Methods and apparatus for insomnia

Abstract

A technology system implements processing apparatus, such as one or more server(s) and / or respiratory therapy device(s) (4000), to characterize insomnia such as for comorbid sleep apnea and insomnia (COMISA) subjects. The technology may be implemented with artificial intelligence, such as machine learning. The technology may be configured to receive objective data relating to a user's therapy and / or sleep from sensor(s) associated with the user. The sensor(s) may be in. or associated with, a positive airway pressure (PAP) device. The technology may be configured to receive subjective data relating to the user's sleep. The technology may be configured to input the objective data and subjective data into a classification system or classifier. The classifier may then apply the objective and subjective data to (a) determine key characteristics for patients that distinguish phenotypes of COMISA; and / or (b) distinguish phenotypes of COMISA based on previously7 determined ones of the key characteristics.

Description

RMDDHI-010 METHODS AND APPARATUS FOR INSOMNIA 0. CROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of United States Provisional PatentApplication No. 63 / 683,919, filed August 16, 2024, the entire content of which is incorporated herein by reference. therapy. BACKGROUND OF THE TECHNOLOGY1.1 FIELD OF THE TECHNOLOGY

[0002] The present technology relates to one or more of the screening, diagnosis,monitoring, treatment, prevention and amelioration of respiratory-related disorders. The present technology also relates to medical devices or apparatus, and their use.1.2 DESCRIPTION OF THE RELATED ART1.2.1 Human Respiratory System and its Disorders

[0003] The respiratory system of the body facilitates gas exchange. The nose andmouth form the entrance to the airways of a patient.

[0004] The airways include a series of branching tubes, which become narrower,shorter and more numerous as they penetrate deeper into the lung. The prime function of the lung is gas exchange, allowing oxygen to move from the inhaled air into the venous blood and carbon dioxide to move in the opposite direction. The trachea divides into right and left main bronchi, which further divide eventually into terminal bronchioles. The bronchi make up the conducting airways, and do not take part in gas exchange. Further divisions of the airways lead to the respiratory bronchioles, and eventually to the alveoli. The alveolated region of the lung is where the gas exchange takes place, and is referred to as the respiratory zone. See “Respiratory Physiology”, by John B. West, Lippincott Williams & Wilkins, 9th edition published 2012.

[0005] A range of respiratory disorders exist. Certain disorders may becharacterised by particular events, e.g. apneas, hypopneas, and hyperpneas.

[0006] Examples of respiratory 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.

[0007] Obstructive Sleep Apnea (OSA), a form of Sleep Disordered Breathing(SDB), is characterised by events including occlusion or obstruction of the upper airRMDDHI-010 passage during sleep. It results from a combination of an abnormally small upper airway and the normal loss of muscle tone in the region of the tongue, soft palate and posterior oropharyngeal wall during sleep. The condition causes the affected patient to stop breathing for periods typically of 30 to 120 seconds in duration, sometimes 200 to 300 times per night. It often causes excessive daytime somnolence, and it may cause cardiovascular disease and brain damage. The syndrome is a common disorder, particularly in middle aged overweight males, although a person affected may have no awareness of the problem. See US Patent No.4,944,310 (Sullivan).

[0008] Cheyne-Stokes Respiration (CSR) is another form of sleep disorderedbreathing. CSR is a disorder of a patient's respiratory controller in which there are rhythmic alternating periods of waxing and waning ventilation known as CSR cycles. CSR is characterised by repetitive de-oxygenation and re-oxygenation of the arterial blood. It is possible that CSR is harmful because of the repetitive hypoxia. In some patients CSR is associated with repetitive arousal from sleep, which causes severe sleep disruption, increased sympathetic activity, and increased afterload. See US Patent No. 6,532,959 (Berthon-Jones).

[0009] A range of therapies have been used to treat or ameliorate such conditions.Furthermore, otherwise healthy individuals may take advantage of such therapies to prevent respiratory disorders from arising. However, these have a number of shortcomings.1.2.2 Therapies

[0010] Various respiratory therapies, such as Continuous Positive Airway Pressure(CPAP) therapy, Non-invasive ventilation (NIV) and Invasive ventilation (IV) have been used to treat one or more of the above respiratory disorders.1.2.2.1 Respiratory pressure therapies

[0011] Respiratory pressure therapy is the application of a supply of air to anentrance to the airways at a controlled target pressure that is nominally positive with respect to atmosphere throughout the patient’s respiratory cycle (in contrast to negative pressure therapies such as the tank ventilator or cuirass).

[0012] Continuous Positive Airway Pressure (CPAP) therapy has been used to treatObstructive Sleep Apnea (OSA). The mechanism of action is that continuous positive airway pressure acts as a pneumatic splint and may prevent upper airway occlusion, such as by pushing the soft palate and tongue forward and away from the posteriorRMDDHI-010 oropharyngeal wall. Treatment of OSA by CPAP therapy may be voluntary, and hence patients may elect not to comply with therapy if they find devices used to provide such therapy one or more of: uncomfortable, difficult to use, expensive and aesthetically unappealing.

[0013] Non-invasive ventilation (NIV) provides ventilatory support to a patientthrough the upper airways to assist the patient breathing and / or maintain adequate oxygen levels in the body by doing some or all of the work of breathing. The ventilatory support is provided via a non-invasive patient interface. NIV has been used to treat CSR and respiratory failure, in forms such as OHS, COPD, NMD and Chest Wall disorders. In some forms, the comfort and effectiveness of these therapies may be improved.

[0014] Invasive ventilation (IV) provides ventilatory support to patients that are nolonger able to effectively breathe themselves and may be provided using a tracheostomy tube. In some forms, the comfort and effectiveness of these therapies may be improved.1.2.3 Respiratory therapy Systems

[0015] These respiratory therapies may be provided by a respiratory therapysystem or device. Such systems and devices may also be used to screen, diagnose, or monitor a condition without treating it.

[0016] A respiratory therapy system may comprise a Respiratory Pressure TherapyDevice (RPT device), an air circuit, a humidifier, a patient interface, an oxygen source, and data management.1.2.3.1 Patient Interface

[0017] A patient interface may be used to interface respiratory equipment to itswearer, for example by providing a flow of air to an entrance to the airways. The flow of air may be provided via a mask to the nose and / or mouth, a tube to the mouth or a tracheostomy tube to the trachea of a patient. Depending upon the therapy to be applied, the patient interface may form a seal, e.g., with a region of the patient's face, to facilitate the delivery of gas at a pressure at sufficient variance with ambient pressure to effect therapy, e.g., at a positive pressure of about 10 cmH2O relative to ambient pressure.1.2.3.2 Respiratory Pressure Therapy (RPT) Device

[0018] A respiratory pressure therapy (RPT) device may be used individually or aspart of a system to deliver one or more of a number of therapies described above, such as by operating the device to generate a flow of air for delivery to an interface to the airways. The flow of air may be pressure-controlled (for respiratory pressure therapies)RMDDHI-010 or flow-controlled (for flow therapies such as HFT). Thus, RPT devices may also be configured to act as flow therapy devices. Examples of RPT devices include a CPAP device and a ventilator.1.2.3.3 Air circuit

[0019] An air circuit is a conduit or a tube constructed and arranged to allow, inuse, a flow of air to travel between two components of a respiratory therapy system such as the RPT device and the patient interface. In some cases, there may be separate limbs of the air circuit for inhalation and exhalation. In other cases, a single limb air circuit is used for both inhalation and exhalation.1.2.3.4 Humidifier

[0020] Delivery of a flow of air without humidification may cause drying ofairways. The use of a humidifier with an RPT device and the patient interface produces humidified gas that minimizes drying of the nasal mucosa and increases patient airway comfort. In addition, in cooler climates, warm air applied generally to the face area in and about the patient interface is more comfortable than cold air. Humidifiers therefore often have the capacity to heat the flow of air was well as humidifying it.

[0021] COMISA

[0022] Obstructive sleep apnea and insomnia are the two most common sleepdisorders. These comorbidities can affect a patient’s quality of life, mood, energy, daytime functioning and sleep disturbances. COMISA exists when a patient experiences both sleeping disorders, that is, they suffer from comorbid insomnia and sleep apnea. This condition is a largely understudied and often unknown area of research for companies specialising in one of these areas. The co-occurrence of the two disorders complicates OSA treatment, reducing compliance with PAP therapy in the presence of insomnia when not treated effectively together. The two sleep disorders share some common features but have different pathophysiological mechanisms and need a different approach for treatment.

[0023] As previously mentioned, OSA is repetitive brief closure (apnea) ornarrowing (hypopnea) of the pharyngeal airway during sleep, which can result in the reduction of airflow, commonly causing post-apnoeic arousal from sleep, and then the resumption of airflow. OSA is a result of factors, including having a narrow airway and unstable control of breathing. Having these constant respiratory events and arousal from sleep reduces quality of life, and increases tiredness and daytime sleepiness. TheRMDDHI-010 commonly used index of OSA severity for individuals is the AHI, which represents the average number of respiratory events experienced per hour of sleep. The most effective treatment for OSA is continuous PAP therapy. CPAP therapy stabilises breathing throughout the night, ultimately improving the quality of life for patients by reducing daytime sleepiness.

[0024] Insomnia is frequent and chronic self-reported difficulties initiating sleep,maintaining sleep, and early morning awakenings from sleep. This, in turn, leads to depreciated daytime functioning, mood, and quality of life. It has been estimated that a significant percentage of the general population suffer from chronic insomnia disorder. The medication which is usually prescribed is a sedative-hypnotic medication that is used as both an initial and ongoing treatment for patients. Similar to OSA, insomnia is frequently associated with psychological disorders. Psychological symptoms such as depression and anxiety are commonly reported in adults. Some studies have demonstrated that effectively addressing sleep-disordered breathing (SDB) can lead to an improvement in insomnia.

[0025] The presence of both Obstructive Sleep Apnea (OSA) and insomnia hasbeen termed COMISA. Both OSA and insomnia rank among prevalent sleep disorders, collectively affecting a significant fraction of the global population. These disorders can profoundly affect patient quality of life by impacting mood, energy reserves, and daytime functionality. Despite the prevalence of either condition alone, sleep research has not sufficiently examined how OSA and insomnia interact. The co-occurrence of these two conditions can complicate the therapeutic landscape, leading to diminished adherence to PAP therapy. The disparate pathophysiological underpinnings of OSA and insomnia necessitate tailored treatment strategies. Indeed, while PAP therapy has historically shown promise in alleviating insomnia symptoms in COMISA patients, a structured and holistic approach to this dual affliction remains elusive.

[0026] Co-morbid sleep disorders remain largely uncharted territories in medicalresearch, necessitating a deeper probe into their prevalence and significance within society. The intricacies of these conditions pose unique challenges, as they often intertwine and exacerbate each other, leading to a complex clinical picture. This complexity underscores the importance of developing predictive models capable of early identification of patients at risk of co-morbid sleep disorders. Timely and accurate predictions are paramount, as they hold the potential to revolutionize patient care,RMDDHI-010 steering it towards a more proactive and personalised approach. Early intervention, facilitated by these predictive models, can significantly alter the course of treatment, resulting in improved patient outcomes and substantial reductions in healthcare expenditures. Moreover, a nuanced understanding of these co-morbid conditions can enhance the efficacy of sleep therapy devices, ensuring they are tailored to meet the specific needs of each patient.

[0027] There is significant overlap of symptoms among COMISA patients. Asignificant percentage of OSA patients report insomnia symptoms. The prevalence of insomnia is known to be higher among patients with OSA compared to general populations. The prevalence of OSA is known to be higher among patients with insomnia compared to the general population. It has also been observed that COMISA is also associated with increased risk of mortality over time compared to people with neither condition.

[0028] Current COMISA research has proposed three groups of COMISA patients:1) OSA patients with Sleep Maintenance Insomnia: Those patients with OSA who struggle to stay asleep. For these patients, it is concluded that CPAP will help cure their insomnia; 2) OSA patients with Sleep Onset Insomnia: Those patients with OSA who struggle to fall asleep. Therefore, CPAP will likely cause more sleep-related issues; 3) OSA patients with Sleep Onset Insomnia and Sleep Maintenance Insomnia: Patients with both forms of insomnia.

[0029] There is clear evidence to suggest that treating OSA through PAP therapywill help treat insomnia. Some studies report improved insomnia following PAP therapy in COMISA patients. It has been observed that insomnia symptoms may reduce CPAP adherence and nightly overall adherence. However, many patients with COMISA are sufficiently compliant with CPAP therapy and display improvements in both OSA and insomnia symptoms.

[0030] Other research suggests that COMISA may be treated by CognitiveBehavioral Therapy for Insomnia (CBT-I) in conjunction with PAP therapy; however, CBT-I can have varying effectiveness depending on the type of insomnia and therefore accurate subcategorization of COMISA is crucial.

[0031] Phenotypes have been also been categorized in relation to therapy. Suchphenotypes may include: Phenotype 1, where patients have mild OSA and insomnia. Insomnia complaints predominate issues with OSA, and therefore, therapy such asRMDDHI-010 CBT-I should be used for these groups of patients. Patients may be diagnosed with Phenotype 2, where patients with moderate to severe OSA with maintenance insomnia often have high AHI. They typically respond well to PAP therapy. Patients may also be diagnosed with Phenotype 3, where patients with moderate to severe OSA with insomnia who are non-adherent to PAP therapy. Insomnia is independent of OSA. A variety of treatment options can be used as each patient is extremely unique.

[0032] The prediction of COMISA is still a relatively unexplored area in modernresearch. There is no clear way to identify patients who are likely to have both conditions together. There remains a need for predictive models for COMISA patients. The methodology hinges on crafting a rules-based classification system to distinguish between various COMISA patient phenotypes.2 BRIEF SUMMARY OF THE TECHNOLOGY

[0033] The present technology is directed towards providing medical devices usedin the screening, diagnosis, monitoring, amelioration, treatment, or prevention of sleep related, and / or respiratory, disorders having one or more of improved comfort, cost, efficacy, ease of use and manufacturability.

[0034] Some implementations of the present technology may include apparatus forrespiratory therapy. The apparatus may include a pressure generator configured to generate a flow of air for delivery to a patient interface via a delivery conduit for a respiratory therapy for a patient. The apparatus may include one or more sensors to sense a characteristic of the flow of air. The apparatus may include one or more processors. The one or more processors may be configured to evaluate data, where the data may include one or both of objective data and subjective data. The one or more processors may be configured to classify, such as in a classifier, based on the evaluated data, the patient according to at least one of a plurality of COMISA states. The COMISA states may include at least two different insomnia classifications. The one or more processors may be configured to output a classification determined by the classifying.

[0035] In some implementations, the at least two different insomnia classificationmay include any of a sleep onset insomnia patient class and a sleep maintenance insomnia class. The one or more processors may include a controller of the pressure generator, wherein the controller may be configured to control operation of the pressure generator based on the output classification. The evaluated data may include a pluralityRMDDHI-010 of features including any two or more of, or all of: an apnea-hypopena index (AHI), inspiratory pressure, a 95th percentile pressure, a total number of usage days of a respiratory pressure therapy device, a body mass index (BMI), patient age, a median inspiratory pressure, patient gender, expiratory pressure relief (EPR) mode use or setting, amount of respiratory pressure therapy device usage in the last thirty days, median mask leak amount, on-status of a smooth breathing pressure curve mode of a respiratory pressure therapy device, median inspiratory pressure, a total time amount of use of an EPR mode, EPR mode off-status, an EPR level setting, and detected mask ON and detected mask off events. The evaluation of the data may include comparing values of the plurality of features with one or more threshold values.

[0036] In some implementations, the output classification may include amaintenance state. The classifying of the maintenance state may include an evaluation of any one or more of: an apnea hypopnea index (AHI), inspiratory pressures, a 95th percentile inspiratory pressure, a total number of respiratory pressure therapy device usage days, a body mass index (BMI), patient age, and a median inspiratory pressure. The output classification may include an onset state. The classifying of the onset state may include an evaluation of any one or more of: patient gender, EPR mode use, respiratory pressure therapy device usage amount for a last 30 days, a median mask leak, and on-status of a smooth breathing pressure curve mode of a respiratory pressure therapy device. The output classification may include an onset and maintenance state. The classifying of the onset and maintenance state may include an evaluation of any one or more of: an apnea index (AI), a median expiratory pressure, a mask leak amount, a 95th percentile mask leak amount, and total number of sessions of use of a respiratory pressure therapy device. The one or more processors may be further configured to classify an absence of insomnia state based on the evaluated data. For the classifying of the absence of insomnia state, the one or more processors may be configured to evaluate any one or more of a median inspiratory pressure, a full amount of time of use of an EPR mode, an EPR mode off-status, an amount of usage of a respiratory pressure therapy device in last 30 days, and an EPR level setting.

[0037] Some implementations of the present technology may include a method ofevaluating a patient using apparatus for a respiratory therapy. The method may include controlling a pressure generator to generate a flow of air for delivery to a patient interface via a delivery conduit for a respiratory therapy for the patient. The methodRMDDHI-010 may include operating one or more sensors to sense a characteristic of the flow of air. The method may include evaluating data, where the data may include one or both of objective data and subjective data. The method may include classifying the patient according to one of a plurality of COMISA states. The COMISA states may include at least two different insomnia classifications. The method may include outputting a classification determined by the classifying.

[0038] In some implementations, the at least two different insomnia classificationmay include any of a sleep onset insomnia patient class and a sleep maintenance insomnia class. The controlling of the pressure generator may be based on the output classification. The evaluated data may include a plurality of features including any, one, two or more of, or all of: an apnea-hypopena index (AHI), inspiratory pressure, a 95th percentile pressure, a total number of usage days of a respiratory pressure therapy device, a body mass index (BMI), patient age, a median inspiratory pressure, patient gender, expiratory pressure relief (EPR) mode use or setting, amount of respiratory pressure therapy device usage in the last thirty days, median mask leak amount, on- status of a smooth breathing pressure curve mode of a respiratory pressure therapy device, median inspiratory pressure, a total time amount of use of an EPR mode, EPR mode off-status, an EPR level setting, and detected mask ON events and detected mask off events. The evaluation of the data may include comparing values of the plurality of features with one or more threshold values. The output classification may include a maintenance state. Classifying the maintenance state may include an evaluation of any one or more of, or all of: an apnea hypopnea index (AHI), inspiratory pressures, a 95th percentile inspiratory pressure, a total number of respiratory pressure therapy device usage days, a body mass index (BMI), patient age, and a median inspiratory pressure. The output classification may include an onset state. Classifying the onset state may include an evaluation of any one or more of, or all of: patient gender, EPR mode use, respiratory pressure therapy device usage amount for a last 30 days, a median mask leak, and on-status of a smooth breathing pressure curve mode of a respiratory pressure therapy device. The output classification may include an onset and maintenance state. Classifying the onset and maintenance state may include an evaluation of any one or more of, or all of: an apnea index (AI), a median expiratory pressure, a mask leak amount, a 95th percentile mask leak amount, and total number of sessions of use of a respiratory pressure therapy device. The one or more processors may be furtherRMDDHI-010 configured to classify an absence of insomnia state based on the evaluated data. For classifying the absence of insomnia state, the one or more processors may evaluate any one or more of, or all of, a median inspiratory pressure, a full amount of time of use of an EPR mode, an EPR mode off-status, an amount of usage of a respiratory pressure therapy device in last 30 days, and an EPR level setting.

[0039] Some implementations of the present technology may include a processorreadable medium that may be configured with processor control instructions for controlling one or more processors to execute a method of evaluating a patient using apparatus for a respiratory therapy. The method of the processor control instructions may include any of the aspects of the methods described herein. The one or more processors may comprise one or more servers. The one or more processors may comprise a respiratory pressure therapy device.

[0040] Some implementations of the present technology may include a method forcharacterizing insomnia in COMISA subjects. The method may include receiving objective data relating to a user’s therapy and / or sleep from one or more sensors associated with the user, which one or more sensors may be in, or associated with, a positive airway pressure (PAP) device. The method may include receiving subjective data relating to the user’s sleep. The method may include

[0041] inputting the objective data and subjective data into a classification system.The method may include applying the classification system to the objective data and the subjective data to (a) determine characteristics for patients that distinguish phenotypes of COMISA; and / or (b) distinguish phenotypes of COMISA based on previously determined ones of the key characteristics.

[0042] In some implementations, the objective data may include usage hours, AI,AHI, Leak, mask events, compliance, and EPR levels, inspiratory pressure, Easy Breathe on-status, Cheyne stroke respiration minutes, closed apnea index, or EEG signals. The objective data may include patient demographics, age, BMI, gender, setup date. The subjective data may comprise survey information and sleep diaries. The classification system may be implemented by rules-based classification. The classification system may be implemented by machine learning. Phenotypes for the classification may be onset, maintenance, or onset and maintenance. The machine learning model may be Logistic Regression, feed-forward artificial neural networks with back propagation learning, random forest, stochastic gradient boosting machines,RMDDHI-010 or Artificial Neural Networks. The classification system may be implemented with predictive analytics. The rules-based classification may be implemented with Fuzzy Rule-Based Classification or SVM-Q. The predictive analytics may be naïve bayes, support vector machine, K-Nearest Neighbours, Logistic Regression, or Random Forest.

[0043] Some implementations of the present technology may include a system.The system may include one or more processors. The one or more processors of the system may be configured to receive objective data relating to a user’s therapy and / or sleep from one or more sensors associated with the user, which one or more sensors may be comprised in, or associated with, a positive airway pressure (PAP) device. The one or more processors of the system may be configured to receive subjective data relating to the user’s sleep. The one or more processors of the system may be configured to input the objective data and subjective data into a classification system. The one or more processors of the system may be configured to apply a classification system to the objective data and the subjective data to (a) determine key characteristics for patients that distinguish phenotypes of COMISA; and / or (b) distinguish phenotypes of COMISA based on previously determined ones of the key characteristics.

[0044] In some implementations, the objective data may include usage hours, AI,AHI, Leak, mask events, compliance, and EPR levels, inspiratory pressure, Easy Breathe on-status, Cheyne stroke respiration minutes, closed apnea index, or EEG signals. The objective data may include patient demographics, age, BMI, gender, setup date. The subjective data may include survey information and sleep diaries. The classification system may be implemented with rules-based classification. The classification system may be implemented with machine learning. The phenotypes of the classification may be onset, maintenance, or onset and maintenance. The machine learning model may be or involve Logistic Regression, feed-forward artificial neural networks with back propagation learning, random forest, stochastic gradient boosting machines, or Artificial Neural Networks. The classification system may be implemented with predictive analytics. The rules-based classification may be implemented with Fuzzy Rule-Based Classification or SVM-Q. The predictive analytics may be naïve bayes, support vector machine, K-Nearest Neighbours, Logistic Regression, or Random Forest. The system may further include a PAP machine, configured to generate user data. The system may include a polysomnographyRMDDHI-010 machine, configured to generate user data. The system may be further configured to determine a therapy parameter for operating a respiratory therapy device based on any one or more of the distinguished phenotypes of COMISA and / or the previously determined ones of the key characteristics. The determined therapy parameter for operating a respiratory therapy device may include a pressure setting. The determined therapy parameter for operating a respiratory therapy device may include a flow rate setting. The system may be further implemented to generate a signal for operating the respiratory therapy device based on determined therapy parameter. The system may be further configured to present a therapy option based on any one or more of the distinguished phenotypes of COMISA and / or any one or more of the previously determined ones of the key characteristics. The therapy option may include any one of a PACED breathing therapy and an automated CBT-I therapy. The PACED breathing therapy may be provided by a respiratory therapy device.

[0045] A first aspect of the present technology relates to apparatus used in thescreening, diagnosis, monitoring, amelioration, treatment or prevention of a sleep and / or respiratory disorders, such as insomnia in sleep disordered breathing patients.

[0046] Another aspect of the present technology relates to methods used in thescreening, diagnosis, monitoring, amelioration, treatment or prevention of a sleep related disorders, such as COMISA.

[0047] The disclosed technology may involve apparatus for respiratory therapy.The apparatus may include a pressure generator configured to generate a flow of air for delivery to a patient interface via a delivery conduit for a respiratory therapy for a patient. The apparatus may include one or more sensors to sense a characteristic of the flow of air. The apparatus may include one or more processors. The one or more processors may be configured to evaluate data, comprising one or both of objective data and subjective data. The one or more processors may be configured, such as with a machine learning and / or rules-based classifier, to classify the patient according to one of a plurality of COMISA states, the COMISA states comprising at least two different insomnia classes. The one or more processors may be configured to output a classification determined by the classifying.

[0048] In some implementations, the at least two different insomnia classes mayinclude any of a sleep onset insomnia patient class and a sleep maintenance insomnia class. The one or more processors may include a controller of the pressure generator.RMDDHI-010 The controller may be configured to control operation of the pressure generator based on the output classification. The classifications may be based on any of the features described in more detail herein.

[0049] Some versions of the present technology may include a method ofevaluating a patient using apparatus for a respiratory therapy. The method may include controlling a pressure generator to generate a flow of air for delivery to a patient interface via a delivery conduit for a respiratory therapy for the patient. The method may include operating one or more sensors to sense a characteristic of the flow of air. The method may include evaluating data, comprising one or both of objective data and subjective data. The method may include classifying the patient according to one of a plurality of COMISA states, the COMISA states comprising at least two different insomnia classifications. The method may include outputting a classification determined by the classifying. The at least two different insomnia classifications may include any of a sleep onset insomnia patient class and a sleep maintenance insomnia class. The controlling of the pressure generator may be based on the output classification.

[0050] Some versions of the present technology may include a processor readablemedium configured with program instructions for controlling one or more processors to execute a method of evaluating a patient using apparatus for a respiratory therapy, the method may include any of the methods described herein. In some implementations, the one or more processors may comprise one or more servers. In some implementations, the one or more processors may be part of a respiratory pressure therapy device.

[0051] The methods, systems, devices and apparatus described may beimplemented so as to improve the functionality of a processor, such as a processor of a specific purpose computer, respiratory monitor and / or a respiratory therapy apparatus. Moreover, the described methods, systems, devices and apparatus can provide improvements in the technological field of automated management, monitoring and / or treatment of respiratory conditions, including, for example, sleep disordered breathing.

[0052] Of course, portions of the aspects may form sub-aspects of the presenttechnology. Also, various ones of the sub-aspects and / or aspects may be combined in various manners and also constitute additional aspects or sub-aspects of the present technology.RMDDHI-010

[0053] Other features of the technology will be apparent from consideration of theinformation contained in the following detailed description, abstract, drawings and claims.3 BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present technology is illustrated by way of example, and not by way oflimitation, in the figures of the accompanying drawings, in which like reference numerals refer to similar elements including:3.1 RESPIRATORY THERAPY SYSTEMS

[0055] Fig.1A shows a system including a patient 1000 wearing a patient interface3000, in the form of nasal pillows, receiving a supply of air at positive pressure from an RPT device 4000. Air from the RPT device 4000 is conditioned in a humidifier 5000, and passes along an air circuit 4170 to the patient 1000. A bed partner 1100 is also shown.

[0056] Fig.1B shows a system including a patient 1000 wearing a patient interface3000, in the form of a nasal mask, receiving a supply of air at positive pressure from an RPT device 4000. Air from the RPT device is humidified in a humidifier 5000, and passes along an air circuit 4170 to the patient 1000.

[0057] Fig.1C shows a system including a patient 1000 wearing a patient interface3000, in the form of a full-face mask, receiving a supply of air at positive pressure from an RPT device 4000. Air from the RPT device is humidified in a humidifier 5000, and passes along an air circuit 4170 to the patient 1000.3.2 RESPIRATORY SYSTEM AND FACIAL ANATOMY

[0058] Fig.2 shows an overview of a human respiratory system including the nasaland oral cavities, the larynx, vocal folds, oesophagus, trachea, bronchus, lung, alveolar sacs, heart and diaphragm.3.3 PATIENT INTERFACE

[0059] Fig. 3 shows a patient interface in the form of a nasal mask in accordancewith one form of the present technology.3.4 RPT DEVICE

[0060] Fig. 4A shows an RPT device in accordance with one form of the presenttechnology.

[0061] Fig. 4B is a schematic diagram of the pneumatic path of an RPT device inaccordance with one form of the present technology. The directions of upstream andRMDDHI-010 downstream are indicated with reference to the blower and the patient interface. The blower is defined to be upstream of the patient interface and the patient interface is defined to be downstream of the blower, regardless of the actual flow direction at any particular moment. Items which are located within the pneumatic path between the blower and the patient interface are downstream of the blower and upstream of the patient interface.

[0062] Fig. 4C is a schematic diagram of the electrical components of an RPTdevice in accordance with one form of the present technology.

[0063] Fig. 4D is a schematic diagram of the algorithms implemented in an RPTdevice in accordance with one form of the present technology.

[0064] Fig. 4E is a flow chart illustrating a method carried out by the therapyengine module of Fig.4D in accordance with one form of the present technology.3.5 HUMIDIFIER

[0065] Fig. 5A shows an isometric view of a humidifier in accordance with oneform of the present technology.

[0066] Fig. 5B shows an isometric view of a humidifier in accordance with oneform of the present technology, showing a humidifier reservoir 5110 removed from the humidifier reservoir dock 5130.3.6 BREATHING WAVEFORMS

[0067] Fig. 6 shows a model typical breath waveform of a person while sleeping.3.7 COMISA DATA

[0068] Fig. 7 shows one example of a Patient Reported Outcome Measures ((PROMS) question and answer prompt(s) that may be in user interface screens (e.g., graphic user interface (GUI)) presented on a display by an application (app) such as on a processing device (e.g., smart phone, tablet and / or an RPT) that may be used to assess patient characteristics.

[0069] Fig. 8 is a sequence of example question-and-answer prompt(s) in userinterface screen(s) (e.g., graphic user interface (GUI)) that may be presented on a display by an application (app) such as on a processing device (e.g., smart phone, tablet and / or an RPT), and used for patient onboarding. Such input data may provide subjective and / or objective information for classification of the states described herein.

[0070] Fig. 9 is an example sequence of question and answer prompt(s), that maybe in user interface screens (e.g., graphic user interface (GUI)) presented by the app onRMDDHI-010 a display of a processing device, and may be used for patient follow-up. Such input data may provide subjective and / or objective information for classification of the states described herein.

[0071] Fig. 9A is another example sequence of question-and-answer prompt(s),that may be in user interface screens (e.g., graphic user interface (GUI)) presented by the app on a display of a processing device, such as to received subjective and / or objective information for classification. 3.8 CLASSIFYING COMISA

[0072] Fig. 10 shows one example of a methodology for classifying a sleepmaintenance COMISA state.

[0073] Fig. 11 shows an example methodology for classifying a sleep onsetCOMISA state in patients.

[0074] Fig. 12 is an example methodology for classifying a sleep onset and sleepmaintenance COMISA state.

[0075] Fig. 13 is a schematic for classifying an OSA without insomnia state (i.e.,No Insomnia state).

[0076] Fig. 14 illustrates state categorization labelling according to the classifiedstates for multiple nights (e.g., 7). In this regard, a response to a state detection may trigger a therapy adjustment if a state detection / classification occurs a plurality of times such as several times in a number of nights (e.g., 7) 3.9 MACHINE LEARNING

[0077] Fig.15 shows an example of a methodology for training of a model for statedetection using machine learning.

[0078] Fig. 16 shows an example of a correlation matrix for a state for COMISApatients.

[0079] Fig. 17 shows an example of a correlation matrix for a No insomnia state(OSA only) patients.

[0080] Fig. 18 shows an example of a correlation matrix for a sleep maintenanceCOMISA state.

[0081] Fig. 19 shows an example of correlation matrix for a sleep onset COMISAstate.

[0082] Fig. 20 shows an example of a correlation matrix for a state of both of asleep maintenance COMISA and a sleep onset COMISA.RMDDHI-010

[0083] Fig. 21 shows an example of significant feature coefficients from logisticregression for a non-COMISA state.

[0084] Fig. 22 is an example of significant feature coefficients from logisticregression for sleep maintenance COMISA state patients.

[0085] Fig. 23 is an example of significant feature coefficients from logisticregression for sleep onset COMISA state patients.

[0086] Fig. 24 is an example of significant feature coefficients from logisticregression for sleep onset and sleep maintenance COMISA state patients.

[0087] Fig. 25 is an example of significant feature coefficients from logisticregression for non-Insomnia state patients.

[0088] Fig.26 illustrates example therapy methodologies that may be implementedbased on a classification of the aforementioned states.4 DETAILED DESCRIPTION OF EXAMPLES OF THE TECHNOLOGY

[0089] Before the present technology is described in further detail, it is to beunderstood that the technology is not limited to the particular examples described herein, which may vary. It is also to be understood that the terminology used in this disclosure is for the purpose of describing only the particular examples discussed herein, and is not intended to be limiting.

[0090] The following description is provided in relation to various examples whichmay share one or more common characteristics and / or features. It is to be understood that one or more features of any one example may be combinable with one or more features of another example or other examples. In addition, any single feature or combination of features in any of the examples may constitute a further example.4.1 THERAPY

[0091] The present technology may be applied to a method for treating arespiratory disorder such as with control of applying positive pressure to the entrance of the airways of a patient 1000.4.2 RESPIRATORY THERAPY SYSTEMS

[0092] The present technology may be applied to a respiratory therapy system fortreating a respiratory disorder. A respiratory therapy system may comprise an RPT device 4000 for supplying a flow of air to the patient 1000 via an air circuit 4170 and a patient interface 3000.RMDDHI-0104.3 PATIENT INTERFACE

[0093] A non-invasive patient interface 3000 in accordance with one aspect of thepresent technology comprises the following functional aspects: a seal-forming structure 3100, a plenum chamber 3200, a positioning and stabilising structure 3300, a vent 3400, one form of connection port 3600 for connection to air circuit 4170, and a forehead support 3700. In some forms a functional aspect 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 an entrance to the airways of the patient so as to maintain positive pressure at the entrance(s) to the airways of the patient 1000. The sealed patient interface 3000 is therefore suitable for delivery of positive pressure therapy.4.3.1 Vent

[0094] In one form, the patient interface 3000 includes a vent 3400 constructed andarranged to allow for the washout of exhaled gases, e.g. carbon dioxide.

[0095] In certain forms the vent 3400 is configured to allow a continuous vent flowfrom an interior of the plenum chamber 3200 to ambient whilst the pressure within the plenum chamber is positive with respect to ambient. The vent 3400 is configured such that the vent flow rate has a magnitude sufficient to reduce rebreathing of exhaled CO2 by the patient while maintaining the therapeutic pressure in the plenum chamber in use.

[0096] One form of vent 3400 in accordance with the present technologycomprises 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.

[0097] The vent 3400 may be located in the plenum chamber 3200. Alternatively,the vent 3400 is located in a decoupling structure, e.g., a swivel.4.4 AIR CIRCUIT

[0098] An air circuit 4170 in accordance with an aspect of the present technologyis a conduit or a tube constructed and arranged to allow, in use, a flow of air to travel between two components such as RPT device 4000 and the patient interface 3000 or 3800.

[0099] In particular, the air circuit 4170 may be in fluid connection with the outletof the pneumatic block 4020 and the patient interface 3000. The air circuit may be referred to as an air delivery tube.RMDDHI-0104.4.1 Supplementary gas delivery

[0100] In one form of the present technology, supplementary gas, e.g. oxygen,4180 is delivered to one or more points in the pneumatic path, such as upstream of the pneumatic block 4020, to the air circuit 4170, and / or to the patient interface 3000 or 3800.4.5 RPT DEVICE

[0101] An RPT device 4000 in accordance with one aspect of the presenttechnology comprises mechanical, pneumatic, and / or electrical components and is configured to execute one or more algorithms 4300, such as any of the methods, in whole or in part, described herein. The RPT device 4000 may be configured to generate a flow of air for delivery to a patient’s airways, such as to treat one or more of the respiratory conditions described elsewhere in the present document.

[0102] In one form, the RPT device 4000 is constructed and arranged to be capableof delivering a flow of air in a range of -20 L / min to +150 L / min while maintaining a positive pressure of at least 6 cmH2O, or at least 10cmH2O, or at least 20 cmH2O.

[0103] The RPT device may have an external housing 4010, formed in two parts,an upper portion 4012 and a lower portion 4014. Furthermore, the external housing 4010 may include one or more panel(s) 4015. The RPT device 4000 comprises a chassis 4016 that supports one or more internal components of the RPT device 4000. The RPT device 4000 may include a handle 4018.

[0104] The pneumatic path of the RPT device 4000 may comprise one or more airpath items, e.g., an inlet air filter 4112, an inlet muffler 4122, a pressure generator 4140 capable of supplying air at positive pressure (e.g., a blower 4142), an outlet muffler 4124 and one or more transducers 4270, such as pressure sensors 4272 and flow rate sensors 4274.

[0105] One or more of the air path items may be located within a removable unitarystructure which will be referred to as a pneumatic block 4020. The pneumatic block 4020 may be located within the external housing 4010. In one form a pneumatic block 4020 is supported by, or formed as part of the chassis 4016.

[0106] The RPT device 4000 may have an electrical power supply 4210, one ormore input devices 4220, a central controller 4230, a therapy device controller 4240, a pressure generator 4140, one or more protection circuits 4250, memory 4260, transducers 4270, data communication interface 4280 and one or more output devicesRMDDHI-010 4290. Electrical components 4200 may be mounted on a single Printed Circuit Board Assembly (PCBA) 4202. In an alternative form, the RPT device 4000 may include more than one PCBA 4202.4.5.1 RPT device mechanical & pneumatic components

[0107] An RPT device may comprise one or more of the following components inan integral unit. In an alternative form, one or more of the following components may be located as respective separate units.4.5.1.1 Air filter(s)

[0108] An RPT device in accordance with one form of the present technology mayinclude an air filter 4110, or a plurality of air filters 4110.

[0109] In one form, an inlet air filter 4112 is located at the beginning of thepneumatic path upstream of a pressure generator 4140.

[0110] In one form, an outlet air filter 4114, for example an antibacterial filter, islocated between an outlet of the pneumatic block 4020 and a patient interface 3000.4.5.1.2 Muffler(s)

[0111] An RPT device in accordance with one form of the present technology mayinclude a muffler 4120, or a plurality of mufflers 4120.

[0112] In one form of the present technology, an inlet muffler 4122 is located inthe pneumatic path upstream of a pressure generator 4140.

[0113] In one form of the present technology, an outlet muffler 4124 is located inthe pneumatic path between the pressure generator 4140 and a patient interface 3000.4.5.1.3 Pressure generator

[0114] In one form of the present technology, a pressure generator 4140 forproducing a flow, or a supply, of air at positive pressure is a controllable blower 4142. For example the blower 4142 may include a brushless DC motor 4144 with one or more impellers. The impellers may be located in a volute. The blower may be capable of delivering a supply of air, for example at a rate of up to about 120 litres / minute, at a positive pressure in a range from about 4 cmH2O to about 20 cmH2O, or in other forms up to about 30 cmH2O when delivering respiratory pressure therapy. The blower may be as described in any one of the following patents or patent applications the contents of which are incorporated herein by reference in their entirety: U.S. Patent No. 7,866,944; U.S. Patent No. 8,638,014; U.S. Patent No. 8,636,479; and PCT Patent Application Publication No. WO 2013 / 020167.RMDDHI-010

[0115] The pressure generator 4140 is under the control of the therapy devicecontroller 4240.

[0116] In other forms, a pressure generator 4140 may be a piston-driven pump, apressure regulator connected to a high-pressure source (e.g., compressed air reservoir), or a bellows.4.5.1.4 Transducer(s)

[0117] Transducers may be internal of the RPT device, or external of the RPTdevice. External transducers may be located for example on or form part of the air circuit, e.g., the patient interface. External transducers may be in the form of non- contact sensors such as a Doppler radar movement sensor that transmit or transfer data to the RPT device.

[0118] In one form of the present technology, one or more transducers 4270 arelocated upstream and / or downstream of the pressure generator 4140. The one or more transducers 4270 may be constructed and arranged to generate signals representing properties of the flow of air such as a flow rate, a pressure or a temperature at that point in the pneumatic path.

[0119] In one form of the present technology, one or more transducers 4270 maybe located proximate to the patient interface 3000.

[0120] In one form, a signal from a transducer 4270 may be filtered, such as bylow-pass, high-pass or band-pass filtering.4.5.1.4.1 Flow rate sensor

[0121] A flow rate sensor 4274 in accordance with the present technology may bebased on a differential pressure transducer, for example, an SDP600 Series differential pressure transducer from SENSIRION.

[0122] In one form, a signal generated by the flow rate sensor 4274 andrepresenting a flow rate of the flow of air is received by the central controller 4230.4.5.1.4.2 Pressure sensor

[0123] A pressure sensor 4272 in accordance with the present technology is locatedin fluid communication with the pneumatic path. An example of a suitable pressure sensor is a transducer from the HONEYWELL ASDX series. An alternative suitable pressure sensor is a transducer from the NPA Series from GENERAL ELECTRIC.

[0124] In one form, a signal generated by the pressure sensor 4272 andrepresenting a pressure of the flow of air is received by the central controller 4230.RMDDHI-0104.5.1.4.3 Motor speed transducer

[0125] In one form of the present technology a motor speed transducer 4276 isused to determine a rotational velocity of the motor 4144 and / or the blower 4142. A motor speed signal from the motor speed transducer 4276 may be provided to the therapy device controller 4240. The motor speed transducer 4276 may, for example, be a speed sensor, such as a Hall effect sensor.4.5.1.5 Anti-spill back valve

[0126] In one form of the present technology, an anti-spill back valve 4160 islocated between the humidifier 5000 and the pneumatic block 4020. The anti-spill back valve is constructed and arranged to reduce the risk that water will flow upstream from the humidifier 5000, for example to the motor 4144.4.5.2 RPT device electrical components4.5.2.1 Power supply

[0127] A power supply 4210 may be located internal or external of the externalhousing 4010 of the RPT device 4000.

[0128] In one form of the present technology, power supply 4210 provideselectrical power to the RPT device 4000 only. In another form of the present technology, power supply 4210 provides electrical power to both RPT device 4000 and humidifier 5000.4.5.2.2 Input devices

[0129] In one form of the present technology, an RPT device 4000 includes one ormore 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. The buttons, switches or dials may, in one form, be physically connected to the external housing 4010, or may, in another form, be in wireless communication with a receiver that is in electrical connection to the central controller 4230.

[0130] In one form, the input device 4220 may be constructed and arranged toallow a person to select a value and / or a menu option.4.5.2.3 Central controller

[0131] In one form of the present technology, the central controller 4230 is one ora plurality of processors suitable to control an RPT device 4000.RMDDHI-010

[0132] Suitable processors may include an x86 INTEL processor, a processorbased on ARM® Cortex®-M processor from ARM Holdings such as an STM32 series microcontroller from ST MICROELECTRONIC. In certain alternative forms of the present technology, a 32-bit RISC CPU, such as an STR9 series microcontroller from ST MICROELECTRONICS or a 16-bit RISC CPU such as a processor from the MSP430 family of microcontrollers, manufactured by TEXAS INSTRUMENTS may also be suitable.

[0133] In one form of the present technology, the central controller 4230 is adedicated electronic circuit.

[0134] In one form, the central controller 4230 is an application-specific integratedcircuit. In another form, the central controller 4230 comprises discrete electronic components.

[0135] The central controller 4230 may be configured to receive input signal(s)from one or more transducers 4270, one or more input devices 4220, and the humidifier 5000.

[0136] The central controller 4230 may be configured to provide output signal(s)to one or more of an output device 4290, a therapy device controller 4240, a data communication interface 4280, and the humidifier 5000.

[0137] In some forms of the present technology, the central controller 4230 isconfigured to implement the one or more methodologies described herein, such as the one or more algorithms 4300, or methodologies that may determine or classify COMISA state(s), insomnia state(s), control settings for an RPT, such as for or based on detection of such states or events related thereto, by analysis of stored data expressed 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 an RPT device 4000. However, in some forms of the present technology, some methodologies may be performed by a remotely located device. For example, the remotely located device, such as one or more servers, may determine or classify COMISA state(s), insomnia state(s), control settings for an RPT, such as for or based on detection of such states or events related thereto, by analysis of stored data, such as from any of the sensors described herein or entered input, that may be received from an RPT device at the one or more servers.RMDDHI-0104.5.2.4 Clock

[0138] The RPT device 4000 may include a clock 4232 that is connected to thecentral controller 4230.4.5.2.5 Therapy device controller

[0139] In one form of the present technology, therapy device controller 4240 is atherapy control module 4330 that forms part of the algorithms 4300 executed by the central controller 4230.

[0140] In one form of the present technology, therapy device controller 4240 is adedicated motor control integrated circuit. For example, in one form a MC33035 brushless DC motor controller, manufactured by ONSEMI is used.4.5.2.6 Protection circuits

[0141] The one or more protection circuits 4250 in accordance with the presenttechnology may comprise an electrical protection circuit, a temperature and / or pressure safety circuit.4.5.2.7 Memory

[0142] In accordance with one form of the present technology the RPT device 4000includes memory 4260, e.g., non-volatile memory. In some forms, memory 4260 may include battery powered static RAM. In some forms, memory 4260 may include volatile RAM.

[0143] Memory 4260 may be located on the PCBA 4202. Memory 4260 may be inthe form of EEPROM, or NAND flash.

[0144] Additionally or alternatively, RPT device 4000 includes a removable formof memory 4260, for example a memory card made in accordance with the Secure Digital (SD) standard.

[0145] In one form of the present technology, the memory 4260 acts as a non-transitory computer readable storage medium on which is stored computer program instructions expressing the one or more methodologies described herein, such as the one or more algorithms 4300.4.5.2.8 Data communication systems

[0146] In one form of the present technology, a data communication interface4280 is provided, and is connected to the central controller 4230. Data communication interface 4280 may be connectable to a remote external communication network 4282 and / or a local external communication network 4284. The remote externalRMDDHI-010 communication network 4282 may be connectable to a remote external device 4286, such as one or more servers. The local external communication network 4284 may be connectable to a local external device 4288.

[0147] In one form, data communication interface 4280 is part of the centralcontroller 4230. In another form, data communication interface 4280 is separate from the central controller 4230, and may comprise an integrated circuit or a processor.

[0148] In one form, remote external communication network 4282 is the Internet.The data communication interface 4280 may use wired communication (e.g. via Ethernet, or optical fibre) or a wireless protocol (e.g. CDMA, GSM, LTE) to connect to the Internet.

[0149] In one form, local external communication network 4284 utilises one ormore communication standards, such as Bluetooth, or a consumer infrared protocol.

[0150] In one form, remote external device 4286 is one or more computers, suchas the aforementioned one or more servers, or, for example, a cluster of networked computers. In one form, remote external device 4286 may be virtual computers, rather than physical computers. In either case, such a remote external device 4286 may be accessible to an appropriately authorised person such as a clinician.

[0151] The local external device 4288 may be a personal computer, mobile phone,tablet or remote control.4.5.2.9 Output devices including optional display, alarms

[0152] An output device 4290 in accordance with the present technology may takethe form of one or more of a visual, audio and haptic unit. A visual display may be a Liquid Crystal Display (LCD) or Light Emitting Diode (LED) display.4.5.2.9.1 Display driver

[0153] A display driver 4292 receives as an input the characters, symbols, orimages intended for display on the display 4294, and converts them to commands that cause the display 4294 to display those characters, symbols, or images.4.5.2.9.2 Display

[0154] A display 4294 is configured to visually display characters, symbols, orimages 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 figure “0”, to eight logical signalsRMDDHI-010 indicating whether the eight respective segments are to be activated to display a particular character or symbol.4.5.3 RPT device algorithms

[0155] As mentioned above, in some forms of the present technology, the centralcontroller 4230 may be configured to implement one or more algorithms 4300 expressed as computer programs stored in a non-transitory computer readable storage medium, such as memory 4260. The algorithms 4300 may be generally grouped into groups referred to as modules.

[0156] In other forms of the present technology, some portion or all of thealgorithms 4300 may be implemented by a controller of an external device such as the local external device 4288 or the remote external device 4286. In such forms, data representing the input signals and / or intermediate algorithm outputs necessary for the portion of the algorithms 4300 to be executed at the external device may be communicated to the external device via the local external communication network 4284 or the remote external communication network 4282. In such forms, the portion of the algorithms 4300 to be executed at the external device may be expressed as computer programs stored in a non-transitory computer readable storage medium accessible to the controller of the external device. Such programs configure the controller of the external device to execute the portion of the algorithms 4300.

[0157] In such forms, the therapy parameters generated by the external device viathe therapy engine module 4320 (if such forms part of the portion of the algorithms 4300 executed by the external device) may be communicated to the central controller 4230 to be passed to the therapy control module 4330.4.5.3.1 Pre-processing module

[0158] A pre-processing module 4310 in accordance with one form of the presenttechnology receives as an input a signal from a transducer 4270, for example a flow rate sensor 4274 or pressure sensor 4272, and optionally the pressure-flow curve parameters estimated by the system characterisation algorithm 4305, and performs one or more process steps to calculate one or more output values that will be used as an input to another module, for example a therapy engine module 4320. The pre- processing module 4310 is therefore carried out during therapy with minimal latency between input signals and output signals.RMDDHI-010

[0159] In one implementation of the present technology, the output values includethe interface pressure Pm, the vent flow rate Qv, the respiratory flow rate Qr, and the leak flow rate Ql.

[0160] In various implementations of the present technology, the pre-processingmodule 4310 comprises one or more of the following algorithms: dynamic pressure drop determination 4311, interface pressure estimation 4312, vent flow rate estimation 4314, leak flow rate estimation 4316, and respiratory flow rate estimation 4318.4.5.3.1.1 Dynamic pressure drop determination 4311

[0161] The pressure drop ΔP of gas flow through the air circuit may be a parameterthat is used by the processor or controller to determine and / or control pressure in the patient interface. In this regard, such a pressure drop ΔP is typically a static characterization of the patient circuit 4170 that is typically known such that it is entered into the system or determined with a controlled calibration process. In this regard, it is predetermined (prior to use of the therapy apparatus) and may be used by the therapy device for therapy. Such a pressure drop ΔP may be characterized by a pressure-versus- flow rate curve and will generally remain constant during use of the patient circuit with the RPT.

[0162] In one implementation of the present technology, an interface pressureestimation algorithm 4312 receives as inputs a signal from the pressure sensor 4272 representative of the pressure in the pneumatic path proximal to an outlet of the pneumatic block (the device pressure Pd) and a signal from the flow rate sensor 4274 representative of the flow rate of the airflow leaving the RPT device 4000 (the device flow rate Qd) and provides as an output an estimated pressure, Pm, in the patient interface 3000, which may be taken by the system to be the actual mask therapy pressure.

[0163] In one implementation, the interface pressure estimation algorithm 4312first computes the total flow rate Qt as the device flow rate Qd plus the flow rate of any supplementary gas 4180. The interface pressure estimation algorithm 4312 then applies equation Error! Reference source not found. to estimate the interface pressure Pm as the device pressure Pd minus the air circuit pressure drop ^P at the total flow rate Qt, using the pressure drop characteristic ^P(Q) of the air circuit 4170 or alternatively using the dynamically determined pressure drop to the patient interface ΔPdd-maskas a function of the measure flow rate or total flow rate Qt.RMDDHI-010

[0164] Optionally, with such an estimation, parameter(s) of operation of the RPTdevice may be adjusted, by its controller, based on the estimation. For example, a flow or pressure therapy control parameter, such as for operation of the blower, may be adjusted based on the estimation. Optionally, such an adjusted control parameter may thereafter be applied by the RPT device so as to operate the blower to provide any respiratory therapy described herein based on the adjusted control parameter.4.5.3.1.2 Vent flow rate estimation

[0165] In one implementation of the present technology, a vent flow rateestimation algorithm 4314 receives as an input an estimated pressure, Pm, in the patient interface 3000 from the interface pressure estimation algorithm 4312 and estimates a vent flow rate of air, Qv, from the vent 3400 in the patient interface 3000. The relationship between the vent flow rate Qv and the interface pressure Pm for the particular vent 3400 in use is modelled by the vent characteristic f of equation Error! Reference source not found., which may be provided by the system characterisation algorithm 4305 from its knowledge of the type of patient interface 3000 in use.

[0166] Optionally, with such an estimation, parameter(s) of operation of the RPTdevice may be adjusted, by its controller, based on the estimation. For example, a flow or pressure therapy control parameter, such as for operation of the blower, may be adjusted based on the estimation. Optionally, such an adjusted control parameter may thereafter be applied by the RPT device so as to operate the blower to provide any respiratory therapy described herein based on the adjusted control parameter.4.5.3.1.3 Leak flow rate estimation

[0167] In one implementation of the present technology, a leak flow rate estimationalgorithm 4316 receives as an input the total flow rate Qt from the interface pressure estimation algorithm 4312, the vent flow rate Qv from the vent flow rate estimation algorithm 4314, and provides as an output an estimate of the leak flow rate Ql.

[0168] In one implementation, the leak flow rate estimation algorithm 4316estimates the leak flow rate Ql by calculating a filtered version (e.g., a low-pass filtered version) of the non-vent flow rate (equal to the difference between the total flow rate Qt and the vent flow rate Qv from the vent flow rate estimation algorithm 4314). The time constant of the low-pass filter is sufficiently long to include several respiratory cycles.RMDDHI-010

[0169] In one implementation, the leak flow rate estimation algorithm 4316receives as an input the total flow rate Qt, the vent flow rate Qv, and the estimated pressure Pm in the patient interface 3000 from the interface pressure estimation algorithm 4312, and provides as an output a leak flow rate Ql, by calculating a leak conductance, and determining the leak flow rate Ql to be a function of leak conductance and interface pressure Pm. Leak conductance may be calculated as the quotient of low pass filtered non-vent flow rate and low-pass filtered square root of interface pressure Pm, where the low-pass filter time constant has a value sufficiently long to include several respiratory cycles. The leak flow rate Ql may be estimated as the product of leak conductance and a function, e.g. the square root, of interface pressure Pm.

[0170] In one implementation, the leak flow rate estimation algorithm 4316receives as an input the total flow rate Qt and the device pressure Pd, and provides as an output an estimate of the leak flow rate Ql. The method may be used to implement the leak flow rate estimation algorithm 4316 in one implementation of the present technology.

[0171] The method 12000 starts at step 12010, which applies a filter such as a low-pass filter with a time constant of many respiratory cycles to the device pressure Pd, to obtain a filtered device pressure ^^ ^^. The step 12010 also computes the total flow rate Qt as the device flow rate Qd, optionally plus the flow rate of any supplementary gas 4180, and applies a filter, such as a low-pass filter, e.g. the same low-pass filter as previously mentioned, to the total flow rate Qt to obtain a filtered total flow rate ^^ ^^.

[0172] The next step 12020 finds the bias flow rate Qb at the current filtered devicepressure ^^ ^^ using the pressure-flow curve parameters or a lookup table provided by the system characterisation algorithm 4305. Step 12020 may involve inverting the pressure-flow curve to find the bias flow rate Qb at the current filtered device pressure ^^ ^^. This may be done analytically in the implementations of the technology in which the pressure-flow curve is a quadratic, as in equation Error! Reference source not found.. Alternatively, a lookup table may be created by the system characterisation algorithm 4305, in which values of bias flow rate Qb are tabulated against values of device pressure ^^ ^^ computed using the pressure-flow curve. Step 12020 may then make use of the lookup table to find the bias flow rate Qb.

[0173] Step 12030 then subtracts the bias flow rate Qb from the filtered total flowrate ^^ ^^ to obtain an estimate of the leak flow rate Ql.RMDDHI-010

[0174] Optionally, with such an estimation, an output may be generated. Theoutput may have many forms. In one form, parameter(s) of operation of the RPT device may be adjusted, by its controller, based on the estimation. For example, a flow or pressure therapy control parameter, such as for operation of the blower, may be adjusted based on the estimation. Optionally, such an adjusted control parameter may thereafter be applied by the RPT device so as to operate the blower to provide any respiratory therapy described herein based on the adjusted control parameter. Alternatively, the output may include generating a message (e.g., notification of the leak or recommendation for a specific action to be taken), which is then sent to the user or to a third party, sending data to a remote server etc.4.5.3.1.4 Respiratory flow rate estimation

[0175] In one implementation of the present technology, a respiratory flow rateestimation algorithm 4318 receives as an input the total flow rate Qt, the vent flow rate Qv, and the leak flow rate Ql, and estimates a respiratory flow rate Qr by subtracting the vent flow rate Qv and the leak flow rate Ql from the total flow rate Qt.

[0176] It may be seen that accurate knowledge of the therapy system pressure-flowcharacteristic curve, as provided by the therapy system characterisation algorithm 4305, ripples through to accurate estimation of leak flow rate, vent flow rate, and respiratory flow rate by the algorithms of the pre-processing module 4310, with consequent benefits to the efficacy of the respiratory therapy. The therapy engine module 4320 benefits in particular from accurate estimation of the respiratory flow rate Qr.

[0177] For example, with such an estimation, parameter(s) of operation of the RPTdevice may be adjusted, by its controller, based on the estimation. For example, a flow or pressure therapy control parameter, such as for operation of the blower, may be adjusted based on the estimation. Optionally, such an adjusted control parameter may thereafter be applied by the RPT device so as to operate the blower to provide any respiratory therapy described herein based on the adjusted control parameter.4.5.3.2 Therapy Engine Module

[0178] In one form of the present technology, a therapy engine module 4320receives as inputs one or more of a pressure, Pm, in a patient interface 3000, and a respiratory flow rate of air to a patient, Qr, and provides as an output one or more therapy parameters.RMDDHI-010

[0179] In one form of the present technology, a therapy parameter is a treatmentpressure Pt.

[0180] In one form of the present technology, therapy parameters are one or moreof an amplitude of a pressure variation, a base pressure, and a target ventilation.

[0181] In various forms, the therapy engine module 4320 comprises one or moreof the following algorithms: phase determination 4321, waveform determination 4322, ventilation determination 4323, inspiratory flow limitation determination 4324, apnea / hypopnea determination 4325, snore determination 4326, airway patency determination 4327, target ventilation determination 4328, and therapy parameter determination 4329.4.5.3.2.1 Phase determination

[0182] In one form of the present technology, the RPT device 4000 does notdetermine phase.

[0183] In one form of the present technology, a phase determination algorithm4321 receives as an input a signal representative of respiratory flow rate, Qr, and provides as an output a phase ^ of a current respiratory cycle of a patient 1000.

[0184] In some forms, known as discrete phase determination, the phase output ^is a discrete variable. One implementation of discrete phase determination provides a bi-valued phase output ^ with values of either inhalation or exhalation, for example represented as values of 0 and 0.5 revolutions respectively, upon detecting the start of spontaneous inhalation and exhalation respectively. RPT devices 4000 that “trigger” and “cycle” effectively perform discrete phase determination, since the trigger and cycle points are the instants at which the phase changes from exhalation to inhalation and from inhalation to exhalation, respectively. In one implementation of bi-valued phase determination, the phase output ^ is determined to have a discrete value of 0 (thereby “triggering” the RPT device 4000) when the respiratory flow rate Qr has a value that exceeds a positive threshold, and a discrete value of 0.5 revolutions (thereby “cycling” the RPT device 4000) when a respiratory flow rate Qr has a value that is more negative than a negative threshold. The inhalation time Ti and the exhalation time Te may be estimated as typical values over many respiratory cycles of the time spent with phase ^ equal to 0 (indicating inspiration) and 0.5 (indicating expiration) respectively.

[0185] Another implementation of discrete phase determination provides a tri-valued phase output ^ with a value of one of inhalation, mid-inspiratory pause, and exhalation.RMDDHI-010

[0186] In other forms, known as continuous phase determination, the phase output^ is a continuous variable, for example varying from 0 to 1 revolutions, or 0 to 2^ radians. RPT devices 4000 that perform continuous phase determination may trigger cycle when the continuous phase reaches 0 and 0.5 revolutions, respectively. In one implementation of continuous phase determination, the phase ^^is first discretely estimated from the respiratory flow rate Qr as described above, as are the inhalation time Ti and the exhalation time Te. The continuous phase ^ at any instant may be determined as the half the proportion of the inhalation time Ti that has elapsed since the previous trigger instant, or 0.5 revolutions plus half the proportion of the exhalation time Te that has elapsed since the previous cycle instant (whichever instant was more recent).4.5.3.2.2 Waveform determination

[0187] In one form of the present technology, the therapy parameter determinationalgorithm 4329 provides an approximately constant treatment pressure throughout a respiratory cycle of a patient.

[0188] In other forms of the present technology, the therapy control module 4330controls the pressure generator 4140 to provide a treatment pressure Pt that varies as a function of phase ^^of a respiratory cycle of a patient according to a waveform template ^^^^.

[0189] In one form of the present technology, a waveform determination algorithm4322 provides a waveform template ^(^) with values in the range [0, 1] on the domain of phase values ^^provided by the phase determination algorithm 4321 to be used by the therapy parameter determination algorithm 4329.

[0190] In one form, suitable for either discrete or continuously-valued phase, thewaveform template ^(^) is a square-wave template, having a value of 1 for values of phase up to and including 0.5 revolutions, and a value of 0 for values of phase above 0.5 revolutions. In one form, suitable for continuously-valued phase, the waveform template ^(^) comprises two smoothly curved portions, namely a smoothly curved (e.g. raised cosine) rise from 0 to 1 for values of phase up to 0.5 revolutions, and a smoothly curved (e.g. exponential) decay from 1 to 0 for values of phase above 0.5 revolutions. In one form, suitable for continuously-valued phase, the waveform template ^(^) is based on a square wave, but with a smooth rise from 0 to 1 for values of phase up to a “rise time” that is less than 0.5 revolutions, and a smooth fall from 1RMDDHI-010 to 0 for values of phase within a “fall time” after 0.5 revolutions, with a “fall time” that is less than 0.5 revolutions.

[0191] In some forms of the present technology, the waveform determinationalgorithm 4322 selects a waveform template ^(^) from a library of waveform templates, dependent on a setting of the RPT device. Each waveform template ^(^) in the library may be provided as a lookup table of values ^ against phase values ^. In other forms, the waveform determination algorithm 4322 computes a waveform template ^(^) “on the fly” using a predetermined functional form, possibly parametrised by one or more parameters (e.g. time constant of an exponentially curved portion). The parameters of the functional form may be predetermined or dependent on a current state of the patient 1000.

[0192] In some forms of the present technology, suitable for discrete bi-valuedphase of either inhalation (^^= 0 revolutions) or exhalation (^^= 0.5 revolutions), the waveform determination algorithm 4322 computes a waveform template ^ “on the fly” as a function of both discrete phase ^^and time t measured since the most recent trigger instant. In one such form, the waveform determination algorithm 4322 computes the waveform template ^(^, t) in two portions (inspiratory and expiratory) as follows: ^^ ^ ^ ^, t^ ^ ^ ^ , ^ ^ 0^i t^^^^ ^ ^ ^ ^ ^

[0193] where ^i(t)expiratory portions of thewaveform template ^(^, t). In one such form, the inspiratory portion ^i(t) of the waveform template is a smooth rise from 0 to 1 parametrised by a rise time, and the expiratory portion ^e(t) of the waveform template is a smooth fall from 1 to 0 parametrised by a fall time.4.5.3.2.3 Determination of Inspiratory Flow limitation

[0194] In one form of the present technology, the central controller 4230 executesan inspiratory flow limitation determination algorithm 4324 for the determination of the extent of inspiratory flow limitation.

[0195] In one form, the inspiratory flow limitation determination algorithm 4324receives as an input a respiratory flow rate signal Qr and provides as an output a metric of the extent to which the inspiratory portion of the breath exhibits inspiratory flow limitation.RMDDHI-010

[0196] In one form of the present technology, the inspiratory portion of each breathis identified by a zero-crossing detector. A number of evenly spaced points (for example, sixty-five), representing points in time, are interpolated by an interpolator along the inspiratory flow rate-time curve for each breath. The curve described by the points is then scaled by a scalar to have unity length (duration / period) and unity area to remove the effects of changing breathing rate and depth. The scaled breaths are then compared in a comparator with a pre-stored template representing a normal unobstructed breath, similar to the inspiratory portion of the breath shown in Fig. 6A. Breaths deviating by more than a specified threshold (typically 1 scaled unit) at any time during the inspiration from this template, such as those due to coughs, sighs, swallows and hiccups, as determined by a test element, are rejected. For non-rejected data, a moving average of the first such scaled point is calculated by the central controller 4230 for the preceding several inspiratory events. This is repeated over the same inspiratory events 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 the preceding several inspiratory events, e.g., three events. The moving average of continuously updated values of the (e.g., sixty-five) points are hereinafter called the "scaled flow rate ", designated as Qs(t). Alternatively, a single inspiratory event can be utilised rather than a moving average.

[0197] From the scaled flow rate, two shape factors relating to the determinationof partial obstruction may be calculated.

[0198] Shape factor 1 is the ratio of the mean of the middle (e.g. thirty-two) scaledflow rate points to the mean overall (e.g. sixty-five) scaled flow rate points. Where this ratio is in excess of unity, the breath will be taken to be normal. Where the ratio is unity or less, the breath will be taken to be obstructed. A ratio of about 1.17 is taken as a threshold between partially obstructed and unobstructed breathing, and equates to a degree of obstruction that would permit maintenance of adequate oxygenation in a typical patient.

[0199] Shape factor 2 is calculated as the RMS deviation from unit scaled flowrate, taken over the middle (e.g. thirty-two) points. An RMS deviation of about 0.2 units is taken to be normal. An RMS deviation of zero is taken to be a totally flow–limited breath. The closer the RMS deviation to zero, the breath will be taken to be more flow limited.RMDDHI-010

[0200] Shape factors 1 and 2 may be used as alternatives, or in combination. Inother forms of the present technology, the number of sampled points, breaths and middle points may differ from those described above. Furthermore, the threshold values can be other than those described.4.5.3.2.4 Determination of apneas and hypopneas

[0201] In one form of the present technology, the central controller 4230 executesan apnea / hypopnea determination algorithm 4325 for the determination of the presence of apneas and / or hypopneas.

[0202] In one form, the apnea / hypopnea determination algorithm 4325 receivesas an input a respiratory flow rate signal Qr and provides as an output a flag that indicates that an apnea or a hypopnea has been detected.

[0203] In one form, an apnea will be said to have been detected when a functionof respiratory flow rate Qr falls below a flow rate threshold for a predetermined period of time. The function may determine a peak flow rate, a relatively short-term mean flow rate, or a flow rate intermediate of relatively short-term mean and peak flow rate, for example an RMS flow rate. The flow rate threshold may be a relatively long-term measure of flow rate.

[0204] In one form, a hypopnea will be said to have been detected when a functionof respiratory flow rate Qr falls below a second flow rate threshold for a predetermined period of time. The function may determine a peak flow, a relatively short-term mean flow rate, or a flow rate intermediate of relatively short-term mean and peak flow rate, for example an RMS flow rate. The second flow rate threshold may be a relatively long- term measure of flow rate. The second flow rate threshold is greater than the flow rate threshold used to detect apneas.4.5.3.2.5 Determination of snore

[0205] In one form of the present technology, the central controller 4230 executesone or more snore determination algorithms 4326 for the determination of the extent of snore.

[0206] In one form, the snore determination algorithm 4326 receives as an input arespiratory flow rate signal Qr and provides as an output a metric of the extent to which snoring is present.

[0207] The snore determination algorithm 4326 may comprise the step ofdetermining the intensity of the flow rate signal in the range of 30-300 Hz. Further, theRMDDHI-010 snore determination algorithm 4326 may comprise a step of filtering the respiratory flow rate signal Qr to reduce background noise, e.g., the sound of airflow in the system from the blower.4.5.3.2.6 Determination of airway patency

[0208] In one form of the present technology, the central controller 4230 executesone or more airway patency determination algorithms 4327 for the determination of the extent of airway patency.

[0209] In one form, the airway patency determination algorithm 4327 receives asan input a respiratory flow rate signal Qr, and determines the power of the signal in the frequency range of about 0.75 Hz and about 3 Hz. The presence of a peak in this frequency range is taken to indicate an open airway. The absence of a peak is taken to be an indication of a closed airway.

[0210] In one form, the frequency range within which the peak is sought is thefrequency of a small forced oscillation in the treatment pressure Pt. In one implementation, the forced oscillation is of frequency 2 Hz with amplitude about 1 cmH2O.

[0211] In one form, airway patency determination algorithm 4327 receives as aninput a respiratory flow rate signal Qr, and determines the presence or absence of a cardiogenic signal. The absence of a cardiogenic signal is taken to be an indication of a closed airway.4.5.3.2.7 COMISA Diagnosis and Treatment and / or Insomnia classificationGeneral

[0212] Mechanisms to determine COMISA related states and distinguish betweendifferent phenotypes is difficult. What is proposed here, in part, is a method and apparatus for the diagnosis and / or treatment of COMISA.

[0213] Some implementations of the present technology may detect COMISA,such as the states described herein, by predictive modelling techniques, including rules- based classification and / or Machine Learning (ML) methods. Other modelling techniques have been contemplated and would be known to a person skilled in the art. The automated modelling / classification techniques for COMISA states and / or insomnia states described herein may evaluate data that comprises objective information (e.g., calculated metrics such as based one or more sensor signals) and optionally input subjective information. Subjective information may, for example, be entered as inRMDDHI-010 response to questionaries, such as the questionaries disclosed herein, and may be input to an RPT device or a device linked thereto such as a smart device (e.g., smart phone or tablet, etc.), where such questionaries may be periodically presented to a user of the device(s). Objective information may involve data recording / calculation and event detection using such RPT devices such as any aforementioned RPT detection methodologies. Classification may be made by one or more classifiers operating in an RPT device(s) and / or operating in one or more servers and / or computers / smart device(s), that may be in a communication system, such as with the RPT devices, such that they operate in conjunction. For example, one or more servers (such as a remote external device 4286) in communication with the RPT device, may determine metrics and / or classifications based on input and / or sensor data or data derived from sensor data, that may, at least in part, be provided by RPT device(s), and / or smart device(s) (such as a local external device 4288), to the server(s) over a communications network(s) (e.g., network 4282 and / or network 4284), such as with the smart device acting as part of the communicating in the communications network(s).

[0214] For example, such an automated method, such as classification by machinelearning and / or a rules-based classification, may determine one of several insomnia states or COMISA states such as (a) an absence of insomnia class (e.g., OSA only) (i.e., a non-COMISA state), (b) a sleep maintenance insomnia class (e.g., with OSA and which is also referred to herein as a sleep maintenance COMISA state), (c) a sleep onset insomnia class (e.g., with OSA and which is also referred to herein as a sleep onset COMISA state, and (d) a sleep maintenance and sleep onset insomnia class (e.g., (b) and (c) combined). In response to such classifications, therapy may be modified, which may be dependent on the particularly determined classification. Additional details of such methodologies may be considered in relation to the following examples.

[0215] Such classifications may also take into account multiple nights or sessionsof sleep. For example, as illustrated in Fig.14, a summary classification may be based on classifications from multiple nights or multiple sessions of sleep. In an example, such a process may include examining the labels corresponding to each of the multiple sleep sessions (e.g., 7 nights) and assigning labels as follows:

[0216] • Both: A patient is categorized as Both if Both appears at least once intheir 7-night record or if Onset appears at least once and Maintenance appears at least twice.RMDDHI-010

[0217] • No Insomnia: A patient is labelled as a non-insomniac if No Insomniaappears a minimum of 5 out of 7 nights.

[0218] • Onset: A patient is labelled as Onset if Onset appears a minimum ofonce and Maintenance doesn’t appear in their 7-night labels.

[0219] • Maintenance: A patient is identified with the Maintenance phenotype ifMaintenance is present at least twice and Onset does not feature in their 7-night data.

[0220] Patients who do not meet these criteria may be labelled as None.Data for Classification / Modelling

[0221] The proposed method and apparatus may measure, analyse, or interpretquantitative and qualitative data across a variety of metrics, which may be implemented by any of the aforementioned processors, controllers, external devices, one or more servers previously mentioned and any combinations of them.

[0222] For example, measurements of inspiratory and / or expiratory pressure maybe taken from a CPAP device or other respiratory assessment method or device. The proposed method and apparatus may measure or analyse other respiratory metrics, including tidal volume. Tidal volume is a measurement of air through the lungs each time a patient inhales or exhales. It may also incorporate Easy Breathe, a pressure relief system, such as an expiratory pressure reduction, that offers a more natural breathing comfort in a compact device. Optionally such a device may include a smooth pressure waveform that recreates a patient’s individual breathing pattern.

[0223] Sources of data for analysis (i.e., features for classification) may includethe aforementioned RPT device(s) and / or the external devices such as the one or more servers receiving data from such devices. Such data may include, for example, therapy data, patient data, device settings data, and surveys (e.g., automated questionnaires such as the examples described herein). Other factors that may be evaluated include whether a PAP mask is on / off, (which may for example, be determined by detection of pressure and / or flow changes with a pressure or flow sensor coupled to a mask), BMI, inspiratory pressure (e.g., 95thpercentile), device category, compliance, age, maximum days compliant, mask identification, total usage of CPAP, and CPAP usage in last 30 days. Additional factors may include a particular session number or the total session number, valve leak (e.g., 95thpercentile), the apnea index, the hypopnea index, Cheyne stoke respiration minutes, and the closed apnea index.RMDDHI-010

[0224] The recorded data for each therapy session typically encompassesrespiratory measures of the patient and data relevant to the therapy provided by the PAP or CPAP device. This dataset adopts a time series format, capturing the span of each therapy session from the moment the patient wears their mask to its removal. Therapy data may be transmitted via cloud technology.

[0225] Patient data may include demographic details of each patient, including butare not limited to, Age, Gender, Body Mass Index (BMI), Mask Type, and the Setup Date of treatment and / or monitoring devices. Patient data may be collected from devices or stored / retrieved from databases.

[0226] Device settings data may include settings derived from PAP (e.g., CPAP)machines. Such data may be integral for tailoring therapy to individual patient needs. Notable settings, including but not limited to Expiratory Pressure Relief (EPR) mode, may be included. EPR provides an exhalation relief feature to make patient breathing feel more natural. The proposed method may feature any additional factors described here and above related to CPAP function and use.

[0227] Surveys may be a source of patient-subjective data. Surveys, including e.g.,Patient Reported Outcome Measures (PROMS) surveys, may be designed for patients utilizing PAP devices. Such surveys may collect patient-reported outcomes. Such patient-driven feedback may include surveys, including PROMS results. Questions, as depicted in Fig. 7, may include questions whether symptoms have improved or other changed. Other questions may include whether insomnia was ever a problem, reasons for therapy, and general sleepiness levels. Other questions relevant to ascertaining related criteria may be incorporated.

[0228] By way of further example, an RPT use related Care Check-In / OnboardingSurvey may be implemented with the proposed method and apparatus. As shown in the example of Fig.8, the On-boarding survey may ask a series of questions to help identify or label insomnia patients and build additional COMISA screeners. Such a survey may be presented by the RPT device or an application (app) running on a companion device (e.g., a smart phone or tablet that may be linked to the RPT device). Such questions may include “how were you setup on therapy?”; “what best describes your reason(s) for treatment?”; “which are the sleep problems are currently an issue for you?”; and “have you ever been diagnosed or suspect you may have insomnia?”. Additional care surveys may be periodically provided such as at, e.g., day 14 or day 28 after initialRMDDHI-010 treatment. As further shown in the example of Fig. 9, check-in questions may ask patients questions regarding various metrics related to sleep. Follow-up questions may include assessments of sleepiness levels, improvement in other symptoms, the quality of treatment, and whether materials provided were helpful. The content of subsequent questions may vary based on answer selections. A further example is illustrated in Fig. 9A that is similar to the version of Fig.8. Questions such as "what best describes your reasons for treatment" and "what bothers you most" in relation to a selection of a difficulty falling or staying asleep response to the prior question may be presented. In this regard, a response (e.g., difficulty falling or staying asleep) may trigger a further question (e.g., what bothers you most) with responses that are particular to the prior answer (e.g., difficulty falling or staying asleep). By way of further example, the answer(s) may trigger a further question(s) that may also include "have you ever been diagnosed with or suspect you may have insomnia". Of course, similarly formed questions may be presented regarding the targeted information of the aforementioned quoted questions.

[0229] Other tools, both quantitative and qualitative, may be used in theaforementioned classification(s) for assessing sleep and respiratory disorders including insomnia and sleep apnea. For example, measurements from additional indices such as the Pittsburgh Sleep Quality Index or the Insomnia Severity Index may be incorporated. Sleep Diaries may also be used to assess insomnia. Measurements from the OSA50, STOP-Bang, overnight sleep studies (polysomnography), and others known by those skilled in the art may be used to assess sleep apnea and related sleep and breathing conditions.

[0230] Although examples herein for obtaining input, such as subjective and / orobjective input for classification, may involve a GUI with displayed questions and / or possible answers on a display screen, in some versions input may be obtained using audio, such via a speaker. Thus, a presentation of questions (such as any one or more the questions in Figs.7, 8, 9 and 9a) may be generated by sound, such as a voice asking the questions and / or proposing possible answers to the questions, with or without the GUI display. Responses to the generated sound questions may be received via microphone such as by detection of a spoken answer from a sound signal produced by the microphone and / or by using any other input response such as with a button or screenRMDDHI-010 touch activation associated with a response to a question, such as where the potential responses to the questions are also produced via speaker sound. Rules-Based Classification

[0231] In some implementations, a rules-based classification may include FuzzyRule-Based Classification System (FRBCS) for diagnosing sleep disorders, where symptoms may be represented by linguistic variables to allow for the categorization of specific sleep disorder classes. Such platforms may be implemented in various programming languages, including but not limited to PHP and Python.

[0232] Some implementations may apply methods of classification throughElectroencephalography (EEG) signals. A Rules-Based method may rely on sleep stages defined by EEG waves to directly classify EEG segments (e.g., 30-second segments) after feature extraction. Implementations may employ Support Vector Machine with a quadratic equation (SVM-Q) to classify sleep stages grounded in expert scoring or other scoring methods.

[0233] The methods and apparatus proposed here may use any of these ascombinations of features in a rules-based classification system for COMISA, which may be trained with such features.

[0234] In some implementations of a rules-based classification of COMISA, fourclasses may be assessed: Sleep Maintenance insomnia in OSA patients, Sleep onset insomnia in OSA patients, Both Sleep maintenance and onset insomnia in OSA patients, and OSA patients without insomnia (i.e., No COMISA). Patients may be characterized into such sleep classifications using for example, calculated sleep and awake times. Sleep and awake times may be calculated through the use of mask ON / OFF events. These events may serve as one foundation for the rules-based classification of COMISA or different COMISA phenotypes. Patients may be assumed to be sleeping while wearing their masks. Periods of napping – e.g., sleep that occurs outside of normal sleep times (e.g., daytime) or outside of input, known or learned sleep times, such that it occurs at certain times, such as between predetermined timepoints (e.g., during the day) may be removed from analysis. For example, sleep that occurs during the day for a night sleeper, such as between predetermined times such as 1pm and 4pm may be removed from analysis; however, such short durations of sleep (e.g., less than some short time threshold such as 20 minutes or less) may occur at other intervals and increments.RMDDHI-010

[0235] Fig. 10 shows one example of a methodology for classifying a sleepmaintenance COMISA state. In this example, sleep maintenance COMISA may be classified by removing potential naps, identifying and excluding any rest periods such as between predetermined timepoints that are unlikely to be associated with a normal sleep session as previously discussed. Sleep may be analysed through detection of mask-on / mask-off events. Example criteria for sleep maintenance insomnia may be the occurrence of two or more awakenings during a given sleep session, each lasting for a minimum amount of time (tmin), such as more than 20 minutes or more than 15 minutes, or more than 5 minutes, or other amount of time in a range from, for example, 25 to 5 minutes.

[0236] Fig. 11 shows an example method for classifying a sleep onset COMISAstate in patients. In this embodiment, Sleep onset COMISA state may be classified by removing potential naps as described above. Sleep may be considered throughout the night (or other session when a patient sleeps) where sleep onset COMISA is defined as two or more brief awakenings within an initial period or portion of a sleep session (Tinitial), such as for example, the first 90 minutes of sleep, or the first 60 minutes of sleep, or the first 20 minutes of sleep, or other number of minutes in a range of 0 to 90 minutes, or 0 to 60 minutes. The initial period may begin when the patient puts their mask on for the first time (e.g., as detected by mask on sensing or other input indication of a beginning of a sleep session).

[0237] Fig. 12 illustrates an example method for classifying an onset andmaintenance COMISA state. In this example, a sleep maintenance and sleep onset COMISA state may be classified by removing potential nap periods and measuring the occurrence of two or more awakenings during a given sleep session and experiencing two or more brief awakenings during the initial period or portion of the sleep session as previously described in relation to Fig.11.

[0238] Fig. 13 illustrates an example method for classifying an OSA withoutinsomnia state. In this embodiment, an OSA without insomnia state may be categorized if the patient consistently sleeps a predetermined amount of time (TP), such as an amount of sleep in a range of between 6 and 10 hours per sleep session (e.g. night), such as when using an RPT.

[0239] Fig. 14 illustrates further methods for determining a sleep classification byapplying additional criteria or verification by evaluating additional data such as fromRMDDHI-010 additional sleep sessions data (e.g., 7 to 14 nights,). A verification process may verify that an RPT device being used for at least some predetermined number of sleep sessions, such as nights (e.g., 7), each exceeding some predetermined time, such as a time on the order of minutes or hours (e.g., 4 hours), within the multi-night period (e.g., in a range of 7 to 14-nights). For example, a patient may be categorized as being in a maintenance and onset COMISA state if “both” are detected as existing in at least once in their seven-night record or if Onset appears at least once and maintenance appears at least twice. Similarly, a patient may be categorized as an onset COMISA state if “onset” appears a minimum of once and maintenance does not appear in the seven-night record. In yet another example, a patient may be categorized as maintenance COMISA if “maintenance” is present at least twice and “onset” does not feature within the seven- night record. Finally, a patient may be categorized as in a no insomnia state if “no insomnia” appears a minimum of five out of seven nights.

[0240] In some implementations, additional data assessment(s) may include anApnea Index (AI) or an Apnea-Hypopnea Index (AHI). The AHI represents the average number of apneas and hypopneas a patient experiences during sleep. The AHI is commonly calculated by dividing the total number of apneic and hypopneic events by the total number of hours slept. Comparisons between baseline AHI may also be used to distinguish phenotypes. Some implementations may measure or analyse the Cheyne Stokes’ respiration across various COMISA patient groups. Another aspect of the example may examine mask leak, which is an unintended escape of air between the mask and the patient’s face. Mask leak may be different between phenotypes. Such leaks can substantially compromise therapeutic efficacy. Another aspect of the embodiment may examine the respiratory rate.

[0241] Some implementations may further incorporate the use of subjective data,such as patient surveys. PROMS surveys as described above and in Fig. 7 and survey questions as described above and in Fig. 8-9 may be executed and evaluated for the classification. Patients may be asked reasons for therapy. Patients may be subdivided by PROMS results in distinct categories. For example, patients may be grouped into patients who did not experience sleepiness initially, patients who experienced sleepiness but showed improvement, and patients who remained consistently sleepy. 4.15 Machine LearningRMDDHI-010

[0242] Machine Learning (ML) algorithms with some or all of the aforementioneddata may also be used to analyse or validate data or analysis such as for determining any of the classifications / states described herein. Examples of Machine learning models include, but are not limited to, Logistic Regression (LR), feed-forward artificial neural networks with back propagation learning, random forest, stochastic gradient boosting machines (GBM), and Artificial Neural Networks (ANN). Such models of ML are well- characterized and would be known to a person skilled in the art and are thus not further defined here. Other examples and applications of ML are contemplated and would be known to a person skilled in the art. Training of ML algorithms may be performed with subsets of problem data to validate the algorithm or other related reasons. Thus, the determining of the classifications and generation of output (e.g., therapy described herein), including or based on the classification(s), and may be implemented by an artificial intelligence COMISA classification system, such as with machine learning. The system may distinguish between various COMISA patient phenotypes and may generate output such as for a therapy response as described herein. The system may then learn from the success or failure of the therapy and / or classification, such as with patient feedback as further update training input, to improve / revise the classification models and / or therapy outputs based on the data attributable to the success and / or failure or the previously machine classified patients.

[0243] The present technology may employ Predictive Analytics, including NaïveBayes, Support Vector Machine, K-Nearest Neighbours, Logistic Regression, and Random Forest.

[0244] Naive Bayes uses a supervised learning algorithm based on Bayes’ theoremwith the “naive” assumption of conditional independence between each feature given the class variable. This algorithm requires very little training data to estimate the necessary parameters.

[0245] Support Vector Machine is a supervised ML algorithm that is used mainlyfor classification problems. Each data point is plotted in n-dimensional space (where n is the number of features), with the value being the coordinate point. The classification is formed by finding the optimal hyper-plane that differentiates the two classes, whereby this hyper-plane divide forms the classification.

[0246] K-Nearest Neighbours is also a supervised ML algorithm that can be usedfor classification and regression. The ’K’ denotes the number of nearest neighbours toRMDDHI-010 a new variable that has to be classified. Based on the K-surrounding neighbours, the algorithm forms its classification based on the attributes that are already classified previously in the data set.

[0247] Logistic Regression uses a predictive analysis that estimates / models theprobability of an event occurring based on a given dataset. This can contain independent variables or predictors and their corresponding dependent variables.

[0248] Random Forest combines the output of multiple decision trees to reach asingle result. It can handle both classification and regression problems. This includes hyperparameters such as the number of trees to build, features, leaves required to split an internal node, and maximum leaf nodes in each tree.

[0249] Post-training, the model’s coefficients can be extracted to understand theimportance and influence of each feature on the predicted outcome. These coefficients provide insights into each feature’s positive or negative impact on the dependent variable. In this case, it was initially performed for COMISA vs No Insomnia (OSA only). Then, it was split up into 4 classes: Onset, Maintenance, Both and No Insomnia. 4.16 Validation of Machine Learning

[0250] The proposed method and apparatus may incorporate mechanisms ofvalidation and cross-validation. For example, to ensure that the Logistic Model does not overfit the training data and retrained generalisability, cross-validation techniques have been employed. Splitting the dataset into multiple training and validation sets allows for the ability to assess a model’s performance across various data subsets, ensuring its robustness. Cross-validation may primarily be used in settings where the goal is prediction and one wants to estimate the accuracy of a predictive model in practice. In one embodiment, the dataset is divided into k subsets, known as folds. For each fold, the model is trained using k-1 of the folds. The resulting model is validated on the remaining fold.

[0251] The rules system implemented has been compared to the findings from theexisting reviewed literature. Each rule has empirical evidence backing it from reputable research studies.

[0252] For example, Sleep Onset in the literature has been correlated with sleep-onset latency longer than 60 minutes. Such findings may underscore the 60-minute threshold as a point where sleep-onset latencies beyond this duration might not be directly predictive. Other findings from the literation indicate a significant correlationRMDDHI-010 between the body’s maximum rate of decline (MROD) in temperature and sleep onset. Specifically, the MROD occurred on average 60 minutes prior to sleep onset during the baseline night. This physiological relationship suggests that there’s a biologically relevant 60-minute window preceding sleep initiation, further validating the selected threshold. Therefore, in some implementations, a 60-minute threshold may be applied for classifying a sleep onset state but other durations may be used.

[0253] A Sleep Maintenance COMISA state classification may be defined byexperiencing two or more awakenings during the night, each lasting at least a minimum time or greater (≥tmin), such as 20 minutes or longer. Other findings describe sleep maintenance insomnia as the difficulty in sustaining uninterrupted sleep throughout the night. Typically, this involves waking up one or more times and encountering challenges in resuming sleep for periods between e.g., 20 to 30 minutes. Such fragmented sleep may lead to a reduction in both sleep duration and quality, resulting in a heightened likelihood of daytime drowsiness or lethargy.

[0254] In classifying both Sleep Onset and Sleep Maintenance as a state, anindividual facing both sleep onset and maintenance may have the threshold in place of typically taking over an initial time (Tinitial), such as 60 minutes, to fall asleep (onset) and once asleep, they often wake up multiple times (maintenance). Therefore, using a combination of the thresholds outlined above may indicate that patients may display both sleep onset and sleep maintenance throughout the night so as to be classified into an onset and maintenance state.

[0255] Finally, a patient without insomnia may suffer from reduced levels of sleep.Current recommendations by researchers and sleep physicians suggests that most adults need 7 to 9 hours, although some people may need as few as 6 hours or as many as 10 hours of sleep each day. A No insomnia classification may be defined by sleep duration criterion of, for example, 360 to 600 minutes. Moreover, chronic insomnia may be characterised by disturbances occurring a minimum of 3 nights weekly. A No Insomnia classification may require at least 5 nights of uninterrupted, ‘ideal’ sleep duration within the week. 4.17 Training

[0256] Two examples of algorithms considered for model training during thisphase may include Random Forest (RF) and Logistic Regression (LR) although other algorithms may be contemplated. After evaluating models through cross-validation,RMDDHI-010 Logistic Regression (LR) may be chosen for further classification tasks since it may allow for additional directionality of coefficients which RF lacked. Through the process from Fig. 15, binary classification may be performed using the predefined labels to understand the features for COMISA and No Insomnia. Classifying data into one of four classes or states – Both, Onset, Maintenance, or No Insomnia reveals feature importance across the prediction of the rules-based labelled patients. This step aids in, among other things, understanding which variables (or features) are most pivotal in determining the class labels, offering insights into the nature of the data and potentially leading to improved data collection or feature engineering for making classifications.

[0257] Performance Metrics: relevant metrics including accuracy, precision, andF1 score may be monitored. These metrics may provide insight into both the model’s ability to correctly classify COMISA patients and its proficiency in minimizing false positives and negatives.

[0258] Feature Importance Analysis: Post model training, analysis of featureweights may be conducted to understand which patient characteristics may hold the most predictive power (i.e., significant features or factors). This can operate as a validation check and provide ordered clinical insights into key factors influencing COMISA.

[0259] Integration of Patient Responses: The validation process may include acomparison of model results with actual patient feedback. Outcomes (along with the Rules-based classification) may be compared to real-world experiences and perceptions. Discrepancies between the classification results and the patient-reported experiences with insomnia may be analysed to yield additional information. This feedback loop ensures a layer of qualitative validation of the quantitative metrics.

[0260] In this example, there are four main areas which are explored in thisintegration but other areas may be implemented. This includes patients’ responses in regard to their improvement levels since starting PAP therapy in relation to insomnia. Fig.7 depicts an example of a question asked in a PROMs survey. Secondly, an analysis may be conducted into the percentage of patients who said that insomnia has never been a problem for them. This validation allows a comparison between the patients who said insomnia was never a problem and those patients who have been labelled as No Insomnia. Additionally, patient sleepiness levels may be considered, which include patients characterized as either ’Not sleepy to begin with’, ’Sleepy with improvement’RMDDHI-010 or ’Sleepy with no improvement’. These results allow for additional cross-validation with the results to understand patients’ improvement levels across COMISA groups and the percentage of patients who were not initially considered sleepy. Finally, another patient validation response can be analysed by considering the PROMS patient’s ’Reasons for Therapy’. Particularly, an analysis has been compared across groups for which patients listed ’Restless Sleep’ as a reason for therapy. This aids in identifying the patients who are experiencing difficulties during the night with sensations of restlessness. Readouts and outputs

[0261] Outputs, in additional to classification labels, may include charts depictingdescriptive data, including, but not limited to, mean, median, mode. Similar charts may depict other explorative data and ML coefficients to provide holistic view of data.

[0262] Factors to distinguish COMISA phenotypes comprises any one or more ofage, body mass index (BMI), gender, expiratory and inspiratory pressure, apnea index (AI), apnea hypopnea index (AHI), Cheyne-Stoke Respiration Minutes, Mask Leak, Respiratory Rate, and other factors, including patient-driven feedback. Other factors have been described above and may include other relevant factors known to a person skilled in the art.

[0263] Outputs may include a summary table that provides a comprehensive viewof descriptive statistics for variables / features present. These variables / features may be grouped by distinct sleep classifications. Descriptive statistics such as mean, median, and standard deviation may be evaluated and compared across classifications. Additional statistical analysis would be known to a person skilled in the art and not expanded upon here. Other methods and representations of data and presentation not described here are considered and would be known to a person skilled in the art.

[0264] Outputs may include correlation coefficients within or between distinctsleep categories. Results may be displayed in the form of matrices. This analysis allows for the discernment of potential relationships among variables, especially within each sleep category. Such analysis may offer insight into how variables / features interact differently depending on the data and classification.

[0265] For example, COMISA may be distinguished from No Insomnia (OSAonly) phenotypes through examination of correlation coefficients. Fig. 16 and Fig. 17 depict correlation coefficients across a variety of variables for COMISA and OSA,RMDDHI-010 respectively. Variables / features may be among those described above or others not presented here. In another example, Fig.18 shows a correlation matrix for maintenance patients. In yet another example, Fig. 19 shows a correlation matrix for onset patients. Finally, Fig.20 shows a correlation matrix for maintenance and onset patients.

[0266] Datasets may be used to track insomnia versus no insomnia and determinethe most influential features for predicting the presence of insomnia. Fig.21 is just one example of an analysis that may show the significant features (or feature coefficients from logistic regression) for non-COMISA patients. The results may be produced for a binary setup as depicted here but other setups may be incorporated. 4.19 Logistic Regression

[0267] Analysis may include logistic regression of feature importance for theclasses. Logistic regression may be selected because it allows for coefficient directionality but other methods may be applied. Results may be normalised or standardized to a scale with characteristic values shown on the plots.

[0268] As shown in Fig.22, significant feature(s), such as feature coefficients fromlogistic regression, for maintenance state classification may include any one or more, or all of, an apnea hypopnea index (AHI), inspiratory pressures (e.g., a 95thpercentile inspiratory pressure), total number of RPT device usage days, body mass index (BMI), patient age, and median inspiratory pressure. As shown in Fig.23, significant feature(s), such as feature coefficients from logistic regression, for onset state classification may include any one or more, or all of, patient gender, use of an expiratory pressure relief (EPR) mode, RPT device usage amount in the last 30 days, median mask leak, and Easy Breath (a smooth pressure curve delivery mode from a respiratory pressure therapy device) on-status. As shown in Fig. 24, significant feature(s), such as feature coefficients from logistic regression, for onset and maintenance state classification may include any one or more, or all of, apnea index (AI), median expiratory pressure, mask leak (a 95thpercentile mask leak), and a total number of sessions with an RPT device.

[0269] Finally, as shown in Fig. 25, significant feature(s), such as featurecoefficients from logistic regression, for no insomnia (OSA only) state classification may include any one or more, or all of, a median inspiratory pressure, the full amount of time of use of EPR mode, the EPR mode off-status, usage in last 30 days, and EPR level two. Such features may be applied in one or more classifiers for classifying the different COMISA phenotypes as described herein or otherwise evaluated byRMDDHI-010 comparisons of the values of such features with thresholds indicative of, or contraindicative of, the pertinent states or classes. COMISA based Therapy

[0270] The method and apparatus described herein may be used to direct treatmentregimens for COMISA and related sleep and breathing disorders, such as by automating the state detection(s) and generating one or more signals for controlling or setting (or changing a setting of) an operation of a therapy device, such as a respiratory therapy device, based on the state detection(s). Such an operation may be a provision of therapy, or change in therapy, based on a detection of a state or state(s). Fig.26 shows examples of treatment methodology for COMISA phenotypes described herein. As depicted, treatment options that may be triggered by the state detections may focus on combinations of CBT-I (such as an electronic presented therapy) and PAP, but other treatment modalities may be directed by the COMISA characterization methods described herein. For example, a PAP device may adjust a treatment pressure to support a particular insomnia classification, such as by providing initial lower pressure for insomnia patients with onset issues. Similarly, breathing exercises for relaxing such patients, which may in part be instructed with generated output from an RPT or an application running on a device such as a smart phone or tablet, that may be paired for operations with an RPT, such as pressure based breathing exercises or PACED breathing, may be provided as part of automated CBT-I for such patients with onset issues. For example, in the event of a detection / classification of a sleep onset COMISA state, an RPT, monitoring server, and / or a linked device, may be triggered to present the patient with a CBT-I therapy such as on a display screen of a user device (e.g., RPT screen and / or smart phone screen etc.) and / or with generated audio (such as with a speaker of the user device) and continue with such a therapy or other therapy (e.g., PAP) based on one or more further state detections or an absence of such state detection (e.g., no sleep onset state classification). Similarly, in the event of a detection / classification of a sleep maintenance COMISA state, an RPT, monitoring server, and / or a linked device, may be triggered to adjust a therapy provided by a PAP device, and may also provide a CBT-I therapy as previously described in the event of continued detection of the sleep maintenance state, or further adjust a change to a PAP therapy in the event of a subsequent detection of an absence of the sleep maintenance state. By way of further example, in the event of detection of a sleep maintenance andRMDDHI-010 sleep onset COMISA state, both of a CBT-I therapy may be triggered and an adjustment to a therapy provided by a PAP may also be triggered. Moreover, based on subsequent detection of the state or the absence of detection of the state, the therapy may be further modified. For example, in the absence of the state detection, the CBT-I therapy may be discontinued and a PAP therapy may be modified such as to a protocol prior to the state detection. However, a further detection / classification of the state may trigger a further therapy, such as a message to contact sleep therapist consult.4.5.3.2.8 Determination of therapy parameters

[0271] Thus, in some forms of the present technology, the central controller 4230executes one or more therapy parameter determination algorithms 4329 for the determination of one or more therapy parameters using the values returned by one or more of the other algorithms in the therapy engine module 4320. Such output may include, for example, providing initial lower pressures or a PACED breathing therapy.

[0272] In one form of the present technology, the therapy parameter is aninstantaneous treatment pressure Pt. In one implementation of this form, the therapy parameter determination algorithm 4329 determines the treatment pressure Pt using the equation Pt ^ A ^ ^ ^, t ^ ^ P 0 (1)

[0273] where:^A is the amplitude,^ ^(^^^t) is the waveform template value (in the range 0 to 1) at the currentvalue ^ of phase and t of time, and ^P0 is a base pressure.

[0274] If the waveform determination algorithm 4322 provides the waveformtemplate ^(^^^t) as a lookup table of values ^ indexed by phase ^, the therapy parameter determination algorithm 4329 applies equation (1) by locating the nearest lookup table entry to the current value ^ of phase returned by the phase determination algorithm 4321, or by interpolation between the two entries straddling the current value ^ of phase. The values of the amplitude A and the base pressure P0 may be set by thetherapy parameter determination algorithm 4329 depending on the chosen respiratory pressure therapy mode in the manner described below.

[0276] RMDDHI-0104.5.3.3 Therapy Control module

[0277] The therapy control module 4330 in accordance with one aspect of thepresent technology receives as inputs the therapy parameters from the therapy parameter determination algorithm 4329 of the therapy engine module 4320, and controls the pressure generator 4140 to deliver a flow of air in accordance with the therapy parameters.

[0278] In one form of the present technology, the therapy parameter is a treatmentpressure Pt, and the therapy control module 4330 controls the pressure generator 4140 to deliver a flow of air whose interface pressure Pm at the patient interface 3000 is equal to the treatment pressure Pt.4.5.3.4 Detection of fault conditions

[0279] In one form of the present technology, the central controller 4230 executesone or more methods 4340 for the detection of fault conditions. The fault conditions detected by the one or more methods 4340 may include at least one of the following: ^Power failure (no power, or insufficient power)^ Transducer fault detection^ Failure to detect the presence of a component^ Operating parameters outside recommended ranges (e.g. pressure, flow rate,temperature, PaO2) ^Failure of a test alarm to generate a detectable alarm signal.

[0280] Upon detection of the fault condition, the corresponding algorithm 4340signals the presence of the fault by one or more of the following: ^Initiation of an audible, visual & / or kinetic (e.g. vibrating) alarm^ Sending a message to an external device^ Logging of the incident4.6 HUMIDIFIER4.6.1 Humidifier overview

[0281] In one form of the present technology there is provided a humidifier 5000(e.g. as shown in Fig.5A) to change the absolute humidity of air or gas for delivery to a patient relative to ambient air. Typically, the humidifier 5000 is used to increase the absolute humidity and increase the temperature of the flow of air (relative to ambient air) before delivery to the patient’s airways.RMDDHI-010

[0282] The humidifier 5000 may comprise a humidifier reservoir 5110, ahumidifier inlet 5002 to receive a flow of air, and a humidifier outlet 5004 to deliver a humidified flow of air. In some forms, as shown in Fig. 5A and Fig. 5B, an inlet and an outlet of the humidifier reservoir 5110 may be the humidifier inlet 5002 and the humidifier outlet 5004 respectively. The humidifier 5000 may further comprise a humidifier base 5006, which may be adapted to receive the humidifier reservoir 5110 and comprise a heating element 5240.4.7 BREATHING WAVEFORMS

[0283] Fig.6A shows a model typical breath waveform of a person while sleeping.The horizontal axis is time, and the vertical axis is respiratory flow rate. While the parameter values may vary, a typical breath may have the following approximate values: tidal volume Vt 0.5L, inhalation time Ti 1.6s, peak inspiratory flow rate Qpeak 0.4 L / s, exhalation time Te 2.4s, peak expiratory flow rate Qpeak -0.5 L / s. The total duration of the breath, Ttot, is about 4s. The person typically breathes at a rate of about 15 breaths per minute (BPM), with Ventilation Vent about 7.5 L / min. A typical duty cycle, the ratio of Ti to Ttot, is about 40%.

[0284] Fig. 6B shows selected polysomnography channels (pulse oximetry, flowrate, thoracic movement, and abdominal movement) of a patient during non-REM sleep breathing normally over a period of about ninety seconds, with about 34 breaths, being treated with automatic PAP therapy, and the interface pressure being about 11 cmH2O. The top channel shows pulse oximetry (oxygen saturation or SpO2), the scale having a range of saturation from 90 to 99% in the vertical direction. The patient maintained a saturation of about 95% throughout the period shown. The second channel shows quantitative respiratory airflow, and the scale ranges from -1 to +1 LPS in a vertical direction, and with inspiration positive. Thoracic and abdominal movement are shown in the third and fourth channels.

[0285] Fig. 6C shows polysomnography of a patient before treatment. There areeleven signal channels from top to bottom with a 6 minute horizontal span. The top two channels are both EEG (electoencephalogram) from different scalp locations. Periodic spikes in the second EEG represent cortical arousal and related activity. The third channel down is submental EMG (electromyogram). Increasing activity around the time of arousals represents genioglossus recruitment. The fourth & fifth channels are EOG (electro-oculogram). The sixth channel is an electocardiogram. The seventhRMDDHI-010 channel shows pulse oximetry (SpO2) with repetitive desaturations to below 70% from about 90%. The eighth channel is respiratory airflow using a nasal cannula connected to a differential pressure transducer. Repetitive apneas of 25 to 35 seconds alternate with 10 to 15 second bursts of recovery breathing coinciding with EEG arousal and increased EMG activity. The ninth channel shows movement of chest and the tenth shows movement of abdomen. The abdomen shows a crescendo of movement over the length of the apnea leading to the arousal. Both become untidy during the arousal due to gross body movement during recovery hyperpnea. The apneas are therefore obstructive, and the condition is severe. The lowest channel is posture, and in this example it does not show change.

[0286] Fig. 6D shows patient flow rate data where the patient is experiencing aseries of total obstructive apneas. The duration of the recording is approximately 160 seconds. Flow rates range from about +1 L / s to about -1.5 L / s. Each apnea lasts approximately 10-15s.4.8 RESPIRATORY THERAPY MODES

[0287] Various respiratory therapy modes may be implemented by the disclosedrespiratory therapy system.4.8.1 CPAP therapy

[0288] In some implementations of respiratory pressure therapy, the centralcontroller 4230 sets the treatment pressure Pt according to the treatment pressure equation (1) as part of the therapy parameter determination algorithm 4329. In one such implementation, the amplitude A is identically zero, so the treatment pressure Pt (which represents a target value to be achieved by the interface pressure Pm at the current instant of time) is identically equal to the base pressure P0 throughout the respiratory cycle. Such implementations are generally grouped under the heading of CPAP therapy. In such implementations, there is no need for the therapy engine module 4320 to determine phase ^ or the waveform template ^(^).

[0289] In CPAP therapy, the base pressure P0 may be a constant value that is hard-coded or manually entered to the RPT device 4000. Alternatively, the central controller 4230 may repeatedly compute the base pressure P0as a function of indices or measures of sleep disordered breathing returned by the respective algorithms in the therapy engine module 4320, such as one or more of flow limitation, apnea, hypopnea, patency, and snore. This alternative is sometimes referred to as APAP therapy.RMDDHI-010

[0290] Fig. 4E is a flow chart illustrating a method 4500 carried out by the centralcontroller 4230 to continuously compute the base pressure P0as part of an APAP therapy implementation of the therapy parameter determination algorithm 4329, when the pressure support A is identically zero.

[0291] The method 4500 starts at step 4520, at which the central controller 4230compares the measure of the presence of apnea / hypopnea with a first threshold, and determines whether the measure of the presence of apnea / hypopnea has exceeded the first threshold for a predetermined period of time, indicating 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 with a second threshold. If the measure of airway patency exceeds the second threshold, indicating the airway is patent, the detected apnea / hypopnea is deemed central, and the method 4500 proceeds to step 4560; otherwise, the apnea / hypopnea is deemed obstructive, and the method 4500 proceeds to step 4550.

[0292] At step 4530, the central controller 4230 compares the measure of flowlimitation with a third threshold. If the measure of flow limitation exceeds the third threshold, indicating inspiratory flow is limited, the method 4500 proceeds to step 4550; otherwise, the method 4500 proceeds to step 4560.

[0293] At step 4550, the central controller 4230 increases the base pressure P0 bya predetermined pressure increment ^P, provided the resulting treatment pressure Pt would not exceed a maximum treatment pressure Pmax. In one implementation, the predetermined pressure increment ^P and maximum treatment pressure Pmax are 1 cmH2O and 25 cmH2O respectively. In other implementations, the pressure increment ^P can be as low as 0.1 cmH2O and as high as 3 cmH2O, or as low as 0.5 cmH2O and as high as 2 cmH2O. In other implementations, the maximum treatment pressure Pmax can be as low as 15 cmH2O and as high as 35 cmH2O, or as low as 20 cmH2O and as high as 30 cmH2O. The method 4500 then returns to step 4520.

[0294] At step 4560, the central controller 4230 decreases the base pressure P0 bya decrement, provided the decreased base pressure P0 would not fall below a minimum treatment pressure Pmin. The method 4500 then returns to step 4520. In one implementation, the decrement is proportional to the value of P0-Pmin, so that the decrease in P0to the minimum treatment pressure Pmin in the absence of any detected events is exponential. In one implementation, the constant of proportionality is set suchRMDDHI-010 that the time constant ^^of the exponential decrease of P0is 60 minutes, and the minimum treatment pressure Pmin is 4 cmH2O. In other implementations, the time constant ^^could 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 implementations, the minimum treatment pressure Pmin can be as low as 0 cmH2O and as high as 8 cmH2O, or as low as 2 cmH2O and as high as 6 cmH2O. Alternatively, the decrement in P0could be predetermined, so the decrease in P0 to the minimum treatment pressure Pmin in the absence of any detected events is linear.4.8.2 Bi-level therapy

[0295] In other implementations of this form of the present technology, the valueof amplitude A in equation (1) may be positive. Such implementations are known as bi- level therapy, because in determining the treatment pressure Pt using equation (1) with positive amplitude A, the therapy parameter determination algorithm 4329 oscillates the treatment pressure Pt between two values or levels in synchrony with the spontaneous respiratory effort of the patient 1000. That is, based on the typical waveform templates ^(^^^t) described above, the therapy parameter determination algorithm 4329 increases the treatment pressure Pt to P0+ A (known as the IPAP) at the start of, or during, or inspiration and decreases the treatment pressure Pt to the base pressure P0 (known as the EPAP) at the start of, or during, expiration.

[0296] In some forms of bi-level therapy, the IPAP is a treatment pressure that hasthe same purpose as the treatment pressure in CPAP therapy modes, and the EPAP is the IPAP minus the amplitude A, which has a “small” value (a few cmH2O) sometimes referred to as the Expiratory Pressure Relief (EPR). Such forms are sometimes referred to as CPAP therapy with EPR, which is generally thought to be more comfortable than straight CPAP therapy. In CPAP therapy with EPR, either or both of the IPAP and the EPAP may be constant values that are hard-coded or manually entered to the RPT device 4000. Alternatively, the therapy parameter determination algorithm 4329 may repeatedly compute the IPAP and / or the EPAP during CPAP with EPR. In this alternative, the therapy parameter determination algorithm 4329 repeatedly computes the EPAP and / or the IPAP as a function of indices or measures of sleep disordered breathing returned by the respective algorithms in the therapy engine module 4320 in analogous fashion to the computation of the base pressure P0in APAP therapy described above.RMDDHI-0104.9 GLOSSARY

[0297] For the purposes of the present technology disclosure, in certain forms ofthe present technology, one or more of the following definitions may apply. In other forms of the present technology, alternative definitions may apply.4.9.1 General

[0298] Air: In certain forms of the present technology, air may be taken to meanatmospheric air, and in other forms of the present technology air may be taken to mean some other combination of breathable gases, e.g. atmospheric air enriched with oxygen.

[0299] Ambient: In certain forms of the present technology, the term ambient willbe taken to mean (i) external of the treatment system or patient, and (ii) immediately surrounding the treatment system or patient.

[0300] For example, ambient humidity with respect to a humidifier may be thehumidity of air immediately surrounding the humidifier, e.g. the humidity in the room where a patient is sleeping. Such ambient humidity may be different to the humidity outside the room where a patient is sleeping.

[0301] In another example, ambient pressure may be the pressure immediatelysurrounding or external to the body.

[0302] In certain forms, ambient (e.g., acoustic) noise may be considered to be thebackground noise level in the room where a patient is located, other than for example, noise generated by an RPT device or emanating from a mask or patient interface. Ambient noise may be generated by sources outside the room.

[0303] Automatic Positive Airway Pressure (APAP) therapy: CPAP therapy inwhich the treatment pressure is automatically adjustable, e.g. from breath to breath, between minimum and maximum limits, depending on the presence or absence of indications of SDB events.

[0304] Continuous Positive Airway Pressure (CPAP) therapy: Respiratorypressure therapy in which the treatment pressure is approximately constant through a respiratory cycle of a patient. In some forms, the pressure at the entrance to the airways will be slightly higher during exhalation, and slightly lower during inhalation. In some forms, the pressure will vary between different respiratory cycles of the patient, for example, being increased in response to detection of indications of partial upper airway obstruction, and decreased in the absence of indications of partial upper airway obstruction.RMDDHI-010

[0305] Flow rate: The volume (or mass) of air delivered per unit time. Flow ratemay refer to an instantaneous quantity. In some cases, a reference to flow rate will be a reference to a scalar quantity, namely a quantity having magnitude only. In other cases, a reference to flow rate will be a reference to a vector quantity, namely a quantity having both magnitude and direction. Flow rate may be given the symbol Q. ‘Flow rate’ is sometimes shortened to simply ‘flow’ or ‘airflow’.

[0306] In the example of patient respiration, a flow rate may be nominally positivefor the inspiratory portion of a respiratory cycle of a patient, and hence negative for the expiratory portion of the respiratory cycle of a patient. Device flow rate, Qd, is the flow rate of air leaving the RPT device. Total flow rate, Qt, is the flow rate of air and any supplementary gas reaching the patient interface via the air circuit. Vent flow rate, Qv, is the flow rate of air leaving a vent to allow washout of exhaled gases. Leak flow rate, Ql, is the flow rate of leak from a patient interface system or elsewhere. Respiratory flow rate, Qr, is the flow rate of air that is received into the patient's respiratory system.

[0307] Humidifier: The word humidifier will be taken to mean a humidifyingapparatus constructed and arranged, or configured with a physical structure to be capable of providing a therapeutically beneficial amount of water (H2O) vapour to a flow of air to ameliorate a medical respiratory condition of a patient.

[0308] Leak: An unintended flow of air. In one example, leak may occur as theresult of an incomplete seal between a mask and a patient's face. In another example leak may occur in a swivel elbow to the ambient.

[0309] Patient: A person, whether or not they are suffering from a respiratorycondition.

[0310] Pressure: Force per unit area. Pressure may be expressed in a range of units,including cmH2O, g-f / cm2and hectopascal. 1 cmH2O is equal to 1 g-f / cm2and is approximately 0.98 hectopascal (1 hectopascal = 100 Pa = 100 N / m2= 1 millibar ~ 0.001 atm). In this specification, unless otherwise stated, pressure is given in units of cmH2O.

[0311] The pressure in the patient interface is given the symbol Pm, while thetreatment pressure, which represents a target value to be achieved by the interface pressure Pm at the current instant of time, is given the symbol Pt.RMDDHI-010

[0312] Respiratory Pressure Therapy (RPT): The application of a supply of air toan entrance to the airways at a treatment pressure that is typically positive with respect to atmosphere.

[0313] Ventilator: A mechanical device that provides pressure support to a patientto perform some or all of the work of breathing.4.9.2 Respiratory cycle

[0314] Apnea: According to some definitions, an apnea is said to have occurredwhen flow falls below a predetermined threshold for a duration, e.g. 10 seconds. An obstructive apnea will be said to have occurred when, despite patient effort, some obstruction of the airway does not allow air to flow. A central apnea will be said to have occurred when an apnea is detected that is due to a reduction in breathing effort, or the absence of breathing effort, despite the airway being patent. A mixed apnea occurs when a reduction or absence of breathing effort coincides with an obstructed airway.

[0315] Breathing rate: The rate of spontaneous respiration of a patient, usuallymeasured in breaths per minute.

[0316] Duty cycle: The ratio of inhalation time, Ti to total breath time, Ttot.

[0317] Effort (breathing): The work done by a spontaneously breathing personattempting to breathe.

[0318] Expiratory portion of a respiratory cycle: The period from the start ofexpiratory flow to the start of inspiratory flow.

[0319] Flow limitation: Flow limitation will be taken to be the state of affairs in apatient's respiration where an increase in effort by the patient does not give rise to a corresponding increase in flow. Where flow limitation occurs during an inspiratory portion of the respiratory cycle it may be described as inspiratory flow limitation. Where flow limitation occurs during an expiratory portion of the respiratory cycle it may be described as expiratory flow limitation.

[0320] Hypopnea: According to some definitions, a hypopnea is taken to be areduction in flow, but not a cessation of flow. In one form, a hypopnea may be said to have occurred when there is a reduction in flow below a threshold rate for a duration. A central hypopnea will be said to have occurred when a hypopnea is detected that is due to a reduction in breathing effort. In one form in adults, either of the following may be regarded as being hypopneas:RMDDHI-010 (i) a 30% reduction in patient breathing for at least 10 seconds plus an associated 4% desaturation; or (ii) a reduction in patient breathing (but less than 50%) for at least 10 seconds, with an associated desaturation of at least 3% or an arousal.

[0321] Hyperpnea: An increase in flow to a level higher than normal.

[0322] Inspiratory portion of a respiratory cycle: The period from the start ofinspiratory flow to the start of expiratory flow will be taken to be the inspiratory portion of a respiratory cycle.

[0323] Patency (airway): The degree of the airway being open, or the extent towhich the airway is open. A patent airway is open. Airway patency may be quantified, for example with a value of one (1) being patent, and a value of zero (0), being closed (obstructed).

[0324] Positive End-Expiratory Pressure (PEEP): The pressure above atmospherein the lungs that exists at the end of expiration.

[0325] Peak flow rate (Qpeak): The maximum value of flow rate during theinspiratory portion of the respiratory flow waveform.

[0326] Respiratory flow rate, 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 litres per minute.

[0327] Tidal volume (Vt): The volume of air inhaled or exhaled during normalbreathing, when extra effort is not applied. In principle the inspiratory volume Vi (the volume of air inhaled) is equal to the expiratory volume Ve (the volume of air exhaled), and therefore a single tidal volume Vt may be defined as equal to either quantity. In practice the tidal volume Vt is estimated as some combination, e.g. the mean, of the inspiratory volume Vi and the expiratory volume Ve.

[0328] (inhalation) Time (Ti): The duration of the inspiratory portion of therespiratory flow rate waveform.

[0329] (exhalation) Time (Te): The duration of the expiratory portion of therespiratory flow rate waveform.RMDDHI-010

[0330] (total) Time (Ttot): The total duration between the start of one inspiratoryportion of a respiratory flow rate waveform and the start of the following inspiratory portion of the respiratory flow rate waveform.

[0331] Typical recent ventilation: The value of ventilation around which recentvalues of ventilation Vent over some predetermined timescale tend to cluster, that is, a measure of the central tendency of the recent values of ventilation.

[0332] Upper airway obstruction (UAO): includes both partial and total upperairway obstruction. This may be associated with a state of flow limitation, in which the flow rate increases only slightly or may even decrease as the pressure difference across the upper airway increases (Starling resistor behaviour).

[0333] Ventilation (Vent): A measure of a rate of gas being exchanged by thepatient’s respiratory system. Measures of ventilation may include one or both of inspiratory and expiratory flow, per unit time. When expressed as a volume per minute, this quantity is often referred to as “minute ventilation”. Minute ventilation is sometimes given simply as a volume, understood to be the volume per minute.4.10 OTHER REMARKS

[0334] A portion of the disclosure of this patent document contains material whichis 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 Patent Office patent files or records, but otherwise reserves all copyright rights whatsoever.

[0335] Unless the context clearly dictates otherwise and where a range of values isprovided, it is understood that each intervening value, to the tenth of the unit of the lower limit, between the upper and lower limit of that range, and any other stated or intervening value in that stated range is encompassed within the technology. The upper and lower limits of these intervening ranges, which may be independently included in the intervening ranges, are also encompassed within the technology, subject to any specifically excluded limit in the stated range. Where the stated range includes one or both of the limits, ranges excluding either or both of those included limits are also included in the technology.

[0336] Furthermore, where a value or values are stated herein as beingimplemented as part of the technology, it is understood that such values may be approximated, unless otherwise stated, and such values may be utilized to any suitableRMDDHI-010 significant digit to the extent that a practical technical implementation may permit or require it.

[0337] Unless defined otherwise, all technical and scientific terms used hereinhave the same meaning as commonly understood by one of ordinary skill in the art to which this technology belongs. Although any methods and materials similar or equivalent to those described herein can also be used in the practice or testing of the present technology, a limited number of the exemplary methods and materials are described herein.

[0338] When a particular material is identified as being used to construct acomponent, obvious alternative materials with similar properties may be used as a substitute. Furthermore, unless specified to the contrary, any and all components herein described are understood to be capable of being manufactured and, as such, may be manufactured together or separately.

[0339] It must be noted that as used herein and in the appended claims, the singularforms "a", "an", and "the" include their plural equivalents, unless the context clearly dictates otherwise.

[0340] All publications mentioned herein are incorporated herein by reference intheir entirety to disclose and describe the methods and / or materials which are the subject of those publications. The publications discussed herein are provided solely for their disclosure prior to the filing date of the present application. Nothing herein is to be construed as an admission that the present technology is not entitled to antedate such publication by virtue of prior invention. Further, the dates of publication provided may be different from the actual publication dates, which may need to be independently confirmed.

[0341] The terms "comprises" and "comprising" should be interpreted as referringto elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced.

[0342] The subject headings used in the detailed description are included only forthe ease of reference of the reader and should not be used to limit the subject matter found throughout the disclosure or the claims. The subject headings should not be used in construing the scope of the claims or the claim limitations.RMDDHI-010

[0343] Although the technology herein has been described with reference toparticular examples, it is to be understood that these examples are merely illustrative of the principles and applications of the technology. In some instances, the terminology and symbols may imply specific details that are not required to practice the technology. For example, although the terms "first" and "second" may be used, unless otherwise specified, they are not intended to indicate any order but may be utilised to distinguish between distinct elements. Furthermore, although process steps in the methodologies may be described or illustrated in an order, such an ordering is not required. Those skilled in the art will recognize that such ordering may be modified and / or aspects thereof may be conducted concurrently or even synchronously.

[0344] It is therefore to be understood that numerous modifications may be madeto the illustrative examples and that other arrangements may be devised without departing from the spirit and scope of the technology.4.11 REFERENCE SIGNS LISTpatient 1000 bed partner 1100 patient interface 3000 seal - forming structure 3100 plenum chamber 3200 structure 3300 vent 3400 connection port 3600 forehead support 3700 RPT device 4000 external housing 4010 upper portion 4012 portion 4014 panel s 4015 chassis 4016 handle 4018 pneumatic block 4020 air filters 4110 inlet air filter 4112RMDDHI-010 outlet air filter 4114 mufflers 4120 inlet muffler 4122 outlet muffler 4124 pressure generator 4140 blower 4142 motor 4144 anti - spill back valve 4160 air circuit 4170 supplementary gas 4180 electrical components 4200 Printed Circuit Board Assembly 4202 power supply 4210 input devices 4220 central controller 4230 clock 4232 therapy device controller 4240 protection circuits 4250 memory 4260 transducers 4270 pressure sensor 4272 flow rate sensor 4274 motor speed transducer 4276 data communication interface 4280 remote external communication network 4282 local external communication network 4284 remote external device 4286 local external device 4288 output device 4290 display driver 4292 display 4294 algorithms 4300 system characterisation algorithm 4305RMDDHI-010 pre - processing module 4310 interface pressure estimation algorithm 4312 vent flow rate estimation algorithm 4314 leak flow rate estimation algorithm 4316 respiratory flow rate estimation algorithm 4318 therapy engine module 4320 phase determination algorithm 4321 waveform determination algorithm 4322 ventilation determination 4323 inspiratory flow limitation determination algorithm 4324 apnea / hypopnea determination algorithm 4325 snore determination algorithm 4326 airway patency determination algorithm 4327 target ventilation determination 4328 therapy parameter determination algorithm 4329 therapy control module 4330 methods 4340 method 4500 step 4520 step 4530 step 4540 step 4550 step 4560 humidifier 5000 humidifier inlet 5002 humidifier outlet 5004 humidifier base 5006 humidifier reservoir 5110 humidifier reservoir dock 5130 heating element 5240

Claims

RMDDHI-010 CLAIMS 1. Apparatus for respiratory therapy, the apparatus comprising: a pressure generator configured to generate a flow of air for delivery to a patient interface via a delivery conduit for a respiratory therapy for a patient; one or more sensors to sense a characteristic of the flow of air; and one or more processors configured to: evaluate data, comprising one or both of objective data and subjective data; classify, based on the evaluated data, the patient according to at least one of a plurality of COMISA states, the COMISA states comprising at least two different insomnia classifications; output a classification determined by the classifying.

2. The apparatus of claim 1 wherein the at least two different insomnia classification comprises any of a sleep onset insomnia patient class and a sleep maintenance insomnia class.

3. The apparatus of any one of claims 1 to 2 wherein the one or more processors comprises a controller of the pressure generator, wherein the controller is configured to control operation of the pressure generator based on the output classification.

4. The apparatus of any one of claims 1 to 3, wherein the evaluated data comprises a plurality of features including any two or more of: an apnea-hypopena index (AHI), inspiratory pressure, a 95th percentile pressure, a total number of usage days of a respiratory pressure therapy device, a body mass index (BMI), patient age, a median inspiratory pressure, patient gender, expiratory pressure relief (EPR) mode use or setting, amount of respiratory pressure therapy device usage in the last thirty days, median mask leak amount, on-status of a smooth breathing pressure curve mode of a respiratory pressure therapy device, median inspiratory pressure, a total time amount of use of an EPR mode, EPR mode off-status, an EPR level setting, and detected mask ON and / or detected mask off events.

5. The apparatus of claim 4, wherein the evaluation of the data comprises comparing values of the plurality of features with one or more threshold values.RMDDHI-010 6. The apparatus of any one of claims 1 to 5, wherein the output classification comprises a maintenance state.

7. The apparatus of claim 6, wherein classifying the maintenance state comprises an evaluation of any one or more of: an apnea hypopnea index (AHI), inspiratory pressures, a 95th percentile inspiratory pressure, a total number of respiratory pressure therapy device usage days, a body mass index (BMI), patient age, and a median inspiratory pressure.

8. The apparatus of any one of claims 1 to 5, wherein the output classification comprises an onset state.

9. The apparatus of claim 8, wherein classifying the onset state comprises an evaluation of any one or more of: patient gender, EPR mode use, respiratory pressure therapy device usage amount for a last 30 days, a median mask leak, and on-status of a smooth breathing pressure curve mode of a respiratory pressure therapy device.

10. The apparatus of any one of claims 1 to 5, wherein the output classification comprises an onset and maintenance state.

11. The apparatus of claim 10, wherein classifying the onset and maintenance state comprises an evaluation of any one or more of: an apnea index (AI), a median expiratory pressure, a mask leak amount, a 95th percentile mask leak amount, and total number of sessions of use of a respiratory pressure therapy device.

12. The apparatus of any one of claims 1 to 11, wherein the one or more processors are further configured to classify an absence of insomnia state based on the evaluated data.

13. The apparatus of claim 12 wherein classifying the absence of insomnia state, the one or more processors evaluates any one or more of a median inspiratory pressure, a full amount of time of use of an EPR mode, an EPR mode off-status, an amount of usage of a respiratory pressure therapy device in last 30 days, and an EPR level setting.RMDDHI-010 14. A method of evaluating a patient using apparatus for a respiratory therapy, the method comprising: controlling a pressure generator to generate a flow of air for delivery to a patient interface via a delivery conduit for a respiratory therapy for the patient; operating one or more sensors to sense a characteristic of the flow of air; and evaluating data that comprises one or both of objective data and subjective data; classifying the patient according to one of a plurality of COMISA states, the COMISA states comprising at least two different insomnia classifications; outputting a classification determined by the classifying.

15. The method of claim 14 wherein the at least two different insomnia classification comprises any of a sleep onset insomnia patient class and a sleep maintenance insomnia class.

16. The method of any one of claims 14 to 15 wherein the controlling of the pressure generator is based on the output classification.

17. The method of any one of claims 14 to 16, wherein the evaluated data comprises a plurality of features including any two or more of: an apnea-hypopena index (AHI), inspiratory pressure, a 95th percentile pressure, a total number of usage days of a respiratory pressure therapy device, a body mass index (BMI), patient age, a median inspiratory pressure, patient gender, expiratory pressure relief (EPR) mode use or setting, amount of respiratory pressure therapy device usage in the last thirty days, median mask leak amount, on-status of a smooth breathing pressure curve mode of a respiratory pressure therapy device, median inspiratory pressure, a total time amount of use of an EPR mode, EPR mode off-status, an EPR level setting, and detected mask ON events and / or detected mask off events.

18. The method of claim 17, wherein the evaluation of the data comprises comparing values of the plurality of features with one or more threshold values.RMDDHI-010 19. The method of any one of claims 14 to 18, wherein the output classification comprises a maintenance state.

20. The method of claim 19, wherein classifying the maintenance state comprises an evaluation of any one or more of: an apnea hypopnea index (AHI), inspiratory pressures, a 95th percentile inspiratory pressure, a total number of respiratory pressure therapy device usage days, a body mass index (BMI), patient age, and a median inspiratory pressure.

21. The method of any one of claims 14 to 18, wherein the output classification comprises an onset state.

22. The method of claim 21, wherein classifying the onset state comprises an evaluation of any one or more of: patient gender, EPR mode use, respiratory pressure therapy device usage amount for a last 30 days, a median mask leak, and on-status of a smooth breathing pressure curve mode of a respiratory pressure therapy device.

23. The method of any one of claims 14 to 18, wherein the output classification comprises an onset and maintenance state.

24. The method of claim 23, wherein classifying the onset and maintenance state comprises an evaluation of any one or more of: an apnea index (AI), a median expiratory pressure, a mask leak amount, a 95th percentile mask leak amount, and total number of sessions of use of a respiratory pressure therapy device.

25. The method of any one of claims 14 to 24, wherein the one or more processors are further configured to classify an absence of insomnia state based on the evaluated data.

26. The method of claim 25, wherein classifying the absence of insomnia state, the one or more processors evaluates any one or more of a median inspiratory pressure, a full amount of time of use of an EPR mode, an EPR mode off-status, an amount of usage of a respiratory pressure therapy device in last 30 days, and an EPR level setting.RMDDHI-010 27. A processor readable medium configured with program instructions for controlling one or more processors to execute a method of evaluating a patient using apparatus for a respiratory therapy, the method comprising the method of any one of claims 14 to 26.

28. The processor readable medium of claim 27, wherein the one or more processors comprises one or more servers.

29. The processor readable medium of claim 27, wherein the one or more processors comprises a respiratory pressure therapy device.

30. A method for characterizing insomnia in COMISA subjects, comprising: receiving objective data relating to a user’s therapy and / or sleep from one or more sensors associated with the user, which one or more sensors may be comprised in, or associated with, a positive airway pressure (PAP) device; receiving subjective data relating to the user’s sleep; inputting the objective data and subjective data into a classification system; applying the classification system to the objective data and the subjective data to (a) determine characteristics for patients that distinguish phenotypes of COMISA; and / or (b) distinguish phenotypes of COMISA based on previously determined ones of the key characteristics.

31. The method of claim 30, wherein objective data includes usage hours, AI, AHI, Leak, mask events, compliance, and EPR levels, inspiratory pressure, Easy Breathe on-status, Cheyne stroke respiration minutes, closed apnea index, or EEG signals.

32. The method of any one of claims 30 to 31, wherein objective data includes patient demographics, age, BMI, gender, setup date.

33. The method of any one of claims 30 to 32, wherein subjective data may survey information and sleep diaries.RMDDHI-010 34. The method of any one of claims 30 to 33, wherein the classification system uses rules-based classification.

35. The method of any one of claims 30 to 34, wherein the classification system uses machine learning.

36. The method of any one of claims 30 to 35 wherein phenotypes may be onset, maintenance, or onset and maintenance.

37. The method of claim 36, wherein machine learning model is Logistic Regression, feed-forward artificial neural networks with back propagation learning, random forest, stochastic gradient boosting machines, or Artificial Neural Networks.

38. The method of any one of claims 30 to 37, wherein the classification system uses predictive analytics.

39. The method of claim 34, wherein the rules-based classification uses Fuzzy Rule-Based Classification or SVM-Q.

40. The method of claim 38, wherein the predictive analytics are naïve bayes, support vector machine, K-Nearest Neighbours, Logistic Regression, or Random Forest.

41. A system comprising one or more processors configured to: receive objective data relating to a user’s therapy and / or sleep from one or more sensors associated with the user, wherein the one or more sensors is comprised in, or associated with, a respiratory therapy device; receive subjective data relating to the user’s sleep; input the objective data and subjective data into a classification system; apply, by the classification system, the objective data and the subjective data to (a) determine key characteristics for patients that distinguish phenotypes of COMISA; and / or (b) distinguish phenotypes of COMISA based on previously determined ones of the key characteristics.RMDDHI-010 42. The system of claim 41, wherein objective data includes usage hours, AI, AHI, Leak, mask events, compliance, and EPR levels, inspiratory pressure, Easy Breathe on-status, Cheyne stroke respiration minutes, closed apnea index, or EEG signals.

43. The system of any one of claims 41 to 42, wherein objective data includes patient demographics, age, BMI, gender, setup date.

44. The system of any one of claims 41 to 43, wherein subjective data may survey information and sleep diaries.

45. The system of any one of claims 41 to 44, wherein the classification system uses rules-based classification.

46. The system of any one of claims 41 to 45, wherein the classification system uses machine learning.

47. The system of any one of claims 41 to 46, wherein phenotypes may be onset, maintenance, or onset and maintenance.

48. The system of claim 47, wherein machine learning model is Logistic Regression, feed-forward artificial neural networks with back propagation learning, random forest, stochastic gradient boosting machines, or Artificial Neural Networks.

49. The system of any one of claims 41 to 42, wherein the classification system uses predictive analytics.

50. The system of claim 49, wherein the rules-based classification uses Fuzzy Rule-Based Classification or SVM-Q.RMDDHI-010 51. The method of claim 49, wherein the predictive analytics are naïve bayes, support vector machine, K-Nearest Neighbours, Logistic Regression, or Random Forest.

52. The system of any one of claims 41 to 51, further comprising a PAP machine, configured to generate user data.

53. The system of any one of claims 41 to 52, further comprising a polysomnography machine, configured to generate user data.

54. The system of any one of claims 41 to 53, further configured to determine a therapy parameter for operating the respiratory therapy device based on any one or more of the distinguished phenotypes of COMISA and / or the previously determined ones of the key characteristics.

55. The system of claim 54, wherein the determined therapy parameter for operating a respiratory therapy device comprises a pressure setting.

56. The system of claim 54, wherein the determined therapy parameter for operating a respiratory therapy device comprises a flow rate setting.

57. The system of any one of claims 54 to 56, further configured to generate a signal for operating the respiratory therapy device based on determined therapy parameter.

58. The system of any one of claims 41 to 57, may be further configured to present a therapy option based on any one or more of the distinguished phenotypes of COMISA and / or any one or more of the previously determined ones of the key characteristics.

59. The system of claim 58 wherein the therapy option comprises any one of a PACED breathing therapy and an automated CBT-I therapy.

60. The system of claim 58 wherein the PACED breathing therapy is provided by the respiratory therapy device.

Images