Prediction of use or compliance

Abstract

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

Description

Technical Background 1.1 Technical Field

[0002] The technology relates to one or more of screening, diagnosis, monitoring, treatment, prevention and improvement of breathing-related disorders. The technology also relates to medical devices or equipment and their uses. The technology also relates to prediction of compliance, use or use withdrawal of respiratory therapy devices, websites and other software, exercise equipment, drivers of on-demand taxi services or other applications.

[0003] 1.2 Description of Related Technology

[0004] 1.2.1 Human respiratory system and its disorders

[0005] The body's respiratory system facilitates gas exchange. The nose and mouth form the entrance to a patient's airway.

[0006] The airway contains a series of branching tubes, which become narrower, shorter and more numerous as the branching tracheae penetrate deeper into the lungs. The main function of the lungs is gas exchange, allowing oxygen to enter the venous blood from the inhaled air and expel carbon dioxide in the opposite direction. The trachea is divided into the left main bronchi and the right main bronchi, which are eventually divided into terminal bronchioles. The bronchi constitute the conducting airways and do not participate in gas exchange. Further airway division leads to respiratory bronchioles and eventually to alveoli. The alveolar region of the lungs is where gas exchange occurs and is called the respiratory zone. See "Respiratory Physiology", 9th edition, published by John B. West, Lippincott Williams & Wilkins in 2012.

[0007] There are a range of respiratory disorders. Some disorders can be characterised by specific events such as apnea, hypopnea and hyperpnea.

[0008] Examples of breathing disorders include obstructive sleep apnea (OSA), Cheyne-Stokes respiration (CSR), respiratory insufficiency, obesity hyperventilation syndrome (OHS), chronic obstructive pulmonary disease (COPD), neuromuscular disease (NMD), and chest wall disorders.

[0009] Obstructive sleep apnea (OSA) is a form of sleep-disordered breathing (SDB), characterized by events including occlusion or obstruction of the upper airway during sleep. This is caused by abnormally small upper airway in the area of ​​the tongue, soft palate and posterior oropharyngeal wall during sleep, plus normal loss of muscle tone. The disease causes affected patients to stop breathing, typically for a period of 30 to 120 seconds, sometimes 200 to 300 times per night. It often leads to excessive daytime sleepiness and may cause cardiovascular disease and brain damage. Although the affected person 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 No. 4,944,310 (Sullivan).

[0010] 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 alternating cycles of wanting ventilation, known as CSR cycles. 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 awakenings from sleep, which leads to severe sleep disruption, increased sympathetic activity, and increased afterload. See U.S. Pat. No. 6,532,959 (Berthon-Jones).

[0011] Respiratory failure is an umbrella term for a breathing disorder in which the lungs cannot take in enough oxygen or exhale enough CO. 2 to meet the needs of the patient. Respiratory failure can include some or all of the following disorders.

[0012] Patients with respiratory insufficiency, a form of respiratory failure, may experience abnormal shortness of breath during exercise.

[0013] Obesity hyperventilation syndrome (OHS) is defined as the combination of severe obesity and chronic hypercapnia in the absence of other known causes of hypoventilation. Symptoms include dyspnea, morning headache, and daytime sleepiness.

[0014] Chronic obstructive pulmonary disease (COPD) includes any of a group of lower airway diseases that have certain common features. These include increased resistance to air movement, prolonged expiratory phase of breathing, and loss of normal elasticity of the lungs. Examples of COPD are emphysema and chronic bronchitis. COPD is caused by chronic smoking (a major risk factor), occupational exposure, air pollution, and genetic factors. Symptoms include dyspnea on exertion, chronic cough, and excessive sputum.

[0015] Neuromuscular disease (NMD) is a broad term that encompasses many diseases and ailments that impair muscle function directly via intrinsic muscle pathology or indirectly via neuropathology. Some NMD patients are characterized by progressive muscle damage, leading to loss of ambulation, wheelchair confinement, dysphagia, respiratory muscle weakness, and ultimately death due to respiratory failure. Neuromuscular disorders can be divided into rapidly progressive and slowly progressive types: (i) rapidly progressive disorders: characterized by muscle damage that worsens over 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 many years and only slightly reduces life expectancy (e.g., limb girdle, scapulohumeral and myotonic dystrophy). Symptoms of NMD respiratory failure include: increasing general weakness, dysphagia, dyspnea on exertion and at rest, fatigue, drowsiness, morning headaches, and difficulty concentrating and changing moods.

[0016] Chest wall disorders are a group of chest deformities that result in inefficient coupling between the respiratory muscles and the thorax. These disorders are usually characterized by restrictive defects and have the potential for prolonged hypercapnic respiratory failure. Scoliosis and / or kyphosis can lead to severe respiratory failure. Symptoms of respiratory failure include: dyspnea on effort, peripheral edema, orthopnea, recurrent chest infections, morning headaches, fatigue, poor sleep quality, and loss of appetite.

[0017] A range of therapies have been used to treat or ameliorate such conditions. In addition, such treatments can be used to prevent breathing disorders in otherwise healthy individuals. However, these have a number of disadvantages.

[0018] 1.2.2 Therapy

[0019] 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-mentioned breathing disorders.

[0020] 1.2.2.1 Respiratory pressure therapy

[0021] Continuous positive airway pressure (CPAP) has been used to treat obstructive sleep apnea (OSA). Its mechanism of action is that the continuous positive airway pressure acts as a pneumatic splint and prevents 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 such therapy to be uncomfortable, difficult to use, expensive, and unsightly, they may choose not to comply with the therapy.

[0022] Non-invasive ventilation (NIV) provides ventilation support to patients through the upper airway to help patients breathe and / or maintain adequate oxygen levels in the body by performing some or all of the work of breathing. The ventilation support is provided via a non-invasive patient interface. NIV has been used to treat CSR and respiratory failure in the form of OHS, COPD, NMD and chest wall disorders. In some forms, the comfort and effectiveness of these therapies can be improved.

[0023] Invasive ventilation (IV) provides ventilation support to patients who are no longer able to breathe effectively on their own and may be provided using a tracheostomy tube. In some forms, the comfort and effectiveness of these therapies may be improved.

[0024] 1.2.2.2 Flow therapy

[0025] Not all respiratory therapies are designed to deliver a prescribed therapeutic pressure. The goal of some respiratory therapies is 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) is a continuous, heated, humidified air flow provided to the airway entrance through an unsealed or open patient interface at a "therapeutic flow" that remains approximately constant throughout the respiratory cycle. The therapeutic 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 of air at the airway entrance flushes or washes away exhaled CO from the patient's anatomical dead space. 2 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.

[0026] Another form of flow therapy is long-term oxygen therapy (LTOT) or supplemental oxygen therapy. A physician may prescribe a continuous flow of oxygen-enriched gas at a specific oxygen concentration (from 21%, the oxygen fraction in ambient air, to 100%) delivered to a patient's airway at a specific flow rate (e.g., 1 liter per minute (LPM), 2 LPM, 3 LPM, etc.).

[0027] 1.2.2.3 Supplemental oxygen

[0028] For some patients, oxygen therapy can be combined with respiratory pressure therapy or HFT by adding supplemental oxygen to the pressurized air flow. 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.

[0029] 1.2.3 Treatment system

[0030] These respiratory therapies can be provided by a therapeutic system or device.Such systems and devices can also be used to screen, diagnose, or monitor a condition without treating it.

[0031] A respiratory therapy system may include a respiratory pressure therapy device (RPT device), air circuit, humidifier, patient interface, oxygen source, and data management.

[0032] Another form of treatment system is a mandibular repositioning device.

[0033] 1.2.3.1 Patient interface

[0034] The patient interface can be used to connect a respiratory device to its wearer, for example, by providing a flow of air to the entrance of the airway. The flow of air can be provided to the patient's nose and / or mouth via a 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 seal) with an area of ​​the patient's face to facilitate air flow at about 10 cmH relative to ambient pressure. 2 O at a pressure that varies sufficiently from ambient pressure to achieve therapy. For other forms of therapy, such as oxygen delivery, the patient interface may not contain a pressure sufficient to facilitate the delivery of approximately 10 cmH 2 A gas supply of O under positive pressure is delivered to the seal of the airway.

[0035] Certain other mask systems may not be functionally suitable for this field. For example, a purely decorative mask may not be able to maintain appropriate pressure. A mask system used for underwater swimming or diving may be configured to prevent the entry of water from a higher pressure outside, but will not maintain the internal air at a pressure higher than the ambient pressure.

[0036] Certain masks may be clinically undesirable for the present technology, for example, if they block airflow through the nose and only allow airflow through the mouth.

[0037] If certain masks require the patient to insert a portion of the mask structure into their mouth to create and maintain a seal through their lips, this may be uncomfortable or impractical with the present technology.

[0038] Certain masks may not be feasible for use while sleeping, such as when sleeping on one's side in bed with the head on a pillow.

[0039] The design of a patient interface presents many challenges. The face has a complex three-dimensional shape. The size and shape of the nose varies significantly from person to person. Because the head contains bone, cartilage, and soft tissue, different areas of the face respond differently to mechanical forces. The jaw or mandible can move relative to other bones of the skull. The entire head can move during respiratory therapy.

[0040] Due to these challenges, some masks face one or more of the following problems: obtrusive, unsightly, expensive, disproportionate, difficult to use, and uncomfortable, especially when worn for long periods of time or when the patient is not familiar with the system. A mask of the wrong size may lead to reduced compliance, reduced comfort, and poor patient outcomes. Masks designed only for pilots, masks designed to be part of personal protective equipment (e.g., filtering masks), SCUBA masks, or masks designed to apply anesthetics are acceptable for their original applications, but such masks are not as comfortable as ideal for long periods of time (e.g., several hours). This discomfort may lead to reduced patient compliance with treatment. This is even more true if the mask is worn during sleep.

[0041] CPAP therapy is very effective in treating certain breathing disorders, assuming the patient complies with the treatment. If the mask is uncomfortable or difficult to use, the patient may not comply with the treatment. Since patients are often advised to clean their masks regularly, if the mask is difficult to clean (e.g., difficult to assemble or disassemble), the patient may not clean their mask, which may affect patient compliance.

[0042] While a mask used for other applications (such as a navigator) may not be suitable for treating sleep-disordered breathing, a mask designed to treat sleep-disordered breathing may be suitable for use in other applications.

[0043] For these reasons, patient interfaces for delivering CPAP during sleep have emerged as a distinct field.

[0044] 1.2.3.1.1 Sealing structure

[0045] 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 may directly affect the effectiveness and comfort of the patient interface.

[0046] The patient interface can be characterized in part according to the design intent of the seal-forming structure to engage with the face when in use. In one form of patient interface, the seal-forming structure may include a first sub-portion that forms a seal around the left nostril and a second sub-portion that forms a seal around the right nostril. In one form of patient interface, the seal-forming structure may include a single element that surrounds both nostrils when in use. This single element may be designed to, for example, cover the upper lip area and the bridge of the nose area of ​​the face. In one form of patient interface, the seal-forming structure may include an element that surrounds the mouth area when in use, for example, by forming a seal on the lower lip area of ​​the face. In one form of patient interface, the seal-forming structure may include a single element that surrounds both nostrils and the mouth area when in use. These different types of patient interfaces may be given various names by their manufacturers, including nasal masks, full-face masks, nasal pillows, nasal sprays, and oronasal masks.

[0047] A seal-forming structure that may be effective in one area of ​​a patient's face may not be suitable in another area, for example, because the shape, structure, variability, and sensitive areas of the patient's face are different. For example, a seal on swimming goggles that covers a patient's forehead may not be suitable for use on the patient's nose.

[0048] Certain seal-forming structures may be designed for mass manufacturing so that one design fits and is comfortable and effective for a wide range of different face shapes and sizes. To the extent there is a mismatch between the shape of the patient's face and the seal-forming structure of a mass-manufactured patient interface, one or both must adapt to form a seal.

[0049] One type of seal-forming structure extends around the periphery of the patient interface and is intended to seal against the patient's face when a force is applied to the patient interface while the seal-forming portion is in facing engagement with the patient's face. The seal-forming structure may comprise an air or fluid filled cushion, or a molded or formed surface of a resilient sealing element made of an elastomer such as rubber. With 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.

[0050] Another type of seal-forming structure incorporates a sheet seal of thin material positioned around the perimeter of the mask to provide a self-sealing action against the patient's face when positive pressure is applied within the mask. Similar to the previous forms of seal-forming portions, if the fit between the face and the mask is not good, additional force may be required to achieve a seal, or the mask may leak. In addition, if the shape of the seal-forming structure does not match the shape of the patient, it may wrinkle or bend during use, causing leaks.

[0051] Another type of seal-forming structure may include friction-fit elements, for example for insertion into a nostril, however some patients find these uncomfortable.

[0052] Another form of seal-forming structure can use adhesive to achieve the seal. Some patients may find it inconvenient to frequently apply and remove adhesive from their face.

[0053] A range of patient interface seal forming structure technologies are disclosed in the following patent applications assigned to ResMed Limited: WO 1998 / 004,310; WO 2006 / 074,513; WO 2010 / 135,785.

[0054] One form of nasal pillow is found in the Adam Circuit manufactured by Puritan Bennett. Another nasal pillow or snus is the subject of U.S. Patent No. 4,782,832 (Trimble et al.), assigned to Puritan-Bennett Company.

[0055] 1.2.3.1.2 Positioning and stabilization

[0056] The seal-forming structure of the patient interface for positive air pressure therapy is subjected to the corresponding force of the air pressure that will destroy the seal. Therefore, various techniques have been used to position the seal-forming structure and keep it in a sealing relationship with the appropriate part of the face.

[0057] One technique is to use an adhesive. See, for example, US Patent Application Publication No. US 2010 / 0000534. However, some people may feel uncomfortable using an adhesive.

[0058] Another technique is to use one or more straps and / or stabilizing harnesses.Many such harnesses suffer from one or more of poor fit, bulk, discomfort, and awkward use.

[0059] 1.2.3.2 Respiratory Pressure Therapy (RPT) Devices

[0060] A respiratory pressure therapy (RPT) device can 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 airflow can be pressure controlled (for respiratory pressure therapy) or flow controlled (for flow therapy, such as HFT). Therefore, an RPT device can also be used as a flow therapy device. Examples of RPT devices include CPAP devices and ventilators. Examples of RPT devices include CPAP devices and ventilators.

[0061] Air pressure generators are known in the context 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 reliability, size and weight requirements for medical devices. Furthermore, even devices designed for medical use may have disadvantages with respect to one or more of the following: comfort, noise, ease of use, efficacy, size, weight, manufacturability, cost and reliability.

[0062] One example of a special requirement for certain RPT devices is noise.

[0063] Table of noise output levels of existing RPT devices (one sample only, using the test method specified in ISO3744 at 10cmH 2 O in CPAP mode).

[0064] RPT device name A-weighted sound pressure level dB(A) Years (approximately) <![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

[0065] One known RPT device for treating sleep-disordered breathing is the S9 Sleep Therapy System manufactured by ResMed Limited. Another example of an RPT device is a ventilator. The ResMed Stellar ventilator for adults and pediatrics is TM The series of ventilators can provide invasive and non-invasive non-dependent ventilation support for a range of patients treating a variety of conditions such as but not limited to NMD, OHS and COPD.

[0066] ResMed Elisée TM 150 ventilator and ResMed VS III TM Ventilators can provide support for invasive and non-invasive dependent ventilation for adult or pediatric patients for the treatment of a variety of disorders. These ventilators provide capacity ventilation modes and pressure ventilation modes with single-limb circuits 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 a positive pressure. The outlet of the RPT device is connected to a patient interface such as those described above via an air circuit.

[0067] The designer of the device may be presented with an infinite number of choices that can be made. Design criteria often conflict, which means that some design choices are far from conventional or unavoidable. In addition, some aspects of comfort and efficacy may be highly sensitive to small and subtle changes in one or more parameters.

[0068] 1.2.3.3 Humidifier

[0069] Delivering an air flow without humidification can result in airway drying. Using a humidifier with an RPT device and a patient interface to produce humidified gas minimizes drying of the nasal mucosa and increases patient airway comfort. Additionally, in colder climates, warm air, which is often applied to the facial area in and around the patient interface, is more comfortable than cold air.

[0070] A range of artificial humidification devices and systems are known, however they may not meet the specific requirements of a medical humidifier.

[0071] Medical humidifiers are used to increase the humidity and / or temperature of an air stream relative to ambient air when needed, typically where a patient is asleep or resting (e.g., in a hospital). Medical humidifiers for bedside placement can be small. Medical humidifiers can be configured to humidify and / or heat only the air stream delivered to the patient, without humidifying and / or heating the patient's surroundings. Room-based systems (e.g., saunas, air conditioners, or evaporative coolers), for example, can also humidify the air that the patient breathes, however these systems also humidify and / or heat the entire room, which can cause discomfort to the occupants. In addition, medical humidifiers can have more stringent safety constraints than industrial humidifiers.

[0072] Although many medical humidifiers are known, they may have one or more disadvantages. Some medical humidifiers may provide insufficient humidification and may be difficult or inconvenient for some patients to use.

[0073] 1.2.3.4 Data Management

[0074] There may be clinical reasons for obtaining data to determine whether a patient who has been prescribed a respiratory therapy has been "compliant," such as if 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 a requirement that, in order to be considered compliant, a patient use a respiratory pressure therapy device for at least four hours each night on at least twenty-one (21) days out of thirty (30) consecutive days. In order to determine a patient's compliance, a provider of an RPT device (such as a healthcare provider) may manually obtain data describing treatment of a patient using the RPT device, calculate usage over a predetermined time period, and compare to the compliance rules. Once the healthcare provider has determined that the patient has used their RPT device in accordance with the compliance rules, the healthcare provider may notify a third party that the patient is compliant.

[0075] There may be other aspects of patient treatment that would benefit from communication of treatment data to a third party or external system.

[0076] Existing processes for communicating and managing such data may be one or more of expensive, time consuming, and prone to errors.

[0077] 1.2.3.5 Ventilation technology

[0078] Some forms of treatment systems may include a vent to allow exhaled carbon dioxide to escape. The vent may allow gas to flow from an interior space of a patient interface (eg, a plenum chamber) to the exterior of the patient interface (eg, to the surrounding environment).

[0079] The vent may include a vent through which the gas may flow when the mask is in use. Many such vents are noisy. Others may become blocked during use, thereby providing insufficient flushing. Some vents may disturb the sleep of the patient's 1000 bed partner 1100, for example, by noise or concentrated airflow.

[0080] ResMed Ltd. has developed many improved mask ventilation technologies, see International Patent Application Publication No. WO1998 / 034,665; International Patent Application Publication No. WO2000 / 078,381; U.S. Patent No. US6,581,594; U.S. Patent Application Publication No. US2009 / 0050156; U.S. Patent Application Publication No. US2009 / 0044808.

[0081] Noise table of existing masks (ISO 17510-2:2007, 10cmH at 1m 2 O pressure)

[0082]

[0083] (*One sample only, using the test method specified in ISO 3744 in CPAP mode at 10 cmH 2 Measured at O

[0084] The sound pressure values ​​for various objects are listed below

[0085]

[0086] 1.2.4 Screening, diagnosis and monitoring systems

[0087] Polysomnography (PSG) is a conventional system for diagnosing and monitoring cardiopulmonary 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 apnea involves observing the patient for two nights in the clinic, one night for pure diagnosis, and one night for clinician titration of treatment parameters. Therefore, PSG is expensive and inconvenient. In particular, it is not suitable for home screening / diagnosis / monitoring of sleep apnea.

[0088] Screening and diagnosis generally describe the identification of a condition from its signs and symptoms. Screening typically gives a true / false result indicating whether the patient's SDB is severe enough to warrant further investigation, 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 / diagnostic systems are only suitable for screening / diagnosis, while some can also be used for monitoring.

[0089] 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 where clinical experts may not be able to afford. Different clinical experts may have different opinions on a patient's condition. Furthermore, a given clinical expert may apply different criteria at different times. Summary of the invention

[0090] The present technology is directed to providing medical devices for screening, diagnosing, monitoring, ameliorating, treating or preventing breathing disorders with improved one or more of comfort, cost, efficacy, ease of use and manufacturability.

[0091] A first aspect of the present technology relates to a device for screening, diagnosing, monitoring, ameliorating, treating or preventing a respiratory disorder.

[0092] Another aspect of the present technology relates to methods for use in website or computer software usage and monitoring, as well as usage monitoring of other applications including for on-demand taxi services and drivers of exercise equipment.

[0093] 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.

[0094] One form of the present technology includes a respiratory therapy device, a computer system, exercise equipment, or other system that outputs usage data, and a controller that processes the usage data to determine whether a user or patient will reduce usage of the respiratory therapy device, exercise equipment, computer system and software or other application within a time window.

[0095] Another aspect of one form of the present technology is to determine the likelihood that a user using a respiratory therapy device computer system, exercise equipment, or other system will log off within a specified time window.

[0096] Another aspect of one form of the present technology is to identify weekly trends in non-usage days, average usage per day, and standard deviation of usage for users of respiratory therapy device computer systems, exercise equipment, or other systems to determine if the user is dropping out or reducing usage.

[0097] 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 system to determine whether a user will drop out within a specified time window (e.g., two weeks, one week, or three weeks).

[0098] The described methods, systems, devices and apparatus may 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. In addition, the described methods, systems, devices and apparatus may provide improvements in the art of automated management, monitoring and / or treatment of respiratory conditions including, for example, sleep-disordered breathing.

[0099] Of course, a part of these aspects may form a sub-aspect of the present technology. Each aspect and / or each of the aspects may be combined in various ways and also constitute other aspects or sub-aspects of the present technology.

[0100] Other features of the present technology will become apparent from consideration of the information contained in the following detailed description, abstract, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] 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, including:

[0102] 3.1 Treatment system

[0103] Figure 1A A system is shown that includes a patient 1000 wearing a patient interface 3000 in the form of nasal pillows receiving a supply of air under positive pressure from an RPT device 4000. 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.

[0104] Figure 1B A system is shown that includes a patient 1000 wearing a patient interface 3000 in the manner of a nasal mask receiving a supply of air under positive pressure from an RPT device 4000. Air from the RPT device is humidified in a humidifier 5000 and flows along an air circuit 4170 to the patient 1000.

[0105] Figure 1C A system is shown that includes a patient 1000 wearing a patient interface 3000 in the form of a full face mask receiving a supply of air under positive pressure from an RPT device 4000. 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 side-lying sleeping position.

[0106] 3.2 Respiratory system and facial anatomy

[0107] Figure 2A An overview of the human respiratory system is shown, including the nasal and oral cavities, larynx, vocal cords, esophagus, trachea, bronchi, lungs, alveolar sacs, heart, and diaphragm.

[0108] 3.3 Patient Interface

[0109] Figure 3A A patient interface in the form of a nasal mask is shown in accordance with one form of the present technology.

[0110] 3.4 RPT device

[0111] Figure 4A Shown is an exploded view of an RPT device in accordance with one form of the present technology.

[0112] Figure 4B is a schematic diagram of the pneumatic path of an RPT device in accordance with one form of the present technology. Upstream and downstream directions are indicated with reference to a blower and a 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.

[0113] Figure 4C is a schematic diagram of the electrical components of an RPT device according to one form of the present technology.

[0114] Figure 4D is a schematic diagram of an algorithm implemented in an RPT device according to one form of the present technology.

[0115] Figure 4E is a diagram showing a form of the present technology. Figure 4D A flowchart of a method performed by a treatment engine module.

[0116] 3.5 Humidifier

[0117] Figure 5A is an isometric view of a humidifier according to one form of the present technology.

[0118] Figure 5B An isometric view of a humidifier in accordance with one form of the present technology is shown showing the humidifier reservoir 5110 removed from the humidifier reservoir base 5130.

[0119] Figure 5C A schematic diagram of a humidifier according to one form of the present technology is shown.

[0120] 3.6 Respiratory waveform

[0121] Fig. 6A A model typical breathing waveform of a person during sleep is shown.

[0122] Figure 6B Selected polysomnographic channels (pulse oximetry, flow, chest motion, and abdominal motion) are shown for a patient's non-REM sleep breathing period, typically over about 90 seconds.

[0123] 3.7 Screening, diagnosis and surveillance systems

[0124] Fig. 7A A patient undergoing a polysomnogram (PSG) is shown. The patient sleeps in a supine sleeping position.

[0125] Figure 7B A monitoring device for monitoring a patient's condition is shown. The patient is sleeping in a supine sleeping position.

[0126] 3.8 Data Transmission

[0127] Fig. 8A is a block diagram of a system for receiving usage data and other data from a respiratory therapy device.

[0128] Figure 8B is a block diagram of an alternative system for receiving usage data and other data from a respiratory therapy device.

[0129] 3.9 Prediction of Reduction or Discontinuation of Treatment

[0130] Fig. 9 A flow chart illustrating a method of predicting patient compliance based on usage data output from a respiratory therapy device is shown.

[0131] Fig.10 A schematic diagram showing examples of time windows of usage data considered in algorithms applied with the disclosed techniques. DETAILED DESCRIPTION

[0132] Before describing the present technology in further detail, it should be understood that the present technology is not limited to the specific examples described herein, which may be varied. It should also be understood that the terminology used in the present disclosure is only for the purpose of describing the specific examples described herein and is not intended to be limiting.

[0133] The following description is provided about various examples that can share one or more common characteristics and / or features. It should be understood that one or more features of any example can be combined with one or more features of other examples. In addition, in any of the examples, any single feature or combination of features can constitute another example.

[0134] 4.1 Treatment

[0135] In one form, the present technology comprises a method for treating a breathing disorder, the method comprising the step of applying positive pressure to an airway entrance of a patient 1000 .

[0136] In certain examples of the present technology, a supply of air at a positive pressure is provided to the patient's nasal passages via one or both nostrils.

[0137] In some examples of the present technology, mouth breathing is restricted, restricted, or prevented.

[0138] 4.2 Treatment system

[0139] 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 .

[0140] 4.3 Patient Interface

[0141] A non-invasive patient interface 3000 according to one aspect of the present technology includes the following functional aspects: a seal-forming structure 3100, a plenum chamber 3200, a positioning and stabilizing structure 3300, a vent 3400, a connection port 3600 for connecting to a form of 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, one physical component may provide one or more functional aspects. In use, the seal-forming structure 3100 is arranged to surround the entrance of the patient's airway to facilitate the supply of positive pressure air to the airway.

[0142] The unsealed patient interface 3800 in the form of a nasal cannula comprises nasal prongs 3810a, 3810b, which can deliver air to the corresponding nostrils of the patient 1000. Such nasal prongs are usually not sealed with the inner or outer skin surface of the nostrils. Air can be delivered to these nasal prongs by one or more air supply lumens 3820a, 3820b connected to the nasal cannula 3800. Lumens 3820a, 3820b are guided from the nasal cannula 3800 to the RT device, which generates air flow with a high flow rate. The "vent" at the unsealed patient interface 3800 is a passage to the atmosphere via the patient's nostrils between the ends of the nasal prongs 3810a and 3810b of the cannula 3800, and excess airflow escapes to the surrounding environment through the vent.

[0143] If a 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.

[0144] 4.3.1 Sealing structure

[0145] 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 is likely to occur. The area where sealing actually occurs - the actual sealing surface - can vary from day to day and from patient to patient within a given treatment period, depending on a number of factors including, for example, where the patient interface is placed on the face, the tension in the positioning and stabilizing structures, and the shape of the patient's face.

[0146] In one form, the target seal-forming area is located on an outer surface of the seal-forming structure 3100 .

[0147] In some forms of the present technology, the seal-forming structure 3100 is formed from a biocompatible material such as silicone rubber.

[0148] The seal-forming structure 3100 according to the present technology can be composed of a soft, flexible, elastic material such as silicone.

[0149] In some 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 may include one form of seal-forming structure 3100 that is suitable for large-sized heads but not for small-sized heads, and another form that is suitable for small-sized heads but not for large-sized heads.

[0150] 4.3.1.1 Sealing mechanism

[0151] In one form, the seal forming structure comprises a sealing flange that utilizes a pressure assisted sealing mechanism. In use, the sealing flange can readily respond to the system positive pressure acting on the interior of the plenum chamber 3200 on its underside, so that it forms a tight sealing engagement with the face. The pressure assist mechanism can act together with the elastic tension in the positioning and stabilizing structure.

[0152] In one form, the seal forming structure 3100 includes a sealing flange and a support flange. The sealing flange includes a relatively thin member having a thickness of less than about 1 mm, such as about 0.25 mm to about 0.45 mm, which extends around the periphery of the plenum 3200. The support flange can be relatively thicker than the sealing flange. The support flange is arranged between the sealing flange and the edge of the plenum 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 sealing flange from buckling during use.

[0153] 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 constructed and arranged to be in a compressed state, for example as a result of elastic tension in the positioning and stabilizing structure.

[0154] In one form, the seal-forming structure comprises a tensioning portion. In use, the tensioning portion is held in tension, for example, by an adjacent region of the sealing flange.

[0155] In one form, the seal-forming structure comprises a region having a sticky or adhesive surface.

[0156] In certain forms of the present technology, the seal-forming structure may include one or more of a pressure-assisted sealing flange, a compression sealing portion, a gasket sealing portion, a tensioning portion, and a portion having a tacky or adhesive surface.

[0157] 4.3.1.2 Nose bridge or nasal ridge area

[0158] In one form, the non-invasive patient interface 3000 includes a seal-forming structure which, in use, forms a seal over a nasal bridge region or nasal ridge region of a patient's face.

[0159] In one form, the seal-forming structure includes a saddle-shaped region configured to form a seal over a nasal bridge region or a nasal ridge region of the patient's face.

[0160] 4.3.1.3 Upper lip area

[0161] 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 (ie, upper lips) of a patient's face.

[0162] In one form, the seal-forming structure comprises a saddle-shaped region configured to form a seal on an upper lip region of a patient's face in use.

[0163] 4.3.1.4 Chin area

[0164] In one form, the non-invasive patient interface 3000 includes a seal-forming structure that forms a seal when used on the chin area of ​​the patient's face.

[0165] In one form, the seal-forming structure includes a saddle-shaped region configured to form a seal when used on a chin area of ​​a patient's face.

[0166] 4.3.1.5 Forehead area

[0167] In one form, the seal-forming structure forms a seal on the forehead area of ​​the patient's face during use. In this form, the inflatable chamber can cover the eyes during use.

[0168] 4.3.1.6 Nasal pillows

[0169] In one form, the seal-forming structure of the non-invasive patient interface 3000 comprises a pair of nasal masks or pillows, each nasal mask or pillow being constructed and arranged to form a seal with a corresponding nostril of the patient's nose.

[0170] A nasal pillow according to one aspect of the present technology includes: a frustoconical body, at least a portion of which forms a seal on the bottom surface of the patient's nose; a stem; and a flexible region on the bottom surface of the frustoconical body and connecting the frustoconical body to the stem. In addition, the structure to which the nasal pillows of the present technology are connected includes a flexible region adjacent to the bottom of the stem. The flexible regions can work together to facilitate a universal engagement structure that can accommodate relative movement of both displacement and angle between the frustoconical body and the structure to which the nasal pillows are connected. For example, the position of the frustoconical body can be moved axially toward the structure to which the stem is connected.

[0171] 4.3.2 Inflatable chamber

[0172] The plenum 3200 has a perimeter that is shaped to complement the surface contour of an average person's face in the area where a seal will be formed in use. In use, the edge of the plenum 3200 is positioned proximate to an adjacent surface of the face. The seal-forming structure 3100 provides actual contact with the face. The seal-forming structure 3100 may extend around the entire perimeter of the plenum 3200 in use. In some forms, the plenum 3200 and the seal-forming structure 3100 are formed from a single homogeneous sheet of material.

[0173] In some forms of the present technology, the plenum chamber 3200 does not cover the patient's eyes during use. In other words, the eyelets are outside the pressurized volume defined by the plenum chamber. Such forms tend to be less invasive and / or more comfortable for the wearer, which can improve compliance with treatment.

[0174] In some forms of the present technology, the plenum chamber 3200 is constructed of a transparent material, such as transparent polycarbonate. The use of a transparent material can reduce the obtrusiveness of the patient interface and help improve compliance with treatment. The use of a transparent material can help the clinician observe how the patient interface is positioned and functioning.

[0175] In some forms of the present technology, the plenum chamber 3200 is constructed of a translucent material. The use of a transparent material can reduce the obtrusiveness of the patient interface and help improve compliance with therapy.

[0176] 4.3.3 Positioning and stabilizing the structure

[0177] The seal-forming structure 3100 of the patient interface 3000 of the present technology may be maintained in a sealed state during use by the positioning and stabilizing structure 3300 .

[0178] In one form, the positioning and stabilising structure 3300 provides a retaining force that is at least sufficient to overcome the positive pressure in the plenum 3200 to lift off the face.

[0179] In one form, the positioning and stabilising structure 3300 provides a retaining force to overcome the effects of gravity on the patient interface 3000 .

[0180] In one form, the positioning and stabilising structure 3300 provides a retaining force as a safety margin to overcome the potential effects of damaging forces on the patient interface 3000, such as from tube drag or accidental interference with the patient interface.

[0181] In one form of the present technology, a positioning and stabilizing structure 3300 is provided that 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 bulk of the device. In one example, the positioning and stabilizing structure 3300 includes at least one strap that is rectangular in cross-section. In one example, the positioning and stabilizing structure 3300 includes at least one flat strap.

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

[0183] In one form of the present technology, a positioning and stabilizing structure 3300 is provided that is configured so as not to be too large and bulky to prevent a patient from lying in a side sleeping position with the side area of ​​the patient's head on a pillow.

[0184] In one form of the present technology, the positioning and stabilising structure 3300 is provided with a decoupling portion located between the front of the positioning and stabilising structure 3300 and the back of the positioning and stabilising structure 3300. The decoupling portion does not resist compression and may be, for example, a flexible band or soft strap. The decoupling portion is constructed and arranged such that when a patient lies their head on the pillow, the presence of the decoupling portion prevents forces acting on the back from being transmitted along the positioning and stabilising structure 3300 and disrupting the seal.

[0185] In one form of the present technology, the positioning and stabilizing structure 3300 comprises a belt configured from a laminate of a fabric patient contacting layer, a foam inner layer, and a fabric outer layer. In one form, the foam is porous to allow moisture (e.g., sweat) to pass through the belt. In one form, the fabric outer layer comprises a loop material for engaging with a hook material portion.

[0186] In some forms of the present technology, the positioning and stabilizing structure 3300 comprises a strap that is extendable, such as elastically extendable. For example, the strap can be configured to be in a tensioned state when in use and to direct a force to bring the seal-forming structure into sealing contact with a portion of the patient's face. In one example, the strap can be configured as a tie.

[0187] In one form of the present technology, the positioning and stabilizing structure includes a first strap that is configured and arranged so that in use at least a portion of a lower edge of the first strap passes through the supraauricular base of the patient's head and covers a portion of the parietal bone without covering the occipital bone.

[0188] In one form of the present technology applicable to a nasal-only mask or to a full-face mask, the positioning and stabilizing structure includes a second strap that is configured and arranged so that in use at least a portion of an upper edge of the second strap passes below the subauricular base of the patient's head and covers or is located below the occipital bone of the patient's head.

[0189] In one form of the present technology suitable for use with a nasal-only mask or with a full-face mask, the positioning and stabilizing structure includes a third strap configured and arranged to interconnect the first strap and the second strap to reduce the tendency of the first strap and the second strap to separate from each other.

[0190] In some forms of the present technology, the positioning and stabilizing structure 3300 comprises a belt that is bendable and, for example, non-rigid. An advantage of this aspect is that the belt makes it more comfortable for the patient to lie on while sleeping.

[0191] In some forms of the present technology, the positioning and stabilising structure 3300 comprises a belt configured to be breathable to allow moisture vapor to be transmitted through the belt.

[0192] In some forms of the present technology, a system is provided that includes more than one positioning and stabilizing structure 3300, each positioning and stabilizing structure configured to provide retention forces to correspond to a different range of sizes and / or shapes. For example, the system may include one form of positioning and stabilizing structure 3300 that is suitable for large-sized heads but not for small-sized heads, while another form of positioning and stabilizing structure is suitable for small-sized heads but not for large-sized heads.

[0193] In some forms of the present technology, the stabilizing structure 3300 includes sensors configured to output data related to tension or other related forces, stresses, or mechanical values ​​along the longitudinal axis of the straps. In other examples, the stabilizing structure 3300 may include pressure sensors on one side that sense the pressure of the strap against the patient's head.

[0194] 4.3.4 Ventilation

[0195] In one form, the patient interface 3000 includes a vent 3400 constructed and arranged to allow flushing of exhaled gases, such as carbon dioxide.

[0196] In some forms, vent 3400 is configured to allow continuous ventilation flow from the interior of plenum chamber 3200 to the surrounding environment while the pressure within the plenum chamber is positive relative to the surrounding environment. Vent 3400 is configured so that the vent flow rate has a sufficient amount to reduce the patient's exposure to exhaled CO. 2 The amplitude of rebreathing while maintaining the therapeutic pressure in the inflation chamber during use.

[0197] One form of a vent 3400 according to the present technology comprises a plurality of holes, for example, about 20 to about 80 holes, or about 40 to about 60 holes, or about 45 to about 55 holes.

[0198] The vent 3400 may be located in the plenum chamber 3200. Alternatively, the vent 3400 is located in a decoupling structure (eg, a swivel joint).

[0199] In one form of the present technology, the vent 3400 may include an acoustic sensor to determine if vent noise is emanating from the vent 3400. For example, an acoustic sensor on the vent 3400 may be compared to noise output from a remote sensor or sensor on another component of the RPT device 4000 to determine noise associated with the vent 3400 as opposed to other components of the RPT device 4000.

[0200] 4.3.5 Forehead support

[0201] In one form, the patient interface 3000 includes a forehead support 3700 .

[0202] 4.3.6 Ports

[0203] In one form of the present technology, the patient interface 3000 includes one or more ports that allow access to the volume within the plenum chamber 3200. In one form, this allows the clinician to supply supplemental oxygen. In one form, this allows direct measurement of properties of the gas within the plenum chamber 3200, such as pressure.

[0204] 4.4 RPT device

[0205] 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 herein in whole or in part. The RPT device 4000 can be configured to generate an air flow for delivery to the airway of a patient, such as for treating one or more respiratory conditions described elsewhere in this document.

[0206] In one form, the RPT device 4000 is configured and arranged to deliver air flow in the range of -20 L / min to +150 L / min while maintaining at least 6 cmH 2 O, or at least 10 cmH 2 O, or at least 20 cmH 2 Positive pressure of O.

[0207] 4.4.1 Mechanical and pneumatic components of the RPT device

[0208] 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.

[0209] 4.4.1.1 Converter

[0210] The transducer may be internal to the RPT device, or external to the RPT device. An external transducer may be located, for example, on or form part of an air circuit (e.g., a patient interface). An external transducer may 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.

[0211] 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 may be configured and arranged to generate a signal representative of a characteristic of the air flow at that point in the pneumatic path, such as flow, pressure or temperature.

[0212] In one form of the present technology, one or more transducers 4270 may be located proximate to the patient interface 3000 or 3800 and may include one or more acoustic sensors.

[0213] In one form, the signal from converter 4270 may be filtered, such as by low pass, high pass, or band pass filtering.

[0214] 4.4.1.1.1 Flow sensor

[0215] A flow sensor 4274 according to the present technology may be based on a differential pressure transducer, such as the SDP600 series differential pressure transducers from SENSIRION.

[0216] In one form, the central controller 4230 receives a signal representing flow from the flow sensor 4274.

[0217] 4.4.1.1.2 Pressure sensor

[0218] A pressure sensor 4272 according to the present technology is in fluid communication with the pneumatic path. An example of a suitable pressure transducer is a sensor from the HONEYWELLASDX series. Another suitable pressure transducer is a sensor from the NPA series from GENERALELECTRIC.

[0219] In one form, signals from pressure sensor 4272 are received by central controller 4230.

[0220] 4.4.1.1.3 Motor speed converter

[0221] In one form of the present technology, a motor speed converter 4276 is used to determine the rotational speed of the motor 4144 and / or blower 4142. A motor speed signal from the motor speed converter 4276 may be provided to the treatment device controller 4240. The motor speed converter 4276 may be, for example, a speed sensor, such as a Hall effect sensor.

[0222] 4.4.2 Electrical components of CPG device

[0223] 4.4.2.1 Power supply

[0224] The power source 4210 may be located inside or outside the housing 4010 of the RPT device 4000 .

[0225] In one form of the present technology, the power supply 4210 provides power only to the RPT device 4000. In another form of the present technology, the power supply 4210 provides power to both the RPT device 4000 and the humidifier 5000.

[0226] 4.4.2.2 Input device

[0227] 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 may be physical devices, or software devices accessible via a touch screen. In one form, these buttons, switches, or dials may be physically connected to the external housing 4010, or in another form, may be in wireless communication with a receiver electrically connected to a central controller 4230.

[0228] In one form, input device 4220 may be constructed and arranged to allow a person to select values ​​and / or menu options.

[0229] 4.4.2.3 Central Controller

[0230] In one form of the present technology, the central controller 4230 is one or more processors suitable for controlling the RPT device 4000.

[0231] Suitable processors may include x86 INTEL processors based on the ARM Holdings A processor of a processor, such as a STM32 series microcontroller from STMICROELECTRONICS. In some alternative forms of the present technology, a 32-bit RISC CPU manufactured by TEXAS INSTRMENTS (such as a STR9 series microcontroller from STMICROELECTRONICS) or a 16-bit RISC CPU (such as a processor from an MSP430 series microcontroller) may also be suitable.

[0232] In one form of the present technology, the central controller 4230 is a dedicated electronic circuit.

[0233] In one form, the central controller 4230 is an application specific integrated circuit. In another form, the central controller 4230 includes discrete electronic components.

[0234] 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 .

[0235] The central controller 4230 may be configured to provide output signals to one or more of the output device 4290 , the treatment device controller 4240 , the data communication interface 4280 , and the humidifier 5000 .

[0236] In some forms of the present technology, the central controller 4230 is configured to implement one or more methods described herein, such as one or more algorithms 4300 represented as computer programs stored in a non-transitory computer-readable storage medium (such as 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 methods may be performed by a remotely located device. For example, the remotely located device may determine control settings for the ventilator or detect a breathing-related event by analyzing stored data (such as data from any of the sensors described herein).

[0237] 4.4.2.4 Clock

[0238] The RPT device 4000 may include a clock 4232 connected to a central controller 4230 .

[0239] 4.4.2.5 Treatment device controller

[0240] 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 the central controller 4230 .

[0241] In one form of the present technology, the treatment device controller 4240 is a dedicated motor control integrated circuit. For example, in one form, the MC33035 brushless DC motor controller manufactured by ONSEMI is used.

[0242] 4.4.2.6 Protection circuit

[0243] One or more protection circuits 4250 in accordance with the present technology may include electrical protection circuits, temperature and / or pressure safety circuits.

[0244] 4.4.2.7 Memory

[0245] According to one form of 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.

[0246] Memory 4260 may be located on PCBA 4202. Memory 4260 may be in the form of EEPROM or NAND flash memory.

[0247] Additionally, the RPT device 4000 includes memory 4260 in a removable form, such as a memory card manufactured according to the Secure Digital (SD) standard.

[0248] In one form of the present technology, the memory 4260 acts as a non-transitory computer-readable storage medium on which are stored computer program instructions expressing one or more methods described herein, such as one or more algorithms 4300 .

[0249] 4.4.2.8 Data Communication System

[0250] In one form of the present technology, a data communication interface 4280 is provided and 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 can be connected to a remote external communication network 4282 and / or a local external communication network 4284. The remote external communication network 4282 can be connected to a remote external device 4286. The local external communication network 4284 can be connected to a local external device 4288.

[0251] In one form, the data communications interface 4280 is part of the central controller 4230. In another form, the data communications interface 4280 is separate from the central controller 4230 and may comprise an integrated circuit or processor.

[0252] In one form, remote external communication network 4282 is the Internet. Data communication interface 4280 may connect to the Internet using wired communication (eg, via Ethernet or fiber optic) or wireless protocols (eg, CDMA, GSM, LTE).

[0253] In one form, the local external communication network 4284 utilizes one or more communication standards, such as Bluetooth or Consumer Fiber Optic Protocol.

[0254] In one form, remote external device 4286 is one or more computers, such as a networked computer cluster. In one form, remote external device 4286 can be a virtual computer, rather than a physical computer. In either case, such remote external device 4286 can be accessed by a properly authorized person, such as a clinician.

[0255] The local external device 4288 may be a personal computer, a mobile phone, a tablet computer, or a remote control.

[0256] In some forms of the present technology, the central controller 4230 will record usage data 9045 in memory 4260, which may include output from the treatment device controller 4240, computer system, exercise equipment, or other system. The usage data 9045 may include several blocks or data portions, including: (1) date and time stamp, (2) start and stop times of usage, (3) time of usage for a session, (4) date and time of turning on and off the RPT device 4000, computer system, exercise equipment, or other system, 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, this may be the speed or intensity of exercise (e.g., stepper speed)).

[0257] In some forms of the present technology, the usage data 9045 will be stored in the local memory 4260. The usage data 9045 may also be sent to a remote external device 4286 or a local external device 4288 via the data communication interface 4280 over a network.

[0258] In some examples, the central controller 4230 will send usage data 9085 via the data communication interface 4280 one hour, two hours, three hours, or other suitable time range after a treatment period or other period (e.g., an exercise period, a driving period, a website usage period) has ended. In other examples, the usage data 9045 will be sent weekly. In some examples, if no usage period is turned on on a particular day, the controller 4230 may send usage data 9045 via the data communication interface 4280 at 1:00 a.m. or other suitable time the next day or weekend. The usage data 9045 will indicate that the particular day or time period includes a non-usage day. In some examples, the usage data 9045 may 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 back on, and the amount of non-usage days since the last period identified by the controller 4230 and stored in the memory 4260 will be determined.

[0259] The data sent through the data communication interface 4280 can be raw data, or can be pre-processed data to save bandwidth, particularly in areas of poor cellular signal or other remote external communication network 4282 bandwidth. For example, the usage data 9045 can be pre-processed to output relevant features for use reduction or termination prediction. This can include non-use days, average usage (e.g., hours), and standard deviation of usage. The relevant features can then be processed by the algorithm 4300 on the remote external device 4286 or server.

[0260] In some forms of the present technology, the full usage prediction algorithm may reside in local memory 4260, and the controller 4230 may process the usage data 9045 to determine the likelihood that the patient 1000 or other user (depending on the application) will exit or reduce the use of the device itself. In these cases, the controller 4230 may send a signal to send an output to the display 4294, and / or send the data to a local or remote external device, such as if the percentage likelihood exceeds a threshold.

[0261] 4.4.2.9 Output devices, including optional displays, alarms

[0262] Output devices 4290 in accordance with the present technology may take the form of one or more of visual, audio, and tactile units. [000170] The visual display may be a liquid crystal display (LCD) or a light emitting diode (LED) display.

[0263] 4.4.2.9.1 Display Driver

[0264] Driver 4292 is shown receiving as input characters, symbols, or images to be displayed on display 4294 and converting them into commands that cause display 4294 to display these characters, symbols, or images.

[0265] 4.4.2.9.2 Display

[0266] 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 may be an eight-segment display, in which case the display driver 4292 converts each character or symbol, such as the number "0," into eight logic signals indicating whether to activate the eight corresponding segments to show the particular character or symbol.

[0267] In some examples, the display may include a touch screen or a remote interface such as a smartphone that receives input from the user or patient 1000 .

[0268] 4.4.3 Algorithm

[0269] As described above, in some forms of the present technology, the central controller 4230 or other processor may be configured to implement one or more algorithms represented as computer programs stored in a non-transitory computer-readable storage medium, such as memory 4260. The algorithms are generally grouped into multiple groups referred to as modules. These algorithms may include feature detection algorithms and machine learning algorithms for predicting reduction or termination of therapy, use of exercise equipment, or participation in use of an on-demand service, such as a taxi service using a mobile application that can track use (e.g., users or employees - such as drivers).

[0270] 4.4.3.1 Preprocessing module

[0271] A pre-processing module 4310 according to one form of the present technology receives as input a signal from a transducer 4270 (e.g., a flow sensor 4274 or a pressure sensor 4272) and performs one or more process steps to calculate one or more output values ​​to be used as input to another module (e.g., a therapy engine module 4320).

[0272] In one form of the present technology, the output values ​​include the port pressure Pm, the respiratory flow rate Qr, and the leakage flow rate Q1.

[0273] In various forms of the present technology, the pre-processing 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 .

[0274] 4.4.3.1.1 Interface pressure estimation

[0275] In one form of the present technology, an interface pressure estimation algorithm 4312 receives as input a signal from a pressure sensor 4272 indicating a pressure in the pneumatic path near the outlet of the pneumatic block (device pressure Pd) and a signal from a flow sensor 4274 representing the flow rate of the gas flow leaving the RPT device 4000 (device flow Qd). The device flow rate Qd without any supplemental gas 4180 can be used as the total flow rate Qt. The interface pressure algorithm 4312 estimates the pressure drop ΔP through the air circuit 4170. The dependence of the pressure drop ΔP on the total flow rate Qt can be modeled for a particular air circuit 4170 by a pressure drop characteristic ΔP(Q). The interface pressure estimation algorithm 4312 provides as output an estimated pressure Pm in the patient interface 3000 or 3800. 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.

[0276] 4.4.3.1.2 Ventilatory flow estimation

[0277] In one form of the present technology, ventilation flow estimation algorithm 4314 receives as input the estimated pressure Pm in patient interface 3000 or 3800 from interface pressure estimation algorithm 4312, and estimates ventilation flow Qv of air from vent 3400 in patient interface 3000 or 3800. For a particular vent 3400 in use, the dependence of vent flow Qv on interface pressure Pm may be modeled by vent characteristic Qv(Pm).

[0278] 4.4.3.1.3 Leakage flow estimation

[0279] In one form of the present technology, the leak flow estimation algorithm 4316 receives the total flow Qt and the ventilation flow Qv as inputs and provides an estimate of the leak flow Q1 as output. In one form, the leak flow estimation algorithm estimates the leak flow Q1 by averaging the difference between the total flow Qt and the ventilation flow Qv over a sufficiently long period of time (e.g., about 10 seconds).

[0280] In one form, the leak flow estimation algorithm 4316 receives as input the total flow Qt, the ventilation flow Qv, and the estimated pressure Pm in the patient interface 3000 or 3800, and provides as output a leak flow Q1 by calculating the leak conductance and determining the leak flow Q1 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 low-pass filtered pressure square root Pm, where the low-pass filter time constant has a value long enough to encompass several breathing cycles, such as approximately 10 seconds. The leak flow Q1 can be estimated as the product of the leak conductance and the function of the pressure Pm.

[0281] 4.4.3.1.4 Respiratory flow estimation

[0282] In one form of the present technology, a respiratory flow estimation algorithm 4318 receives as inputs a total flow Qt, a ventilation flow Qv, and a leak flow Q1 and estimates a respiratory flow Qr of air to the patient by subtracting the ventilation flow Qv and the leak flow Q1 from the total flow Qt.

[0283] 4.4.3.2 Treatment Engine Module

[0284] In one form of the present technology, therapy engine module 4320 receives as input one or more of pressure Pm in patient interface 3000 or 3800 and respiratory flow Qr of air to the patient, and provides as output one or more therapy parameters.

[0285] In one form of the present technology, the treatment parameter is the treatment pressure Pt.

[0286] In one form of the present technology, the therapy parameter is one or more of pressure amplitude, basal pressure, and target ventilation.

[0287] In various forms, the therapy engine module 4320 includes one or more of the following algorithms: phase determination 4321, waveform determination 4322, ventilation determination 4323, inspiratory flow limitation determination 4324, apnea / hypopnea determination 4325, snoring determination 4326, airway patency determination 4327, target ventilation determination 4328 and therapy parameter determination 4329.

[0288] 4.4.3.2.1 Phase determination

[0289] In one form of the present technology, the RPT device 4000 is phase indeterminate.

[0290] In one form of the present technology, the phase determination algorithm 4321 receives as input a signal indicative of respiratory flow Qr and provides as output the phase Φ of the current respiratory cycle of the patient 1000.

[0291] In some forms, referred to as discrete phase determination, the phase output Φ is a discrete variable. One embodiment of discrete phase determination provides a two-value phase output Φ having an inspiratory or expiratory value, such as values ​​represented as 0 and 0.5 turns, respectively, when the onset of spontaneous inspiration and expiration, respectively, is detected. "Triggering" and "cycling" the RPT device 4000 that effectively performs discrete phase determination, because the trigger point and the cycle point are the moments when the phase changes from exhalation to inspiration and from inspiration to exhalation, respectively. In one embodiment of the two-value phase determination, when the respiratory flow rate Qr has a value exceeding a positive threshold, the phase output Φ is determined to have a discrete value of 0 (thereby "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 a discrete value of 0.5 turns (thereby "cycling" the RPT device 4000). The inspiratory time Ti and the expiratory time Te can be estimated as typical values ​​over many respiratory cycles of the time spent with the phase Φ equal to 0 (indicating inspiration) and 0.5 (indicating exhalation), respectively.

[0292] Another embodiment of discrete phase determination provides a three-value phase output Φ having one of inspiration, mid-inspiratory pause, and expiration.

[0293] In other forms, referred to as continuous phase determination, the phase output Φ is a continuous variable, for example, varying from 0 to 1 turn or 0 to 2 radians. The RPT device 4000 performing continuous phase determination can trigger and cycle when the continuous phase reaches 0 and 0.5 turns, respectively. In one embodiment 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 generally referred to as a "fuzzy phase". In one embodiment of the fuzzy phase determination algorithm 4321, the following rules are applied to the respiratory flow rate Qr:

[0294] 1. If the respiratory flow is zero and increases rapidly, the phase is 0 turns.

[0295] 2. If the respiratory flow is large, positive and stable, the phase is 0.25 turns.

[0296] 3. If the respiratory flow is zero and decreases rapidly, the phase is 0.5 turns.

[0297] 4. If the respiratory flow is negative and stable, the phase is 0.75 turns.

[0298] 5. If the respiratory flow is zero and stable, and the absolute value of the 5-second low-pass filter of the respiratory flow is large, the phase is 0.9 turns.

[0299] 6. If the respiratory flow is positive and the phase is exhalation, the phase is 0 turns.

[0300] 7. If the respiratory flow is negative and the phase is inspiratory, the phase is 0.5 turns.

[0301] 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.

[0302] The output of each rule can be represented as a vector whose phase is the result of the rule and whose magnitude is the fuzziness of the rule being true. The fuzziness of respiratory flow "large", "stable", etc. is determined using appropriate membership functions. The results of the rules are represented as vectors and then combined by some functions such as taking the centroid. In such a combination, the rules can be weighted equally, or differently.

[0303] In another embodiment of continuous phase determination, as described above, the phase Φ, the inspiratory time Ti and the expiratory time Te are first estimated discretely from the respiratory flow Qr. The continuous phase Φ at any time can be determined as half of the proportion of the inspiratory time Ti that has passed since the previous trigger time, or 0.5 turns plus half of the proportion of the expiratory time Te that has passed since the previous cycle time (whichever time is more recent).

[0304] 4.4.3.2.2 Waveform measurement

[0305] In one form of the present technology, the therapy parameter determination algorithm 4329 provides a substantially constant therapy pressure throughout the patient's breathing cycle.

[0306] In other forms of the present technology, the therapy control module 4330 controls the pressure generator 4140 to provide a therapy pressure Pt that varies according to a waveform template Π(Φ) as a function of the phase Φ of the patient's respiratory cycle.

[0307] In one form of the present technology, the waveform determination algorithm 4322 provides a waveform template Π(Φ) having values ​​in the range [0, 1] over the domain of phase values ​​Φ provided by the phase determination algorithm 4321 for use by the treatment parameter determination algorithm 4329.

[0308] In one form, suitable for discrete or continuous valued phases, the waveform template Π(Φ) is a square wave template having a value of 1 for phase values ​​up to and including 0.5 turns, and having a value of 0 for phase values ​​above 0.5 turns. In one form, suitable for continuous valued phases, the waveform template Π(Φ) contains two smooth curved portions, namely a smooth curve (e.g., raised cosine) rising from 0 to 1 for phase values ​​up to 0.5 turns, and a smooth curve (e.g., exponential) falling from 1 to 0 for phase values ​​above 0.5 turns. In one form, suitable for continuous valued phases, 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" of less than 0.5 turns, and has a smooth fall from 1 to 0 for phase values ​​within a "fall time" after 0.5 turns, with a "fall time" of less than 0.5 turns.

[0309] In some forms of the present technology, the waveform determination algorithm 4322 selects a waveform template Π(Φ) from a library of waveform templates based on the settings of the RPT device. Each waveform template Π(Φ) in the library may be provided as a lookup table of values ​​for phase values. In other forms, the waveform determination algorithm 4322 calculates the "on-the-fly" waveform template Π(Φ) using a predetermined functional form that may be parameterized by one or more parameters (e.g., the time constant of the exponential curve portion). The parameters of the functional form may be predetermined or dependent on the current state of the patient 1000.

[0310] In some forms of the present technology, the waveform determination algorithm 4322 is applied to a discrete two-value phase of inspiration (Φ=0 revolutions) or exhalation (Φ=0.5 revolutions), and the waveform determination algorithm 4322 calculates a "running" waveform template Π(Φ, t) as a function of the discrete phase Φ and the time t measured since the most recent triggering moment. In one such form, the waveform determination algorithm 4322 calculates the waveform template Π(Φ, t) for both parts (inspiration and exhalation) as follows:

[0311]

[0312] Among them i (t) and П e (t) is the inspiratory and expiratory portion of the waveform template Π(Φ, t). In one such form, the inspiratory portion of the waveform template Π i (t) is a smooth rise from 0 to 1 parameterized by the rise time, the exhalation part of the waveform template П e (t) is a smooth decline from 1 to 0 parameterized by the decline time.

[0313] 4.4.3.2.3 Ventilation measurement

[0314] In one form of the present technology, a ventilometry algorithm 4323 receives an input of respiratory flow Qr and determines a measurement Vent indicative of current patient ventilation.

[0315] In some embodiments, the ventilation determination algorithm 4323 determines a measure of ventilation that is an estimate of actual patient ventilation. One such embodiment is to take half the absolute value of the respiratory flow Qr, optionally filtered through a low pass filter (such as a second order Bessel low pass filter with a 0.11 Hz corner frequency).

[0316] In other embodiments, the ventilation determination algorithm 4323 determines a measure of ventilation that is approximately proportional to actual patient ventilation. One such embodiment estimates the peak respiratory flow Qpeak over the inspiratory portion of the cycle. This process and many other processes involving sampling the respiratory flow rate Qr produce a measure that is approximately proportional to ventilation as long as the flow waveform shape does not vary greatly (herein, two breaths are considered to have similar shapes when the flow waveforms of the breaths normalized in time and amplitude are similar). Some simple examples include the median respiratory flow, the median of the absolute values ​​of the respiratory flow, and the standard deviation of the flow. Any linear combination of any order statistics of the absolute values ​​of the respiratory flow using positive coefficients, and even some arbitrary linear combination of any order statistics using positive and negative coefficients, is approximately proportional to ventilation. Another example is the average of the respiratory flow in the middle K proportions (by time) of the inspiratory portion, where 0<K<1. If the flow shape is constant, there are an arbitrarily large number of measurements that are exactly proportional to ventilation.

[0317] 4.4.3.2.4 Determining inspiratory flow limitation

[0318] In one form of the present technology, the central controller 4230 executes an inspiratory flow limitation determination algorithm 4324 to determine the extent of inspiratory flow limitation.

[0319] In one form, the inspiratory flow limitation determination algorithm 4324 receives as input the respiratory flow signal Qr and provides as output a measure of the degree to which the inspiratory portion of the breath exhibits inspiratory flow limitation.

[0320] In one form of the present technology, the inspiratory portion of each breath is identified by a zero crossing detector. An interpolator interpolates a number of evenly spaced points (e.g., sixty-five) representing time points along the inspiratory flow rate-time curve for 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 breathing rate and depth. The scaled breath is then compared in a comparator to a pre-stored template representing a normal unobstructed breath, similar to Fig. 6AThe inspiratory portion of the breath shown. Breaths that deviate from this template by more than a specified threshold (typically 1 scale unit) at any time during inspiration, such as breaths due to coughing, sighing, swallowing, and hiccups as determined by the test element, are rejected. For data that is not rejected, a moving average of the first such scaled point is calculated by the central controller 4230 for the previous several inspiratory events. This is repeated on the same inspiratory event for the second such point, and so on. Thus, for example, sixty-five scaled data points are generated by the central controller 4230 and represent a moving average of several previous inspiratory events, such as three events. The moving average of the continuously updated values ​​of these (e.g., 65) points is hereinafter referred to as the "scaled flow", designated as Qs(t). Alternatively, a single inspiratory event may be used instead of a moving average.

[0321] From the scaled flow, two shape factors relevant to the determination of partial obstruction can be calculated.

[0322] Shape Factor 1 is the ratio of the average of the intermediate (e.g., 32) scaled flow points to the overall average (e.g., 65) scaled flow points. In the event that this ratio exceeds unity, the breath will be considered normal. In the event that this ratio is unity or less, the breath will be obstructed. A ratio of about 1.17 is considered the threshold between partially obstructed and unobstructed breaths and is equal to the degree of obstruction that allows adequate oxygenation to be maintained in a typical patient.

[0323] The shape factor 2 is calculated as the RMS deviation of unit scaled flow taken from the middle (e.g. 32) points. An RMS deviation of about 0.2 units is considered normal. An RMS deviation of 0 is taken as a fully flow-restricted breath. The closer the RMS deviation is to zero, the more flow-restricted the breath is.

[0324] Shape factors 1 and 2 may be used as an alternative or in combination. In other forms of the present technology, the number of sampling points, breaths, and midpoints may be different from those described above. Furthermore, the thresholds may be different from those described.

[0325] 4.4.3.2.5 Determination of apnea and hypopnea

[0326] In one form of the present technology, the central controller 4230 executes an apnea / hypopnea determination algorithm 4325 for determining the presence of apnea and / or hypopnea.

[0327] In one form, the apnea / hypopnea determination algorithm 4325 receives as input the respiratory flow signal Qr and provides as output a flag indicating that an apnea or hypopnea has been detected.

[0328] In one form, when the function of respiratory flow Qr falls below a flow threshold for a predetermined period of time, apnea is considered to have been detected. The function may determine a peak flow, a relatively short-term average flow, or a flow between a relatively short-term average and peak flow, such as RMS flow. The flow threshold may be a relatively long-term measure of flow.

[0329] In one form, when the function of respiratory flow Qr falls below a second flow threshold within a predetermined time period, hypopnea is considered to have been detected. The function may determine a peak flow, a relatively short-term average flow, or a flow between a relatively short-term average flow and a peak flow, such as an RMS flow. The second flow threshold may be a relatively long-term measure of flow. The second flow threshold is greater than a flow threshold for detecting apnea.

[0330] 4.4.3.2.6 Determination of snoring

[0331] In one form of the present technology, the central controller 4230 executes one or more snoring determination algorithms 4326 for determining the level of snoring.

[0332] In one form, the snoring determination algorithm 4326 receives as input the respiratory flow signal Qr and provides as output a measure of the degree to which snoring is present.

[0333] The snore determination algorithm 4326 may include a step of determining the strength of the flow signal in the range of 30-300 Hz. In addition, the snore determination algorithm 4326 may include a step of filtering the respiratory flow signal Qr to reduce background noise (eg, the sound of airflow in the system from a blower).

[0334] 4.4.3.2.7 Determination of airway patency

[0335] In one form of the present technology, the central controller 4230 executes one or more airway patency determination algorithms 4327 for determining airway patency.

[0336] In one form, the airway patency determination algorithm 4327 receives the respiratory flow signal Qr as input and determines the signal power within a frequency range of about 0.75 Hz and about 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.

[0337] In one form, the frequency range in which the peak is sought is the frequency of a small forced oscillation in the process pressure Pt. In one embodiment, the frequency of the forced oscillation is 2 Hz and the amplitude is approximately 1 cmH 2 O.

[0338] In one form, the airway patency determination algorithm 4327 receives as input the respiratory flow signal Qr and determines the presence or absence of a cardiogenic signal. The absence of a cardiogenic signal is considered to be indicative of a closed airway.

[0339] 4.4.3.2.8 Determining target ventilation

[0340] In one form of the present technology, the central controller 4230 takes the current ventilation Vent as input and executes one or more target ventilation determination algorithms 4328 for determining a target value Vtgt for ventilation.

[0341] In some forms of the present technology, there is no target ventilation determination algorithm 4328 and the target value Vtgt is predetermined, for example by hard coding during configuration of the RPT device 4000 or by manual entry via the input device 4220.

[0342] In other forms of the present technology, such as adaptive servo-ventilation (ASV), the target ventilation determination algorithm 4328 calculates a target value Vtgt based on a value Vtyp representing the patient's typical recent ventilation.

[0343] In some forms of adaptive servo-ventilation, the target ventilation Vtgt is calculated as a high proportion of the typical most recent ventilation Vtyp, but less than the typical most recent ventilation Vtyp. The high proportion in these forms may be in the range of (80%, 100%) or (85%, 95%) or (87%, 92%).

[0344] In other forms of adaptive servo-ventilation, the target ventilation Vtgt is calculated to be an integer multiple slightly larger than the typical most recent ventilation Vtyp.

[0345] The typical recent ventilation Vtyp is a value around which the distribution of measurements of the current ventilation Vent at multiple moments on a predetermined time scale tends to cluster, i.e., a measure of the central tendency of the measurements of the current ventilation in the recent history. In one embodiment of the target ventilation determination algorithm 4328, the recent history is on the order of minutes, but in any case should be longer than the time scale of the Cheyne-Stokes waxing and waxing cycles. The target ventilation determination algorithm 4328 can use any of a variety of well-known central tendency measures to determine the typical recent ventilation Vtyp based on the measure of the current ventilation 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.

[0346] 4.4.3.2.9 Determination of treatment parameters

[0347] 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 may include algorithms 4300 for changing treatment parameters in the event that the patient 1000 is flagged for reduction or termination of treatment.

[0348] 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:

[0349] Pt=AΠ(Φ,t)+P 0 (1)

[0350] in:

[0351] A is the amplitude,

[0352] Π(Φ, t) is the value of the waveform template at the current value Φ of phase and time t (in the range 0 to 1), and

[0353] P 0 It is the base pressure.

[0354] If the waveform determination algorithm 4322 provides a waveform template Π(Φ, t) as a lookup table of values ​​Π indexed by phase Φ, the treatment parameter determination algorithm 4329 applies equation (1) by locating the nearest lookup table entry to the current value Φ of the phase returned by the phase determination algorithm 4321, or by interpolating between two entries that span the current value Φ of the phase.

[0355] Amplitude A and base pressure P 0 The value of can be set by the therapy parameter determination algorithm 4329 in the manner described below according to the selected respiratory pressure therapy mode.

[0356] 4.4.3.3 Treatment Control Module

[0357] The therapy control module 4330 according to one aspect of the present technology receives as input therapy parameters from the therapy parameter determination algorithm 4329 of the therapy engine module 4320 and controls the pressure generator 4140 to deliver air flow according to the therapy parameters.

[0358] In one form of the present technology, the therapy parameter is a therapy pressure Pt and the therapy control module 4330 controls the pressure generator 4140 to deliver an air flow having an interface pressure Pm at the patient interface 3000 or 3800 equal to the therapy pressure Pt.

[0359] 4.4.3.4 Detecting Fault Conditions

[0360] In one form of the present technology, the central controller 4230 executes one or more methods 4340 for detecting a fault condition. The fault condition detected by the one or more methods 4340 may include at least one of the following:

[0361] Power failure (no power or insufficient power)

[0362] Converter fault detection

[0363] Unable to detect the presence of parts

[0364] Operating parameters outside the recommended range (e.g., pressure, flow, temperature, PaO 2 ).

[0365] The test alarm fails to generate a detectable alarm signal.

[0366] Upon detecting a fault condition, the corresponding algorithm 4340 signals the presence of the fault by one or more of:

[0367] Activate audible, visual and / or dynamic (e.g., vibration) alarms

[0368] Send messages to external devices

[0369] Event logging

[0370] 4.5 Humidifier

[0371] 4.5.1 Humidifier Overview

[0372] In one form of the present technology, a humidifier 5000 (e.g., as in Figure 5A ) to change the absolute humidity of air or gas for delivery to a patient relative to ambient air. Typically, a humidifier 5000 is used to increase the absolute humidity and increase the temperature of the air stream (relative to ambient air) before delivery to the patient's airway.

[0373] The humidifier 5000 may include a humidifier reservoir 5110, a humidifier inlet 5002 for receiving an air flow, and a humidifier outlet 5004 for delivering a humidified air flow. Figure 5A and 5B As shown, the inlet and outlet of the humidifier reservoir 5110 can be respectively a humidifier inlet 5002 and a humidifier outlet 5004. The humidifier 5000 can also include a humidifier base 5006, which can be adapted to receive the humidifier reservoir 5110 and include a heating element 5240.

[0374] 4.6 Respiratory waveform

[0375] Fig. 6A A model of a typical breathing waveform of a person during sleep is shown. The horizontal axis is time, and the vertical axis is respiratory flow. While the parameter values ​​may vary, a typical breath may have the following approximate values: tidal volume Vt 0.5L, inspiratory time Ti 1.6s, peak inspiratory flow Qpeak 0.4L / s, expiratory time Te 2.4s, peak expiratory flow Qpeak-0.5L / s. The total duration of the breath Ttot is approximately 4s. A person typically breathes at a rate of approximately 15 breaths per minute (BPM), with a ventilation outlet of approximately 7.5L / min. A typical duty cycle, the ratio of Ti to Ttot is approximately 40%.

[0376] Figure 6B 1 shows selected polysomnographic 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, with approximately 34 breaths being treated with auto-PAP therapy and an interface pressure of approximately 11 cmH 2 O. The top channel shows pulse oximetry (oxygen saturation or SpO 2 ), which has a saturation range from 90% to 99% in the vertical direction. The patient maintained about 95% saturation during the time period shown. The second channel shows quantitative respiratory airflow, with a scale from -1 LPS to +1 LPS in the vertical direction, with inspiration being positive. Chest and abdominal movements are shown in the third and fourth channels.

[0377] 4.7 Screening, diagnosis and monitoring systems

[0378] 4.7.1 Polysomnography

[0379] Fig. 7A A patient 1000 undergoing a polysomnogram (PSG) is shown. 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; submandibular EMG electrodes 2030; snoring sensor 2035; respiratory inductive plethysmogram (respiratory effort sensor) 2040 on a chest strap; respiratory inductive plethysmogram (respiratory effort sensor) 2045 on an abdominal strap; oral and nasal cannula 2050 with oral thermistor; 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.

[0380] 4.7.2 Non-intrusive monitoring system

[0381] Figure 7BAn example of a monitoring device 7100 for monitoring the breathing of a sleeping patient 1000 is shown. The monitoring device 7100 includes a non-contact motion sensor that is generally directed toward the patient 1000. The motion sensor is configured to generate one or more signals representing the body movement of the patient 1000, from which a signal representing the patient's breathing movement can be obtained. In other examples, the system can include environmental and other acoustic sensors to sense noise of the environment, the vent, and the patient 1000.

[0382] 4.7.3 Respiratory multispectral analysis

[0383] Respiratory polygraph (RPG) is a term used for a simplified form of PSG that does not have electrical signals (EOG, EEG, EMG), snoring, or body position sensors. The RPG contains at least a chest motion signal from a respiratory induced 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 (e.g., pulse oximeter 2055). These three RPG signals or channels are received by an RPG headbox similar to PSG headbox 2000.

[0384] In certain configurations, the nasal pressure signal is a satisfactory proxy for the nasal flow signal generated by a flow transducer in line with a sealing 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.

[0385] FIG. 7C is a block diagram showing a screening / diagnosis / monitoring device 7200 that can be used to implement an RPG headbox in an RPG screening / diagnosis / monitoring system. The screening / diagnosis / monitoring device 7200 receives the above three RPG channels (a signal indicating chest movement, a signal indicating nasal flow, and a signal indicating oxygen saturation) at a data input interface 7260. The screening / diagnosis / monitoring device 7200 also includes a processor 7210 configured to execute coded instructions. The screening / diagnosis / monitoring device 7200 also includes a non-transitory computer-readable memory / storage medium 7230.

[0386] The memory 7230 may be an internal memory of the screening / diagnosis / monitoring device 7200, such as RAM, flash memory, or ROM. In some embodiments, the memory 7230 may also be a removable or external memory linked to the screening / diagnosis / monitoring device 7200, such as, for example, an SD card, a server, a USB flash drive, or an optical disk. In other embodiments, the memory 7230 may be a combination of an external memory and an internal memory. The memory 7230 includes storage data 7240 and a processor control instruction (code) 7250 suitable for configuring the processor 7210 to perform a specific task. The storage data 7240 may include RPG channel data received by the data input interface 7260, as well as other data provided as a component of the application. The processor control instruction 7250 may also be provided as a component of the application. The processor 7210 is configured to read the code 7250 from the memory 7230 and execute the encoded instructions. Specifically, the code 7250 may include instructions suitable for configuring the processor 7210 to execute a method for processing the RPG channel data provided by the interface 7260. One such method may be to store the RPG channel data as data 7240 in memory 7230. Another such method may be to analyze the stored RPG data to extract features. Processor 7210 may store the results of such analysis as data 7240 in memory 7230.

[0387] The screening / diagnostic / monitoring device 7200 may also include a communication interface 7220. The code 7250 may include instructions configured to allow the processor 7210 to communicate with an external computing device (not shown) via the communication interface 7220. The communication mode may be wired or wireless. In one such embodiment, the processor 7210 may transmit the stored RPG channel data from the data 7240 to a remote computing device. In such an embodiment, the remote computing device may be configured to analyze the received RPG data to extract features. In another such embodiment, the processor 7210 may transmit the analysis results from the data 7240 to the remote computing device.

[0388] Alternatively, if the memory 7230 is removable from the screening / diagnostic / monitoring device 7200, the remote computing device may be configured to connect to the removable memory 7230. In such an embodiment, the remote computing device may be configured to analyze the RPG data retrieved from the removable memory 7230 to extract features.

[0389] 4.8 Respiratory therapy mode

[0390] The RPT device 4000 can implement various respiratory therapy modes.

[0391] 4.8.1 CPAP therapy

[0392] In some embodiments of respiratory pressure therapy, the central controller 4230 sets the treatment pressure Pt according to the treatment pressure equation (1) as part of the treatment parameter determination algorithm 4329. In one such embodiment, the amplitude A is equal to zero, so the treatment pressure Pt (which represents the target value achieved by the interface pressure Pm at the current moment) is equal to zero throughout the breathing cycle. Such embodiments are generally classified under the heading of CPAP therapy. In these embodiments, the treatment engine module 4320 is not required to determine the phase Φ or waveform template Π(Φ).

[0393] In CPAP therapy, the basic pressure P 0 The basal pressure P may be a constant value that is hard-coded or manually input into the RPT device 4000. Alternatively, the central controller 4230 may repeatedly calculate the basal pressure P based on indicators or measurements of sleep-disordered breathing (such as one or more of flow limitation, apnea, hypopnea, openness, and snoring) returned by a corresponding algorithm in the therapy engine module 4320. 0 This alternative approach is sometimes called APAP therapy.

[0394] Figure 4E 43 is a diagram showing that when the pressure support A is equal to zero, as part of the APAP therapy implementation of the therapy parameter determination algorithm 4329, the central controller 4230 is executed to continuously calculate the base pressure P 0 Flow chart of method 4500.

[0395] The method 4500 begins at step 4520, where the central controller 4230 compares the measure of the presence of an apnea / hypopnea to a first threshold and determines whether the measure of the presence of an apnea / hypopnea has exceeded the first threshold for a predetermined period of time, indicating that an apnea / hypopnea is occurring. If so, the method 4500 proceeds to step 4540; otherwise, the method 4500 proceeds to step 4530. At step 4540, the central controller 4230 compares the measure of airway patency to 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 the method 4500 proceeds to step 4560; otherwise, the apnea / hypopnea is considered obstructive and the method 4500 proceeds to step 4550.

[0396] At step 4530, central controller 4230 compares the measure of flow limitation to a third threshold. If the measure of flow limitation exceeds the third threshold, indicating that inspiratory flow is limited, method 4500 proceeds to step 4550; otherwise, method 4500 proceeds to step 4560.

[0397] In step 4550, if the obtained process pressure Pt does not exceed the maximum process 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 1cmH20 and 25cmH20 respectively. In other embodiments, the pressure increment P can be as low as 0.1cmH 2 O and up to 3cmH 2 O, or as low as 0.5 cmH 2 O and up to 2cmH 2 In other embodiments, the maximum processing pressure P max Can be as low as 15cmH 2 O and up to 35cmH 2 O, or as low as 20 cmH 2 O and up to 30cmH 2 O. Method 4500 may then return to step 4520.

[0398] At step 4560, the central controller 4230 sets the base pressure P 0 To reduce the reduction, just reduce the base pressure P 0 Will not drop to the minimum processing pressure P min Method 4500 may then return to step 4520. In one embodiment, the reduction amount is related to P 0 -P min The value of is proportional to such that in the absence of any detected event, P 0 To the minimum processing pressure P min The decrease in is exponential. In one embodiment, the proportionality constant is set so that P 0 The time constant of the exponential decrease is 60 minutes, and the minimum treatment pressure P min 4cmH 2 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 processing pressure P min Can be as low as 0cmH 2 O and up to 8cmH 2 O, or as low as 2 cmH 2 O and up to 6cmH 2 Alternatively, P can be preset 0 The reduction in P 0 To the minimum processing pressure P min The reduction is linear.

[0399] 4.8.2 Bi-level treatment

[0400] 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 bi-level therapy because when the therapy pressure Pt is determined using equation (1) with a positive amplitude A, the therapy parameter determination algorithm 4329 oscillates the therapy pressure Pt between two values ​​or levels that are synchronized with the spontaneous breathing effort of the patient 1000. That is, based on the above-described typical waveform template Π(Φ, t), the therapy parameter determination algorithm 4329 increases the therapy pressure Pt to Pt at the beginning of exhalation or during inspiration. 0 + A (called IPAP), and at the beginning of exhalation or during exhalation, the treatment pressure Pt is reduced to the base pressure P 0 (called EPAP).

[0401] In some forms of bi-level therapy, IPAP is the treatment pressure with the same purpose as the treatment pressure in the CPAP treatment mode, and EPAP is IPAP minus Amplitude A, which has a "small" value (a few cmH 2 In the present invention, the RPT device 4000 may be provided with a CPAP therapy that is performed with an EPR (expiratory pressure relief) or a CPAP therapy that is performed with an EPR (expiratory pressure relief). This form of therapy is sometimes referred to as CPAP therapy with EPR, which is generally considered to be more comfortable than straight CPAP therapy. In CPAP therapy with EPR, one or both of IPAP and EPAP may be constant values ​​that are hard-coded or manually entered into the RPT device 4000. Alternatively, the therapy parameter determination algorithm 4329 may repeatedly calculate IPAP and / or EPAP during CPAP with EPR. In this alternative, the therapy parameter determination algorithm 4329 calculates IPAP and / or EPAP at the same base pressure P as described above in APAP therapy. 0 In a similar manner to the calculation, EPAP and / or IPAP are repeatedly calculated based on the indicators or measurements of sleep disordered breathing returned by the corresponding algorithms in the treatment engine module 4320.

[0402] In other forms of bi-level therapy, Amplitude A is large enough that the RPT device 4000 performs some or all of the work of breathing for the patient 1000. In this form, known as pressure support ventilation therapy, Amplitude A is referred to as pressure support or oscillation. In pressure support ventilation therapy, IPAP is based on the basal pressure P 0 Pressure support A, EPAP is the basic pressure P 0 .

[0403] In some forms of PSVT, known as fixed-PSVT, the pressure support A is fixed at a predetermined value, such as 10 cmH 2 O. The predetermined pressure support value is a setting of the RPT device 4000 and may be set, for example, by hard coding during configuration of the RPT device 4000 or by manual input via the input device 4220.

[0404] In other forms of pressure support ventilation therapy, broadly referred to as servo-ventilation, a therapy parameter determination algorithm 4329 takes as input some currently measured or estimated parameter of the respiratory cycle (e.g., a currently measured value of ventilation Vent) and a target value for that respiratory parameter (e.g., a target value of ventilation Vtgt), and repeatedly adjusts the parameters of equation (1) to bring the currently measured value of the respiratory parameter to the target value. In a form of servo-ventilation known as adaptive servo-ventilation (ASV), which has been used to treat CSR, the respiratory parameter is ventilation, and the target ventilation value Vtgt is calculated by a target ventilation value determination algorithm 4328 based on a typical recent ventilation value Vtyp, as described above.

[0405] In some forms of servo-ventilation, the therapy parameter determination algorithm 4329 applies a control method to repeatedly calculate the pressure support A in order to bring the current measured value of the respiratory parameter to the target value. One such control method is proportional integral (PI) control. In one embodiment of PI control, applicable to ASV mode, where the target ventilation volume Vtgt is set slightly less than the typical recent ventilation volume Vtyp, the pressure support A is repeatedly calculated as:

[0406] A=G∫(Vent-Vtgt)dt (2)

[0407] Where G is the gain of the PI control. Larger gain values ​​G can result in positive feedback in the treatment engine module 4320. Smaller gain G values ​​can allow for some residual untreated CSR or central sleep apnea. In some embodiments, the gain G is fixed to a predetermined value, such as -0.4 cmH 2 O / (L / min) / sec. Alternatively, the gain G may 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 parameters of a treatment session to assess the severity of CSR during the treatment session may be employed in such an embodiment. In other embodiments, the gain G may vary based on the difference between the current ventilation measurement Vent and the target ventilation Vtgt.

[0408] Other servo-ventilation control methods that may be applied by the therapy parameter determination algorithm 4329 include proportional (P), proportional-derivative (PD), and proportional-integral-derivative (PID).

[0409] Pressure support limit A min and A max It is a setting of the RPT device 4000, for example, set by hard coding during configuration of the RPT device 4000 or by manual input through the input device 4220.

[0410] In the pressure support ventilation therapy mode, EPAP is the basic pressure P 0 . Compared with the basic pressure P in CPAP therapy 0 Similarly, the EPAP may be a constant value specified or determined during the titration period. Such a constant EPAP may be set, for example, by hard coding during configuration of the RPT device 4000 or by manual input via the input device 4220. This alternative approach is sometimes referred to as fixed EPAP pressure support ventilation therapy. Titration of a given patient's EPAP may be performed by a clinician with the aid of PSG during a titration period with the goal of preventing obstructive apnea, thereby maintaining a constant pressure P corresponding to the baseline pressure in constant CPAP therapy. 0 The titration is similar to maintaining an open airway for pressure support ventilation therapy.

[0411] Alternatively, the therapy parameter determination algorithm 4329 may repeatedly calculate the basal pressure P during pressure support ventilation therapy. 0 In such an embodiment, the therapy parameter determination algorithm 4329 repeatedly calculates EPAP based on an indicator or metric of sleep disordered breathing, such as one or more of flow limitation, apnea, hypopnea, openness, and snoring, returned by a corresponding algorithm in the therapy engine module 4320. Because the continuous calculation of EPAP is similar to the manual adjustment of EPAP by a clinician during EPAP titration, the process is sometimes also referred to as automatic titration of EPAP, and the therapy mode is referred to as automatically titrating EPAP pressure support ventilation therapy or auto-EPAP pressure support ventilation therapy.

[0412] 4.8.3 High-flow therapy

[0413] In other forms of respiratory therapy, the pressure of the air flow is not controlled as 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 Qd is controlled to a therapeutic or target flow Qtgt. This type of form is generally classified under the heading of flow therapy. In flow therapy, the therapeutic flow Qtgt can be a constant value that is hard-coded or manually entered into the RPT device 4000. If the therapeutic flow Qtgt is sufficient to exceed the patient's peak inspiratory flow, the therapy is generally referred to as high flow therapy (HFT). Alternatively, the therapeutic flow can be a curve Qtgt(t) that varies with the respiratory cycle.

[0414] 4.9 Data Transfer and Collection

[0415] Such as Figure 4A A connected device such as the RPT 4000 in the , or other equipment such as exercise equipment (treadmill or stationary exercise bike) can store and send different levels of data. For example, Figure 4CCentral controller 4230 or an applicable device processor in RPT 4000 may send data to external source 4286. Such data may include data collected by sensors of RPT 4000, such as flow rate sensor 4272 or pressure sensor 4272, data collected by exercise equipment sensors, such as speed and length of exercise, data collected by a computer system, such as frequency and type of user interaction with a user interface; data generated by algorithms of pre-processing module 4310 or other algorithms; or data generated by algorithms of therapy engine module 4320. Such data may be combined for analysis by algorithms that generate more data.

[0416] Fig. 8A A block diagram is shown showing one embodiment 7000 of a system according to the present technology, which may 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 service or system. Thus, in addition to the RPT system, the system and apparatus may also include:

[0417] Exercise and health system

[0418] Electronic exercise equipment including treadmills that output usage data;

[0419] Stationary bike, digital weights;

[0420] Fitness trackers, such as wearables that detect movement, exercise, and other factors; and

[0421] Other exercise and health systems

[0422] Computer systems, software and interfaces

[0423] Websites and software programs that track usage data, including healthcare software used to monitor adherence to CBT programs and other online or software programs;

[0424] Weight loss monitoring applications that monitor things like eating, exercise, food types, and other things that can track usage and other data;

[0425] Computer hardware and software used to coordinate on-demand services, such as on-demand taxi services, where the software and / or hardware can track usage data; and

[0426] Other software and services.

[0427] System 7000 may include device 4000 configured to provide respiratory pressure therapy to patient 1000 or other services to a user, data server 7010, and computing device 7050 associated with patient 1000 or user. Computing device 7050 may be located with user 1000 and device 4000 (such as an RPT device). Fig. 7A In 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 WAN can be wired or wireless. Figure 4C The remote external communication network 4282 is used to identify, and the data server 7010 can be used Figure 4C The computing device 7050 may be a personal computer, a mobile phone, a tablet computer, or other device, and may be incorporated into the various devices disclosed herein. The computing device 7050 may be configured to be between a user (e.g., a patient 1000) and a data server 7010 via a wide area network 7090. In one embodiment, the intermediary is performed by a software application 7060 running on the computing device 7050. The user program 7060 may be a dedicated application referred to as a "user application" that interacts with a supplementary 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 100B, 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). Figure 4C The local external communication network 4284 is used to identify the local network and can be used Figure 4C The local external device 4288 of the user computing device 110 is identified. In an alternative embodiment 7000B, the user patient computing device 7050 is configured via the user program 7060 to be 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 system 7000 may be understood to apply equally to alternative embodiment 7000B, unless explicitly stated otherwise.

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

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

[0433] Device 4000 may be configured to send data to 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 in different situations, as will be explained below. Data server 7010 may receive data from device 4000 according to a "pull" model, whereby device 4000 sends data in response to a query from data server 7010. Alternatively, data server 7010 may receive data according to a "push" model, whereby device 4000 sends data to data server 7010 as soon as possible after a period of time.

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

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

[0436] Usage data can include one or more of the following usage variables:

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

[0438] Apnea-hypopnea index (AHI) for the time period;

[0439] Average leakage flow rate during the period

[0440] The average mask pressure for the time period;

[0441] The number of “sub-periods” in the RPT period, i.e. the number of intervals of RPT treatment between “shield on” and “shield off” events;

[0442] Other statistical summaries of treatment variables, such as 95th percentile pressure, median pressure, and histograms of pressure values;

[0443] Average speed measured by running, cycling or other exercise systems;

[0444] Length of exercise session;

[0445] For example, heart rate or other physiological metrics tracked by a wearable during exercise or other use;

[0446] Repetition frequency;

[0447] Power (speed times weight)

[0448] ● Acceleration;

[0449] Average number of hours of exercise per week;

[0450] Burn calories

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

[0452] Number of mouse clicks per time period;

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

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

[0455] ●Others.

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

[0457] In an alternative embodiment, the device 4000 calculates the usage variables at the end of each period from data stored by the device 4000. The device 4000 then sends the usage variables to the data server 7010 according to the "push" or "pull" model described above.

[0458] In another embodiment, the memory 4260 in which the device 4000 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 suitable for the alternative embodiment 7000B of the system, the device 4000 is configured to transmit the therapy / usage data to the user computing device 7050 via a wireless communication protocol such as Bluetooth described above. The user computing device 7050 then transmits the therapy / usage data to the data server 7010. The data server 7010 may receive the therapy / usage data from the user computing device 7050 according to a "pull" model, whereby the user computing device 7050 transmits the therapy / usage data in response to a query from the data server 7010. Alternatively, the data server 7010 may receive the therapy / usage data according to a "push" model, whereby the user computing device 7050 transmits the therapy / usage data to the data server 7010 as soon as it is available after a period of time.

[0460] In some embodiments, the data server 7010 may perform some post-processing of the usage data, such as with one or more processors in communication with or included in the data server 7010. One example of such post-processing is determining whether the most recent period is a "compliance period." Some compliance rules specify required RPT device usage within a compliance period (such as 30 days) based on a minimum duration (e.g., four hours) of device usage per period for some minimum number of days (e.g., 21 days) within the compliance period.

[0461] A period is considered compliant if the duration of the period exceeds a minimum duration. Usage data post-processing can determine whether the most recent period is a compliant period by comparing the usage duration to the minimum duration from the compliance rules. The result of this post-processing is compliance data, such as a Boolean compliance variable, which forms part of the usage data. Another example of multi-period usage data is a count of compliant periods since the start of an RPT treatment or other type of period.

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

[0463] The data server 7010 is also configured to send an electronic message to the user computing device 7050. The message may be in the form of an email, an SMS message, an automated voice message, or a notification within the user program 7060.

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

[0465] The data server 7010 hosts a process 7020, as described in detail below, which is configured to increase or maintain the user's motivation to continue treatment or continue other services. In broad terms, 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 the most recent treatment session or other type of user session as disclosed herein. The process 7020 then transmits the quality indicator to the user or patient 1000, for example, via a user program 7060 running on the user computing device 7050. The need for increased motivation can be detected by analyzing low-resolution data, and high-resolution data can be obtained to optimize methods for increasing or maintaining patient motivation.

[0466] The patient 1000 or user perceives the therapy or other quality of use indicator as a concise indicator of how their therapy, exercise or other session is progressing. The user or patient 1000 is thereby motivated to stick with their therapy. It is known that tracking and measuring performance can be a strong motivation for people to achieve their goals, and the therapy quality indicator is used as such a performance measure in the case of respiratory pressure therapy.

[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 poorly adjusted patient interface 3000, lack of tolerance for the prescribed level of positive airway pressure sensation, excessive leakage that causes noise or interruptions for the patient or bedside companion, and lack of improvement in subjective well-being. This results in low compliance for the patient 1000, lower compensation and suboptimal health outcomes and higher overall long-term health care costs, as well as additional health care costs in the form of worsening related conditions for non-compliant patients 100. For example, in some countries, patients must meet a minimum level of compliance in order to be reimbursed. Therefore, the inventors have developed techniques for predicting whether a patient 1000 will comply with treatment and automatically intervening to improve compliance and ongoing treatment adherence and utilization.

[0469] As with other systems and services, maintaining user engagement is also key to their success, and identifying patients who are likely to stop using or drop out of services may be critical to intervening before they drop out or significantly reduce their use.

[0470] Specifically, the disclosed techniques and associated apparatus 4000 may enable an automated system that monitors usage to identify a patient 1000 or other user who may be decreasing usage and automatically intervenes, including by notifying a provider or the patient 1000 or user. This provides an opportunity to adjust therapy, exercise, or other related settings, switch to more appropriate equipment, correct any issues the patient 1000 or user may be having with therapy or services, or provide other suggestions to help increase patient 1000 or user compliance and long-term compliance outcomes or service enrollment.

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

[0472] Fig. 9An example of a process is shown for predicting whether a patient or user will reduce or cease use of device 4000. First, patient 1000 may begin a session or service (e.g., RPT therapy session, exercise session) by turning on device 4000, using the device (e.g., wearing the device for a therapy session), and then turning off the device (e.g., and / or removing the mask once completed).

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

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

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

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

[0477] The disclosed technology can utilize various algorithms to determine the percentage chance that a patient 1000 or user will reduce or stop usage (or maintain current usage levels) within a specific time window. The platform can utilize various data sources, including: (1) usage data 9045 (including recent time period and historical usage data and other types of data disclosed above), (2) demographic data 9035 (including the patient's age), 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 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 including data from usage periods within the previous usage time window. For example, the disclosed technology can determine patterns of non-usage days, average usage hours, average usage hours per week, age, engagement with associated online platforms, and other factors. In some examples, these features can be calculated weekly to determine weekly trends for each of these features.

[0479] In some forms of the present technology, these features are then input into various algorithms to output a percentage likelihood that the patient 1000 will reduce usage by a certain amount within a certain time window 9030. For example, the system may 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 trees, random forests, Bayesian networks, support vector machines, neural networks, or probabilistic models may be used to output the probability that the input features will cause the patient 1000 to terminate treatment. In other examples, a combination of machine learning algorithms and algorithms may be used to classify the inputs into usage categories. This may include linear classifiers (logistic regression, bayes classifier), support vector machine, decision tree, boosted tree, random forest, neural network, stochastic gradient descent, nearest neighbor, etc.

[0480] In addition, other machine learning algorithms can be used. In some examples, a decision tree can be used to determine which pre-trained machine learning algorithm to apply. For example, different algorithms can be used depending on the age cohort to which the patient 1000 or user belongs. In other examples, for example, different suppliers or different types of devices 4000 can have different algorithms trained with data from these suppliers. In other examples, the algorithm can output a binary determination of whether the patient 1000 or user is likely to quit, or the amount of the range of use that the patient 1000 or user will likely fit (e.g., 4-2 hours, 2-0 hours, or stop using).

[0481] Next, if the algorithm's output percentage exceeds a threshold 9040, the disclosed technology can output an indication that the patient 1000 or user may be withdrawing or reducing usage within a certain time window. This can include marking the patient 1000 or user on an internal database of medical records, sending a notification to a display 4294 of an associated computing device, server, or apparatus 4000. This will allow a healthcare provider to contact the patient 1000 or user or initiate various action steps discussed below.

[0482] 4.9.2 If the predicted usage is low, then perform intervention steps

[0483] In some forms of the present technology, the notification can trigger an action to improve treatment 9050 or reduce the likelihood that the patient 1000 or user will terminate or reduce treatment or other services. For example, the patient 1000 or user terminal terminates or reduces its use for many reasons, including treatment adaptation challenges, problems related to equipment management, environmental factors, and motivational issues. Some of the following reasons: (1) the size or fit of the patient interface 3000 is not appropriate, (2) the patient 1000 is not accustomed to wearing the RPT device 4000 while sleeping, (3) the patient 1000 has difficulty breathing forced air, (4) a leaking patient interface 3000 that dries out the patient's 1000 nose or mouth, (5) excessive noise, (6) loud exercise equipment, (7) pain or pain, (8) or other.

[0484] Thus, the action steps will best address the reasons why the patient 1000 or user wants to reduce or terminate the treatment or other service. Thus, the disclosed technology may first apply various workflows or algorithms to determine the reasons why the patient 1000 or user may reduce or terminate usage. For example, the disclosed technology may send a notification or request to the display 4294 on the device 4000 that provides a menu or options and requests the patient 1000 or user to indicate which aspects of the treatment or other service the patient 1000 or user does not like or is not effective for.

[0485] The notification may also be a text, an email, a pop-up notification on a mobile device, or other types of notifications. In some examples, according to the probability of termination of treatment or other services, or the classification used, the notification frequency or content may be changed to increase incentives. In some examples, a menu may provide options for common problems that a patient 1000 or a user may select. This may then provide further remedial options to the patient 1000 or user based on the patient 1000 or user's selection, which will attempt to overcome the patient's or user's difficulties with treatment or other services disclosed herein. In some examples, this may include displaying a video to the patient 1000, user, or other content to help the patient 1000 or other user use the device 4000 when the patient 1000 or other user has difficulty using the device 4000.

[0486] In some examples, current technology can use machine learning or other algorithms to estimate the reasons why patients 1000 or users may exit. This can include monitoring periods or certain aspects of the device 400 that are known to increase the chances that patients 1000 or users may terminate treatment. In some examples, the determination that patients 1000 or users can terminate treatment or reduce use will trigger analysis of other metrics that can be analyzed to determine the highest probability reasons for patients 1000 or users to exit. For example, leak flow, noise, respiratory events, sleep scores, and other variables can be analyzed to determine which has the highest deviation from normal, successful patients 1000 or users. Then, the disclosed technology can ask patients 1000 or users questions starting with the reasons for reducing services (e.g., respiratory therapy) identified with the highest probability, and perform appropriate interventions, as described in detail below. In some examples, the determination of possible reasons can take into account demographic information (known that specific age groups have difficulty using devices or their features). The following is a list of action steps that can be taken, as well as monitoring or other algorithms that can automatically determine when to take these steps.

[0487] Changing service settings

[0488] In response to a prompt on the RPT device 4000 or an associated application or software program on the computing device, the patient or clinician 1000 or user may input a selection on the display or via the cloud management system 4294 indicating that there is high leakage from the patient interface, that the patient is having trouble falling asleep or repeatedly waking up during the night, that their sleep disordered breathing is not being effectively treated, or is experiencing other treatment-related issues that are resulting in ineffective treatment. Thus, the current technology may 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 may send instructions to the controller of the RPT device 4000 to implement the changes.

[0489] Tilt pressure when the patient is asleep

[0490] Some patients 1000 marked for reduced usage may indicate that they are uncomfortable at high pressures and do not fall asleep easily (e.g., in response to a notification with a query about their usage). The current technology may then present the patient 1000 with the option to select a “RAMP” feature that implements a protocol on the RPT device 4000 to slowly increase the basal pressure until the patient 1000 falls asleep upon initiating treatment.

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

[0492] Pressure, expiratory pressure relief and therapy mode adjustments

[0493] In some examples, the patient 1000 may wake up frequently, potentially indicating that the therapy settings were not optimal once the patient 1000 fell asleep. In this example, patient notifications and input may be of less value because the patient 1000 may not be consciously aware of the therapy settings while they are asleep. Therefore, certain algorithms (as disclosed herein) may be utilized to identify disturbed sleep, breathing, or other sleep issues and automatically adjust therapy and breathing comfort settings. This may also include other adjustments to therapy modes, including APAP vs. 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 may change the inspiratory pressure delivered to the patient 1000. In other examples, this may be provided as a mode to try the patient 1000, perhaps if the patient 1000 does not know why their therapy is making them uncomfortable.

[0496] humidification

[0497] In some examples, the patient 1000 may 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 may automatically recommend increasing or decreasing the humidification level.

[0498] In other examples, if the patient 1000 provides input that they have dry mouth or dry nose, the current technology may automatically determine whether the leakage flow rate QV exceeds a threshold indicating that humidity should be increased. For example, once the current technology receives input from the patient 1000 indicating that they have dry mouth, the current technology or RTP device 4000 may automatically query or initiate the leakage flow estimate 4316 to determine whether it exceeds a 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 the computing device, the patient or clinician 1000 may input a selection on the display 4294 indicating that their mouth is dry, the fit of the patient interface 3000 is not optimal (e.g., an injury to their face). For example, the patient 1000 may indicate that they feel a leak between the skin and the patient interface 3000, or other issues with the fit of the device 9075, including as described herein. As described above, the leakage flow estimation 4316 module may determine that there is a problem with leakage through the patient interface 3000.

[0501] Thus, the current technology can prompt the patient 1000 to determine if they feel the fit of the patient interface 3000 is wrong, and specifically, if it feels too small or too large. Thus, the current technology can then recommend a replacement patient interface 3000 for the patient 1000 based on the data profile indicating the patient's 1000 current patient interface 3000 and the fit issue.

[0502] In some examples, the current technology may prompt the patient 1000 to indicate uncomfortable portions of the face that are in contact with the patent interface 3000. For example, the current technology may request the patient 1000 to click on a diagram of the face to indicate non-deformable locations around the seal-forming structure 3100, the positioning and stabilizing structure 3300, or other portions of the patient interface 3000. The platform may then recommend an alternative patient interface 3000 based on the uncomfortable locations.

[0503] In some examples, the patient interface 3000 may include sensors on the positioning and stabilizing structure 3300 to determine, for example, how tight the strap is. In some examples, this may include a simple assessment of the tension or pressure between the strap and the head of the patient 1000. This information may be compared to average tension and pressure to provide a recommendation to the patient 1000 to loosen or tighten the positioning and stabilizing structure 3300 or to change the size.

[0504] noise

[0505] Noise is a frequent reason for patients 1000 to discontinue therapy, including at the request of their sleeping partners. In response to a prompt on the RPT device 4000 or an associated application or software program on a computing device, the patient 1000 or clinician may input a selection on the display or cloud software 4294 indicating that the noise is excessive or that their partner perceives the noise to be excessive. In this example, the current technology may perform a diagnostic check to determine if 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 assess whether ambient noise from the RPT device 4000 deviates from average or expected noise levels.

[0507] Thus, the current technology and / or RPT device 4000 may include acoustic sensors that sense ambient noise, noise associated with the RPT device 4000, and other forms of noise. In some cases, a machine learning algorithm may be used to classify the type of noise and identify the level of RPT device 4000-associated noise (or "exhaust" noise and separate it from patient 1000 snoring and other ambient noise) and compare it to standard values. If those values ​​exceed a threshold, the current technology may recommend maintenance, resupply, or other remedial measures for components.

[0508] In other examples, if the patient 1000 indicates that noise is a major problem, the current technology can automatically change the therapy settings within a range and optimize the settings to reduce noise.

[0509] Types of treatment

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

[0511] 4.9.3 Example 1: Treatment Termination Predictor

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

[0513] Feature Set

[0514] In this example, the usage data 9045 is first preprocessed to identify target features for processing by the random forest and logistic regression algorithms. First, the current technique determines the time window and prediction window of the data to be considered. Fig.10 As 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 arrangement of the following data information:

[0515] Date / time stamp;

[0516] · Treatment start time, treatment stop 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 may be output from the RPT device 4000 (e.g., usage data and treatment data), and other portions of the data may come from a provider database). Next, each period of data identified is processed to identify usage features that can be input into the algorithm. For example, the following table shows an example set of usage features determined based on the period data used in the study:

[0521]

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

[0523]

[0524] The data was processed using a logistic regression algorithm trained using prior data of treatments that were actually dropped with real drop data (whatever patient 1000). Through model manipulation, the study revealed that some predictive features included: (1) non-zero use days (periods) ("NZD"), (2) average non-zero use ("NZUse"), and (3) non-zero use standard deviation ("NZSD"). Therefore, in some examples, a logistic regression algorithm can be developed that utilizes these three features or other combinations of features.

[0525] Processing algorithm

[0526] In this study, usage trends based on these features are processed using random forest and logistic regression algorithms to output the probability that each patient 1000 will terminate use within a two-week period. This involves examining the trends of the features on a weekly basis (features for an entire week compared to subsequent weeks 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 prior to the day predicted by the model. Thus, for the training data, for a patient 1000 who ends up terminating treatment, a separate model can be trained using a three-week window of prior usage data that ends: (a) 1 day prior to termination, (b) 2 days prior to termination, and so on, so that 14 models are trained in this case, since the termination prediction window in this case is two weeks.

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

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

[0529] Here is an example of some raw data, with the probability of indicating for each of the 1000 patients (one anonymized patient per column) and whether they actually terminated within two weeks ("true decline"):

[0530]

[0531] The study provides evidence that the disclosed platform can predict treatment termination for patient 1000 with 88%-93% accuracy within a two-week window. These surprising results will be extremely beneficial to health care providers, allowing them to intervene before patient 1000 stops treatment. For example, intervention is more difficult once the patient has actually made the decision to terminate treatment. Therefore, some of the advantages of this technology arise from the fact that termination is predicted rather than monitored or detected. The platform has the potential to predict future low adherence and termination, rather than low use or compliance warnings. This will likely lead to much higher adherence and retention rates, as well as greatly improved outcomes for patient 1000 suffering from sleep disorders.

[0532] 4.9.4 Example 2: Treatment Adherence Predictor

[0533] The disclosed techniques are also used for data sets from healthcare providers to test whether specific linear and logistic regression algorithms can predict whether patients will remain compliant in future time windows. This is advantageous because in some countries, reimbursement depends on past compliance. For example, reimbursement for the next month may depend on the level of compliance meeting a threshold for the previous month (e.g., compliance over the past 28-day period may determine reimbursement for the next 28-day period). In some countries, reimbursement may only be based on compliance 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 comply with the next week, two weeks, three weeks, four weeks, eight weeks, or other time period according to local regulations. In this example, the disclosed technology is used to determine whether compliance can be predicted for the next 28-day period based on the usage data of the past 28 days. Specifically, the disclosed technology predicts whether the average usage of patient 1000 in the next 28-day period is:

[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 of usage between consecutive 4-week intervals is very high (0.9). Therefore, the average usage of the previous four weeks can be used to estimate the usage of the next four-week interval. For example, the following equation is an example of how this 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 over 28 days:

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

[0542] (2) U2: Average usage in the previous week during the first 28 days

[0543] (3) Non-zero days: The number of non-zero usage days in the previous 28 days.

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

[0545] (5) Interval: The number of 28-day intervals 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 in the first model using the following multiple linear regression 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 features may be discarded and the model should be trained for each interval (every 28 day period after startup). The interval data may be obtained from the setup data output by the RTP device 4000 .

[0550] The above model (or additional models) may be trained using data output from the RPT device 4000, profile data, and other patient 1000 data. This includes real historical usage data and other data from various 28 day intervals (in this example). The model may 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 accuracy could be improved between 28-day intervals for some categories:

[0552]

[0553] Therefore, a second model was developed to train the logistic regression algorithm to classify the data into [0.2] and [2, 24] classes. This model can then be applied to predict patients who fall into [0, 2] and [2, 4] from the first model and reclassify them using the second model. The second model uses a logistic regression equation with the same features as above. Using this method increased the accuracy of the predictions and showed the following results for the 28-day interval from week 3 to week 4:

[0554]

[0555] This greatly improves the prediction accuracy for the [0, 2] class. Thus, continued improvements can be made to increase the accuracy of each class, such that the disclosed technique can reliably classify a patient's usage predictor with close to 90% accuracy.

[0556] The most important features identified for adherence prediction included U1, U2, NOZERO_DAYS, SD_NZ, age, and time interval. Less important features (at least in this model) included AHI (Apnea-Hypopnea Index), LEAK (Leak Flow Rate), and Patient App Indicators.

[0557] Example 3 Exercise Adherence Predictor

[0558] The disclosed technology can also be implemented in exercise equipment or other wearable devices that measure exercise, sports or other programs that require patients to adhere to or participate in. The hardware can include exercise equipment (such as a stepper, stationary bicycle 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 notifications about when a user is likely to quit or reduce their use of a device or digital service. For example, when usage data drops or a usage trend is identified, it can be determined that the user is likely to quit exercising, or participate in a physical or other treatment program. In some examples, the data can indicate that the user will reduce use of the wearable device.

[0560] Thus, appropriate interventions may be initiated, including notifications to the user using the exercise equipment or other motivators disclosed herein. For example, a notification may be sent to the user's mobile device, or other interventions may be initiated. Various other interventions may be utilized, including notifications to an application associated with a software program that communicates with the device containing the exercise equipment.

[0561] Various machine learning algorithms can be used to identify users who may have comparable or decreased engagement or adherence, including [attached example algorithms] random forests and logistic regression algorithms. This includes trends in exercise frequency, duration, intensity, and other suitable metrics.

[0562] Example 4 Website Usage / Engagement Predictor

[0563] The disclosed technology can also be implemented to monitor user interactions with a website or software program to predict engagement or compliance with the service or program. The system can include a server, control system, and user device as disclosed herein, and can additionally include a user interface including a touch screen, mouse, keyboard, or other.

[0564] Thus, the system can monitor various usage data output from a user's interaction with a user interface of a particular software program, website, or other application. For example, usage data that can be monitored can include: (1) the amount of time spent browsing a particular site, (2) use of 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 may be used to identify users who are likely to have comparable or reduced engagement or adherence, including [additional example algorithms] random forests and logistic regression algorithms. This includes analyzing usage trends and determining whether a user is likely to reduce engagement or terminate their use of a website or software program.

[0566] Example 5: On-demand service / labor forecasting

[0567] The disclosed technology may also be implemented to monitor user interactions with a software program, such as on a mobile device, computer system, or other device, to determine whether an employee or independent contractor will likely have their employment or services terminated based on their interactions and use of one or more user interfaces of the 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 into the service and be available for rides, deliveries, or other services. Thus, the user's mobile phone and associated software can output usage data including the frequency of logging in / making themselves available, the length of time periods or service availability, the number of service requests satisfied, customer ratings, and other usage data.

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

[0570] 4.10 Glossary

[0571] For purposes of this technical disclosure, one or more of the following definitions may apply in certain forms of the technology. In other forms of the technology, alternative definitions may apply.

[0572] 4.10.1 General

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

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

[0575] For example, the ambient humidity relative to the humidifier may be the humidity of the air directly surrounding the humidifier, such as the humidity within the room that the patient is sleeping in. This ambient humidity may be different from the humidity outside the room that the patient is sleeping in.

[0576] In another example, ambient pressure may be the pressure immediately surrounding or external to the body.

[0577] In some forms, ambient (e.g., acoustic) noise may be considered to be the background noise level in the room the patient is in addition to noise generated, for example, by the RPT device or from a mask or patient interface. Ambient noise may be generated by sources external to the room.

[0578] Automatic Positive Airway Pressure (APAP) Therapy: CPAP therapy in which therapy pressure is automatically adjustable, e.g., from breath to breath, between minimum and maximum limits, 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 approximately constant over the patient's breathing cycle. In some forms, the pressure at the airway entrance will be slightly higher during exhalation and slightly lower during inspiration. In some forms, the pressure will vary between different breathing cycles of the patient, for example increasing in response to detecting an indication of partial upper airway obstruction and decreasing when there is no indication of partial upper airway obstruction.

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

[0581] In the example of a patient breathing, the flow may be nominally positive for the inspiratory portion of the patient's breathing cycle, and therefore negative for the expiratory portion 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 that reaches the patient interface via the air circuit. The ventilation flow Qv is the flow of air leaving the vent to allow flushing of exhaled gases. The leakage flow Q1 is the leakage flow from the patient interface system or elsewhere. The respiratory flow Qr is the flow of air received into the patient's respiratory system.

[0582] Humidifier: The term humidifier shall be deemed to refer to a humidifying device constructed and arranged or configured with a physical structure capable of providing therapeutically beneficial amounts of water (H2O) vapor to an air flow to improve a patient's medical respiratory condition.

[0583] Leakage: The word leakage refers to an unwanted flow of air. In one example, a leak may occur due to an incomplete seal between the mask and the patient's face. In another example, a leak may occur in the return elbow to the ambient environment.

[0584] Noise, conducted (acoustic): Conducted noise in this document refers to the noise brought to the patient through the pneumatic path (such as the air circuit and patient interface and the air therein). In one form, 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 is the noise carried to the patient by the ambient air. In one form, radiated noise can be quantified by measuring the sound power / pressure level of the object in question according to ISO 3744.

[0586] Noise, Ventilation (Acoustic): Ventilation noise in this document refers to the noise generated by the flow of air through any vent, such as the vent holes of a 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 of cmH 2 O, gf / cm 2 and hectopascal. 1cmH 2 0 is equal to 1g-f / cm 2 And about 0.98 hPa (1 hPa = 100 Pa = 100 N / m 2 =1 mbar-0.001 atm). In this specification, unless otherwise specified, pressure is expressed in cmH 2 The units are given in O.

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

[0590] Respiratory Pressure Therapy (RPT): The application of a supply of air to the entrance of the airways at a treatment pressure that is usually positive relative to 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: Synthetic rubber. In this specification, references to silicone refer 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 Wacker. Unless otherwise specified to the contrary, exemplary forms of LSR have a Shore A (or Type A) indentation hardness in the range of about 35 to about 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, an apnea is said to have occurred when the flow drops below a predetermined threshold for a duration of, for example, 10 seconds. An obstructive apnea is said to have occurred when some obstruction of the airway does not allow air to flow despite the patient's efforts. A central apnea is said to have occurred when an apnea is detected due to a reduction or absence of respiratory effort despite a patent airway. A mixed apnea is said to have occurred when a reduction or absence of respiratory effort occurs simultaneously with an obstructed airway.

[0597] Respiratory rate: The rate at which a patient breathes spontaneously, usually measured in breaths per minute.

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

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

[0600] Expiratory portion of the breathing cycle: the period from the start of expiratory flow to the start of inspiratory flow.

[0601] Flow Limitation: Flow limitation will be considered a condition in the 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 breathing cycle, it may be described as inspiratory flow limitation. In the case where flow limitation occurs during the expiratory portion of the breathing cycle, it may be described as expiratory flow limitation.

[0602] Flow-limited inspiratory waveform type:

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

[0604] (ii) M-shape: has 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 shape: has a single local peak at the leading edge followed by a relatively flat section.

[0606] (iv) Inverted chair type: It has a relatively flat portion followed by a single local peak located at the trailing edge.

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

[0608] (i) The patient's respiration decreases by 30% for at least 10 seconds plus an associated 4% desaturation; or

[0609] (ii) The patient's breathing is reduced (but less than 50%) for at least 10 seconds, with associated desaturations or arousals of at least 3%.

[0610] Hyperpnea: Increased flow rate above normal levels.

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

[0612] Patency (Airway): The degree to which the airway is open, or the extent to which the airway is open. The patient's airway is open. Airway patency can be quantified, such that 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 the atmosphere that exists in the lungs at the end of exhalation.

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

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

[0616] Tidal volume (Vt): The volume of air inhaled or exhaled during normal breathing when no additional effort is exerted. In principle, the inspiratory volume Vi (the volume of air inhaled) is equal to the expiratory volume Ve (the volume of air exhaled), so a single tidal volume vt can be defined to be equal to either volume. 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): Duration of the inspiratory portion of the respiratory flow waveform.

[0618] (Expiratory) Time (Te): 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 the respiratory flow waveform.

[0620] Typical recent ventilation: The ventilation value around which recent values ​​of ventilation Vent tend to cluster over some predetermined time scale, ie a measure of the central tendency of recent values ​​of ventilation.

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

[0622] Ventilation (Vent): A measure of the rate at which gases are exchanged by a patient's respiratory system. Measurements of ventilation may include either or both of inspiratory and expiratory flow per unit time. When expressed as volume per minute, this quantity is often referred to as "minute ventilation." Minute ventilation is sometimes expressed simply as volume, understood as volume per minute.

[0623] 4.11 Other notes

[0624] A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent Office patent file or records, but otherwise reserves all copyright rights whatsoever.

[0625] Unless the context clearly indicates and provides a numerical range, it should be understood that each intervening 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 intervening value in the range are broadly included in the present technology. The upper and lower limits of these intermediate ranges may be independently included in the intermediate ranges and are also included in the present technology, but are subject to any explicitly excluded limits in the range. In the case where the range includes one or both of the limiting values, the present technology also includes ranges excluding any one or both of those included limiting values.

[0626] Furthermore, where a value or values ​​are used herein as part of implementation as part of the present technology, it should be understood that such values ​​may be approximate unless otherwise indicated and that such values ​​may be used to any appropriate number of significant digits to the extent permitted or required by practical technical 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 the invention belongs. Although any methods and materials similar or equivalent to those described herein can 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 specific material is identified for configuring a component, obvious alternative materials with similar properties are used as substitutes. In addition, unless otherwise specified, any and all components described herein are understood to be capable of being manufactured and thus can be manufactured together or separately.

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

[0630] All publications mentioned herein are incorporated herein in their entirety by reference, to disclose and describe methods and / or materials as the subject of those publications. Providing the publications discussed herein is only for the disclosures before the filing date of the present application. Anything herein should not be construed as admitting that the present technology is not entitled to the priority of these publications due to previous inventions. In addition, the publication date provided may be different from the actual publication date, which may need to be confirmed separately.

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

[0632] The subject headings used in the detailed description are for the convenience of the reader and should not be used to limit the subject matter that can be found in the disclosure or claims as a whole. 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 only illustrate the principles and applications of the present technology. In some cases, terms and symbols may imply specific details that are not required for practicing the present technology. For example, although the terms "first" and "second" may be used, unless otherwise specified, they are not intended to represent an arbitrary order, but may be used to distinguish different elements. In addition, although the process steps in the 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 be performed simultaneously or even synchronously.

[0634] It is therefore to be understood that numerous modifications may be made to the exemplary embodiments and that other arrangements may be devised without departing from the spirit and scope of the present technology.

Claims

1. A system for treating a respiratory disorder in a patient, the system comprising: a respiratory therapy device configured to output usage data; a memory comprising a machine-readable medium including machine-executable code having instructions stored thereon; as well as A control system coupled to the memory, the control system comprising one or more processors, the control system configured to execute the machine executable code so that the control system: receiving a usage data set for a treatment session of a patient from the respiratory therapy device; identifying a previously stored usage data set for the patient within a past time window, the past time window being divided into a first duration and a second duration; processing the usage data set and the previously stored usage data set with an algorithm to determine a likelihood that the patient will reduce usage of the respiratory therapy device within a future time window, the algorithm comprising a first regression model having corresponding coefficients for scaling corresponding inputs to the first regression model to determine the likelihood that the patient will reduce usage, the first regression model having a plurality of features as inputs, the features comprising an average number of hours of use of the device during the first duration and an average number of hours of use of the device during the second duration; as well as If the likelihood is above a predetermined threshold, an indication is output that the patient may reduce usage.

2. The system according to claim 1, wherein: The usage data is output after each completed treatment session for the patient.

3. The system according to claim 1, wherein: The usage data includes total usage time for a period, as well as date and time stamp data.

4. The system according to claim 1, wherein: The likelihood that the patient will reduce usage includes a likelihood that the patient will cease using the respiratory therapy device.

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

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

7. The system according to claim 1, wherein: The algorithm pre-processes the usage data to determine the number of non-usage days, the average number of usage hours, and the standard deviation of the usage hours.

8. The system according to claim 7, wherein: The algorithms include random forest or logistic regression algorithms.

9. The system according to claim 7, wherein: The algorithm outputs a probability of abandonment for the patient.

10. The system according to claim 7, wherein: The algorithm further pre-processes the usage data to determine weekly trends in non-usage days, average usage hours, and standard deviation of usage hours.

11. The system according to claim 7, wherein: The algorithm is an ensemble of logistic regression models, each of which is trained using a separate previous time window of training data to estimate the probability of abandonment for each day in the future time window.

12. The system of claim 1, wherein: The indication is an alarm, a notification on a patient mobile device, a notification on a provider computing device, or a notification on a display of the respiratory therapy device.

13. The system of claim 1, wherein: Further instructions include instructions sent to a display to depict selectable alternative therapies for the patient including at least RAMP therapy, and wherein each of the alternative therapies is associated with a set of therapy settings for the respiratory therapy device.

14. The system according to claim 13, wherein: The control system is further configured to: receiving patient input including a selectable displayed selection of an alternative therapy by the patient; and Instructions are sent to the respiratory therapy device to change the therapy setting of the respiratory therapy device based on the patient input.

15. The system of claim 1, wherein: Further instructions include instructions sent to a display to depict a selectable alternative patient interface to the patient.

16. The system of claim 15, wherein: The control system is further configured to: receiving patient input, the patient input comprising a selection by the patient of a selectable display of the alternate patient interface; and Instructions are sent to a remote external device to purchase and deliver the patient's selection to the patient.

17. The system of claim 13, wherein: The control system is further configured to: receiving a second usage data set output from the respiratory therapy device; identifying a second previously stored usage data set for the patient within a second past time window, the second past time window having a length equal to the length of the past time window; processing the second set of usage data and the second previously stored set of usage data with the algorithm to determine a likelihood that the patient will reduce usage of the respiratory therapy device within a second future time window; as well as If the likelihood is above a predetermined threshold, an indication is output that the patient may reduce usage.

18. The system of claim 13, wherein: The control system is further configured to: determining whether usage data has been received within a specific time window; and If the control system determines that no usage data has been received within the specific time window, non-usage data is stored that references the specific time window.

19. The system of claim 18, wherein: The specific time window is a 24-hour period.

20. The system of claim 19, wherein: The non-usage data is a non-usage day.

21. The system of claim 1, wherein: The algorithm is selected by the control system from a group of algorithms, each algorithm in the group of algorithms references a type of respiratory therapy device.

22. The system of claim 1, wherein: The algorithm is selected by the control system from a group of algorithms based on a provider operating the respiratory therapy device.

23. The system of claim 1, wherein: The respiratory therapy device is a CPAP.

24. The system of claim 1, wherein: The algorithm is selected based on the patient's demographic information.

25. A method for predicting compliance, the method comprising: receiving, at a control system including one or more processors, a usage data set for a patient output from a respiratory therapy device; identifying, by the control system, a previously stored set of usage data for the patient within a past time window, the past time window being divided into a first duration and a second duration; preprocessing, by the control system, the usage data set and the previously stored usage data set to output a usage feature set; receiving, by the control system, profile data of the patient, the profile data including an age of the patient, a type of respiratory therapy device used by the patient, and a health care provider of the patient; selecting, by the control system, an algorithm based on the profile data; as well as processing, by the control system, the set of features with a selected algorithm to determine a likelihood that the patient will reduce usage of the respiratory therapy device within a future time window, the algorithm comprising a first regression model having corresponding coefficients for scaling corresponding inputs to the first regression model to determine the likelihood that the patient will reduce usage, the first regression model having a plurality of features as inputs, the features comprising an average number of hours of use of the device during the first duration and an average number of hours of use of the device during the second duration; as well as If the likelihood is above a predetermined threshold, an indication is output that the patient may reduce usage.

26. The method according to claim 25, wherein: The algorithm is a set of models, and each model in the set of models estimates the probability that the patient is likely to reduce use on a single day in the future time window, and each model in the set of models comprises a machine learning algorithm that is pre-trained using a training data set from patients with known termination outcomes and a previous time window starting from the day on which the model estimated the probability that the patient would reduce use of respiratory therapy.

27. The method according to claim 25, wherein: The algorithm was trained using data from the group of patients who terminated treatment and the group of patients who did not terminate treatment.

28. A non-transitory machine-readable medium having stored thereon instructions for performing a method comprising machine-executable code which, when executed by at least one machine, causes the machine to: receiving, from a respiratory therapy device, a usage data set for a patient over a past time window, the past time window divided into a first duration and a second duration; retrieving profile data of the patient from a database, the profile data including the age of the patient, the type of respiratory therapy device used by the patient, and the patient's health care provider; processing the usage data set and the profile data with an algorithm to determine a likelihood that the patient will reduce usage of the respiratory therapy device within a future time window, the algorithm comprising a first regression model having corresponding coefficients for scaling corresponding inputs to the first regression model to determine the likelihood that the patient will reduce usage, the first regression model having as inputs a plurality of features, the features comprising an average number of hours of use of the device during the first duration and an average number of hours of use of the device during the second duration, and an age of the patient; as well as If the likelihood is above a predetermined threshold, an indication is output that the patient may reduce usage.

29. The non-transitory machine-readable medium of claim 28, wherein: The usage data includes treatment settings.

30. The non-transitory machine-readable medium of claim 28, wherein: The usage data includes sensor readings output from the respiratory therapy device.

31. A non-transitory machine-readable medium having stored thereon instructions for performing a method comprising machine-executable code which, when executed by at least one machine, causes the machine to: receiving a patient usage data set from a respiratory therapy device; identifying a previously stored usage data set for the patient within a past time window, the past time window being divided into a first duration and a second duration; processing the usage data set and the previously stored usage data set with an algorithm to determine a likelihood that the patient will reduce usage of the respiratory therapy device within a future time window, the algorithm comprising a first regression model having corresponding coefficients for scaling corresponding inputs to the first regression model to determine the likelihood that the patient will reduce usage, the first regression model having a plurality of features as inputs, the features comprising an average number of hours of use of the device during the first duration and an average number of hours of use of the device during the second duration; as well as If the likelihood is above a predetermined threshold, an indication is output that the patient may reduce usage.

32. A system for predicting compliance, the system comprising: a device configured to output usage data; a memory comprising a machine-readable medium including machine-executable code having instructions stored thereon; as well as A control system coupled to the memory, the control system comprising one or more processors, the control system configured to execute the machine executable code so that the control system: receiving a usage data set for a time period of a user from the device; identifying a previously stored set of usage data for the user within a past time window, the past time window being divided into a first duration and a second duration; processing the usage data set and the previously stored usage data set with an algorithm to determine a likelihood that the user will reduce usage of the device within a future time window, the algorithm comprising a first regression model having corresponding coefficients for scaling corresponding inputs to the first regression model to determine the likelihood that the patient will reduce usage, the first regression model having a plurality of features as inputs, the features comprising an average number of hours of use of the device during the first duration and an average number of hours of use of the device during the second duration; as well as If the likelihood is above a predetermined threshold, an indication is output that the user is likely to reduce usage.

33. The system of claim 32, wherein: The usage data is output each time a user completes a session.

34. The system of claim 32, wherein: The usage data includes total usage time for a period, as well as date and time stamp data.

35. The system of claim 32, wherein: The likelihood that the user will reduce usage includes the likelihood that the user will terminate use of the device.

36. The system of claim 32, wherein: The likelihood that the user will reduce usage includes a likelihood that the user will reduce usage below a threshold amount of time per week.

37. The system of claim 32, wherein: The algorithm pre-processes the usage data to determine the number of non-usage days, the average number of usage hours, and the standard deviation of the usage hours.

38. The system of claim 32, wherein: The algorithms include random forest or logistic regression algorithms.

39. The system of claim 32, wherein: The algorithm outputs an abandonment probability for the user.

40. The system of claim 32, wherein: The algorithm further pre-processes the usage data to determine weekly trends in non-usage days, average usage hours, and standard deviation of usage hours.

41. The system of claim 32, wherein: The algorithm is an ensemble of logistic regression models, each of which is trained using a separate previous time window of training data to estimate the probability of abandonment for each day in the future time window.

42. The system of claim 32, wherein: The indication is an alert notification on the user device.

43. The system of claim 32, wherein: The device is a fitness machine.

44. The system of claim 32, wherein: The device is a user interface for a software program.

45. The system of claim 32, wherein: The usage data includes intensity, length, or frequency.

46. ​​A system for predicting compliance, the system comprising: a memory comprising a machine-readable medium including machine-executable code having instructions stored thereon; as well as A control system coupled to the memory, the control system comprising one or more processors, the control system configured to execute the machine executable code so that the control system: Receive the usage data set of the user's time period; identifying a previously stored set of usage data for the user within a past time window, the past time window being divided into a first duration and a second duration; processing the usage data set and the previously stored usage data set with an algorithm to determine a likelihood that the user will reduce usage of the device within a future time window, the algorithm comprising a first regression model having corresponding coefficients for scaling corresponding inputs to the first regression model to determine the likelihood that the patient will reduce usage, the first regression model having a plurality of features as inputs, the features comprising an average number of hours of use of the device during the first duration and an average number of hours of use of the device during the second duration; as well as If the likelihood is above a predetermined threshold, an indication is output that the user is likely to reduce usage.

Images