System and method for collection of fit data related to selected mask

Abstract

To provide a system and method to collect feedback data from a patient wearing an interface such as a mask when using a respiratory pressure therapy device such as a CPAP device.SOLUTION: A system includes a storage device including a facial image of the patient. An interface in communication with a respiratory pressure therapy device collects operational data from when the patient uses the interface. A patient interface 100 collects subjective patient input data from the patient in relation to the patient interface. An analysis module correlates a characteristic of the interface with the facial image data, operational data and subjective patient input data.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] This application claims priority and the benefit of Australian Provisional Patent Application No. 2019904285 (filed on November 13, 2019) and US Provisional Patent Application No. 63 / 072,914 (filed on August 31, 2020). The entire content of each of these documents is incorporated herein by reference in its entirety.

[0002] The present disclosure is mainly related to a design incorporation mechanism for a respiratory disease treatment system, and more particularly, to a system that collects patient data related to the effectiveness of a mask of a pneumatic device for future designers.

Background Art

[0003] There is a range of respiratory diseases. Certain diseases can be characterized by certain manifestations (e.g., apnea, hypopnea, and hyperventilation). Obstructive sleep apnea (OSA) is a form of sleep-disordered breathing (SDB) and is characterized by manifestations such as closure or obstruction of the upper airway during sleep. This is the result of a combination of an abnormally small upper airway and the normal loss of muscle tone in the tongue area, and the normal loss of the soft palate and posterior oropharyngeal wall during sleep. Due to such conditions, the breathing cessation of affected patients typically lasts for 30 to 120 seconds, and sometimes the breathing stops 200 to 300 times a night. As a result, excessive daytime sleepiness occurs, which can cause cardiovascular diseases and brain damage. This syndrome is a common disease, especially common in middle-aged overweight men, but patients have no awareness of the symptoms.

[0004] Other sleep-related diseases include Cheyne-Stokes respiration (CSR), obesity hypoventilation syndrome (OHS), and chronic obstructive pulmonary disease (COPD). COPD encompasses any of a group of lower airway diseases that have certain common characteristics. This includes an increase in resistance to the movement of air, an extension of the expiratory phase of breathing, and a decrease in normal elasticity in the lungs. Examples of COPD are emphysema and chronic bronchitis. The causes of COPD include chronic smoking (the first risk factor), occupational exposure, air pollution, and genetic factors.

[0005] Continuous positive airway pressure (CPAP) therapy is used in the treatment of obstructive sleep apnea (OSA). For example, by pushing the soft palate and tongue to advance or retract towards the posterior oropharyngeal wall, the application of continuous positive airway pressure functions as an air sprint, thereby avoiding upper airway closure.

[0006] Non-invasive ventilation (NIV) provides ventilation assistance to a patient through the upper airway to perform part or all of the respiratory function, thereby assisting the patient during full breathing and / or maintaining an appropriate oxygen level in the body. The ventilation assistance is provided via a patient interface. NIV is used in the treatment of CSR and respiratory failure in forms such as OHS, COPD, and chest wall disorders. In some forms, the comfort and effectiveness of these treatments can be improved. Invasive ventilation (IV) provides ventilation assistance to patients who are no longer able to breathe effectively on their own and can be provided using a tracheostomy tube.

[0007] A treatment system may include a respiratory pressure therapy (RPT) device, an air circuit, a humidifier, a patient interface, and data management. The patient interface can be used, for example, to provide an interface to the breathing apparatus to the wearer by providing an air flow to the airway inlet. The air flow can be provided via a mask to the nose and / or mouth, a tube to the mouth, or a tracheostomy tube to the patient's trachea. Depending on the therapy applied, the patient interface S can form a seal with, for example, the area of the patient's face, thereby facilitating gas delivery at a sufficient distributed pressure along with the ambient pressure for therapy execution (e.g., at a positive pressure of about 10 cmH20 relative to the ambient pressure). In other treatment modalities such as oxygen delivery, the patient interface may not include a seal sufficient to facilitate delivery of gas supply to the airway at a positive pressure of about 10 cmH20. Since the treatment of respiratory diseases by such treatment can be spontaneous, if such patients become aware of the following regarding the device used to provide the treatment, they may choose not to comply with the treatment. Discomfort, difficulty in use, high cost, and / or lack of aesthetic appeal.

[0008] In the design of the patient interface, there are multiple challenges. The face has a complex three-dimensional shape. The size and shape of the nose vary greatly from person to person. Since the head includes bone, cartilage, and soft tissue, different regions of the face exhibit different responses to mechanical forces. That is, the jaw or mandible can move relative to other bones of the skull. The entire head can move throughout the respiratory treatment period.

[0009] Due to these challenges, in the case of some masks, especially when the wearing time is long or the patient is unfamiliar with the system, there may be one or more of the reasons such as being overly pressing, aesthetically undesirable, costly, poor fit, difficult to use, and uncomfortable. For example, a mask designed for pilots, personal protective equipment (e.g., filter mask), a mask designed as part of a SCUBA mask, or an anesthesia mask, although tolerable for their original uses, may be unacceptably uncomfortable for wearing over a long period (e.g., several hours). Due to such discomfort, the patient's compliance with the treatment may decrease. This is especially true when the mask needs to be worn during sleep.

[0010] CPAP therapy is extremely effective in the treatment of certain respiratory diseases when the patient has consented to the treatment. The availability of a patient interface enables the patient's participation in positive pressure treatment. When a patient is seeking a first or new patient interface as a replacement for an old interface, it is common to consult a durable medical equipment provider to determine the patient interface size recommended based on the measurement of the patient's facial anatomy, which is often done by the durable medical equipment provider. If the mask is uncomfortable or difficult to use, the patient may not consent to the treatment. Since patients are often recommended to clean the mask regularly, if the mask is difficult to clean (for example, if it is difficult to assemble or disassemble), the patient may not be able to clean the mask, which may affect patient compliance. To effectively deliver pneumatic pressure therapy, it is necessary not only to provide comfort to the patient when wearing the mask, but also to ensure a seal between the face and the mask to minimize air leakage.

[0011] As noted above, patient interfaces can be provided to patients in a variety of forms (e.g., nasal masks or full face masks / oronasal masks (FFMs) or nasal pillows). Such patient interfaces are manufactured with a variety of dimensions to accommodate the specific anatomical features of a particular patient, for example, to facilitate a comfortable interface that functions to provide positive pressure treatment. Such patient interface dimensions may be customized to correspond to the specific facial anatomy of a particular patient or, alternatively, designed to correspond to a population of individuals with anatomical structures that fall within a pre-specified spatial boundary or range. However, in some cases, masks are provided with a variety of standard sizes and it may be necessary to select the appropriate one from among them.

[0012] In this regard, sizing the patient interface to fit the patient is often done by a trained individual (e.g., a durable medical equipment (DME) provider or a physician). Typically, if a patient requires a patient interface for the initiation or continuation of positive pressure therapy, the patient visits a trained individual at a service facility. At this facility, a series of measurements are taken to determine the appropriate patient interface size from a standard size. The appropriate size means a specific combination of dimensions of specific features (e.g., the seal-forming structure of the patient interface) and provides appropriate comfort and sealing for the activation of positive pressure therapy. Thus, sizing is not only laborious but also inconvenient. The inconvenience of taking time out of a busy schedule and, in some cases, the need to travel far are barriers for many patients when receiving a new or replacement patient interface and ultimately barriers to receiving treatment. Due to such inconveniences, patients may not be able to receive the necessary patient interface and may not be able to participate in positive pressure therapy. Nevertheless, the selection of the optimal size is important in the quality and compliance of treatment.

Summary of the Invention

Problems to be Solved by the Invention

[0013] Obtaining feedback from mask users for the improvement of the design interface is needed for future mask designers. A system for collecting mask user feedback data in relation to stored face dimension data for a wide range of user populations is needed. A system for correlating user feedback data with other data related to the selected mask is needed.

Means for Solving the Problems

[0014] According to the disclosed system, an adaptable system for collecting user feedback data related to a mask used with an RPT device is provided. The system combines face image data with collected RPT operation data and other data (e.g., subjective data from a patient population for the support of mask design).

[0015] As an example of one disclosure, there is a method of collecting data related to a patient interface for a respiratory pressure therapy device. Facial image data from a patient is correlated with the patient. Operating data of a respiratory therapy device that the patient uses with the patient interface is collected. Data of subjective patient input is collected from the patient in relation to the patient interface. The characteristics of the interface are correlated with the facial image data, the operating data, and the data of subjective patient input.

[0016] In another implementation of the above-disclosed method, the patient interface is a mask. In another implementation, the respiratory pressure therapy device is one of a continuous positive airway pressure (CPAP) device, a non-invasive ventilation (NIV) device, or an invasive ventilation device. In another implementation, the facial image data is obtained from a mobile device including an application that captures an image of the patient's face. In another implementation, the method further includes displaying the facial image together with an insertion image of the interface and collecting subjective data from the patient based on the location of the insertion image of the interface. In another implementation, the subjective data is collected by displaying questions within the interface on the mobile device. In another implementation, the interface displays a sliding scale for input of the patient's response. In another implementation, the facial image data includes face height, nose width, and nose depth. In another implementation, the method includes adjusting the characteristics of the interface for leakage avoidance. This characteristic is associated with the contact between the face surface and the interface. In another implementation, the method includes adjusting the characteristics of the interface for comfort improvement. This characteristic is associated with the contact between the face surfaces. In another implementation, facial image data from a second patient similar to the patient, operating data of a respiratory therapy device used by the second patient, and subjective data input from the second patient are collected, and the correlation with the characteristics of the interface It is used in attachment. In another implementation, face image data, motion data, and subjective patient input data from a plurality of patients including the patient are collected. By applying machine learning, the types of motion data, subjective data, and face image data correlated with the characteristics are determined to adjust the characteristics of the interface.

[0017] As another example of disclosure, there is a system having a control system including one or more processors and a memory storing machine-readable instructions. The control system is coupled to the memory. The above method is executed when machine-executable instructions in the memory are executed by one of the processors of the control system.

[0018] As another example of disclosure, there is a system for communicating one or more displays to a user. The system includes a control system configured to execute one of the above-described methods.

[0019] As another example of disclosure, there is a computer program product having instructions. When these instructions are executed by a computer, the computer executes one of the above-described methods. In another implementation of an exemplary computer program product, the computer program product is a non-transitory computer-readable medium.

[0020] As another example of disclosure, there is a system for collecting feedback data from a patient using an interface with a respiratory pressure therapy device. This system includes a storage device for storing the patient's face image. When the patient uses the interface, a data communication interface communicates with the respiratory pressure therapy device to collect motion data therefrom. A patient data collection interface collects subjective patient input data from the patient in relation to the patient interface. An analysis module is operable to correlate the characteristics of the interface with the face image data, motion data, and subjective patient input data.

[0021] In other executions of the above-disclosed system, the system includes a manufacturing system that produces an interface based on design data. This analysis module adjusts the design data based on correlated characteristics. In another execution, the patient interface is a mask. In another execution, the respiratory pressure therapy device is one of a continuous positive airway pressure (CPAP) device, a non-invasive ventilation (NIV) device, or an invasive ventilation device. In another execution of the system, the mobile device runs an application that captures a face image of the patient. In another execution, the patient data collection interface displays the face image together with an inserted image of the interface and collects subjective data from the patient based on the location of the inserted image of the interface. In another execution, the collection of subjective data is performed by displaying questions within an interface on the mobile device. In another execution, the interface displays a sliding scale for input of the patient's response. In another execution, the face image data includes face height, nose width, and nose depth. In another execution, the characteristics of the interface are adjusted to avoid leakage. This characteristic is associated with the contact between the face surface and the interface. In another execution, the characteristics of the interface are adjusted to improve comfort. This characteristic is associated with the contact between the face surface and the interface. In another execution, the system includes a machine learning module. This machine learning module is operable to determine motion data, subjective data, and face image data from a plurality of patients correlated with the characteristics and adjust the characteristics of the interface.

[0022] The above summary is not intended to represent each embodiment or each aspect of the present disclosure. That is, the above summary merely shows some examples of the novel aspects and features described herein. The above features and advantages, as well as other features and advantages of the present disclosure, will become readily apparent when read in conjunction with the following detailed description of representative embodiments and aspects for the practice of the invention, the accompanying drawings, and the appended claims.

[0023] The following description of the exemplary embodiments, taken in conjunction with the accompanying drawings, will enhance the understanding of the present disclosure.

Brief Description of the Drawings

[0024]

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 3C

Figure 4A

Figure 4B

Figure 4C

Figure 5

Figure 6

Figure 7A

Figure 7B

Figure 7C

Figure 7D

Figure 8A

Figure 8B

Figure 8C

Figure 8D

Figure 9A

Figure 9B

Figure 9C

Figure 9D

Figure 9E

Figure 10A

Figure 10B

Figure 10C

Figure 10D

Figure 10E

Figure 10F

Figure 11A

Figure 11B

Figure 11C

Figure 11D

Figure 12

Figure 13

Figure 14

Best Mode for Carrying Out the Invention

[0025] The present disclosure has various modifications and alternative forms. Some representative embodiments illustrated in the drawings are detailed below in this specification. However, it should be understood that the present invention is not intended to be limited to the specific forms disclosed, and rather, the present disclosure encompasses all modifications, equivalents, and alternatives within the spirit and scope of the present invention defined by the appended claims.

[0026] The present invention can be embodied in many different forms. Representative embodiments are shown in the drawings and will be described in detail below. This disclosure is an example or illustration of the principles of this disclosure and is not intended to limit the broad aspects of this disclosure to the illustrated embodiments. Therefore, elements or limitations disclosed in sections such as "Summary", "Summary of the Invention", and "Modes for Carrying Out the Invention", even if not specified in the claims, should not be incorporated into the claims, either individually or collectively, by implication, inference, or other means. In this specification, unless otherwise specified, the singular form includes the plural form and vice versa. The term "comprising" means "including but not limited to". Further, in this specification, words representing approximations such as "substantially", "approximately", "substantially", "about" can be used for the purpose of meaning, for example, "exactly", "near", "around", "within 3 - 5% of", "within the range of acceptable manufacturing tolerances", or any logical combination thereof.

[0027] This disclosure relates to systems and methods for collecting feedback data from a mask selected for a user of a respiratory pressure therapy device. The mask is sized based on face data collected for the user. An interface is presented to the user for collecting feedback data about the sized mask. This data is analyzed to further refine the design of masks for similar patients based on factors such as performance data, patient demographics, and patient face features.

[0028] FIG. 1 shows a system including a patient 10 wearing a patient interface 100. This system takes the form of a full face mask (FFM) and receives positive pressure air supplied from a respiratory pressure therapy (RPT) device 40. The air from the RPT device 40 is humidified by a humidifier 60 and moves along an air circuit 50 to the patient 10.

[0029] Figure 2 shows a patient interface 100 according to one aspect of the present technology. The patient interface 100 includes the following functional aspects. A seal-forming structure 160, a plenum chamber 120, a positioning and stabilization structure 130, a ventilation portion 140, a forehead support portion 150, and a form of connection port 170 for connection to the air circuit 50 in FIG. 1. In some forms , the functional aspects can be provided by one or more physical components. In some forms, one physical component can provide one or more functional aspects. In use, the seal-forming structure 160 is arranged to surround the entrance of the patient's airway so as to facilitate the supply of air at positive pressure to the airway.

[0030] In one form of the present technology, the seal-forming structure 160 can provide a seal-forming surface and further provide a cushioning function. The seal-forming structure 160 according to the present technology can be composed of a soft, flexible and elastic material (for example, silicone). In one form, the seal-forming portion of the non-invasive patient interface 100 includes a pair of nasal puffs or nasal pillows. Each nasal puff or nasal pillow is configured and arranged to form a seal with each nostril of the patient's nose.

[0031] The nasal pillow according to the present technology includes a frustum of a cone. At least a part of the frustum of the cone forms a seal on the lower side of the patient's nose, the handle portion, and a flexible region above the lower side of the frustum of the cone, and connects the frustum of the cone to the handle portion. In addition, the structure to which the nasal pillow of the present technology is connected includes a flexible region adjacent to the base of the handle portion. The flexible region can function to facilitate a freely jointed structure. The freely jointed structure corresponds to the mutual movement of both the displacement and angle of the frustum of the cone and the structure to which the nasal pillow is connected. For example, the frustum of the cone can be displaced axially towards the structure to which the handle portion is connected.

[0032] In one form, the non-invasive patient interface 100 includes a seal-forming portion that forms a seal on the upper lip region (i.e., the upper lip) of the patient's face. In one form, the non-invasive patient interface 100 includes a seal-forming portion that forms a seal on the jaw region of the patient's face during use.

[0033] Preferably, the plenum chamber 120 has an edge shaped to be complementary to the surface contour of an average human face in the region where a seal is formed during use. During use, the peripheral edge of the plenum chamber 120 is positioned close to the adjacent surface of the face. The actual contact with the face is provided by the seal formation structure 160. The seal formation structure 160 can extend around the entire edge of the plenum chamber 120 during use.

[0034] Preferably, the seal formation structure 160 of the patient interface 100 of the present technology can be held in a sealed position by the positioning and stabilization structure 130 during use.

[0035] In one form, the patient interface 100 includes a ventilation portion 140 configured and arranged to allow the extrusion of exhaled carbon dioxide. The ventilation portion 140 of one form according to the present technology includes a plurality of holes (e.g., about 20 to about 80 holes or about 40 to about 60 holes or about 45 to about 55 holes).

[0036] FIG. 3A shows a front view of a human face including the inner canthus, nasal alae, nasolabial folds, upper and lower lips, upper and lower vermilion borders, and commissure points. Also shown are the mouth width, the sagittal plane dividing the head into left and right portions, and a direction indicator. The direction indicator indicates the radial inward / outward and upward / downward directions. FIG. 3B is a side view of a human face including the glabella, sellion, nasalis muscle, tip of the nose, subnasale, upper and lower lips, supramenton, alar apex points, and upper and lower ear base points. A direction indicator indicating the upward / downward and forward / backward directions is also shown. FIG. 3C is a bottom view of the nose including several features including the nasolabial fold, lower lip, upper vermilion border, nostril, subnasale, nasal septum, tip of the nose, main axis of the nostril, and sagittal plane.

[0037] The features of the human face shown in FIGS. 3A to 3C will be described in more detail below.

[0038] Ala: The outer wall or "wing" of each nostril (plural: alar)

[0039] Alare: The outermost point on the alar wing.

[0040] Alar curvature (or alar crest) point: The rearmost point on the curvilinear reference line of each alar wing, seen at the crease formed by the junction of the alar wing and the cheek.

[0041] Auricle: The entire visible part of the ear.

[0042] Columella: A skin flap that separates the nostrils and extends from the tip of the nose to the upper lip.

[0043] Columella angle: The angle between a line drawn through the midpoint of the nostrils and a line drawn perpendicular to the Frankfurt horizontal while intersecting the subnasal point.

[0044] Glabella: Located in the soft tissue, the most prominent point on the mid-sagittal of the forehead.

[0045] Nostrils (nares): Generally oval-shaped alar cavities that form the entrance to the nasal cavity. The singular form of nostrils (nares) is naris (nasal cavity). These nostrils are separated by the nasal septum.

[0046] Nasolabial groove or nasolabial fold: A skin fold or groove that extends from each side of the nose to the corner of the mouth, separating the cheek from the upper lip.

[0047] Nasolabial angle: The angle between the columella and the upper lip, intersecting the subnasal point.

[0048] Lower ear attachment point: The lowest point of attachment of the auricle to the facial skin.

[0049] Upper ear attachment point: The highest point of attachment of the auricle to the facial skin.

[0050] Tip of the nose point: The most prominent point or tip of the nose, which can be identified in the side view of the remaining part of the head.

[0051] Philtrum: A midline groove extending from the lower border of the nasal septum to the upper part of the lip in the upper lip region.

[0052] Pogonion: The most anterior midpoint of the jaw, located on the soft tissue.

[0053] (Nasal) sill: The nasal sill is a midline ridge of the nose that extends from the sellion to the tip of the nose.

[0054] Sagittal plane: A vertical plane extending from the front (anterior) to the back (posterior), dividing the body into right and left halves.

[0055] Sellion: The most concave point on the area of the fronto-nasal suture, located on the soft tissue.

[0056] Septal cartilage (nasal): The septal cartilage is part of the septum and divides the front part of the nasal cavity.

[0057] Lowest alar point: The point at the lower periphery of the alar base, where the alar base joins the skin of the upper (superior) lip.

[0058] Subnasale: The point located on the soft tissue where the columella meets the upper lip in the mid-sagittal plane.

[0059] Supramenton: The most concave point in the midline of the lower lip between the midpoint of the lower lip and the soft tissue pogonion 。

[0060] As described below, there are several important dimensions from the face that can be used in the selection of sizing of a patient interface such as mask 10 in FIG. 1. In this example, there are three dimensions including face height, nasal width, and nasal depth. The line 3010 shown in FIGS. 3A - 3B indicates the face height. As can be seen from FIG. 3B, the face height is the distance from the sellion to the supramenton. The line 3020 in FIG. 3A indicates the nasal width between the left alar point and the right alar point. The line 3030 in FIG. 3B indicates the nasal depth.

[0061] Figure 4A shows an exploded view of components of an exemplary RPT device according to one aspect of the present technology that includes mechanical, pneumatic, and / or electrical components and is configured to execute one or more algorithms (e.g., any of the methods described herein, whether in whole or in part). Figure 4B shows the lower portion of the RPT device 40. Figure 4C is a schematic diagram of the electrical components of the RPT device 40 according to one aspect of the present technology. Upstream and downstream directions are shown with respect to the blower and the patient interface. Regardless of the actual flow direction at any given instant, the blower is defined as being upstream of the patient interface and the patient interface is defined as being downstream of the blower. Items disposed within the pneumatic path between the blower and the patient interface are downstream of the blower and upstream of the patient interface. The RPT device 40 can be configured to generate an air flow that is delivered to a patient's airway, for example, for one or more treatments of a respiratory condition.

[0062] The RPT device 40 can have an external housing 4010. The external housing 4010 is formed by two parts (i.e., an upper part 4012 and a lower part 4014). Further, the external housing 4010 can include one or more panels 4015. The RPT device 40 includes a chassis 4016 that supports one or more internal components of the RPT device 40. The RPT device 40 can include a handle 4018.

[0063] The pneumatic path of the pneumatic RPT device 40 can include one or more air path items (e.g., an inlet air filter 4112, an inlet muffler 4122, a pressure generator 4140 (e.g., a blower 4142) capable of supplying air at positive pressure, an outlet muffler 4124) as well as one or more transducers 4270 (e.g., a pressure sensor 4272, a flow sensor 4274, and a motor speed sensor 4276).

[0064] One or more of the air path items may be disposed within a removable integrated structure called a pneumatic block 4020. The pneumatic block 4020 may be disposed within an external housing 4010. In one form, the pneumatic block 4020 is supported by a chassis 4016 or formed as part of the chassis 4016.

[0065] The RPT device 40 can have a power source 4210, one or more input devices 4220, a central controller 4230, a pressure generator 4140, a data communication interface 4280, and one or more output devices 4290. Another controller may be provided for the treatment device. The electrical components 4200 can be mounted on a single printed circuit board assembly (PCBA) 4202. In an alternative form, the RPT device 40 can include more than one PCBA 4202. Also, other components such as one or more protection circuits 4250, transducers 4270, the data communication interface 4280, and a storage device can be mounted on the PCBA 4202.

[0066] The RPT device can include one or more of the following components within an integrated unit. In an alternative form, one or more of the following components can be disposed as separate units.

[0067] The RPT device according to one form of the present technology can include an air filter 4110 or a plurality of air filters 4110. In one form, the inlet air filter 4112 is disposed at the beginning of the upstream of the air pressure path of the pressure generator 4140. In one form, the outlet air filter 4114 (e.g., antibacterial factor) is disposed between the outlet of the pneumatic block 4020 and the patient interface 100.

[0068] The RPT device according to one aspect of the present technology may include a muffler 4120 or a plurality of mufflers 4120. In one aspect of the present technology, the inlet muffler 4122 is disposed above the pressure generator 4140 within the pneumatic path. In one aspect of the present technology, the outlet muffler 4124 is disposed between the pressure generator 4140 and the patient interface 100 of FIG. 1 within the pneumatic path.

[0069] In one aspect of the present technology, the pressure generator 4140 that generates the air flow or supply at positive pressure is a controllable blower 4142. For example, the blower 4142 may include a brushless DC motor 4144 having one or more impellers. The impeller may be disposed within a volute. The blower can deliver the air supply at a speed of, for example, up to about 120 liters per minute, at a positive pressure in the range of about 4 cmH2O to about 20 cmH2O, or in other aspects up to about 30 cmH2O. The blower may be described in any one of the following patents or patent applications, which are hereby incorporated by reference in their entirety herein: 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 WO2013 / 020167.

[0070] The pressure generator 4140 is under the control of a treatment device controller 4240. In other aspects, the pressure generator 4140 may be a piston-driven pump, a pressure regulator connected to a high-pressure source (e.g., a pressurized air reservoir), or a bellows.

[0071] The air circuit 4170 according to one aspect of the present technology is a conduit or tube constructed and arranged such that during use, a pressurized air flow moves between two components (e.g., the humidifier 60 and the patient interface 100). Specifically, the air circuit 4170 may be in fluid communication with the outlet of the humidifier 60 and the plenum chamber 120 of the patient interface 100.

[0072] In one form of the present technology, an anti-spillback valve 4160 can be disposed between the humidifier 60 and the pneumatic block 4020. The anti-spillback valve is constructed and arranged to reduce the risk of water flowing upstream from the humidifier 60 (e.g., to the blower motor 4144).

[0073] The power supply 4210 can be disposed inside or outside the external housing 4010 of the RPT device 40. In one form of the present technology, the power supply 4210 supplies power only to the RPT device 40. In another form of the present technology, power is provided from the power supply 4210 to both the RPT device 40 and the humidifier 60.

[0074] The RT system can include one or more transducers (sensors) 4270 configured to measure one or more of any number of parameters related to the RT system, its patient, and / or its environment. The transducer can be configured to produce an output signal representative of one or more parameters configured to be measured by the transducer.

[0075] This output signal can be one or more of any number of other signals known in the art, such as an electrical signal, a magnetic signal, a mechanical signal, a visual signal, an optical signal, an audio signal, etc.

[0076] The transducer can be integrated with other components of the RT system, and one exemplary arrangement is where the transducer is built into the RPT device. The transducer can be a substantially "stand-alone" component of the RT system, and an exemplary arrangement would be where the transducer is external to the RPT device.

[0077] The transducer may be configured to transmit its output signal to one or more components of the RT system, such as an RPT device, a local external device, or a remote external device. The external transducer may be located, for example, in a patient interface or an external computing device such as a smartphone. The external transducer may be disposed, for example, on the air path or may form part of the air path (e.g., the patient interface).

[0078] One or more transducers 4270 may be constructed and arranged to generate a signal indicative of a property of air (e.g., flow rate, pressure, or temperature). The air may be the air flow from the RPT device to the patient, the air flow from the patient to the atmosphere, ambient air, or the like. The signal may represent the nature of the air flow at a particular point, such as the air flow in the air pressure path between the RPT device and the patient. In one form of the technology, one or more transducers 4270 may be disposed upstream and / or downstream of the pressure generator 60.

[0079] According to one aspect of the technology, one or more transducers 4270 include a pressure sensor located in fluid communication with the air pressure path. One example of a suitable pressure sensor is a transducer from the HONEYWELL ASDX series. Another suitable pressure sensor is a transducer from the NPA series from GENERAL ELECTRIC. In one embodiment, the pressure sensor is located in the air circuit 4170 adjacent to the outlet of the humidifier 60.

[0080] The microphone pressure sensor 4278 is configured to generate an acoustic signal representative of a change in pressure within the air circuit 4170. The acoustic signal from the microphone 4278 may be received by the central controller 4230 for acoustic processing and analysis as configured by one or more of the algorithms described below. The microphone 4278 may be directly exposed to the air path to enhance sensitivity to sound or may be encapsulated on the back side of a thin layer of flexible membrane material. This membrane may function to protect the microphone 4278 from heat and / or moisture.

[0081] Data from transducers 4270 such as pressure sensor 4272, flow sensor 4274, motor speed sensor 4276, and microphone 4278 can be periodically collected by central controller 4230. Such data is mainly related to the operating state of RPT device 40. In this example, central controller 4230 encodes such data from the sensors in a dedicated data format. The data encoding may be performed in a standardized data format.

[0082] In one form of the present technology, RPT device 40 includes one or more input devices 4220 in the form of buttons, switches or dials to enable a human to interact with the device. The buttons, switches or dials can be physical or software devices accessible via a touch screen. The buttons, switches or dials may in one form be physically connected to external housing 4010, or in another form may communicate wirelessly with a receiver electrically connected to central controller 4230. In one form, input device 4220 can be constructed and arranged to enable a human to select values and / or menu options.

[0083] In one form of the present technology, central controller 4230 is for controlling RPT device 40 One or more suitable processors. Suitable processors may include processors based on the ARM® Cortex®-M processors from ARM Holdings, x86 INTEL processors (e.g., the S®32 series of microcontrollers from STMicroelectronics). In certain alternative forms of the present technology, a 32-bit RISC CPU (e.g., the STR9 series of microcontrollers from STMicroelectronics) or a 16-bit RISC CPU (e.g., a processor from the MSP430 family of microcontrollers manufactured by TEXAS INSTRUMENTS) may also be suitable. In one form of the present technology, the central controller 4230 is a dedicated electronic circuit. In one form, the central controller 4230 is an application-specific integrated circuit. In another form, the central controller 4230 includes discrete electronic components. 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 60.

[0084] The central controller 4230 may be configured to provide output signal(s) to one or more of the output device 4290, the therapy device controller 4240, the data communication interface 4280, and the humidifier 60.

[0085] In some forms of the present technology, the central controller 4230 is configured to implement one or more methods described herein (e.g., one or more algorithms expressed as a computer program recorded in a non-transitory computer-readable recording medium on an internal memory). In some forms of the present technology, the central controller 4230 may be integrated with the RPT device 40. However, in some forms of the present technology, some methods may be performed by remotely located devices (e.g., mobile computing devices). For example, a remotely located device may determine control settings for a ventilator or detect respiratory-related events by analyzing recorded data (e.g., from any of the sensors described herein). As described above, all of the data and operations of the external source or the central controller 4230 are often specific to the manufacturer of the RPT device 40. Therefore, data from the sensors and any other additional operational data are often not accessible from any other device.

[0086] In one form of the present technology, a data communication interface is provided and connected to the central controller 4230. The data communication interface may be connectable to a remote external communication network and / or a local external communication network. The remote external communication network may be connectable to a remote external device (e.g., a server or a database). The local external communication network may be connectable to a local external device (e.g., a mobile device or a health monitoring device). Therefore, the local external communication network may be used by either the RPT device 40 or a mobile device for the purpose of collecting data from other devices.

[0087] In one form, the data communication interface is part of the central controller 4230. In another form, the data communication interface 4280 is separate from the central controller 4230 and may include an integrated circuit or a processor. In one form, the remote external communication network is the Internet. The data communication interface may use wired communication (e.g., via Ethernet® or fiber optic) or a wireless protocol (e.g., CDMA, GSM®, 2G, 3G, 4G / LTE Cat-M, NB-IoT, 5G New Radio, satellite, beyond 5G) to connect to the Internet. In one form, the local external communication network 4284 uses one or more communication standards (e.g., Bluetooth® or consumer infrared protocol).

[0088] As shown in FIG. 4C, an exemplary RPT device 40 includes an integrated sensor and communication electronics. In the case of an older RPT device, a retrofit with a sensor module that may include communication electronics for transmitting the collected data may be possible. Such a sensor module may be attached to the RPT device and thus may send the operating data to the remote analysis engine 130.

[0089] In some implementations of the disclosed acoustic analysis techniques, cepstrum analysis based on an audio signal from a sensor (e.g., audio sensor 4278) can be performed. The audio signal can reflect a user's physiological state (e.g., sleep or respiration) as well as the operating data of the RPT. The cepstrum can be considered, for example, as the inverse Fourier transform of the logarithmic spectrum of the forward Fourier transform of the decibel spectrum. This operation can substantially transform the impulse response function (IRF) and the convolution of sound sources into an addition operation, whereby the sound sources can then be easily accounted for or removed so as to separate the IRF data for analysis. The techniques of cepstrum analysis are described in detail in the following scientific literature: "The Cepstrum: A Guide to Processing" (Childers et al., Proceedings of the IEEE, Vol. 65, No. 10, Oct 1977) and Randall RB, Frequency Analysis, Copenhagen: Bruel & Kjaer, p. 344 (1977, revised ed. 1987). The application of cepstrum analysis to respiratory therapy system component characteristics is described in PCT Publication No. WO2010 / 091462 (entitled "Acoustic Detection for Respiratory Treatment Apparatus"). The entire content of this document is incorporated herein by reference for all purposes.

[0090] As described above, a respiratory therapy system typically includes an RPT device, a humidifier, an air delivery conduit, and a patient interface (e.g., the components shown in FIG. 1). A variety of different forms of patient interfaces can be used with a given RPT device (e.g., nasal pillows, nasal prongs, nasal masks, nasal & oral (oronasal) masks, or full face masks). Additionally, different forms of air delivery conduits can be used. To improve the control of therapy delivery to the patient interface, the measurement or estimation of therapy parameters (e.g., pressure and ventilation flow within the patient interface) can be analyzed. In older systems, the determination of the type of components the patient is using can be done as follows for the determination of the optimal interface for the patient. In some RPT devices, a menu system is included that allows the patient to select the type of system components (e.g., the patient interface being used) (e.g., brand, form, model). When the patient inputs the type of component, the RPT device can select the appropriate operating parameters of the flow generator that optimally cooperates with the selected component. The data collected by the RPT device can be used to evaluate the effectiveness of a particular selected component (e.g., the patient interface in the pressurized air supply to the patient).

[0091] According to the analysis method included in this technology, it is possible to separate the reflection of the acoustic mask from other system noises and responses (non-limiting examples include blower noise). As a result, it is possible to identify the differences between acoustic reflections from different masks (which are often determined by the shape, configuration, and material of the mask), and it may be possible to identify different masks without user or patient intervention.

[0092] As an exemplary method for identifying the mask, the output audio signal y(t) generated by the microphone 4278 is sampled at least at the Nyquist rate (e.g., 20 kHz). After calculating the cepstrum from the sampled output signal, the cepstrum There is a method of separating the reflection component of the ram from the input signal component of the cepstrum. Since the reflection component of the cepstrum includes acoustic reflections from the mask of the input audio signal, it is called the "acoustic signature" or "mask signature" of the mask. Next, the acoustic signature is compared with a predetermined database of pre-measured acoustic signatures obtained from a system including a predefined database or known masks. Optionally, certain decision criteria are set for determining the appropriate similarity. In one exemplary embodiment, the comparison can be completed based on a single maximum data peak in the cross-correlation between the measured and stored acoustic signatures. However, this approach can also be improved by comparing several data peaks, or these comparisons can be completed for a unique set of extracted cepstrum features.

[0093] Thereafter, according to the present technology, the data associated with the reflection component can be compared with similar data from the previously identified mask reflection component (e.g., those included in the memory or database of the mask reflection component).

[0094] As described above, the RPT device 40 can provide data on the type of patient interface and operational data. By correlating the operational data with the mask type and patient-related data, it may be possible to determine whether a particular mask type is effective. For example, the operational data can reflect both the usage time of the RPT device 40 and the presence or absence of treatment effectiveness due to the usage. The type of patient interface can be correlated with the level of patient compliance or treatment effectiveness as determined from the operational data collected by the RPT device 40. By using the correlation data, an effective interface can be more effectively determined for a new patient in need of respiratory treatment from a similar RPT device. Combining this selection with the face dimensions obtained from a face scan of the new patient aids in the selection of the interface.

[0095] Thus, according to the present technology, by performing the integration of data collected from the use of the RPT device in relation to different masks by a patient population (including the individual patient's face features determined by the scan process), patients can obtain a patient interface such as a mask more quickly and easily. The scan process enables the patient to comfortably perform the measurement of their own facial anatomical structure from home using a computing device (e.g., a desktop computer, tablet, smartphone or other mobile device) quickly. Thereafter, the computing device may receive recommendations regarding the appropriate patient interface size after analysis of the patient's face dimensions, and the types and data from the general patient population associated with different interfaces. The collection of face data may also be performed by other methods such as pre-stored face images. Such face data is stored and correlated with the information related to the patient and the operational data from the RPT device.

[0096] In this example, for the collection of face data, an application that can be downloaded from a manufacturer or third-party server to a smartphone or tablet equipped with an integrated camera may be used. When launched, visual instructions and / or voice instructions may be provided from the application. In accordance with the instructions, the user (i.e., the patient) may stand in front of a mirror and press the camera button on the user interface. Next, the activated process may obtain the face dimensions for the selection of the interface (based on the photo analysis by the processor) within, for example, about 2 seconds after taking a series of photos of the user's face. As described below, after the selection of the mask and the start of use with the RPT40, it may be possible to collect feedback from the user using such an application.

[0097] The user / patient may capture one image or a series of images of their facial structure. Instructions provided from an application stored on a computer-readable medium When executed, for example, by a processor, various face landmarks in an image are detected, the distances between the landmarks are measured and scaled, these distances are compared to data records, and an appropriate patient interface size is recommended. Thus, by a consumer's automated device, high-precision patient interface selection may be possible, for example, at home, and a customer may be able to make sizing decisions (without the presence of a trained partner).

[0098] The exemplary system 200 shown in FIG. 5 may be used when collecting patient interface feedback data from a patient. The system 200 may also include automated face feature measurement and patient interface selection. The system 200 may primarily include one or more of a server 210, a communication network 220, and a computing device 230. The server 210 and the computing device 230 may communicate via the communication network 220. The communication network 220 may be wired network data with a wired network 222, a wireless network 224, or a wireless link 226. In some versions, the server 210 may communicate unidirectionally with the computing device 230 by providing information to the computing device 230, and vice versa. In other embodiments, the server 210 and the computing device 230 may share information and / or processing tasks. The system 200 may be implemented to enable, for example, automated purchase of a patient interface (e.g., mask 100 in FIG. 1), where the process may include the automated sizing process described in more detail herein. For example, a customer may be able to place an online data order for a mask after executing a mask selection process. According to this mask selection process, an appropriate mask size is automatically identified by combining image analysis of the customer's face features with motion data from other masks and RPT motion data from a patient population using different types and sizes of masks. After the mask is used by the patient, the system 200 continuously collects feedback data.

[0099] Server 210 and / or computing device 230 may also communicate with a respiratory therapy device (e.g., RPT 250 similar to RPT 40 shown in FIG. 1). In this example, the RPT device 250 may perform operation data collection in relation to patient utilization, mask leakage, and other related data, and provide feedback in relation to mask utilization. Data from the RPT device 250 is collected and correlated with the individual patient data of the patient using the RPT device 250 in the patient database 260. The patient interface database 270 includes data about different types and sizes of interfaces (e.g., masks) that can be used by new patients. The patient interface database 270 may also include acoustic signature data of various masks. This acoustic signature data may enable the determination of the mask type from the voice data collected from the respiratory therapy device. The mask analysis engine executed by the server 210 is used for correlating and determining the effective mask size and shape from the individual's face dimension data with the corresponding effectiveness from the operation data (including the entire patient population) collected by the RPT device 250. For example, evidence of a valid fitting includes minimal leakage detection, maximum compliance with the treatment plan (e.g., mask-on time and mask-off time, and the frequency of on-events and off-events), the number of apneas overnight, the AHI level, the pressure settings used on the patient's device, and the specified pressure settings. This data may be correlated with the face dimension data of the new patient. As described below, the server 210 collects data from a plurality of patients stored in the database 260 and the corresponding mask size type data stored in the database 270, and selects an appropriate mask based on the optimal mask that best fits the scanned face dimension data collected from the new patient and the mask that achieved the best operation data for patients with face dimensions, sleep behavior data, and demographic data similar to the new patient. Such data is used when the patient uses the RPT device 250 It is supplemented by additional feedback taking the form of subjective data entered manually and operational data from the RPT device 250 related to the patient interface or mask.

[0100] The computing device 230 can be a desktop or laptop computer 232 or a mobile device (e.g., smartphone 234 or tablet 236). FIG. 6 shows a general architecture 300 of the computing device 230. The computing device 230 can include one or more processors 310. The computing device 230 can also include a display interface 320, a user control / input interface 331, sensors 340 and / or a sensor interface for one or more sensors, an inertial measurement unit (IMU) 342, and a non-volatile memory / data storage device 350.

[0101] The sensor 340 can be one or more cameras (e.g., a CCD charge-coupled device or an active pixel sensor) and can be integrated with the computing device 230 (e.g., provided within a smartphone or a laptop). Alternatively, if the computing device 230 is a desktop computer, the device 230 can include a sensor interface for connection to an external camera (e.g., the webcam 233 shown in FIG. 5). Other exemplary sensors that can be used to assist in the methods described herein can be integrated with the computing device or provided external to the computing device, and include, for example, a stereo camera for three-dimensional image capture or a photodetector capable of detecting reflected light from a laser or strobe / structured light source.

[0102] Via the user control / input interface 331, the user can provide commands or respond to prompts or instructions provided to the user. This can be, for example, a touch panel, keyboard, mouse, microphone, and / or speaker.

[0103] The display interface 320 may include a monitor, an LCD panel, etc. for the following displays. Prompts, output information (e.g., face measurement or interface size recommendations), and other information (e.g., capture displays as described in more detail below).

[0104] The memory / data storage device 350 may be the internal memory of the computing device (e.g., RAM, flash memory, or ROM). In some embodiments, the memory / data storage device 350 may be an external memory (e.g., an SD card, a server, a USB flash drive, or an optical disk) linked to the computing device 230. In other embodiments, the memory / data storage device 350 may be a combination of external memory and internal memory. The memory / data storage device 350 includes stored data 354 and processor control instructions 352 that instruct the processor 310 to perform specific tasks. The stored data 354 may include data received by the sensor 340 (e.g., captured images) and other data provided as component parts of the application. The processor control instructions 352 may be provided as component parts of the application.

[0105] As described above, the face image may be captured by a mobile computing device (e.g., smartphone 234). Appropriate 3D related face data can be obtained for assistance in appropriate mask selection by an appropriate application executed on the computing device 230 or the server 210. In this application, any appropriate face scanning method may be used. Examples of such applications are given below. the Capture (StandardCyborg) (https: / / www.standardcyborg.com / ), applications from Scandy Pro (https: / / www.scandy.co / products / scandy-pro), the Beauty3D application from Qianxun3d (http: / / www.qianxun3d.com / scanpage), the Unre 3D FaceApp (http: / / www.unre.ai / index.php?route=ios / detail) and applications from Bellus3D (https: / / www.bellus3d.com / ). In the detailed process of face scanning, the technology disclosed in WO2017000031 is included. In this specification, the entire document is incorporated by reference for all purposes.

[0106] One such application is an application for face feature measurement and / or patient data collection 360, which is downloadable to a mobile device (e.g., smartphone 234 and / or tablet 236). The application 360 can also collect face features and data of patients already using such masks for improving the feedback collection from such masks. The application 360, which can be stored on a computer-readable medium (e.g., memory / data storage device 350), includes programmed instructions for causing the processor 310 to perform certain tasks related to face feature measurement and / or sizing of the patient interface. This application also includes data that can be processed by an algorithm of an automated method. Such data includes, as will be further detailed below, data records, reference features, and correction factors.

[0107] When application 360 is executed by processor 310, a patient's facial features are measured using a 2D or 3D image, and based on the measurements obtained, an appropriate patient interface size and type are selected, for example, from a group of standard sizes. The method can be mainly characterized as including the following three or four different phases: a pre-capture phase, a capture phase, a post-capture image processing phase, and a comparison and output phase.

[0108] In some cases, the application for facial feature measurement can control processor 310 to output a visual display including reference features on display interface 320. The user can position this feature adjacent to their own facial features, for example, by moving the camera. Next, when certain conditions (e.g., alignment conditions) are met, the processor can capture one or more images of the facial features and save them in association with the reference features. This can be done by using a mirror. The mirror reflects the displayed reference features and the user's face to the camera. Next, the application controls processor 310 to identify specific facial features in the image and measure the distance between them. Next, through image analysis processing, using a scale factor, facial feature measurements, which can be the number of pixel counts, can be converted into standard mask measurement values based on the reference features. Such values can be, for example, a reference measurement unit (e.g., meter or inch) and a value expressed in a unit suitable for mask sizing.

[0109] Additional correction factors may be applied to these measurements. The face feature measurements may be compared to a data record that includes a measurement range corresponding to different patient interface sizes adapted to a particular patient interface form (e.g., nasal mask and FFM). Next, a recommended size may be selected and output to the user / patient as a recommendation based on the comparison(s). Such a process may be comfortably and conveniently performed at any suitable user location. The application may perform the method within seconds. In one example, the application performs the method in real time.

[0110] In the pre-capture phase, in particular, the processor 310 assists the user in establishing conditions suitable for the capture of one or more images for sizing processing. Some of these conditions include, for example, appropriate lighting and camera direction and motion blur (due to the computing device 230 being held by hand and thus unstable).

[0111] The user may conveniently download an application for performing automatic measurements and sizing on the computing device 230 from a server (e.g., a third-party application storage server) onto his or her computing device 230. Once downloaded, such an application may be stored on the internal non-volatile memory (e.g., RAM or flash memory) of the computing device. The computing device 230 is preferably a mobile device (e.g., smartphone 234 or tablet 236).

[0112] When the user launches the application, the processor 310 may prompt the patient to provide certain information (e.g., age, gender, weight, and height) via the display interface 320. However, the processor 310 may prompt the user to enter this information at any time (e.g., after measuring the user's facial features and after the user has used the mask with the RPT). The processor 310 may also present a tutorial. This tutorial may be provided audibly and / or visually (e.g., provided by the application to assist the user in understanding their role during the process). The prompt may also require information about the patient interface type (e.g., nasal or full-face) and the type of device that the patient interface is intended for. Also, during the pre-capture phase, the application may extrapolate patient-specific information based on information that the user has already collected, for example, after receiving a captured image of the user's face and based on machine learning techniques or through artificial intelligence. Other information may also be collected through the interface as described below.

[0113] The state that the user is ready to proceed can be indicated in response to a prompt via the user input or the user control / input interface 331. If the user is ready to proceed, the processor 310 activates the sensor 340 as directed by the processor control instruction 352. The sensor 340 is preferably a camera facing the front of the mobile device and is disposed on the mobile device on the same side as the display interface 320. The camera is generally configured to capture a two-dimensional image. Mobile devices that capture two-dimensional images are ubiquitous. In this technology, this ubiquity is utilized to avoid the need for the user to bear the burden of obtaining special equipment.

[0114] Almost simultaneously with the activation of the sensor / camera 340, the processor 310 presents the capture display on the display interface 320 as directed by the application. The capture display may include a live action preview of the camera, reference features, target setting boxes, and one or more status indicators or any combination thereof. In this example, the reference feature is displayed in the center on the display interface and has a width corresponding to the width of the display interface 320. The vertical position of the reference feature may be such that the upper edge of the reference feature is adjacent to the uppermost edge of the display interface 320 or the lower edge of the reference feature is adjacent to the lowermost edge of the display interface 320. A portion of the display interface 320 displays the camera live action preview 324. The camera live action preview 324 typically shows the user's face features captured in real time by the sensor / camera 340 (when the user is in the correct position and orientation).

[0115] The reference feature is a feature known to a (predetermined) computing device 230 and provides a reference frame that enables the processor 310 to perform scaling of the captured image. The reference feature may preferably be a feature other than the user's face features or anatomical features. Thus, during the image processing phase, the reference feature assists the processor 310 in determining the timing at which certain alignment conditions are met (e.g., during the pre-capture phase). The reference feature may be a Quick Response (QR) code (registered trademark) or a known template or marker, and may provide the processor 310 with specific information (e.g., scaling information, orientation, and / or any other desired information that may optionally be determined from the structure of the QR code (registered trademark)). The QR code (registered trademark) may have a square or rectangular shape. When displayed on the display interface 320, the reference feature has a predetermined dimension (e.g., in millimeters or centimeters). The dimension value may be encoded into the application and communicated to the processor 310 at an appropriate time. The actual dimension of the reference feature 326 may vary depending on the various computing devices. In some versions, the application may be configured to be specific to the computing device model. That is, the dimension of the reference feature 326 is known when displayed on a particular model. However, in other embodiments, the application may instruct the processor 310 to obtain specific information (e.g., display size and / or zoom characteristics) from the device 230. As a result, the processor 310 can calculate the real-world / actual dimension of the reference feature as displayed on the display interface 320 via scaling. Nevertheless, the actual dimension of the reference feature as displayed on the display interface 320 of such a computing device is often known prior to post-capture image processing.

[0116] Along with the reference feature, the target setting box can be displayed on the display interface 320. The target setting box enables the user to align a specific component within the capture display 322 in the target setting box. This is desirable for the success of image capture.

[0117] The status indicator provides information regarding the status of the process to the user. As a result, the user is assisted in ensuring that major adjustments to the positioning of the sensor / camera are made before the completion of image capture.

[0118] Thus, when the user holds the display interface 320 parallel to the face feature being measured and provides the user display interface 320 to a mirror or other reflective surface, the reference feature is displayed large, overlaid on the real-time image being viewed by the camera / sensor 340, and reflected by the mirror. This reference feature can be fixed in the vicinity of the upper part of the display interface 320. Since this reference feature is displayed large at least in part in this way, the sensor 340 can clearly view the reference feature and the processor 310 can easily identify the feature. In addition, since the reference feature can be overlaid on the live view of the user's face, it helps to avoid user confusion.

[0119] Instructions from the processor 310 to the user may be given via audible instructions (via the speaker of the computing device 230) via the display interface 320 to position the position display interface 320 within the plane of the face feature being measured, or may be given prior to the tutorial in terms of time. For example, the user may have the display interface 320 facing forward and The display interface 320 may be instructed to be positioned such that it is aligned with a particular face feature to be measured and is disposed below the user's chin, opposite the user's chin, or adjacent to the user's chin. For example, the display interface 320 may be disposed while maintaining a face alignment with the selion and the supramenton. When the finally captured image is two-dimensional, the face alignment helps to ensure that the scale of the reference feature 326 can be equally applied to the face feature measurement. In this regard, the distances between the mirror and both the user's face features and the display are approximately the same.

[0120] When the user is positioned in front of the mirror and the display interface 320 including the reference feature is roughly positioned while maintaining a face alignment with the face feature to be measured, the processor 310 checks for certain conditions to assist in ensuring sufficient alignment. As one exemplary condition that may be established by the application, as described above, for progression, it is necessary to detect the entire reference feature within the target setting box 328. If the processor 310 detects that the entire reference feature is not positioned within the target setting box, the processor 310 may prohibit or delay the image capture. Next, the user may move their face together with the display interface 320 to maintain planarity until the reference feature as displayed within the live action preview is positioned within the target setting box. This assists in the optimal alignment of the face features and the display interface 320 with respect to the mirror for image capture.

[0121] When the processor 310 detects the entire reference feature within the target setting box, the processor 310 can read the IMU 342 of the computing device for detecting the device tilt angle. The IMU 342 may include, for example, an accelerometer or a gyroscope. Thus, the processor 310 can confirm that the device tilt is within an appropriate range by evaluating the device tilt (e.g., by comparison with one or more thresholds). For example, if it is determined that the computing device 230 and (as a result) the display interface 320 and the user's face features are tilted in any direction within about +-5 degrees, the process can proceed to the capture phase. In other embodiments, the tilt angle to be counted can be within about +-10 degrees, +-7 degrees, +-3 degrees, or +-1 degree. If excessive tilt is detected, a warning message can be displayed or an audio cue provided for correcting the undesirable tilt. This is particularly useful in user assistance for avoiding or reducing excessive tilt (especially in the front-to-back direction), and if the excessive tilt is not corrected, it can lead to measurement errors due to the aspect ratio of the captured reference image becoming inappropriate.

[0122] Once the alignment is determined by the processor 310 as directed by the application, the processor 310 proceeds to the capture phase. The capture phase is preferably performed automatically when the alignment parameters and any other prerequisite conditions are met. However, in some embodiments, the user may initiate the capture in response to a prompt to do so.

[0123] When image capture starts, the processor 310 captures a plurality of images (preferably more than one image) via the sensor 340. For example, the number of images captured by the processor 310 via the sensor 340 is, for example, about 5 to 20 images, 10 to 20 images, or 10 to 15 images. The number of images captured can be time-based. In other words, the number of images captured can be based on the number of images of a predetermined resolution that can be captured by the sensor 340 at a predetermined time interval. For example, if the number of images that the sensor 340 can capture at a predetermined resolution in one second is 40 images and the predetermined time interval during capture is 1 second, the sensor 340 captures 40 images for processing by the processor 310. The number of images may be defined by the user, determined by the server 210 based on artificial intelligence or machine learning of the detected environmental conditions, or alternatively, based on the intended accuracy target. For example, if high precision is required, a larger number of captured images may be needed. Although it is preferable to capture a plurality of images for processing, a single image is also conceivable and can be usefully used for utilization to enable high-precision measurement. However, using more than one image enables average measurement. As a result, errors / discrepancies can be reduced and accuracy can be improved. These images can be stored by the processor 310 into the stored data 354 of the memory / data storage device 350 for post-capture processing.

[0124] After the image capture is completed, the image is processed by the processor 310 to detect or identify face features / landmarks and measure the distance between them. Using the resulting measurements, a recommendation for the appropriate patient interface size can be made. Alternatively, this processing may be performed by the server 210 that received the transmitted capture image and / or on the user's computing device (e.g., smartphone). The processing may be performed by a combination of the processor 310 and the server 210. In one example, the recommended patient interface size may be based primarily on the width of the user's nose. In other examples, the recommended patient interface size may be based on the user's mouth dimensions and / or nose dimensions.

[0125] The processor 310, which is controlled by the application, retrieves one or more capture images from the storage data 354. Next, these images are extracted by the processor 310 for the identification of each pixel including the two-dimensional capture image. Next, the processor 310 detects specific pre-specified face features within the pixel arrangement configuration.

[0126] The detection by the processor 310 can be performed using edge detection (e.g., Canny, Prewitt, Sobel, or Robert edge detection). These edge detection techniques / algorithms assist in identifying the locations of specific facial features within the pixel arrangement configuration corresponding to the actual facial features of the patient as presented for image capture. For example, according to the edge detection technique, first, the user's face in the image can be identified, and the locations of the pixels in the image corresponding to specific facial features (e.g., eyes and their boundaries, mouth and its corners, left and right wings, sellion, spratmenton, glabella, and left and right nasolabial folds) can also be identified. Next, the processor 310 can mark, tag, or save the specific pixel location(s) of each of these facial features. Alternatively, if such detection by the processor 310 / server 210 fails, the pre-specified facial features may be manually detected and marked, tagged, or saved by a human operator. These captured images are visually accessible through the user interface of the processor 310 / server 210.

[0127] Once the pixel coordinates of these facial features are identified, the application controls the processor 310 to measure the pixel distances between specific ones of the identified features. For example, this distance can be mainly determined by the number of pixels of each feature and may include scaling. For example, by measuring the distance between the left and right wings and determining the pixel width of the nose and / or the pixel width between the sellion and spratmenton, the pixel height of the face can be determined. Other examples include the pixel distance between the eyes, the pixel distance between the corners of the mouth, and the pixel distance between the left and right nasolabial folds, and further measurement data of specific structures such as the mouth can be obtained. Further distances between facial features can be measured. In this example, the specific dimensions of the face are used for the patient interface selection process.

[0128] After pixel measurements of pre-specified face features are obtained, anthropometric correction factor(s) may be applied to these measurements. It should be understood that the application of this correction factor may be performed before or after the application of the scale factor, as described below. The anthropometric correction factor enables the correction of errors that may occur in an automated process, which may occur consistently among patients. In other words, without the correction factor, while consistent results may be obtained among patients when using the automated process alone, it may lead to a patient interface of a specific amount of incorrect size. The correction factor may be empirically extracted from population trials, and through correction formation, a result closer to the true measurement is obtained, assisting in reducing or eliminating incorrect sizing. As the measurement and sizing data for each patient are communicated from each computing device to server 210, the accuracy of this correction factor can be refined or improved over time. In server 210, further processing of such data may enable the improvement of the correction factor. The anthropometric correction factor may also vary depending on the form of the patient interface. For example, the correction factor for a specific patient seeking an FFM may be different from that for a patient seeking a nasal mask. Such correction factors may be derived from tracking mask purchases (e.g., by monitoring mask returns and determining the size difference between the replacement mask and the returned mask).

[0129] To apply face feature measurements to sizing the patient interface, these measurements may be scaled, with or without correction by anthropometric correction factors, from pixel units to other values that actually reflect the distances between the patient's face features as presented for image capture. Reference features may be used to obtain the scaling value(s). Thus, the processor 310 also determines the dimensions of the reference features (e.g., measurements of the pixel width and / or pixel height (x and y) of the entire reference feature (e.g., pixel count)). More detailed measurements of the pixel dimensions of a number of squares / dots, including the QR code (registered trademark) reference feature and / or the pixel area occupied by the reference feature and its components, may also be determined. Thus, each square or dot of the QR code (registered trademark) reference feature may be measured in pixel units to determine a scaling factor based on the pixel measurements of each point, and then the average of all the measured squares or dots may be calculated, resulting in an improved accuracy of the scaling factor compared to a single measurement of the overall size of the QR code (registered trademark) reference feature. However, regardless of how the reference features are measured, it should be understood that these measurements can be used to scale the pixel measurements of the reference features to the reference features of known corresponding dimensions.

[0130] After the measurements of the reference features are made by the processor 310, a scaling factor is calculated by the processor 310 under the control of the application. The pixel measurements of the reference features are related to the known corresponding dimensions of the reference features (e.g., reference feature 326 as presented by the display interface 320 for image capture to obtain a conversion or scaling factor). Such a scaling factor may take the form of length / pixel or area / pixel A2. In other words, the known dimension(s) may be divided by the corresponding pixel measurement(s) (e.g., count(s)).

[0131] Next, the processor 310 applies the scale factor to the face feature measurements (pixel counts) to convert the measurements from pixel units to other units so as to reflect the actual distances between the patient's face features suitable for mask sizing. In this conversion, typically, for example, multiplication of the scale factor by the pixel count of the distance(s) related to the face features relevant for mask sizing can be performed.

[0132] These measurement steps and calculation steps for both the face features and the reference features are repeated for each captured image until the face feature measurements in the set of images are scaled and / or corrected.

[0133] Next, the collection of the set of images and the scaled measurements are optionally averaged by the processor 310 to obtain a final measurement of the patient's facial anatomical structure. Such a measurement may reflect the distances between the patient's face features.

[0134] In the comparison and output phase, the results from the post - capture image processing phase may be directly output (displayed) to the subject, or alternatively, compared with the data record(s) to obtain an automatic recommendation for the patient interface size.

[0135] After all the measurements are determined, the results (e.g., the average) can be displayed to the user by the processor 310 via the display interface 320. In one embodiment, thereby, the automated process can be terminated. The user / patient can record these measurements for further use by the user.

[0136] Alternatively, the final measurement can be transferred automatically or upon the user's command from the computing device 230 via the communication network 220 to the server 210. The server 210 or an individual on the server side can perform further processing and analysis to determine the appropriate patient interface and patient interface size.

[0137] In a further embodiment, a final face feature measurement that reflects the distance between a patient's actual face features is compared by the processor 310 to, for example, patient interface size data during data recording. This data recording can be part of an application for automatic measurement of face features and sizing of the patient interface. An example of this data recording is a look-up table, for example accessible from the processor 310, that can include patient interface sizes corresponding to a range of face feature distances / values. Multiple tables can be included in the data recording, many of which can correspond to a particular form of patient interface and / or a particular model of patient interface provided by a manufacturer.

[0138] By an exemplary process for selection of a patient interface, primary landmarks are identified from the face image captured by the above method. In this example, in an initial correlation to a potential interface, face landmarks (e.g., face height, nose width, and nose depth as shown by lines 3010, 3020, and 3030 in FIGS. 3A - 3B) are included. These three face landmark measurements are collected by the application to assist, for example, in selection of a size of a matching mask through a look-up table or the tables described above.

[0139] As described above, after mask selection or after detailed manufacture of a mask for a particular patient, the operation data of each RPT can be collected for a large population of patients. This can include usage data based on when each patient operates the RPT. Therefore, compliance data (e.g., the length and frequency of time a patient uses the RPT over a given period) can be determined from the collected operation data. Leakage data can be determined from the operation data (e.g., analysis of flow rate data or pressure data). Mask switching data can be derived using acoustic signal analysis to determine whether the mask is being switched. The RPT can be operable to determine the mask type based on a combination of an internal or external acoustic sensor (e.g., microphone 4278 in FIG. 4B) and cepstrum analysis as described above. Alternatively, in the case of an older mask type, the operation data can be used to determine the mask type through correlation of the collected acoustic data with the acoustic signature of a known mask.

[0140] In this example, the collection of patient input of feedback data can be performed via a user application executed on computing device 230 or smartphone 234. The user application can be part of user application 360 that instructs the user to obtain facial landmark features or a separate application. This can also include subjective data obtained via a questionnaire. The questionnaire includes the following: questions for collecting data about comfort preferences, whether the patient is a mouth breather or a nose breather (e.g., questions such as "Is your mouth dry when you wake up?"), and mask material preferences (e.g., silicone, foam, fabric, gel). For example, the collection of patient input can be performed through the patient's response via the user application to subjective questions related to the comfort of the patient interface. Other questions can be related to relevant user behavior (e.g., sleep characteristics). For example, questions that can be included in subjective questions are listed below. Is your mouth dry when you wake up?, Are you a mouth breather?, or Please tell me your comfort preferences. Such sleep information includes sleep duration, the user's sleep pattern, and external factors (e.g., temperature, stress factors). The subjective data can be a simple numerical evaluation of comfort or a more detailed response. Such subjective data can be collected from a graphical interface. For example, to select leakage from the interface, the user can be asked to select the illustrated part of the selected interface and collect it. The collected patient input data can be assigned to patient database 260 in FIG. 6. The subjective input data from the patient can be used as feedback regarding mask design and features to be referred to in the future. Other subjective data can be collected in relation to the patient's psychological safety. For example, questions (e.g., whether the patient feels claustrophobic about a particular mask, or whether the patient feels psychologically comfortable when staying with a bed partner while wearing the mask) can be asked to collect input.

[0141] Other data sources may collect data that can be correlated to a particular mask among the data not utilized by the RPT. Examples of such data include patient demographic data (e.g., age, gender, or location); the AHI severity indicating the level of sleep apnea the patient is experiencing. Other data may include the prescribed pressure settings for new patients of the RPT device.

[0142] After mask selection, system 200 continues to collect operational data from RPT 250. The collected data is added to databases 260 and 270. Using feedback from new patients, the recommendations can be refined for mask option improvement. For example, if it is determined from the operational data that there is a high level of leakage in the recommended mask, another type of mask can be recommended to the patient. Through the feedback loop, the selection algorithm can be refined for learning the facial geometry of certain aspects that may be optimal for a particular mask. Using this correlation, the mask recommendations for new patients with such facial geometry can be refined. Thus, the collected data and the correlated mask type data may enable further updating of the criteria for mask selection and design. Therefore, the present system can obtain further insights for improving the mask selection or design for the patient.

[0143] In addition to mask selection, according to the present system, analysis of mask selection related to the effectiveness and compliance of respiratory therapy may also be possible. Such additional data enables optimization of respiratory therapy based on data through the feedback loop.

[0144] The application of machine learning may enable providing correlations between mask types / characteristics and improving compliance with respiratory therapy. These correlations can be used for the selection or design of characteristics for new mask designs. Such machine learning can be executed by server 210. The mask analysis algorithm is based on the output of suitable operational results and inputs (e.g., patient demographics, mask size and type, and subjective data collected from the patient) for training data It can be learned using a dataset. Using machine learning, correlations between desired mask characteristics and predictive inputs (e.g., face dimensions, patient demographics, motion data from an RPT device, and environmental conditions) can be discovered. In machine learning, techniques such as neural networks, clustering, or conventional regression techniques can be used. Test data can be used to test different types of machine learning algorithms and determine the one with the best accuracy in relation to correlation prediction.

[0145] The model for the selection of the optimal interface can be continuously updated by new input data from the system in FIG. 5. Thus, with the expansion of the utilization of the analysis platform, the accuracy of the model can be improved.

[0146] As described above, one part of the system in FIG. 5 is related to the recommendation of interfaces for patients using RPT. As a second function of the system, there is a feedback data collection process. This process collects data for future mask design or adjustment. After a mask recommended to a patient is provided and the patient uses the mask over a certain period (e.g., two days, two weeks, or another period), the system can monitor RPT utilization and collect other data. Based on this collected data, if the mask performance is not at a high level (as determined from unfavorable data indicating leakage, compliance decline, or dissatisfaction feedback), the system can re-evaluate the mask selection and update the database 260 and the machine learning algorithm with the patient's results. Next, the system can recommend a new mask suitable for the newly collected data. For example, if a relatively high leakage flow rate is determined from data from an acoustic signature or other sensors, there may be a possibility that the patient's mouth is open during REM sleep. In that case, it may indicate that a different type of interface (e.g., a full-face mask instead of the initially selected nasal-only or smaller full-face mask) is required.

[0147] The system may also be able to adjust the recommendations in response to satisfactory follow-up data. For example, in the motion data, if it is shown that there is no leakage from the selected full-face mask, the routine may recommend trying a smaller mask. To maximize compliance, a trade-off between style, material, variations, and correlation with patient preferences may be used, and follow-up of the recommendations may be made possible. The trade-off for an individual patient may be determined through an input tree presented to the patient from the application. For example, if the patient indicates that skin irritation is a problem from a menu of potential problems, an illustration of the location of potential irritation on the face image may be presented to collect data from the patient as the specific irritation site. This specific data may make it possible to improve the correlation to the optimal mask for a specific patient.

[0148] This process enables the collection of feedback data and the correlation with face feature data, and can provide data for the design of other masks to the mask designer. As part of another application executed by an application 360 or a computing device (e.g., the computing device 230 or the mobile device 234 in FIG. 5) that collects face data, feedback information related to the mask can be collected.

[0149] The application 360 may collect initial patient information and provide security means for protecting data (e.g., password setting). After the patient configures the application and associates the application 360 with the identification information of a specific patient, the application may collect feedback data.

[0150] If face data for the patient has already been collected, the application 360 may Proceed to data collection. If there is no facial data previously collected for the patient, Application 360 provides the patient with options regarding facial data collection. In FIG. 7A, a facial image 710 is shown on the interface 700 of the application. The patient can capture a facial image 710 similar to the facial scan process described above for mask selection. After the display of the facial image 710, a face mesh can be generated. The second interface 720 shown in FIG. 7B displays the face mesh 712 generated from the facial image 710. Next, the facial data can be derived and saved from the face mesh 710 and transmitted to the server 210 for storage in the database 260 in FIG. 5.

[0151] Application 360 collects all relevant data for the evaluation of characteristics for mask design from the patient through the other interfaces displayed. The sleep data collection interface 730 shown in FIG. 7C enables the collection of subjective patient data related to the quality of sleep. This data can be collected and correlated with the objective sleep data or related motion data collected by the RPT described above. The interface 730 includes questions 732 related to the sleep position. The interface 730 includes options for the user to select (e.g., back selection 734, abdomen selection 736, and side selection 738). If the user is not confident in the selection, the user can select the "don't know" option 740. Thus, the interface 730 collects sleep position data correlated with a specific user.

[0152] Another sleep interface 750 shown in FIG. 7D is displayed to collect the sleep type. The interface 750 includes questions 752 regarding the sleep type. The interface 750 includes selections for the user including a selection 754 for "light sleep", a selection 756 for "moderate sleep depth", and a selection 758 for "deep sleep". If the user is not confident in the selection, the user can select the "don't know" option 760. Thus, the interface 750 collects sleep type data correlated with a specific user.

[0153] Application 360 also collects information about the current mask used by the patient. FIG. 8A is an interface 800 including the selection of a nose-only or nose-and-mouth mask. Thus, the user selects the nose-only mask selection 802 or the nose-and-mouth mask selection 804. In this example, the selections 802 and 804 include useful illustrations for the description of the mask type. This selection determines a further interface specific to the manufacturer and the mask model. After the patient makes a selection, a mask brand selection interface 810 shown in FIG. 8B is displayed, which enables the patient to select the brand of the mask. The interface 810 includes the selection 812 of manufacturer A, the selection 814 of manufacturer B, the selection 816 of manufacturer C, and the selection 818 of manufacturer D. The application enables access to all mask models of each of manufacturers A to D, and this information is provided to subsequent interfaces to enable the selection of specific masks of the selected manufacturers A to D.

[0154] FIG. 8C shows an interface 820 for the selection of a mask model. The selection in the interface 820 is determined by the manufacturer selected in the interface 810 in FIG. 8B. The interface 820 lists the selections (e.g., selections 822, 824, 826, and 828) for each applicable model provided by the manufacturer.

[0155] After the selection of the mask model, the application 360 displays an interface 830 for determining the cushion size of the mask as shown in FIG. 8D. The interface 830 includes an illustrated image 832 of the mask model selected from the interface 820 in FIG. 8C. The illustrated image 832 shows the user where to determine the size of the mask. The int erface 830 includes a small size selection 834, a medium size selection 836, and a large size selection 838.

[0156] Alternatively, the application 360 may be programmed to perform mask identification by analyzing the obtained illustrated image of the mask and comparing this image with identification data associated with a known mask model. The instruction interface 900 shown in FIG. 9A provides options for obtaining automatic visual identification of the mask. The photo interface 910 shown in FIG. 9B enables the capture of an image 912 of the mask. The photo interface 920 shown in FIG. 9C shows the captured image 912 of the mask.

[0157] The application 360 also includes an interface for collecting data for determining the mask being used. The short-term utilization interface 930 in FIG. 9D determines whether the mask is for single-use purposes by displaying a question 932 about mask usage in the most recent 30 days. The interface 930 may display an illustration of the mask model previously selected by the user. The user may select a "Yes" selection 934 or no selection 936 (indicating that another mask is being used). The application 360 may also provide an input for collecting data about previous masks.

[0158] The long-term usage interface 940 shown in FIG. 9E determines whether the mask is the only one by displaying questions 942 related to mask usage. The interface 940 may display an illustration of the mask model previously selected by the user. The user may select a "Yes" selection 944 or no selection 946 (indicating that another mask is being used).

[0159] The application 360 may also determine comfort feedback data from the patient. The interface 1000 shown in FIG. 10A determines whether there is any mask discomfort. A question 1002 is displayed, asking the patient whether they feel any discomfort from the mask. The patient may select a "No" option 1004 or a "Yes" option 1006.

[0160] When the patient selects the "Yes" option 1006, the visual discomfort recognition interface 1010 is displayed as shown in FIG. 10B. The interface 1010 displays an image 1020 of a face feature. The image 1020 can be selected from a comprehensive face image according to the patient's gender or other characteristics. Alternatively, the image 1020 can be an individual's face image, in which case it may be stored on a portable computing device (if acquired by application 320) or accessed from a database from the patient's previously acquired face images. A location grid 1022 in the shape of a mask is overlaid on the patient's face image 1020. A selection list 1024 is displayed. The selection list 1024 describes, for example, the following five potential discomfort regions: a) the bridge of the nose, b) the upper side of the nose, c) the lower side / corner of the nose, d) the side / corner of the mouth, and e) the jaw / lower lip. The location grid 1022 includes lines that define five regions 1030, 1032, 1034, 1036, and 1038 corresponding to the regions described in list 1024 to assist the patient in discovering discomfort regions. These regions 1030, 1032, 1034, 1036, and 1038 each indicate a contact region between the face and the mask. The user can select one or more discomfort regions from the list 1024. Next, the list of discomforts and the corresponding regions in the grid 1022 are highlighted. In this example, the location mask is specific to a full-face mask, but other types of masks (e.g., a cradle-type mask) may have different discomfort regions that are specific to the type of mask, along with a different location grid 1022.

[0161] FIG. 10C shows an example of the interface 1010 when the patient selects a discomfort region. In this example, the patient has selected the upper side of the nose from the list 1024. Therefore, this selection is highlighted. The region 1032 of the grid 1022 indicating the upper side of the nose is also highlighted, thereby showing the discomfort region relative to the face image 1020.

[0162] Application 360 can also determine leakage feedback data from the patient. Interface 1050 shown in FIG. 10D determines whether there is any air leakage at the seal between the mask and the face. Question 1052 is displayed to ask the patient whether they have experienced any leakage from the mask. The patient can select the "No" option 1054 or the "Yes" option 1056.

[0163] If the patient selects the "Yes" option 1056, the visual discomfort identification interface 1060 is displayed as shown in FIG. 10E. Interface 1060 displays an image 1070 of the patient. Image 1070 can be stored on a portable computing device if acquired by application 320, or can be accessed from a database of previously acquired face images of the patient. A location grid 1072 in the shape of a mask is overlaid on the patient's face image 1070. A selection list 1074 is displayed, describing the following five potential air leakage areas: a) bridge of the nose, b) upper side of the nose, c) lower side / corner of the nose, d) side / corner of the mouth, and e) jaw / lower lip. The location grid 1072 includes lines that define the five regions 1080, 1082, 1084, 1086, and 1088 corresponding to the above described in list 1074, to assist the patient in discovering leakage between the mask and their own face within the regions 1080, 1082, 1084, 1086, and 1088 (which indicate the contact area between the face and the mask). The user can select one or more discomfort regions from list 1074. Next, the discomfort list is highlighted along with the corresponding regions in grid 1072.

[0164] FIG. 10F shows an example of interface 1060 when the patient has selected a discomfort region. In this example, the patient has selected "upper side of the nose" in list 1074. Therefore, this selection is highlighted. Region 1082 of grid 1072 is also highlighted, so this discomfort region is displayed relative to face image 1070.

[0165] The interface 1100 shown in FIG. 11A collects subjective feedback data from the patient regarding the impact of air leakage. When the user selects the "Yes" option 1056 from the interface 1050 in FIG. 10E, the interface 1100 is displayed. The question 1102 included in the interface 1100 requests the patient to represent the level of difficulty due to air leakage in a numerical scale input. The interface 1100 includes a scale 1104 in the range of 0 (not troubled) to 10 (very troubled). The patient can select the slider 1106. The slider 1106 displays the numerical input from the scale, as shown in the image of the interface 1100'. Other similar interfaces may be provided for other questions (e.g., questions related to discomfort in specific areas or regions on the face).

[0166] The interface 1150 shown in FIG. 11B collects subjective feedback data from the patient regarding the patient's satisfaction with the current mask. The question 1152 included in the interface 1150 requests the patient to numerically evaluate the mask regarding whether to recommend a specific mask model. The interface 1150 includes a scale 1154 in the range of 0 (low probability) to 10 (very high probability). The patient can select the slider 1156. The slider 1156 displays the numerical input from the scale, as shown in the image of the interface 1150'.

[0167] FIG. 11C is an exemplary interface 1160 that can be displayed for the collection of patient demographic data. The interface 1160 includes an age selection field 1162, a gender selection field 1164, and a race field 1166. Thus, the patient can use the fields 1162, 1164, and 1166 to input data on their age, gender, and race. This data can be collected to assist in the analysis of mask designs related to patient demographics.

[0168] FIG. 11D is an exemplary schematic diagram and is inserted to collect discomfort and air leakage according to the selection of mask types in the generated interface and is used for determining discomfort as shown, for example, in FIG. 10B or for determining leakage as shown, for example, in FIG. 10C. The series of five different overlay illustrations 1170, 1172, 1174, 1776 and 1178 shown in FIG. 11D show different mask shapes. For example, overlay illustrations 1170, 1176 and 1178 show different types of nose-only masks. Overlay illustrations 1172 and 1174 show different types of masks and nose masks. Appropriate illustrations 1170, 1172, 1174, 1776 and 1178 are inserted based on the mask selection by the user.

[0169] FIG. 12 shows a tree diagram 1200 of data collected through the exemplary application 360 described herein. Input 1210 requests to select the one closest to the user's situation. Input 1210 may include user 1212 of a mask manufactured by a vendor, user 1214 of a mask manufactured by a third party, and user 1216 who currently has no mask. When the user identifies whether they are a user of a mask manufactured by a vendor or a user of a mask manufactured by a third party, input 1220 determines whether the mask covers the nose or the nose and mouth. Next, in data collection, data related to the sleep position 1222 is collected. If the user indicates that they have no mask currently in use, the routine directly collects data related to the sleep position 1222. Input 1224 collects data on whether the user has difficulty raising both arms higher than the head. At input 1226, it is determined whether the user has difficulty breathing through the nose. At input 1228, it is determined whether the user is troubled by a dry nose. At input 1230, it is determined whether the user has claustrophobia. At input 1232, it is determined whether the user uses face cream at night.

[0170] If the genders are different, different face features are also different. Therefore, in input 1234, the gender of the user is determined. The user can select male or female. If the user rejects the answer, in input 1236, the gender at the user's birth is determined. The user can answer male, female, or answer rejection. If the user answers male for input 1234 or 1236, in input 1238, it is determined whether the user has hair on the face. Next, the routine presents a set of general questions regarding gender, including input 1240 related to whether the face or skin is prone to irritation, input 1242 (whether the user wears glasses), input 1244 (whether the user has a roommate), input 1246 (whether the user cares about the appearance when wearing mask 1248), and input 1250 (whether the user has difficulty falling asleep). As described above, using the collected data, an appropriate mask for the user can be recommended or selected. The collected data can also be categorized or correlated with other user-specific data, thereby obtaining guidelines for new mask designs related to a specific patient subgroup or the general patient population.

[0171] For example, patient input data may indicate mask leakage in a specific area (e.g., above the nose). This leakage can be confirmed through the operation data from the RPT device. Next, this data can be correlated with the face data related to above the nose. By analyzing and elongating the mask edge that interfaces with above the nose to minimize leakage, the dimensions of the mask can be changed. As another example, the patient input data may indicate that "it feels uncomfortable when wearing a mask above the nose". Next, this data is related to above the nose It can be correlated with the facial data related thereto. By performing an analysis and shortening the mask edge that interfaces with the upper side of the nose to minimize leakage, the dimensions of the mask can be changed. Of course, such data may be provided to a healthcare provider to recommend masks of different sizes or types for reducing discomfort or leakage. Alternatively, this data can be used to change the mask initially selected by the patient to one that is individually adjusted to fit the patient.

[0172] The patient data collected from the above application and additional data (e.g., operation data from the RPT device 250 in FIG. 5) can be diverted or processed in the data processing step for the design support of an improved interface for the user. Using the scanned mirror image (surface topography) of the face, an interface such as a mask can be generated. However, such a patient interface may not always be ideal. This is because in certain regions of the sealing area on the face, different levels of sealing force may be required, it may be more sensitive to high headgear pressure, or the possibility of leakage at that location may be higher due to the complex facial geometry. By taking into account such fine details related to performance and comfort in further processing, it leads to a more optimal mask design.

[0173] In one example, when the direct measurement of the deformed geometry is not possible or the deformed geometry is unavailable, it may be possible to attempt and provide a display of the deformed geometry using the relaxed state geometry data from the collection of the relaxed state data. Simulation software can be used in the relaxed data post - processing to simulate the deformed state. Without limitation, an example of suitable simulation software is ANSYS, which performs the conversion of the state geometry data from "relaxed" to "deformed" in the relaxed data.

[0174] By obtaining additional facial images, it may be possible to determine the relaxed and deformed states of the facial geometry. By obtaining both the "relaxed" and "deformed" states of the geometry data, it may be possible to calculate the approximate pressure values (in the pressure generated in the simulation) that occur between the patient interface contact area and the patient's face using finite element software (e.g., ANSYS). Alternatively, pressure data may be collected separately via pressure mapping. Thus, from the collection of relaxed state data, it may be possible to estimate the deformed geometry and the generated pressure.

[0175] The measurement data, which is either geometry data or pressure data, may enable the determination and handling of areas or features on the patient's face that require special consideration in specific feature processing. Optionally, since a comprehensive model including both a geometry data set and a pressure data set may be obtained from data from any combination of measurement sources, the purpose of providing design comfort, effectiveness, and compliance is further achieved.

[0176] The face is not a static surface. That is, the face adapts and changes in response to interactions with external conditions (e.g., forces from the patient interface, air pressure on the face, and gravity). By taking these interactions into account, the additional benefit of providing an optimal seal and comfort for the patient is obtained. This process is illustrated by three examples.

[0177] First, since users wearing these patient interfaces experience CPAP pressure, this knowledge can be used to improve the comfort and sealing of the patient interface. By using simulation software with known properties (e.g., soft tissue properties or elastic modulus), it may be possible to assist in predicting the deformation of the facial surface at a specific air pressure within the patient interface.

[0178] For groups related to any of the following facial locations, tissue characteristics may be known and collected: above the glabella, glabella, nasion, tip of the nose, philtrum, upper lip margin, lower lip margin, mentolabial sulcus, canine eminence, base of the mandible, anterior eminence, supraorbital, lateral glabella, lateral nose, infraorbital, lower cheek, lateral nostril, nasolabial fold, supra canina, sub canina, ant. canine tubercle, mid lateral orbital, supraarticular fossa, zygomatic bone, lateral, supra-M2, mid masseter, occlusal line, sub-m2, gonion, and intermediate mandibular angle.

[0179] For example, soft tissue thickness is known from an anthropometric database for at least one of the following facial features. For example, nasion, tip of the nose, philtrum, mentolabial sulcus, canine eminence, infraorbital, lower cheek, lateral nostril, nasolabial fold, supra canina and sub canina. Specific locations (e.g., infraorbital, lower cheek, lateral nostril, nasolabial fold, supra canina and sub canina) are located on both sides of the face.

[0180] Known tissue characteristics at any one or more of these locations may include any one or more of the following: soft tissue thickness, modulus data based on force, deflection, modulus and thickness, soft tissue thickness ratio information, and body mass index (BMI).

[0181] Second, the skin surface on the patient's face deforms significantly when the CPAP patient interface is strapped onto the face. Using an initial 3D measurement of the geometric surface of the head and face in a relaxed state, it may be possible to predict surface changes with the knowledge of the above-described skin / soft tissue characteristics and simulation software. Such a technique is an iterative optimization process and can be used with the design process.

[0182] Third, when in the sleep position, the skin surface can move due to gravity. Predicting these changes using knowledge of skin and soft tissue properties and simulation software can lead to the design of a more robust and comfortable high-performance patient interface for various sleep positions. Data related to geometric changes from upright to supine can be collected and utilized from one or more target areas of the face (e.g., nasion, nasal tip, philtrum, mentolabial fold, suborbital, lateral nares, nasolabial ridge, supra canina, and sub canina).

[0183] Finite element analysis (FEA) software (e.g., ANSYS) can be used to calculate approximate pressure values that occur between the interface contact area and the user's face. In one form, inputs that can be included are face geometry in the "relaxed" and "deformed" states, and properties at various locations on the face (e.g., measured elastic modulus, or substructures where properties such as stiffness are known). Using such inputs, it may be possible to construct a finite element (FE) model of the face, and then use this finite element (FE) model to predict one or more responses of the face to inputs (e.g., deformation or loading). For example, using the FE model of the face, it may be possible to predict the face shape at a given pressure level (e.g., 15 cmH2O) in a patient interface. In some forms, the FE model may further include a patient interface model or a part thereof (e.g., a cushion), and the patient interface model or a part thereof includes cushion geometry and its properties (e.g., mechanical properties such as elastic modulus). Such a model can predict cushion deformation (e.g., when an internal load is applied to the cushion due to CPAP pressure addition) and the resulting interaction between the cushion and the face (e.g., load / pressure between the two, face deformation). Specifically, by using the distance change at each point between the relaxed and deformed states together with the corresponding tissue properties, it may be possible to predict the pressure that occurs at a given point (e.g., on the cheekbone).

[0184] In certain areas or features on the face, special considerations may be required. By identifying and adjusting these features, the overall comfort of the interface can be improved. From the data collection techniques and estimation techniques described above, appropriate features can be applied to the custom patient interface.

[0185] In addition to the pressure sensitivity, pressure compliance, shear sensitivity, and shear compliance indicators described above, special considerations may be given to facial hair, hairstyles, and extreme facial landmarks (e.g., prominent nasal bridge, gaunt cheeks). As used herein, "shear sensitivity" refers to the shear felt by the patient, and "shear compliance" refers to the level at which the patient's skin moves smoothly with the shear or is compliant with the shear.

[0186] The feedback data collection routine shown in FIG. 13 can be executed over a particular period (s) after an initial selection of an interface by a patient. For example, a follow-up routine can be executed over the first two days of interface and RPT use. The flowchart in FIG. 13 shows exemplary machine-readable instructions to collect and analyze feedback data to select interface characteristics for optimized respiratory pressure therapy tailored to different patient types. In this example, the machine-readable instructions include an algorithm that is executed by (a) a processor, (b) a controller, and / or (c) one or more other suitable processing device(s). The algorithm can be embedded in software stored on a tangible medium (e.g., flash memory, CD-ROM, floppy (R) disk, hard drive, digital video (versatile) disk (DVD) or other memory device). However, one of ordinary skill in the art will understand that all or part of the algorithm can be executed by a device other than a processor and / or embedded in firmware or well-known manners in dedicated hardware (e.g., this can be implemented by application specific integrated circuit [ASIC], programmable logic device [PLD], field programmable logic device [FPLD], field programmable gate array [FPGA], individual logic). For example, any or all of the components of the interface can be executed by software, hardware, and / or firmware. Also, some or all of the machine-readable instructions shown by the flowchart may be executed manually. Further, although the flowchart shown in FIG. 13 is referred to describe the exemplary algorithm, one of ordinary skill in the art will readily understand that many other methods can be used to execute the exemplary machine-readable instructions. For example, the order of executing the blocks can be changed and / or some of the described blocks can be changed, removed or combined.

[0187] As described below, recommendations regarding design changes to different characteristics of the interface (e.g., the area that contacts the face region) can be obtained from the routine in FIG. 13. This data can enable continuous updates of an exemplary machine learning-driven correlation engine.

[0188] In the routine, first, it is determined whether face data about the patient has been collected (1310). If the face data has not been collected, the routine application 360 is launched, and a request is made to perform a user face scan using a mobile device (e.g., mobile device 234 in FIG. 5) that executes the above-described application (1312).

[0189] After the collection of face image data (1312) or if the face data has already been saved from the previous scan, the routine accesses the collection operation data from the RPT (in one set period (e.g., two days of use)) (1314). Of course, other appropriate periods longer or shorter than two days can be used as the collection period for the operation data and other related data from the RPT. For example, the system in FIG. 2 can collect compliance objective data (e.g., usage time or leakage data from RPT 250) from two days of use. In addition, subjective feedback data (e.g., seal, comfort, general likes and dislikes) can be collected from the interface of the user application 360 executed by the computing device 230 (1316). As described above, the subjective data can be collected via an interface that provides questions to the patient. Thus, the subjective data can include answers related to discomfort or leakage and questions about psychological safety (e.g., whether the patient is psychologically comfortable with the mask). Other data can be collected based on the visual display of the mask in relation to the face image.

[0190]

[0191] ​Next, the routine correlates the objective and subjective data with the selected mask type and the patient's face scan data (1318). If the results are favorable, the routine determines that the operational data indicates high compliance, low leakage, and good subjective result data from the patient (1320). Next, the routine updates the database and learning algorithm with the correlation data as successful mask characteristics or features (1322). If the results are not good, the routine also analyzes the correlation data and determines whether the results can be improved by adjusting the mask characteristics (1324). Next, the routine proposes a change in the characteristics according to this analysis (1326). For example, the routine may propose thickening the portion of the mask that joins the nose in order to avoid leakage detection or reporting. Next, the routine stores the results by updating the database and learning algorithm (1322).

[0192] The exemplary generation system 1400 shown in FIG. 14 generates an interface modified based on the collected data from the data collection system 200 in FIG. 5. The server 210 provides the analysis module 1420 with the collected operational data from the population of RPT devices 1410 and the subjective data collected from the population of patients 1412 by the application 230.

[0193] The analysis module 1420 includes access to an interface database 270 that contains data related to masks of different models from one or more different manufacturers. The analysis module 1420 may include a machine learning routine that provides suggestions for changes to specific patients or interface characteristics or features in an interface used by a subgroup of a patient population. For example, by inputting the collected motion and patient input data along with face image data into the analysis module 1420, new characteristics of the mask design can be obtained. Manufacturing data (e.g., CAD / CAM files of existing mask designs) is stored in the database 1430. The modified design is generated by the analysis module and communicated to the manufacturing system 1440 to generate a mask using changes such as dimensions, sizing, materials, etc. In this example, the manufacturing system 1440 may include a tooling machine, a molding machine, a 3D printing system, etc. for mask generation.

[0194] To make the manufacturing method of custom components more efficient than additive manufacturing, prototyping (e.g., 3D printing) of the molding tools in the manufacturing system 1440 can be performed quickly based on the modified changes. In some examples, tooling by high-speed three-dimensional printing may enable an improvement in the cost-effectiveness of small-batch manufacturing methods. Soft tools made of aluminum and / or thermoplastic are also possible. The soft tools enable small-batch molded parts and are more cost-effective than steel tools.

[0195] Hard tooling may be used during the manufacture of custom components. When generated based on feedback data with a suitable amount of interface collected, hard Tooling may be desirable. Hard tools can be composed of various grades of steel or other materials used during the molding process / machining process. The manufacturing process can also include the use of rapid prototyping, soft tools, and any combination of hard tools for the fabrication of any of the components of the patient interface. The structure of the tool can also vary, for example, in the tool itself using any or all of the types of tooling. That is, one half of the tool that can define more comprehensive features of the part can be composed of a hard tooling, and the remaining half of the tool that defines the custom component can be built from rapid prototyping or soft tooling. Combinations of hard tooling or soft tooling are also possible.

[0196] In the case of an interface having an interface within the same component, other manufacturing techniques may also include multi-shot injection molding. For example, a patient interface cushion may include different materials or different grades of soft materials in different regions of the patient interface. Thermoforming (e.g., vacuum forming) may be used, in which case, for example, plastic sheets are heated and these sheets can be vacuum drawn onto a tool mold and then cooled until they take the shape of the mold. This is a viable option for forming components of a custom nasal cavity cover. In yet another form, a material that may initially be malleable may be used to generate a customized patient interface frame (or any other suitable component (e.g., a headgear or a part thereof (e.g., a rigidizer))). One or more of the techniques described herein can be used to generate a patient's "male" mold, and by placing a malleable "template" component on this "male" mold, a shape of a component suitable for the patient can be produced. Next, by "curing" the customized components, these components can be made so that they do not become malleable. Examples of such materials can include thermosetting polymers that have initial malleability until a certain temperature (and then are irreversibly cured) or thermoplastic plastics (also called thermoplastics) that become malleable when exceeding a certain temperature. Custom fabric weaving / knitting / formulating may also be used. This technique is similar to a 3D printing process except that it uses threads instead of plastics. By knitting the structure of the textile component, any three-dimensional shape ideal for making a custom headgear can be imparted.

[0197] As used in this application, terms such as "component", "module", "system", etc. generally refer to computer-related entities that can be either hardware (e.g., circuitry), a combination of hardware and software, software, or an entity related to an operating machine having one or more specific functions. For example, a component can be, but is not limited to, a process executed on a processor (e.g., a digital signal processor), a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of example, both a controller and an application operating on the controller can be components. One or more components can exist within a process and / or an execution thread, and a component can be localized on one computer or distributed between two or more computers. Further, a "device" can take the form of specially designed hardware, off-the-shelf hardware specialized by the execution of software enabling the performance of specific functions, software stored on a computer-readable medium, or a combination thereof.

[0198] The terms used in this specification are for the purpose of describing particular embodiments only and are not intended to limit the invention. The singular forms "a", "an", and "the" used in this specification are intended to include the plural forms as well, unless the context clearly dictates otherwise. Further, in the embodiments for carrying out the invention and the claims, the terms "comprising", "having", or their inflected forms are used, and these terms are intended to be inclusive in the same manner as the term "including". It is intended to be inclusive.

[0199] One or more elements, aspects, or steps or portions (singular or plural) from any one or more of the following claims 1 to 28 can be combined with one or more elements, aspects, or steps or portions (singular or plural) from any one or more of the other claims 1 to 28 or combinations thereof to form one or more further implementations and / or claims of the present disclosure.

[0200] Although the present disclosure has been described with reference to one or more particular implementations or executions, those skilled in the art will recognize that numerous changes may be possible without departing from the intent and scope of the present disclosure. Each of these executions and their obvious variations are intended to fall within the intent and scope of the present disclosure. In further executions or alternative executions according to aspects of the present disclosure, it is also contemplated that any number of features from any of the executions described herein (e.g., those in the alternative executions described below) may be combined.

Claims

1. 1. A method for collecting data relating to a patient interface for a respiratory pressure therapy device, comprising: instructing a patient to capture a facial image of said patient via a mobile device equipped with a camera; correlating facial image data obtained from a facial image of the patient with the patient; displaying an interface that allows the patient to select a type of the patient interface; collecting subjective patient input data from the patient associated with the patient interface; A method comprising:

2. The method of claim 1 , further comprising collecting operational data of a respiratory treatment device used by the patient with the patient interface.

3. correlating characteristics of the patient interface with the facial image data, the motion data, and the subjective patient input data; The method of claim 2 , wherein the characteristics define physical characteristics of the patient interface.

4. The method of claim 1 , wherein the instructions are given by a display of the mobile device, by audio instructions from a speaker of the mobile device, or by a tutorial video played on a display of the mobile device.

5. The method of claim 1 , wherein the patient interface is a mask.

6. 6. The method of claim 1, wherein the respiratory pressure treatment device is one of a continuous positive airway pressure (CPAP) device, a non-invasive assisted ventilation (NIV) device, or an invasive assisted ventilation device.

7. The method of claim 1 , wherein the instructions include instructions to capture multiple facial images from different angles.

8. 8. The method of claim 1, further comprising: displaying a facial image together with an inset image of the patient interface; and collecting the subjective patient input data from the patient based on the patient selecting from a list of locations shown in the inset image of the patient interface.

9. The method of claim 8 , wherein the inset image includes lines defining multiple regions of the patient interface.

10. The method of claim 9 , wherein the subjective patient-entered data includes comfort or leakage data for each region of the inset image.

11. The method according to any one of claims 1 to 10, wherein the subjective patient input data is collected by displaying questions in an interface on a mobile device.

12. The method of claim 11 , wherein the interface on the mobile device displays a sliding scale for entry of the patient's response.

13. 13. The method of claim 1, further comprising the step of collecting the subjective patient input data including at least one of a sleep position, a sleep type, a mask model, or a cushion size.

14. 14. The method of claim 1, wherein the step of displaying an interface comprises displaying a graphical image of the patient interface and comparing the graphical image with identification data for known mask models.

15. The method of claim 1 , wherein the facial image data is used to identify a face height, nose width and nose depth that correlates with the patient.

16. 16. The method of claim 1, further comprising adjusting a characteristic of the manufactured patient interface based on an adjusted characteristic to avoid leakage, the characteristic being associated with contact of the patient interface with a facial surface of the patient.

17. 17. The method of claim 1, further comprising adjusting a characteristic of the patient interface for enhanced comfort, the characteristic being associated with contact with a facial surface of the patient.

18. collecting facial image data from a second patient similar to the patient, operational data of a respiratory treatment device utilized by the second patient, and subjective patient input data from the second patient; 18. The method of claim 1, wherein facial image data from the second patient, operational data of a respiratory treatment device utilized by the second patient, and subjective patient input data from the second patient are used to correlate characteristics of the patient interface.

19. collecting facial image data, motion data, and subjective patient input data from a plurality of patients, including the patient, as a training set; 19. The method of claim 1, further comprising: using machine learning trained on the training set to determine motion data, subjective patient input data, and facial image data that correlate with a desired outcome associated with a characteristic; and adjusting a characteristic of the patient interface to achieve the desired outcome based on outputting the characteristic.

20. 1. A mobile device for collecting data relating to a patient interface for a respiratory pressure therapy device, comprising: a camera for capturing a facial image of the patient; a storage device for storing a facial image of the patient; a patient data collection interface for collecting subjective patient input data from the patient in association with the patient interface; a data communication interface for communicating facial image data of the captured facial image and data of the subjective patient input; A mobile device comprising:

21. an analysis module that correlates characteristics of the patient interface with the facial image data and the subjective patient input data; The mobile device of claim 20, wherein the characteristics define physical characteristics of the patient interface.

22. 22. The mobile device of claim 20 or claim 21, wherein the patient interface is a mask.

23. 23. The mobile device of any one of claims 20 to 22, wherein the respiratory pressure treatment device is one of a continuous positive airway pressure (CPAP) device, a non-invasive assisted ventilation (NIV) device or an invasive assisted ventilation device.

24. 24. The mobile device of claim 20, wherein the patient data collection interface displays a facial image together with an inset image of the patient interface and collects the subjective patient input data from the patient based on the patient selecting from a list of locations shown in the inset image of the patient interface.

25. 25. The mobile device of claim 24, wherein the inset image includes lines defining multiple regions of the patient interface.

26. The mobile device of claim 25, wherein the subjective patient-entered data includes data regarding comfort or leakage for each region of the inset image.

27. 27. The mobile device of any one of claims 20 to 26, wherein the subjective patient input data is collected by displaying questions in an interface on the mobile device.

28. 28. The mobile device of claim 27, wherein the interface on the mobile device displays a sliding scale for entry of the patient's response.

29. 29. The mobile device of any one of claims 20 to 28, further comprising means for comparing a graphical image of the patient interface with identification data relating to known mask models to identify the patient interface.

30. 30. The mobile device of claim 20, wherein the instructions to the patient to capture a facial image are provided by a display of the mobile device, audio instructions from a speaker of the mobile device, or a tutorial video played on a display of the mobile device.

Images