventilation is sometimes simply expressed as a volume, understood to be the volume per minute.

[0623] 4.11 Other remarks

[0624] A portion of the disclosure of this patent document contains copyrighted material. The copyright owner does not object to the facsimile reproduction by anyone of this patent document or patent disclosure as it appears in the patent office patent document or records, but reserves all copyrights.

[0625] Unless the context clearly dictates otherwise and a numerical range is provided, it should be understood that each intermediate value between the upper and lower limits of the range, to one-tenth of the unit of the lower limit, and any other such value or intermediate value within the range is broadly encompassed within the present technology. The upper and lower limits of these intermediate ranges may be independently included within the intermediate range and are also included within the present technology, subject to any explicit exclusionary bounds within the range. In the case where the range includes one or both of the limiting values, ranges excluding any one or both of the included limiting values are also included within the present technology.

[0626] In addition, in the case where one or more values are implemented as part of the present technology herein, it should be understood that such values may be approximate unless otherwise stated, and such values may be used to any appropriate significant digits to the extent permitted or required by the practical technology implementation.

[0627] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Although any methods and materials similar to or equivalent to those described herein may also be used in the practice or testing of the present technology, a limited number of representative methods and materials are described herein.

[0628] When a particular material is identified for configuring a component, obvious alternative materials with similar properties are substituted therefor. In addition, unless otherwise specified, any and all components described herein are understood to be capable of being manufactured and may thus be manufactured together or separately.

[0629] It must be noted that unless the context clearly dictates otherwise, as used herein and in the appended claims, the singular forms "a", "an", and "the" include their plural equivalents.

[0630] All publications mentioned herein are hereby incorporated by reference in their entirety to disclose and describe the methods and / or materials as the subject matter of those publications. The publications discussed herein are provided only for their disclosure prior to the filing date of the present application. Nothing herein is to be construed as an admission that the present technology is not entitled to antedate such publications by virtue of prior invention. In addition, the provided publication dates may differ from the actual publication dates, which may need to be independently verified.

[0631] The terms "comprises" and "comprising" should be understood to mean that each element, each component, or each step in a non-exclusive manner, indicates that the marked element, component, or step may be present or utilized, or a combination with other elements, components, or steps not marked.

[0632] The subject headings used in the detailed description are for the convenience of the reader only and should not be used to limit the subject matter that can be found throughout the present disclosure or the claims. The subject headings should not be used to interpret the scope of the claims or the limitations of the claims.

[0633] Although the present technology has been described herein with reference to specific embodiments, it should be understood that these embodiments merely illustrate the principles and applications of the present technology. In some cases, the terminology and symbols may imply specific details that are not necessary for the practice of the present technology. For example, although the terms "first" and "second" may be used, unless otherwise specified, they are not intended to denote any order, but may be used to distinguish different elements. Additionally, although the process steps in a method may be described or illustrated in a certain order, this order is not required. Those skilled in the art will recognize that this order may be modified, and / or aspects of the order may occur simultaneously or even synchronously.

[0634] Accordingly, it should be understood that numerous adjustments may be made to the exemplary embodiments, and it should be understood that other arrangements may be designed without departing from the spirit and scope of the present technology.

Claims

1. A method for predicting compliance, the method comprising: Receiving a usage dataset for a treatment session of a patient from a respiratory therapy device; Identifying a previously stored usage dataset of the patient within a past time window, the past time window being divided into a first duration and a second duration; Processing the usage dataset and the previously stored usage dataset with an algorithm to determine the likelihood that the patient will reduce usage of the respiratory therapy device within a future time window, the algorithm including a first regression model having corresponding coefficients for scaling corresponding inputs of the first regression model to determine the likelihood of the patient reducing usage, the first regression model having a plurality of features as inputs, the features including the average usage hours of the device during the first duration and the average usage hours of the device during the second duration; And If the likelihood is higher than a predetermined threshold, output an indication that the patient may reduce usage.

2. The method according to claim 1, wherein Output the usage data after each treatment session of the patient is completed.

3. The method according to claim 1, wherein, The usage data includes the total usage time for the session, as well as date and timestamp data.

4. The method according to claim 1, wherein The likelihood that the patient reduces usage includes the likelihood that the patient will terminate usage of the respiratory therapy device.

5. The method according to claim 1, wherein The likelihood that the patient reduces usage includes the likelihood that the patient will reduce usage to less than four hours per night.

6. The method according to claim 1, wherein, The likelihood that the patient reduces usage includes the likelihood that the patient will reduce usage to less than two hours per night.

7. The method according to claim 1, wherein Further includes preprocessing the usage data via the algorithm to determine the number of non-usage days, the average usage hours, and the standard deviation of the usage hours.

8. The method according to claim 7, wherein The algorithm includes a random forest or a logistic regression algorithm.

9. The method according to claim 7, wherein Further includes outputting, via the algorithm, the probability of the patient's discontinuation.

10. The method according to claim 7, wherein, Further includes preprocessing the usage data via the algorithm to determine the weekly trend of the number of non-usage days, the average usage hours, and the standard deviation of the usage hours.

11. The method according to claim 7, wherein The algorithm is a collection of logistic regression models, each of the logistic regression models being trained using a separate previous time window of training data to estimate the probability of discontinuation for each day in the future time window.

12. The method according to claim 1, wherein, The indication is an alert, a notification on the patient's mobile device, a notification on the provider's computing device, or a notification on the display of the respiratory therapy device.

13. The method according to claim 1, wherein A further indication includes instructions sent to the display to depict alternative therapies available to the patient that include at least RAMP therapy, and wherein each of the alternative therapies is associated with a set of treatment settings of the respiratory therapy device.

14. The method according to claim 13, wherein, Further includes: Receiving a patient input, the patient input including the patient's selection of an alternative therapy from an alternative display; And Sending instructions to the respiratory therapy device to change the treatment settings of the respiratory therapy device based on the patient input.

15. The method according to claim 1, wherein, A further indication includes instructions sent to the display to depict an alternative patient interface available to the patient.

16. The method according to claim 15, wherein, Further includes: Receiving a patient input, the patient input including the patient's selection of the alternative patient interface from an alternative display; And Send a purchase to a remote external device and instructions to deliver to the patient what the patient has selected.

17. The method according to claim 13, wherein Further comprising: Receiving a second usage data set output from the respiratory therapy device; Identifying a second previously stored usage data set of the patient within a second past time window, the length of the second past time window being equal to the length of the past time window; Processing the second usage data set and the second previously stored usage data set with the algorithm to determine the likelihood that the patient will reduce the use of the respiratory therapy device within a second future time window; And If the likelihood is higher than a predetermined threshold, output an indication that the patient may reduce use.

18. The method according to claim 13, wherein, Further comprising: Determining whether usage data has been received within a specific time window; And If it is determined that no usage data has been received within the specific time window, store non-usage data referring to the specific time window.

19. The method according to claim 18, wherein, The specific time window is a 24-hour period.

20. The method according to claim 19, wherein The non-usage data is a non-usage day.

21. The method according to claim 1, wherein, Further comprising selecting an algorithm from a group of algorithms, each algorithm in the group of algorithms referring to a type of respiratory therapy device.

22. The method according to claim 1, wherein, Further comprising selecting an algorithm from the group of algorithms based on the provider operating the respiratory therapy device.

23. The method according to claim 1, wherein, The respiratory therapy device is a CPAP.

24. The method according to claim 1, wherein Further comprising selecting an algorithm based on the demographic information of the patient.

25. A method for predicting compliance, the method comprising: Receiving, from a respiratory therapy device, a usage data set of a patient within a past time window, the past time window being divided into a first duration and a second duration; Retrieving the patient's profile data from a database, the profile data including the patient's age, the type of respiratory therapy device used by the patient, and the patient's healthcare provider; Processing the usage data set and the profile data with an algorithm to determine the likelihood that the patient will reduce the use of the respiratory therapy device within a future time window, the algorithm including a first regression model having corresponding coefficients for scaling corresponding inputs of the first regression model to determine the likelihood of the patient reducing use, the first regression model having a plurality of features as inputs, the features including the average number of hours of use of the device during the first duration and the average number of hours of use of the device during the second duration, and the patient's age; And If the likelihood is higher than a predetermined threshold, output an indication that the patient may reduce use.

26. The method according to claim 25, wherein, The usage data includes treatment settings.

27. The method according to claim 25, wherein, The usage data includes sensor readings output from the respiratory therapy device.

Images