WO2019079855A1 - Detection and monitoring of body orientation - Google Patents

Abstract

Methods and apparatus are configured to generate an orientation indicator representing an estimate of body orientation of a person from a baseband signal generated with a contactless motion sensor. One or more processors may access the baseband signal generated with the contactless motion sensor. The baseband signal may represent bodily movement of a person in a sensing vicinity of the sensor. The processor(s) may apply a decomposition process to the baseband signal to generate a decomposition matrix. The processor(s) may extract features from an epoch of the decomposition matrix. The processor(s) may classify the features of the epoch to select a class from a plurality of classes. The plurality of classes may represent different body orientations. The processor(s) may generate the orientation indicator according to the selected class. The orientation indicator may represent an estimate of body orientation of the person during the epoch.

Description

DETECTION AND MONITORING OF BODY ORIENTATION

1 CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of Australian Provisional Application No. 2017904337, filed 26 October 2017, and Australian Provisional Application No. 2018900724, filed 6 March 2018, the entire disclosures of which are hereby incorporated herein by reference.

2 STATEMENT REGARDING FEDERALLY SPONSORED

RESEARCH OR DEVELOPMENT

[0002] Not Applicable

3 SEQUENCE LISTING

[0003] Not Applicable

4 BACKGROUND OF THE TECHNOLOGY

4.1 FIELD OF THE TECHNOLOGY

[0004] The present technology relates to one or more of detection and monitoring of body orientation such as for the detection, diagnosis, monitoring, treatment, prevention and/or amelioration of sleep disorders. The present technology also relates to such devices or apparatus, such as for medical devices or apparatus, and their use for detection of body orientation such as for sleep evaluation.

4.2 DESCRIPTION OF THE RELATED ART

4.2.1 Human Respiratory System and its Disorders

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

[0006] 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 inspired 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.

[0007] A range of respiratory disorders exist. Certain disorders may be characterised by particular events, e.g. apneas, hypopneas, and hyperpneas.

[0008] 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.

[0009] Obstructive Sleep Apnea (OSA), a form of Sleep Disordered Breathing (SDB), is characterised by events including occlusion or obstruction of the upper air 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).

[0010] Cheyne-Stokes Respiration (CSR) is another form of sleep disordered breathing. 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). [0011] Respiratory failure is an umbrella term for cardio-respiratory disorders in which the lungs are unable to inspire sufficient oxygen or expire sufficient CO2 to meet the patient's needs. Respiratory failure may encompass some or all of the following disorders.

[0012] A patient with respiratory insufficiency (a form of respiratory failure) may experience abnormal shortness of breath on exercise.

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

[0014] Chronic Obstructive Pulmonary Disease (COPD) encompasses any of a group of lower airway diseases that have certain characteristics in common. These include increased resistance to air movement, extended expiratory phase of respiration, and loss of the normal elasticity of the lung. Examples of COPD are emphysema and chronic bronchitis. COPD is caused by chronic tobacco smoking (primary risk factor), occupational exposures, air pollution and genetic factors. Symptoms include: dyspnea on exertion, chronic cough and sputum production.

[0015] Heart failure (HF) is a relatively common and severe cardio-respiratory disorder, characterised by the inability of the heart to keep up with the oxygen demands of the body. Management of heart failure is a significant challenge to modern healthcare systems due to its high prevalence and severity. HF is a chronic condition, which is progressive in nature. The progression of HF is often characterized as relatively stable over long periods of time (albeit with reduced cardiovascular function) punctuated by episodes of an acute nature. In these acute episodes, the patient experiences worsening of symptoms such as dyspnea (difficulty breathing), gallop rhythms, increased jugular venous pressure, and orthopnea. This is typically accompanied by overt congestion (which is the buildup of fluid in the pulmonary cavity). This excess fluid often leads to measurable weight gain of several kilograms. In many cases, however, by the time overt congestion has occurred, there are limited options for the doctor to help restabilise the patients, and in many cases the patient requires hospitalization. In extreme cases, without timely treatment, the patient may undergo acute decompensated heart failure (ADHF) events, sometimes referred to as decompensations.

4.2.2 Therapy

[0016] Various therapies, such as Continuous Positive Airway Pressure (CPAP) therapy, Non-invasive ventilation (NIV), Invasive ventilation (IV) and High flow therapy (HFT) have been used to treat one or more of the above respiratory disorders.

[0017] Continuous Positive Airway Pressure (CPAP) therapy has been used to treat Obstructive Sleep Apnea (OS A). 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 posterior 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.

[0018] Non-invasive ventilation (NIV) provides ventilatory support to a patient through 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.

[0019] Invasive ventilation (IV) provides ventilatory support to patients that are no longer 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.

4.2.3 Treatment Systems

[0020] These therapies may be provided by a treatment system or device. Such systems and devices may also be used to diagnose a condition without treating it. [0021] A treatment system may comprise a Respiratory Pressure Therapy Device (RPT device), an air circuit, a humidifier, a patient interface, and data management.

4.2.4 Diagnosis and Monitoring Systems

[0022] Diagnosis is the identification of a condition from its signs and symptoms. Diagnosis tends to be a one-off process, whereas monitoring the progress of a condition can continue indefinitely. Some diagnosis systems are suitable only for diagnosis, whereas some may also be used for monitoring.

[0023] It is of interest to be able to monitor SDB and other sleeping disorders such as insomnia. One parameter of particular interest to such monitoring is nocturnal body orientation (sleeping position). Nocturnal body orientation (such as prone, supine, left side, right side) is known to be related to OSA, insomnia, and periodic limb movement disorder. Knowledge of body orientation is also helpful in determining sleep quality. However, existing body position sensors tend to be wearable and, as such, have variable compliance, being dependent on correct positioning by the patient every night before sleep.

[0024] S+ (pronounced ess-plus) (ResMed Sensor Technologies Ltd, Dublin, Ireland) is a contactless bedside monitor suitable for long-term monitoring of chronic diseases such as HF and COPD. S+ contains a biomotion transceiver sensor operating on radar principles in a licence-free band at 5.8 GHz or 10.5 GHz at ultra-low power (less than 1 mW). S+ is capable of measuring bodily movement over a distance ranging from 0.3 to 1.5 metres; in the case of two people in a bed, a combination of sophisticated sensor design and intelligent signal processing allows S+ to measure only the movement of the person nearest to the sensor. The S+ is suitable for long- term monitoring of SDB as it is unobtrusive and does not present significant compliance issues. However, processing the raw S+ signals to obtain body orientation information useful for chronic SDB monitoring is a difficult task. 5 BRIEF SUMMARY OF THE TECHNOLOGY

[0025] The present technology is directed to automated methods and apparatus for detecting and/or monitoring orientation of a body of a person, such as a sleeping person or a person in a bed.

[0026] The present technology may be directed towards providing devices, such as medical devices, used in the diagnosis, monitoring, amelioration, treatment, or prevention of sleep-disordered breathing having one or more of improved comfort, cost, efficacy, ease of use and manufacturability.

[0027] A first aspect of the present technology relates to apparatus used in the diagnosis or monitoring of sleep-disordered breathing.

[0028] Another aspect of the present technology relates to methods used in the diagnosis or monitoring of sleep-disordered breathing.

[0029] One form of the present technology comprises a monitoring apparatus including a contactless motion sensor, and a processor configured to analyse the baseband signal from the sensor to estimate a patient's body orientation during sleep. The analysis comprises applying a Spatial Dimensions Decomposition to the baseband signal, extracting features, and classifying the features of each sleep epoch to obtain a body orientation estimate for the sleep epoch.

[0030] Some versions of the present technology include a method of one or more processors for generating an orientation indicator representing an estimate of body orientation of a person from a baseband signal generated with a contactless motion sensor. The method in the one or more processors may include accessing the baseband signal generated with the contactless motion sensor. The baseband signal may represent bodily movement of a person in a sensing vicinity of the contactless motion sensor. The method may include applying a decomposition process to the baseband signal to generate a decomposition matrix. The method may include extracting features from an epoch of the decomposition matrix. The method may include classifying the features of the epoch to select a class from a plurality of classes, wherein the plurality of classes represent different body orientations. The method may include generating the orientation indicator according to the selected class, the orientation indicator representing an estimate of body orientation of the person during the epoch.

[0031] In some versions, the decomposition process may be a spatial dimensions decomposition process. The decomposition process may include a predetermined decomposition level D defining a number of iterations of a spatial dimensions transform process. The applying may include computing a three-dimensional vector according to the decomposition process that transforms the baseband signal to components of the three-dimensional vector. The applying may include computing a further three-dimensional vector from each component of the three-dimensional vector according to the decomposition process. The spatial dimensions transform process may include approximating a derivative of the baseband signal. The spatial dimensions transform process may include an amplification factor. The features may be statistical features including one or more of mean, variance, and standard deviation. The classifying may include feeding the features of the epoch into a trained neural network. The trained neural network may be a multi-layer perceptron. The multi-layer perceptron may include two hidden layers. The baseband signal may include an in-phase channel signal and a quadrature channel signal.

[0032] In some versions, the different body orientations represented by the plurality of classes may include a prone orientation, an upright orientation, a supine orientation, a right-side orientation and/or a left-side orientation. The different body orientations represented by the plurality of classes may include any two or more of a prone orientation, an upright orientation, a supine orientation, a right-side orientation and a left-side orientation. The method may include generating, with the one or more processors, a time series of body orientation indicators as selected by the classifying. The time series of body orientation indicators may be presented on a display device. The time series of body orientation indicators may include one or more, or two or more, indicators of a prone orientation, an upright orientation, a supine orientation, a right-side orientation and a left-side orientation. The contactless motion sensor may include a radio-frequency (RF) motion sensor. The three-dimensional vector (S) may be computed as S = (t)U where:

f t) comprises the baseband signal; and φ is an amplification factor.

[0033] Some versions of the present technology may include a processor- readable medium having stored thereon processor-executable instructions which, when executed by one or more processors, cause the one or more processors to generate an orientation indicator representing an estimate of body orientation of a person from a baseband signal generated with a contactless motion sensor. The processor-executable instructions may be configured to execute any of the aspects of the methodologies previously described and/or described in more detail herein.

[0034] Some versions of the present technology may include apparatus. The apparatus may include a contactless motion sensor configured to generate a baseband signal representing bodily movement of a person in a sensing vicinity of the contactless motion sensor. The apparatus may include one or more processors configured to generate an orientation indicator representing an estimate of body orientation of the person from the baseband signal. The one or more processors may be configured to access the baseband signal. The one or more processors may be configured to apply a decomposition process to the baseband signal to generate a decomposition matrix. The one or more processors may be configured to extract features from an epoch of the decomposition matrix. The one or more processors may be configured to classify the features of the epoch to select a class from a plurality of classes, wherein the plurality of classes represent different body orientations. The one or more processors may be configured to generate the orientation indicator according to the selected class, the orientation indicator representing an estimate of body orientation of the person during the epoch. [0035] In some versions, the one or more processors may be co-located with the contactless motion sensor. The apparatus may include communications circuitry configured to transfer data to an external computing device via a connection. The one or more processors may be processor(s) of the external computing device. The contactless motion sensor may be a radio-frequency sensor that generates the baseband signal by processing signals representing transmitted radio-frequency waves and received reflected ones of the transmitted radio -frequency waves. The baseband signal may include an in-phase channel signal and a quadrature channel signal. The apparatus may include any of the processor-readable medium(s) as descried herein. The apparatus may further include a respiratory therapy device. The respiratory therapy device may be configured to adjust a control parameter of a respiratory therapy based on the generated orientation indicator.

[0036] Some versions of the present technology may include a patient monitoring system. The patient monitoring system may include means for generating a baseband signal representing bodily movement of a person in a sensing vicinity of a contactless motion sensor. The patient monitoring system may include processing means for generating an orientation indicator representing an estimate of body orientation of the person from the baseband signal. The processing means may include means for accessing the baseband signal. The processing means may include means for applying a decomposition process to the baseband signal to generate a decomposition matrix. The processing means may include means for extracting features from an epoch of the decomposition matrix. The processing means may include means for classifying the features of the epoch to select a class from a plurality of classes. The plurality of classes may represent different body orientations. The processing means may include means for generating the orientation indicator according to the selected class. The orientation indicator may represent an estimate of body orientation of the person during the epoch.

[0037] The methods, systems, devices and apparatus described herein can provide improved functioning in a processor, such as of a processor of a specific purpose computer, and/ or a sleep and/or sleep-disordered breathing diagnosis / monitoring apparatus. Moreover, in some cases they may be integrated within a controller or processor of a treatment device such as a respiratory pressure therapy device. Moreover, the described methods, systems, devices and apparatus can provide improvements in the technological field of automated management, monitoring and/or treatment of sleep related conditions and/or respiratory conditions, including, for example, sleep disordered breathing or respiratory failure (e.g., COPD).

[0038] Of course, portions of the aspects may form sub-aspects of the present technology. 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.

[0039] Other features of the technology will be apparent from consideration of the information contained in the following detailed description, abstract, drawings and claims.

6 BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present technology is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which like reference numerals refer to similar elements including:

6.1 TREATMENT SYSTEMS

[0041] Fig. 1 shows a system including a patient 1000 wearing a patient interface 3000, 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 4000 is humidified in a humidifier 5000, and passes along an air circuit 4170 to the patient 1000.

6.2 RESPIRATORY SYSTEM AND FACIAL ANATOMY

[0042] Fig. 2 shows an overview of a human respiratory system including the nasal and oral cavities, the larynx, vocal folds, oesophagus, trachea, bronchus, lung, alveolar sacs, heart and diaphragm.

6.3 PATIENT INTERFACE

[0043] Fig. 3 shows a patient interface in the form of a nasal mask in accordance with one form of the present technology. 6.4 RPT DEVICE

[0044] Fig. 4A shows an RPT device in accordance with one form of the present technology.

[0045] Fig. 4B is a schematic diagram of the pneumatic path of an RPT device in accordance with one form of the present technology. The directions of upstream and downstream are indicated.

6.5 HUMIDIFIER

[0046] Fig. 5A shows an isometric view of a humidifier in accordance with one form of the present technology.

[0047] Fig. 5B shows an isometric view of a humidifier in accordance with one form of the present technology, showing a humidifier reservoir 5110 removed from the humidifier reservoir dock 5130.

6.6 BREATHING WAVEFORMS

[0048] Fig. 6A shows a typical respiratory flow rate waveform of a person while sleeping.

[0049] Fig. 6B shows selected polysomnography channels (pulse oximetry, flow rate, thoracic movement, and abdominal movement) of a patient during non-REM sleep breathing normally over a period of about ninety seconds.

6.7 DIAGNOSIS AND MONITORING SYSTEMS

[0050] Fig. 7A shows a patient undergoing polysomnography (PSG). The patient is sleeping in a supine sleeping position.

[0051] Fig. 7B shows a monitoring apparatus monitoring a sleeping patient in accordance with one form of the present technology.

[0052] Fig. 7C is a block diagram illustrating the monitoring apparatus of Fig. 7B in more detail. [0053] Fig. 8 illustrates the spatial dimensions transform used in body orientation estimation according to one form of the present technology.

[0054] Fig. 9 is a block diagram of the spatial dimensions decomposition of a scalar time series that may be used in body orientation estimation according to one form of the present technology.

[0055] Fig. 9A is a block diagram of an example decomposition process employing wavelets that may be used in body orientation estimation according to one form of the present technology.

[0056] Fig. 10 illustrates a classification neural network architecture that may be used in body orientation estimation according to one form of the present technology.

[0057] Fig. 11 is a flow chart illustrating a method of body orientation estimation from the baseband signal of the unobtrusive monitoring apparatus of Fig. 7B according to one form of the present technology.

[0058] Fig. 12 illustrates the performance of the method of Fig. 11 in estimating body orientation over one patient-night of data.

7 DETAILED DESCRIPTION OF EXAMPLES OF THE

TECHNOLOGY

[0059] Before the present technology is described in further detail, it is to be understood 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.

[0060] The following description is provided in relation to various examples which may 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. 7.1 TREATMENT SYSTEMS

[0061] In one form, the present technology comprises an apparatus or device for treating a sleep disorder. The apparatus or device may comprise a respiratory pressure therapy (RPT) device 4000 for supplying pressurised air to the patient 1000 via an air circuit 4170 to a patient interface 3000.

7.1.1 Patient Interface

[0062] A non-invasive patient interface 3000 in accordance with one aspect of the present technology may comprise 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 facilitate the supply of air at positive pressure to the airways. In some forms, the patient interface, such as for delivering a high flow therapy, may be provided without a significant seal forming structure.

7.1.2 RPT Device

[0063] An RPT device 4000, or respiratory therapy device, in accordance with one aspect of the present technology comprises mechanical, pneumatic, and/or electrical components and is configured to execute one or more algorithms. 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.

[0064] In one form, the RPT device 4000 is constructed and arranged to be capable of 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 cmH₂0, or at least 10cmH₂O, or at least 20 cmH₂0. Thus, such a device may be configured as a positive airway pressure device or a high flow therapy device. [0065] 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.

[0066] The pneumatic path of the RPT device 4000 may comprise one or more air path 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.

[0067] One or more of the air path items may be located within a removable unitary structure 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.

[0068] The RPT device 4000 may have an electrical power supply 4210, one or more 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 devices 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.

7.1.3 Air Circuit

[0069] An air circuit 4170 in accordance with an aspect of the present technology is 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.

7.1.4 Humidifier

[0070] 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.

[0071] The humidifier 5000 may comprise a humidifier reservoir 5110, a humidifier 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.

7.2 BREATHING WAVEFORMS

[0072] 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, 0.5 L, inspiratory time, Ti, 1.6 seconds, peak inspiratory flow rate, Qpeak, 0.4 L/s, expiratory time, Te, 2.4 seconds, peak expiratory flow rate, Qpeak, -0.5 L/s. The total duration of the breath, Ttot, is about 4 seconds. 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%.

[0073] Fig. 6B shows selected polysomnography channels (pulse oximetry, flow rate, 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. The top channel shows blood oxygen saturation (Sp0₂), the scale has 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 flow rate, 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. 7.3 MONITORING SYSTEMS

7.3.1 Polysomnography

[0074] Fig. 7A shows a patient 1000 undergoing polysomnography (PSG). A PSG system comprises a headbox 2000 which receives and records signals from the following sensors: an EOG electrode 2015; an EEG electrode 2020; an ECG electrode 2025; a submental EMG electrode 2030; a snore sensor 2035; a respiratory inductance plethysmogram (respiratory effort sensor) 2040 on a chest band; a respiratory inductance plethysmogram (respiratory effort sensor) 2045 on an abdominal band; an oro-nasal cannula 2050 with oral thermistor; a photoplethysmograph (pulse oximeter) 2055; and a body position sensor 2060. The electrical signals are referred to a ground electrode (ISOG) 2010 positioned in the centre of the forehead.

[0075] Despite the quality and reliability of PSG systems, they are not well suited for long-term continuous monitoring and impose limited mobility, causing irritations, distress and discomfort to the patient under monitoring. These limitations have led to stronger demands for non-contact sleep monitoring systems.

7.3.2 Unobtrusive monitoring apparatus

[0076] One example of a monitoring apparatus 7000 for monitoring the respiration of a sleeping patient 1000 is illustrated in Fig. 7B. The unobtrusive monitoring apparatus 7000 contains a contactless motion sensor generally directed toward the chest of the patient 1000. The motion sensor is configured to generate one or more signals representing chest movement of the patient 1000.

[0077] Fig. 7C is a block diagram illustrating the components of the monitoring apparatus 7000 of Fig. 7B in more detail, according to one form of the present technology. In the monitoring apparatus 7000, a contactless sensor unit 7007 includes a contactless motion sensor 7010 generally directed toward the patient 1000. The motion sensor 7010 is configured to generate one or more signals representing chest movement of the patient 1000.

[0078] The sensor unit 7007 may also include a microcontroller unit (MCU) 7001, and a memory 7002 (e.g. a memory card) for recording data. In one implementation, the sensor unit 7007 may include communications circuitry 7004 configured to transfer data to an external computing device 7005, e.g. a local general purpose computer, a remote server, or other processor-controlled treatment device such as an RPT device as described herein, via a connection 7008. The connection 7008 may be wired or wireless, in which case the communications circuitry 7004 has wireless capability, and may be direct or indirect via a local network or a wide-area network (not shown) such as the Internet.

[0079] The sensor unit 7007 includes a processor 7006 that may be configured to process the signals generated by the motion sensor 7010 as described in detail below. The processor 7006 may optionally be integrated with the MCU.

[0080] The sensor unit 7007 may include a display device 7015 configured to provide visual feedback to a patient, such as by displaying an orientation indicator on a display or a time series of orientation indicators corresponding to the changes in patient body orientation over time (e.g., a monitoring session). In one implementation, the display device 7015 comprises one or more warning lights (e.g., one or more light emitting diodes). The display device 7015 may also be implemented as a display screen such as an LCD or a touch- sensitive display. Operation of the display device 7015 is controlled by the processor 7006. The display device 7015 may be operated to show information to a patient of the monitoring apparatus 7000, such as the patient 1000, or a physician or other clinician. The display device 7015 may also display a graphical patient interface for operation of the monitoring apparatus 7000.

[0081] The sensor unit 7007 may also include an audio output 7017 configured to provide acoustic feedback to a patient under the control of the processor 7006, e.g., a tone whose frequency varies with respiratory rate, or an alarm which sounds when certain conditions are met.

[0082] The above descriptions of the visual display 7015 and the audio output 7017 of the monitoring apparatus 7000 apply equally to comparable elements of the external computing device 7005. [0083] Patient control of the operation of the monitoring apparatus 7000 may be based on operation of controls (not shown) that are sensed by the processor 7006 of the monitoring apparatus 7000.

[0084] One example of a sensor unit 7007 is the S+ device manufactured by ResMed Sensor Technologies Ltd, which contains a contactless radio-frequency (RF) motion sensor 7010. The RF motion sensor 7010 processes signals representing transmitted radio-frequency waves and received reflected ones of the transmitted radio-frequency waves. Other examples include the sensors disclosed in United States Patent Application Publication No. US 2015-0216424 and United States Patent Application Publication No. US 2018-0239014, the entire disclosures of which are incorporated herein by reference.

[0085] In one form of the present technology, such as when the S+ device is used as the sensor unit 7007, the motion sensor 7010 includes an RF transmitter 7020 configured to transmit an RF signal 7060. The transmitted signal 7060 for example has the form s(t) = u{t) cos (2nf_ct + e)

(Eq. 1)

[0086] In Eq. 1, the carrier frequency is /_c (typically in the range 100 MHz to 100 GHz, e.g. 3 GHz to 12 GHz, e.g. 5.8 GHz or 10.5 GHz), t is time, Θ is an arbitrary phase angle, and u(f) is a pulse shape. In a continuous wave system, the magnitude of u(f) may be unitary, and can be omitted from Eq. 1. More generally, the pulse u(f) may be defined as in Eq. 2:

[0087] where T is the period width, and T_p is the pulse width. Where T_p «T, this becomes a pulsed continuous wave system. In one case, as T_p becomes very small, the spectrum of the emitted signal becomes very wide, and the system is referred to as an ultra- wideband (UWB) radar or impulse radar. Alternatively, the carrier frequency of the RF transmitted signal 7060 can be varied (chirped) to produce a so-called frequency modulated continuous wave (FMCW) system.

[0088] The radio-frequency signal 7060 may be generated by the transmitter 7020 using a local oscillator 7040 coupled with circuitry for applying the pulse gating. In the FMCW case, a voltage-controlled oscillator is used together with a voltage- frequency converter to produce the RF signal 7060 for transmission. The coupling of the transmitted RF signal 7060 to the air may be accomplished using an antenna 7050. The antenna 7050 can be omnidirectional (transmitting power more or less equally in all directions) or directional (transmitting power preferentially in certain directions). It may be advantageous to use a directional antenna 7050 in the apparatus 7000 so that transmitted and reflected energy are primarily coming from one direction. In one implementation of the apparatus 7000, a single antenna 7050 is used for both the transmitter 7020 and the receiver 7030, with a single carrier frequency. Alternatively, multiple receive and transmit antennas 7050 can be used, with multiple carrier frequencies.

[0089] The apparatus 7000 is compatible in various embodiments with various types of antenna 7050 such as simple dipole antennas, patch antennas, and helical antennas, and the choice of antenna can be influenced by factors such as the required directionality, size, shape, or cost. It should be noted that the apparatus 7000 can be operated in a manner which has been shown to be safe for human use. The apparatus 7000 has been demonstrated with a total system emitted average power of 1 mW (0 dBm) and lower. The recommended safe power density level for RF exposure is 1 mW/cm². At a distance of 1 metre from a system transmitting at 0 dBm, the equivalent power density will be at least 100 times less than this recommended limit.

[0090] In use, the transmitted RF signal 7060 is reflected off objects that reflect radio waves (such as the air-body interface of the patient 1000), and some of the reflected signal 7070 will be received at a receiver 7030, which can be collocated with the transmitter 7020, or which can be separate from the transmitter 7020, in a so- called "bistatic" configuration. The received signal 7070 and the transmitted signal 7060 can be multiplied together in a mixer 7080 (either in an analog or digital fashion). This mixer 7080 can be of the form of a multiplier (as denoted below in (Eq. 3)) or in a circuit which approximates the effect of a multiplier (e.g., an envelope detector circuit which adds sinusoidal waves). For example, in the CW case, the mixed signal will equal

[0091] where (fit) is a phase term resulting from the path difference of the transmitted and received signals 7060 and 7070 (in the case where the reflection is dominated by a single reflective object, the path difference is dependent on the distance to the object), and γ is the attenuation experienced by the reflected signal 7070. If the reflecting object is fixed, then (f t) is fixed. In the apparatus 7000, the reflecting object (e.g., the chest wall of the patient 1000) is in general moving, and (fit) will therefore be time-varying. As a simple example, if the chest wall is undergoing only a sinusoidal respiratory movement of frequency f_m, then the mixed signal m(t) contains a component at f_m (as well as a component centred at 2f_c which can be removed by low-pass filtering, e.g. at 1.6 Hz). The signal at the output of the low-pass filter after mixing is referred to as the baseband signal 7003, and in general represents bodily movement of the patient 1000. In some implementations, the mixer 7080 contains an analog-to-digital converter at its output, so the baseband signal 7003 may be a discrete signal (sequence of samples), e.g. with sampling rate equal to 16

Hz.

[0092] The amplitude of the baseband signal 7003 is affected by the mean path distance of the reflected signal, leading to detection nulls and peaks in the motion sensor 7010 (i.e. areas where the motion sensor 7010 is less or more sensitive). This effect can be minimised by using quadrature techniques in which the transmitter 7020 simultaneously transmits a signal 90 degrees out of phase (in quadrature) with the signal 7060 of Eq. 1. This results in two reflected signals, both of which can be mixed and low-pass filtered by the mixer 7080, leading to two signals representative of bodily movement, referred to as the "I (in-phase) channel" and the "Q (quadrature) channel". The baseband signal 7003 may comprise one or both of these channels. [0093] In this way, the motion sensor 7010, e.g., a radio-frequency sensor, can observe the movement of the part of the body of the patient 1000 toward which the motion sensor 7010 is directed, e.g. the chest.

[0094] In order to improve the quality of the chest movement signal, and more general bodily movement signals, the physical volume from which reflected energy is collected by the sensor unit 7007 can be restricted using various methods. For example, the sensor unit 7007 can be made "directionally selective" (that is, it transmits more energy in certain directions), as can the antenna of the receiver 7030. Directional selectivity can be achieved using directional antennas 7050, or multiple RF transmitters 7020. In alternative forms of the present technology, a continuous wave, an FMCW, or a UWB radar is used to obtain similar signals. A technique called "time-domain gating" can be used to only measure reflected signals 7070 which arise from signals at a certain physical distance from the sensor unit 7007. Frequency domain gating (filtering) can be used to ignore motions of the reflected object above a certain frequency.

[0095] In implementations of the apparatus 7000 using multiple frequencies (e.g., at 500 MHz and 5 GHz), the lower frequency can be used to determine large motions accurately without phase ambiguity, which can then be subtracted from the higher- frequency sensor signals (which are more suited to measuring small motions). Using such a sensor unit 7007, the apparatus 7000 collects information from the patient 1000, and uses that information to determine chest movement information.

[0096] The baseband signal 7003 may be stored in memory 7002 of the sensor unit 7007, and / or transmitted over a link (e.g., connection 7008) for storage in the external computing device 7005, for each monitoring session. In one implementation, each monitoring session is one night in duration.

[0097] The processor 7006 of the sensor unit 7007, or that of the external computing device 7005, may analyse the stored baseband signal 7003 according to an analysis process such as those described in detail below. The instructions for the described processes may be stored on a computer-readable storage medium, e.g. the memory 7002 of the sensor unit 7007, and interpreted and executed by a processor, e.g. the processor 7006 of the sensor unit 7007. Thus, such a processor(s) may determine one or more orientation indicators as described herein and may control generating, such as on a display, an orientation indicator or a time series of orientation indicators corresponding to the changes in patient body orientation over time (e.g., from a monitoring session with the non-contact sensor).

7.3.3 Baseband signal analysis

[0098] One aspect of the present technology comprises one or more analysis processes to obtain body orientation estimates from a signal representing chest movement of the patient 1000.

[0099] In the form of the present technology in which the monitoring apparatus is the unobtrusive monitoring apparatus 7000 illustrated in Fig. 7B and the analysed signal is the baseband signal 7003, an analysis process may be implemented by the processor 7006 of the contactless sensor unit 7007, configured by instructions stored on computer-readable storage medium such as the memory 7002. The results of the analysis, i.e. the body orientation estimate, may be transmitted to the external computing device 7005 via the connection 7008 as described above.

[0100] Alternatively, a processor of the external computing device 7005 may implement all or part of each described analysis process, having obtained the required data, either raw or partly analysed, from the sensor unit 7007 and any other sensors in the apparatus 7000 via the connection 7008 as described above.

[0101] In one example, the external computing device 7005 is a clinician- accessible device such as a patient monitoring device that allows a clinician to review the body orientation estimates, whether these are received from the monitoring apparatus 7000 or obtained by the external computing device 7005 itself. In this example, a database may also be provided to record the body orientation estimates. Through such an external computing device 7005, a clinician may monitor the patient's sleep disordered breathing. 7.3.3.1 Spatial Dimensions Transform (SDT)

[0102] For a scalar function of a single variable, such as a time series /(i), which may be the baseband signal as discussed in more detail herein, the spatial dimensions transform (SDT) is a process that maps the time series fit) to a three-dimensional vector S(i), so the SDT is a technique for data augmentation. The magnitude A of S(t) is equal to fit). The vector S(t) makes an angle of Θ with the x-y plane, and the projection of S onto the x-y plane makes an angle of Θ with the jc-axis.

[0103] Fig. 8 illustrates the vector S and the angle Θ. A_x, A_y, and A_z are the components of S along the x, y, and z-axes respectively, while Axy is the length of the x-y plane projection of S.

[0104] The angle Θ is the inverse tangent of a scalar multiple φ of the derivative or rate of change of (i). The scalar φ is an "amplification factor".

Θ = tarr^/'C ) (Eq. 4)

[0105] For any vector of scalar data, such as a discrete time series fit_n), the derivative f'(t_n) may be approximated in several ways, the simplest of which is as follows:

[0106] It may be shown that under this mapping, the three components of the SDT vector S may be written as

S = /(t)U (Eq. 6)

[0107] where

is the "Unit spatial dimensions transform" (USDT) of f(t), so named because the Euclidean norm of U is always unity. It may be shown that the components of U fall within the following ranges:

0 < U_x≤ 1 (Eq. 8)

1 1

- -≤ U_v≤- (Eq. 9)

2 y 2

-1≤ U_Z≤ 1 (Eq. 10)

[0108] The USDT therefore transforms, normalizes, and scales the input time series f{t) within the unit sphere. The transformation, normalization and scaling of the input time series is achieved by the removal of offsets using the derivative and the modulations of the scaling factor and derivative in unit vector dimensions.

[0109] The effects of the amplification factor φ can be summarized as follows:

• φ = 0 saturates the transformation state.

• φ = 1 is an unsealed transformation state, where the rate of change of/(i) is not amplified.

• φ = - 1 : unsealed transformation state, however, for y- and z-coordinates, the rates of change are reversed.

• φ positive increase: decreases in jc-coordinate and increases in y- and z- coordinates. This will amplify the effects of small changes and saturate large changes.

• φ negative decrease: decreases in jc-coordinate and inverse increases in y- and z-coordinates. This will inversely amplify the effects of small changes and saturate large changes.

[0110] Therefore, the amplification factor φ may be used to enhance and control small changes in data and saturate large changes to minimize the effects of noise.

[0111] The inverse SDT (ISDT) is defined as

[0112] where co is a constant.

7.3.3.2 Spatial Dimensions Decomposition (SDD)

[0113] The SDD is a decomposition process that employs an SDT process iterated to a predetermined decomposition level. The principal aim of the Spatial Dimensions Decomposition (SDD) process is to decompose any time-series function (e.g., the baseband signal), either scalar or vector-valued, into a flattened decomposition matrix consisting of a number of multi-coordinate columns according to the decomposition level. Because the SDD is a mapping from a scalar to a three- dimensional vector, each iteration triples the number of columns. The number C of flattened multi-coordinate columns is therefore calculable from the decomposition level D as follows:

[0114] Fig. 9 illustrates an SDD with D = 2 levels. Appendix A contains Matlab™ code for implementing an SDD over D levels on a scalar time series contained in a column vector/.

[0115] The decomposed flattened multi-coordinate columns produced by the SDD process represent the input data in multi-dimensional space; each of the flattened coordinate columns is by itself an augmented representation of the input data. In addition, the iSDT of each of the decomposed levels is also an augmented representation of the input data.

[0116] The SDT and SDD are designed to be generic to transform, normalize and scale the input data in a single process. The SDD can be used as a multi-dimensional data transformation for any time series, scalar or vector-valued. To apply the SDD to a vector-valued time series, the scalar SDD is applied independently to each component of the vector-valued time series and the resulting decomposition matrix columns are interleaved. The term "data" also encapsulates variations of data types, such as (but not limited to): image, text, dynamic time series or speech signals.

7.3.3.3 Wavelet packet decomposition

[0117] An alternative decomposition process that may be applied is the wavelet packet decomposition (WPD). An example implementation is illustrated in Fig. 9A. Prior to applying the wavelet packet decomposition (WPD), the raw in-phase and quadrature channel signals may be detrended by subtracting their mean values. The detrended in-phase and quadrature channel signals are then decomposed via the WPD to plural levels, with both 'approximation' and 'detail' coefficients decomposed in each level (unlike the conventional wavelet transform in which only the approximation coefficients are decomposed). In one implementation, the mother wavelet for the WPD is Symlet wavelet with a fourth order filter. The decomposed 'detail' coefficients are then reconstructed at the wavelet packet tree (WPT) levels as described in Reference [1] identified herein, the entire content of which is hereby incorporated by reference. The reconstructed wavelet coefficients are then normalized to unit length. To combine the normalized wavelet coefficients from the in-phase and quadrature channels, the magnitude and the Euclidean distance are calculated for each of the normalized wavelet coefficients from the in-phase and quadrature channels. In an example, such a wavelet decomposition process may consider frequencies as follows: (a) slow body movements - frequencies between greater than 0 Hz and 0.25 Hz; (b) respiratory chest movements -frequencies between 0.25 Hz and 0.5 Hz (corresponding to 7.5 - 30 breaths per minute); (c) heart chest movements — frequencies between 0.5 Hz and 1.0 Hz, (corresponding to 30 - 120 heart beats per minute); (d) fast body movements -frequencies between 1.0 Hz and 2.0 Hz). This methodology of the WPD process is illustrated in Fig. 9B. This methodology produces a total of 10 unique wavelet coefficient vectors, consisting of 5 unique magnitude wavelet coefficient vectors and 5 unique Euclidean distance wavelet coefficient vectors. The wavelet coefficient vectors are stored in the columns of a decomposition matrix. 7.3.3.4 Classification

To extract classification features from the decomposition matrix, a window is slid down each column of the decomposition matrix, and statistical features, such as time domain statistical features (e.g., any one, two, etc. or all of mean, variance, median- absolute-deviation, standard deviation, natural logarithm of mean and geometric mean), and/or frequency domain features (e.g., any one, two, etc. or all of the absolute magnitudes of the frequency components from Fourier transform (e.g., FFT or DFT), the derivative of the absolute magnitudes, the sum of the absolute magnitudes, the sum of the derivative of the absolute magnitudes, the PSD magnitudes and the derivative of the PSD magnitudes from a power spectral density PSD, the sum of the PSD magnitudes and the sum of the derivative of the PSD magnitudes) are extracted from the values in each position of the window in each column. In one implementation, the sliding window is of duration equal to two epochs, and the window is slid in steps of one epoch. The duration of an epoch is predetermined. Preferably, the duration of an epoch is comparable to the time scale on which the quantity to be estimated changes.

[0118] Body orientation estimation may be implemented as a classification problem of assigning one of a plurality of classes (e.g., five classes: "Prone", "Upright", "Supine", "Right" and "Left") to the features representing each epoch, where the features are indicative of general body orientation based on training of the classifier. Such a body orientation classifier can select the appropriate class by evaluation of the features to thereby make the detection of body orientation. Such a body orientation classifier can generate, as output such as for monitoring, a time series of body orientation indicators on a per epoch basis such as by generating, for example on a display, a suitable orientation label for each epoch based on the analysis of the decompensation matrix.

[0119] For example, a "prone" label (e.g., text) or other indicator may be understood to represent a body orientation of a person lying prone (e.g., lying down in bed generally facing the bed such as lying on the stomach) in the sensing vicinity of the monitoring apparatus. An "upright" label or indicator may be understood to represent a body orientation of a person sitting up (e.g., sitting up in bed) or standing in the sensing vicinity of the monitoring apparatus. A "supine" label or indicator may be understood to represent a body orientation of a person generally lying supine (e.g., lying down in bed generally facing away from the bed such as lying on a rear side (back) of the person) in the sensing vicinity of the monitoring apparatus. A "Right" label or indicator may be understood to represent a body orientation of a person lying on their right side (e.g., on their right side in bed). A "Left" label or indicator may be understood to represent a body orientation of a person lying on their left side (e.g., on their left side in bed). In some versions, these labels or indicators may be more generalized such as to indicate "laying down" with a classification of any of supine, prone, left or right. Similarly, "side" may indicate that the patient is not on their back or front with a classification of any of left or right.

[0120] The body orientation estimation thus can be produced by the classification process to have a resolution of one estimate per epoch, with a latency equal to the duration of the sliding window. For example, to classify each epoch, the corresponding features may be fed into a classifier such as a trained neural network. Fig. 10 illustrates the neural network architecture 1005 according to one form of the present technology. The neural network 1005 is a fully connected multilayer perceptron (MLP) with 3 layers 1010, 1020, and 1030, of which 2 layers (1010 and 1020) are hidden layers and one (1030) is an output layer. The output layer contains 5 neurons representing the binary classes of "Prone", "Upright", "Supine", "Right" and "Left" respectively. Table 1 contains a summary of the body orientation estimation neural network hyperparameters in one implementation.

TABLE 1: NEURAL NETWORK HYPERPARAMETERS [0121] The training hyperparameters of the neural network 1005 according to one implementation are summarized in Table 2.

TABLE 2: TRAINING HYPERPARAMETERS

[0122] In one implementation, the neural network 1005 is trained with a maximum validation fail criteria of 6 epochs. The training is stopped after the maximum validation fail criterion has been reached. The validation fail criterion is defined as "Validation" error increases while "Training" error decreases.

7.3.3.5 Body orientation estimation

[0123] Fig. 11 is a flow chart illustrating a method 1 100 of body orientation estimation from the baseband signal 7003 of the unobtrusive monitoring apparatus 7000 of Fig. 7B according to one form of the present technology. The method 1100 may be executed by the processor 7006 of the sensor unit 7007, or that of the external computing device 7005, having been configured by program instructions as described above.

[0124] The method 1100 starts at step 1110, which applies an SDD over D levels to the baseband signal 7003 (e.g., one or more signals representative of bodily movement, such as the in-phase channel I and/or the quadrature channel Q from a non-contact sensor). Such a process may, for example, employ equation 7. In one implementation, the value of the amplification factor φ of the SDD is set to one. In some implementations, the baseband signal is a 2-component vector-valued time series whose components are the in-phase and quadrature channel signal time series I{t) and Q(t). The result is a decomposition matrix of 2*C columns where C is calculated from D via Eq. 12. In one such implementation, in which D is equal to 3, C is 39, so the decomposition matrix therefore has 78 columns. In other implementations, the baseband signal 7003 comprises only one component, so the decomposition matrix has 39 columns.

[0125] Step 1120 then extracts statistical features from the columns of the decomposition matrix as described above. In one implementation, three features are extracted from each epoch of each column: mean, variance, and standard deviation. The result for each epoch is a feature vector containing three times the number of columns of the decomposition matrix, e.g. 234 for a 2-component baseband signal. In one implementation, the duration of an epoch is 30 seconds.

[0126] Finally, step 1130 passes the statistical features of each epoch through a classifier (e.g., the trained neural network as described above). The resulting class is the body orientation estimation for the epoch.

[0127] Thanks to the properties of the SDD, no pre-processing of the I and Q channels need be performed. That is, neither DC-offset removal, pre-filtering, expert domain knowledge, wavelet decomposition and/or time-frequency domain analysis is required in the process of extracting the features.

7.3.3.6 Results

[0128] A database consisting of 24 CHF patients with New York Heart Association (NYHA) heart failure classification Class II & III who were sequentially admitted in the Royal Brompton Centre for Sleep, London, United Kingdom, for the diagnosis of sleep apnea, disordered sleep, or both, was selected for the "Training", "Validation" and independent "Test" of the body orientation estimation method. The consented patients underwent full PSG as described above. The patients' data were randomly concatenated and partitioned into 3 datasets of "Training", "Validation" and "Test". The dataset partitions are summarized in Table 3. Sample Rate

Dataset Training Validation

Test (35%) (100%) (50%) (15%)

16 Hz

Total 10698240 5349120 1604736 3744384

Prone 95520 47709 14345 33466

Upright 566387 283456 84402 198529

Sample

Count Supine 2412959 1206070 362890 843999

Right 2381283 1190890 357192 833201

Left 5242091 2620995 785907 1835189

Total 185.7 92.9 27.9 65.0

Prone 1.7 0.8 0.2 0.6

Upright 9.8 4.9 1.5 3.4

Sleep

Hours Supine 41.9 20.9 6.3 14.7

Right 41.3 20.7 6.2 14.5

Left 91.0 45.5 13.6 31.9

Prone 0.9 0.9 0.9 0.9

Upright 5.3 5.3 5.3 5.3

% of Supine 22.5 22.5 22.5 22.5 Total

Sample

Right 22.3 22.3 22.3 22.3

Left 49.0 49.0 49.0 49.0

TABLE 3: DATASET PARTITIONS [0129] During training, according to the maximum validation fail criteria, an example neural network based on aspects of the methodologies described herein was stopped at 22284 epochs. The epoch just before the first validation fail criteria was numbered 22278 and this is referred to as the "best validation" epoch. The network's weights were obtained at the "best validation" epoch.

[0130] Applying the body orientation estimation method 1100 with the trained neural network to the "Test" partition (35% of the total data) achieved a correct classification rate of 99.9% for the 5 binary classes of body orientations.

[0131] Fig. 12 illustrates a graphic display, such as for presenting a time series of body orientation indicators, from the non-contact estimation of nocturnal body orientations according to the method 1100 for one patient-night of baseband data. As shown in Fig. 12, the results in the time series of non-contact body orientations estimated by the method 1100 (lower trace 1320) may be similar to the results in the time series of reference body orientations as determined with a PSG system (upper trace 1310).

7.3.4 Applications

[0132] Airway collapsibility in SDB is related to body orientation. Estimates of body orientation may therefore be used as input to methodologies for automatically adjusting therapy, such as the treatment pressure of a respiratory pressure therapy or flow rate of a high flow therapy. In one implementation, a controller of an RPT device may be configured to make a therapy adjustment, such as with a control parameter therefor, based on a detection of a particular body orientation (e.g., an automated change to a setpoint or setting for pressure or flow rate as determined in the controller in relation to an orientation indicator received by the controller or determined by the controller). For example, the treatment pressure or a flow rate may be increased if the body orientation is estimated to be "supine" as opposed to "left", "right", or "prone". If body orientation is estimated to be "upright", the therapy may be ceased altogether.

[0133] In addition, estimating body orientation, and in particular the frequency of changes of orientation, during sleep helps in determining sleep quality and irregular sleeping patterns of patients. For example, any device as described herein, such as with a processor, may be configured to generate a sleep quality indicator or a report of sleep quality (e.g., a sleep score) based on the indicators of body orientation or classification methodologies as described herein. For example, such a methodology may determine number of changes between the determined orientations, which may be compared to one or more thresholds, in assessing the sleep quality and/or detecting and reporting as output irregular sleeping patterns.

7.4 GLOSSARY

[0134] For the purposes of the present technology disclosure, in certain forms of the present technology, one or more of the following definitions may apply. In other forms of the present technology, alternative definitions may apply.

7.4.1 General

[0135] Air. In certain forms of the present technology, air may be taken to mean atmospheric 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.

[0136] Flow rate: The volume (or mass) of air delivered per unit time. Flow rate may 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'.

[0137] In the example of patient respiration, a flow rate may be nominally positive for the inspiratory portion of a breathing cycle of a patient, and hence negative for the expiratory portion of the breathing cycle of a patient. Total flow rate, Qt, is the flow rate of air leaving the RPT device. Vent flow rate, Qv, is the flow rate of air leaving a vent to allow washout of expired 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. [0138] Humidifier. The word humidifier will be taken to mean a humidifying apparatus constructed and arranged, or configured with a physical structure to be capable of providing a therapeutically beneficial amount of water (H₂0) vapour to a flow of air to ameliorate a medical respiratory condition of a patient.

[0139] Patient: A person, whether or not they are suffering from a respiratory condition.

[0140] Respiratory Pressure Therapy (RPT): The application of a supply of air to an entrance to the airways at a treatment pressure that is typically positive with respect to atmosphere.

[0141] Ventilator. A mechanical device that provides pressure support to a patient to perform some or all of the work of breathing.

7.4.2 Respiratory cycle

[0142] Apnea: According to some definitions, an apnea is said to have occurred when 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.

[0143] Breathing rate: The rate of spontaneous respiration of a patient, usually measured in breaths per minute.

[0144] Duty cycle: The ratio of inspiratory time, Ti to total breath time, Ttot.

[0145] Effort (breathing): The work done by a spontaneously breathing person attempting to breathe.

[0146] Expiratory portion of a breathing cycle: The period from the start of expiratory flow to the start of inspiratory flow. [0147] Flow limitation: Flow limitation will be taken to be the state of affairs in a patient'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 breathing cycle it may be described as inspiratory flow limitation. Where flow limitation occurs during an expiratory portion of the breathing cycle it may be described as expiratory flow limitation.

[0148] Hypopnea: According to some definitions, a hypopnea is taken to be a reduction 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.

[0149] Hyperpnea: An increase in flow to a level higher than normal.

[0150] Inspiratory portion of a breathing cycle: The period from the start of inspiratory flow to the start of expiratory flow will be taken to be the inspiratory portion of a breathing cycle.

[0151] Patency (airway): The degree of the airway being open, or the extent to which 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).

[0152] Positive End-Expiratory Pressure (PEEP): The pressure above atmosphere in the lungs that exists at the end of expiration.

[0153] Peak flow rate (Qpeak): The maximum value of flow rate during the inspiratory portion of the respiratory flow waveform.

[0154] 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 airflow rate, as opposed to "true respiratory flow rate" or "true respiratory airflow rate", which is the actual respiratory flow rate experienced by the patient, usually expressed in litres per minute. [0155] Tidal volume (Vt): The volume of air inspired or expired during normal breathing, when extra effort is not applied.

[0156] Inspiratory Time (Ti): The duration of the inspiratory portion of the respiratory flow rate waveform.

[0157] Expiratory Time (Te): The duration of the expiratory portion of the respiratory flow rate waveform.

[0158] Total Time (Ttot): The total duration between the start of one inspiratory portion of a respiratory flow rate waveform and the start of the following inspiratory portion of the respiratory flow rate waveform.

[0159] Typical recent ventilation: The value of ventilation around which recent values of ventilation Vent over some predetermined timescale tend to cluster, that is, a measure of the central tendency of the recent values of ventilation.

[0160] Upper airway obstruction (UAO): includes both partial and total upper airway 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).

[0161] Ventilation (Vent): A measure of a rate of gas being exchanged by the patient'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.

7.5 OTHER REMARKS

[0162] A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in Patent Office patent files or records, but otherwise reserves all copyright rights whatsoever. [0163] Unless the context clearly dictates otherwise and where a range of values is provided, 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.

[0164] Furthermore, where a value or values are stated herein as being implemented 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 suitable significant digit to the extent that a practical technical implementation may permit or require it.

[0165] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this 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.

[0166] When a particular material is identified as being used to construct a component, 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.

[0167] It must be noted that as used herein and in the appended claims, the singular forms "a", "an", and "the" include their plural equivalents, unless the context clearly dictates otherwise. [0168] All publications mentioned herein are incorporated herein by reference in their 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.

[0169] The terms "comprises" and "comprising" should be interpreted as referring to 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.

[0170] The subject headings used in the detailed description are included only for the 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.

[0171] Although the technology herein has been described with reference to particular 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.

[0172] It is therefore to be understood that numerous modifications may be made to the illustrative examples and that other arrangements may be devised without departing from the spirit and scope of the technology. For example, although the baseband signal as classified herein is described as a motion signal representing bodily movement determined with a radio-frequency type non-contact sensor, it will be understood that other motion signals may be processed according to the classification processes described herein for producing such classifications. For example, a motion signal produced by a sonar type non-contact sensing apparatus may be utilized. An example of such a device may be considered in reference International PCT Patent Publication No. WO2018/050913, filed on 19 September 2017, entitled APPARATUS, SYSTEM, AND METHOD FOR DETECTING PHYSIOLOGICAL MOVEMENT FROM AUDIO AND MULTIMODAL SIGNALS, the entire content of which is incorporated herein by reference.

7.6 REFERENCE SIGNS LIST

vent 3400 connection port 3600 forehead support 3700

RPT device 4000 external housing 4010 upper portion 4012 portion 4014 panel 4015 chassis 4016 handle 4018 pneumatic block 4020 inlet air filter 4112 inlet muffler 4122 outlet muffler 4124 pressure generator 4140 blower 4142 air circuit 4170 electrical components 4200

Printed Circuit Board Assembly 4202 electrical power supply 4210 input devices 4220 central controller 4230 therapy device controller 4240 protection circuits 4250 memory 4260 transducers 4270 pressure sensors 4272 flow rate sensors 4274 data communication interface 4280 output devices 4290 humidifier 5000 humidifier inlet 5002 humidifier outlet 5004 humidifier base 5006 humidifier reservoir 5110 humidifier reservoir dock 5130 heating element 5240 unobtrusive monitoring 7000 apparatus

microcontroller unit MCU 7001 memory 7002 baseband signal 7003 communications circuitry 7004 external computing device 7005 processor 7006 sensor unit 7007 connection 7008 motion sensor 7010 display device 7015 audio output 7017 transmitter 7020 receiver 7030 local oscillator 7040 antenna 7050

RF signal 7060 signals 7070 mixer 7080

8 REFERENCES

1. V. P. Tran, and A. A. Al-Jumaily, "Non-Contact Doppler Radar Based Prediction of Nocturnal Body Orientations Using Deep Neural Network for Chronic Heart Failure Patients," in 2017 International Conference on Electrical and Computing Technologies and Applications (ICECTA), American University of Ras Al Khaimah, Ras Al Khaimah, United Arab Emirates (UAE), 2017.

APPENDIX A

[S_temp, U_temp, U²_temp] = SDT _ unction(f);

S(:, 1:3) = S_temp;

U(:, 1:3) = U emp;

U²(:, 1:3) = U²_temp;

pointer = 1;

start_column = 4;

for i = 2 : D

iteration = 3^Λϊ / 3;

for j = 1 : iteration

If] = S(:, pointer);

end_column = start_column + 2;

[S_temp, U_temp, U²_temp] = SDT Junction (f);

S(:, start_column:end_column) = S_temp;

U(:, start_column:end_column) = U_temp;

U²(:, start_column:end_column) = U²_temp;

pointer = pointer + 1;

start_column = start_column + 3;

end

end

Claims

9 CLAIMS

1. A method of one or more processors for generating an orientation indicator representing an estimate of body orientation of a person from a baseband signal generated with a contactless motion sensor, the method in the one or more processors comprising: accessing the baseband signal generated with the contactless motion sensor, the baseband signal representing bodily movement of a person in a sensing vicinity of the contactless motion sensor; applying a decomposition process to the baseband signal to generate a decomposition matrix; extracting features from an epoch of the decomposition matrix; classifying the features of the epoch to select a class from a plurality of classes, wherein the plurality of classes represent different body orientations; and generating the orientation indicator according to the selected class, the orientation indicator representing an estimate of body orientation of the person during the epoch.

2. The method of claim 1, wherein the decomposition process is a spatial dimensions decomposition process.

3. The method of claim 2 wherein the decomposition process comprises a predetermined decomposition level D defining a number of iterations of a spatial dimensions transform process.

4. The method of claim 3 wherein the applying comprises computing a three- dimensional vector according to the decomposition process that transforms the baseband signal to components of the three-dimensional vector.

5. The method of claim 4 wherein the applying comprises computing a further three- dimensional vector from each component of the three-dimensional vector according to the decomposition process.

6. The method of any one of claims 3 to 5 wherein the spatial dimensions transform process comprises approximating a derivative of the baseband signal.

7. The method of any one of claims 3 to 6, wherein the spatial dimensions transform process comprises an amplification factor.

8. The method of any one of claims 1 to 7, wherein the features are statistical features comprising one or more of mean, variance, and standard deviation.

9. The method of any one of claims 1 to 8, wherein the classifying comprises feeding the features of the epoch into a trained neural network.

10. The method of claim 9, wherein the trained neural network is a multi-layer perceptron.

11. The method of claim 10, wherein the multi-layer perceptron comprises two hidden layers.

12. The method of any of claims 1 to 11, wherein the baseband signal comprises an in-phase channel signal and a quadrature channel signal.

13. The method of any one of claims 1 to 12 wherein the different body orientations represented by the plurality of classes comprises a prone orientation, an upright orientation, a supine orientation, a right-side orientation and a left-side orientation.

14. The method of any one of claims 1 to 13, further comprising generating, with the one or more processors, a time series of body orientation indicators as selected by the classifying.

15. The method of claim 14, wherein the time series of body orientation indicators is presented on a display device.

16. The method of any one of claims 14 and 15 wherein the time series of body orientation indicators comprises one or more indicators of a prone orientation, an upright orientation, a supine orientation, a right-side orientation and a left-side orientation.

17. The method of any one of claims 1 to 16 wherein the contactless motion sensor comprises a radio-frequency (RF) motion sensor.

18. The method of any one of claims 1 to 17 when dependent on claim 4 wherein the three-dimensional vector (S) is computed as:

S = /(t)U where:

f t) comprises the baseband signal; and φ is an amplification factor.

19. A processor-readable medium, having stored thereon processor-executable instructions which, when executed by one or more processors, cause the one or more processors to generate an orientation indicator representing an estimate of body orientation of a person from a baseband signal generated with a contactless motion sensor, the processor-executable instructions configured to execute the method of any one of claims 1 to 18.

20. Apparatus comprising: a contactless motion sensor configured to generate a baseband signal representing bodily movement of a person in a sensing vicinity of the contactless motion sensor; and one or more processors configured to generate an orientation indicator representing an estimate of body orientation of the person from the baseband signal, wherein the one or more processors is configured to: access the baseband signal; apply a decomposition process to the baseband signal to generate a decomposition matrix; extract features from an epoch of the decomposition matrix; classify the features of the epoch to select a class from a plurality of classes, wherein the plurality of classes represent different body orientations; and generate the orientation indicator according to the selected class, the orientation indicator representing an estimate of body orientation of the person during the epoch.

21. The apparatus of claim 20, wherein the one or more processors are co-located with the contactless motion sensor.

22. The apparatus of claim 20, further comprising communications circuitry configured to transfer data to an external computing device via a connection.

23. The apparatus of claim 22, wherein the one or more processors are processors of the external computing device.

24. The apparatus of any one of claims 20 to 23, wherein the contactless motion sensor is a radio -frequency sensor that generates the baseband signal by processing signals representing transmitted radio-frequency waves and received reflected ones of the transmitted radio-frequency waves.

25. The apparatus of claim 24, wherein the baseband signal comprises an in-phase channel signal and a quadrature channel signal.

26. The apparatus of any one of claims 20 to 25 further comprising a processor- readable medium according to claim 19.

27. The apparatus of any one of claims 20 to 26 wherein the apparatus further comprises a respiratory therapy device, the respiratory therapy device configured to adjust a control parameter of a respiratory therapy based on the generated orientation indicator.

28. A patient monitoring system comprising: means for generating a baseband signal representing bodily movement of a person in a sensing vicinity of a contactless motion sensor; and processing means for generating an orientation indicator representing an estimate of body orientation of the person from the baseband signal, the processing means comprising: means for accessing the baseband signal; means for applying a decomposition process to the baseband signal to generate a decomposition matrix; means for extracting features from an epoch of the decomposition matrix; means for classifying the features of the epoch to select a class from a plurality of classes, wherein the plurality of classes represent different body orientations; and means for generating the orientation indicator according to the selected class, the orientation indicator representing an estimate of body orientation of the person during the epoch.