Systems and methods for collecting fit data associated with a selected mask

Abstract

A system and method of collecting feedback data from a patient wearing an interface such as a mask while using a respiratory pressure therapy device such as a CPAP device. The system includes a storage device including a facial image of the patient. An interface in communication with the respiratory pressure therapy device, the interface collecting operational data from the patient while using the interface. The patient interface collects subjective patient input data from the patient regarding the patient interface. An analysis module correlates features of the interface with the facial image data, the operational data, and the subjective patient input data.

Description

[0001] Cross-reference to related applications

[0002] This application claims priority and benefit to Australian Provisional Patent Application No. 2019904285, filed November 13, 2019, and U.S. Provisional Patent Application No. 63 / 072,914, filed August 31, 2020, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present invention generally relates to an air intake mechanism designed for use in a respiratory disease treatment system, and more specifically to a system for future designers to collect patient data related to the effectiveness of a mask for a pressure device. Background Technology

[0004] A range of breathing disorders exist. Some disorders can be characterized by specific events, such as apnea, hypoventilation, and hyperventilation. Obstructive sleep apnea (OSA) is a form of sleep-disordered breathing (SDB) characterized by events involving closure or obstruction of the upper airway during sleep. It arises from a combination of abnormally small upper airway and normal loss of muscle tone in the areas of the tongue, soft palate, and posterior oropharyngeal walls during sleep. The condition causes the affected patient to stop breathing, typically for periods of 30 to 120 seconds, sometimes 200 to 300 times per night. This often leads to excessive daytime sleepiness and can result in cardiovascular disease and brain damage. Concomitant symptoms are common, especially in middle-aged overweight men, but those affected may not be aware of the problem.

[0005] Other sleep-related conditions include Cheyne-Stokes respiration (CSR), obesity-induced hyperventilation syndrome (OHS), and chronic obstructive pulmonary disease (COPD). COPD encompasses any of a group of lower airway diseases that share certain common characteristics. These diseases include increased airflow resistance, prolonged expiratory phase of breathing, and loss of normal lung elasticity. Examples of COPD include emphysema and chronic bronchitis. COPD is caused by chronic smoking (a major risk factor), occupational exposure, air pollution, and genetic factors.

[0006] Continuous positive airway pressure (CPAP) therapy has been used to treat obstructive sleep apnea (OSA). The application of CPAP acts as a pneumatic splint and can prevent upper airway obstruction by pushing the soft palate and tongue forward and away from the posterior oropharyngeal wall.

[0007] Non-invasive ventilation (NIV) provides ventilatory support to a patient through the upper airways to assist the patient in breathing adequately, and / or to maintain an appropriate oxygen level in the body by doing some or all of the work of breathing. This ventilatory support is provided via a patient interface. NIV has been used to treat CSR, OHS, COPD, and Chest Wall disorders. In some forms, the comfort and effectiveness of these therapies can be improved. Non-invasive ventilation (NIV) provides ventilatory support to a patient who is unable to breathe effectively on their own, and can be provided using a tracheostomy tube.

[0008] A treatment system can include a respiratory pressure therapy (RPT) device, an air circuit, a humidifier, a patient interface, and data management. A patient interface can be used to interface a respiratory device to its wearer, for example, by providing a flow of air to an entrance to the airways. The flow of air can be provided via a mask to a patient's nose and / or mouth, a tube to the mouth, or a tracheostomy tube to the trachea of a patient. Depending on the treatment to be applied, the patient interface can form a seal with the area around, for example, the patient's face, to facilitate the delivery of gas at a pressure sufficient to affect treatment, for example, positive pressure of about 10 cm H20 relative to ambient pressure. For other forms of treatment, such as the delivery of oxygen, the patient interface can not include a seal sufficient to facilitate delivery to the airways of a supply of gas at positive pressure of about 10 cm H20. Treatment of respiratory disorders by such therapies can be voluntary, and thus, patients can elect not to comply with treatment if they find the device used to provide such therapies uncomfortable, difficult to use, expensive, and / or unattractive.

[0009] The design of a patient interface presents several challenges. The face has a complex three-dimensional shape. The size and shape of the nose varies considerably between individuals. As the head includes bone, cartilage, and soft tissue, different regions of the face respond differently to mechanical forces. The mandible, or lower jaw, can move relative to other bones of the skull. The whole head can move during the course of a period of respiratory therapy.

[0010] Due to these challenges, some masks face one or more of the following issues: obtrusiveness, unattractiveness, expense, disproportion, difficulty of use, and discomfort, particularly when worn for long periods or when the patient is unfamiliar with the system. For example, a mask designed only for pilots, a mask designed to be part of a personal protection device (such as a filtering face-piece), a SCUBA mask, or a mask designed to administer anesthetic can be acceptable for its original application, but less than ideal for long-term (e.g., several hours) wear. This discomfort can lead to reduced patient compliance with therapy. This is especially true if the mask is worn during sleep.

[0011] Assuming patient adherence, nasal CPAP therapy is highly effective for treating certain breathing difficulties. Obtaining a patient interface allows patients to participate in positive pressure therapy. Patients seeking their first or a new patient interface to replace an older one typically consult with a durable medical device provider to determine the recommended patient interface size based on measurements of the patient's facial anatomy, which is usually performed by the durable medical device provider. Patients may not adhere to therapy if the mask is uncomfortable or difficult to use. Since patients are generally advised to clean their masks regularly, if the mask is difficult to clean (e.g., difficult to assemble or disassemble), patients may be unable to clean their mask, which can affect patient adherence. For pneumatic therapy to be effective, not only must patients be comfortable when wearing the mask, but a strong seal must also be formed between the face and the mask to minimize air leakage.

[0012] As mentioned above, patient interfaces can be provided to patients in various forms, such as, for example, nasal masks or full-face / oronasal masks (FFM) or nasal pillow masks. Such patient interfaces are manufactured in various sizes to accommodate the anatomical features of a particular patient, providing a comfortable interface that facilitates functions such as positive pressure therapy. The size of such patient interfaces can be customized to correspond to the specific facial anatomy of a particular patient, or can be designed to accommodate groups of individuals with anatomical structures falling within predefined spatial boundaries or ranges. However, in some cases, masks may be available in various standard sizes, from which a suitable mask must be selected.

[0013] In this regard, determining the size of a patient's interface is typically performed by trained personnel, such as durable medical device (DME) providers or physicians. Typically, patients requiring a patient interface to begin or continue positive pressure therapy visit a trained person at the conditioning facility, where a series of measurements are taken to determine the appropriate patient interface size from standard dimensions. The appropriate size is intended to represent a specific combination of dimensions for certain features of the patient interface (e.g., the sealing structure) that provides sufficient comfort and a seal for positive pressure therapy. Sizing in this way is not only laborious but also inconvenient. For many patients who receive a new or replaced patient interface and ultimately find it an obstacle to receiving treatment, the inconvenience of taking time out of a busy schedule or, in some cases, having to travel long distances, is a barrier to receiving a new or replaced patient interface and ultimately to receiving treatment. This inconvenience prevents patients from receiving the required patient interface and undergoing positive pressure therapy. However, selecting the most appropriate size is important for treatment quality and compliance.

[0014] Future mask designers need feedback from mask users to better design interfaces. A system is needed to collect and store mask user feedback data related to facial size data from a broad user base. A system is also needed to correlate user feedback data with other data relating to the selected mask. Summary of the Invention

[0015] The disclosed system provides an adaptive system for collecting user feedback data related to the face mask used in an RPT device. The system combines facial image data with collected RPT operational data and other data, such as subjective data from patient populations, to assist in the design of the face mask.

[0016] One publicly disclosed example is a method for collecting data related to a patient interface used in a respiratory pressure therapy device. Facial image data from the patient is associated with the patient. Operational data of the respiratory therapy device used by a patient wearing the patient interface is collected; subjective patient input data from the patient regarding the patient interface is collected; and characteristics of the interface are associated with the facial image data, operational data, and subjective patient input data.

[0017] In other implementations of the disclosed methods, the patient interface is a face mask. In another implementation, the respiratory pressure therapy device is a continuous positive airway pressure (CPAP) device, a non-invasive ventilation (NIV) device, or an invasive ventilation device. In yet another implementation, facial image data is obtained from a mobile device having an application for capturing images of the patient's face. In yet another implementation, the method further includes displaying a facial image with an inserted image of the interface, and collecting subjective data from the patient based on the position of the interface on the inserted image. In yet another implementation, subjective data is collected by displaying a question in an interface on the mobile device. In yet another implementation, the interface interface has a sliding scale to input the patient's answer. In yet another implementation, the facial image data includes facial height, nasal width, and nasal depth. In yet another implementation, the method includes adjusting the characteristics of the interface to prevent leakage. This characteristic is associated with the contact between the facial surface and the interface. In yet another implementation, the method includes adjusting the characteristics of the interface to increase comfort. This characteristic is associated with the contact between the facial surface and the interface. In another implementation, facial image data from a second patient similar to the patient, operational data from a respiratory therapy device used by the second patient, and subjective data input by the second patient are collected and used to associate the characteristics of the interface. In yet another implementation, facial image data, operational data, and subjective patient input data from multiple patients, including the patient, are collected. Machine learning is applied to determine the types of operational data, subjective data, and facial image data associated with the features, in order to adjust the characteristics of the interface.

[0018] Another disclosed example is a system with a control system that includes one or more processors and a memory storing machine-readable instructions. The control system is coupled to the memory. The method described above is implemented when the machine-executable instructions in the memory are executed by one of the processors of the control system.

[0019] Another disclosed example is a system for transmitting one or more instructions to a user. This system includes a control system configured to implement one of the methods described above.

[0020] Another disclosed example is a computer program product having instructions that, when executed by a computer, cause the computer to perform one of the methods described above. Another implementation of the example computer program product is one in which the computer program product is a non-transitory computer-readable medium.

[0021] Another disclosed example is a system for collecting feedback data from a patient using an interface connected to a respiratory pressure therapy device. The system includes a storage device for storing images of the patient's face. A data communication interface communicates with the respiratory pressure therapy device to collect operational data from the patient as they use the interface; a patient data collection interface collects subjective patient input data from the patient regarding the interface; and an analysis module is operable to correlate characteristics of the interface with facial image data, operational data, and subjective patient input data.

[0022] In other implementations of the disclosed system, the system includes a manufacturing system that produces the interface based on design data. An analysis module adjusts the design data based on relevant characteristics. In another implementation, the patient interface is a face mask. In yet 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 of the system, a mobile device executes an application to capture an image of the patient's face. In yet another implementation, a patient data collection interface displays a facial image with an inserted image of the interface, and subjective data from the patient is collected based on the position of the interface on the inserted image. In yet another implementation, subjective data is collected by displaying questions in an interface on the mobile device. In yet another implementation, the interface displays a sliding scale for the patient to input their answers. In yet another implementation, facial image data includes facial height, nasal width, and nasal depth. In yet another implementation, the characteristics of the interface are adjusted to prevent leakage. This characteristic is associated with the contact between the facial surface and the interface. In yet another implementation, the characteristics of the interface are adjusted to increase comfort. This characteristic is associated with the contact between the facial surface and the interface. In another implementation, the system includes a machine learning module operable to determine operational data, subjective data, and facial image data from multiple patients associated with the feature in order to adjust the characteristics of the interface.

[0023] The above summary is not intended to represent every embodiment or aspect of the invention. Rather, the foregoing summary provides only examples of some novel aspects and features set forth herein. The foregoing features and advantages, as well as other features and advantages, will become apparent from the following detailed description of representative embodiments and modes for carrying out the invention, when taken in conjunction with the accompanying drawings and claims. Attached Figure Description

[0024] The invention will be better understood from the following description of exemplary embodiments, taken in conjunction with the accompanying drawings, in which:

[0025] Figure 1 A system is shown that includes a patient wearing a patient interface in the form of a full-face mask to receive PAP treatment from an exemplary respiratory pressure therapy device.

[0026] Figure 2 A patient interface in the form of a nasal mask and a headband according to the present technology are shown.

[0027] Figure 3A It is a frontal view of a face with several features of surface anatomy;

[0028] Figure 3B It is a side view of the head with several features of the surface anatomy that are identified;

[0029] Figure 3C It is a bottom view of the nose with several distinctive features;

[0030] Figure 4A A form of respiratory pressure therapy device according to the present technology is shown.

[0031] Figure 4B This is a schematic diagram of the pneumatic path of one form of respiratory pressure therapy device according to the present technology.

[0032] Figure 4C A schematic diagram of the electrical components of one form of respiratory pressure therapy device according to the present technology is shown.

[0033] Figure 5 This is a diagram of an example system for collecting patient data related to a patient interface that includes a computing device;

[0034] Figure 6 This is a diagram of components of a computing device used to capture facial data;

[0035] Figure 7A This is an example interface that allows facial scanning to create facial images for capturing facial data;

[0036] Figure 7B Is showing the insertion inFigure 7A An example interface for collecting data on a facial image for facial measurements;

[0037] Figure 7C This is an example of a sleep location data collection interface;

[0038] Figure 7D This is an example of a sleep type data collection interface;

[0039] Figure 8A This is an example interface that allows the current mask to be identified by nose or mouth / nose type;

[0040] Figure 8B This is a sample interface that allows the branding of face masks;

[0041] Figure 8C This is a sample interface that allows identification of a specific interface model;

[0042] Figure 8D This is an example interface that allows the identification of interface dimensions;

[0043] Figure 9A This is an example image command interface that allows capturing images from the interface;

[0044] Figure 9B It is an image capture interface used to capture images from the interface;

[0045] Figure 9C This is the post-capture interface that displays the captured image;

[0046] Figure 9D This is a sample interface for determining the short-term use of a face mask;

[0047] Figure 9E This is an example interface for determining the long-term use of a face mask;

[0048] Figure 10A This is an example interface that provides instructions to determine where the mask is uncomfortable;

[0049] Figure 10B This is an example interface that allows users to graphically select the location where mask discomfort occurs;

[0050] Figure 10C After the user selects the uncomfortable area Figure 10B Example interface in the document;

[0051] Figure 10D This is an example interface that provides instructions to determine the location of an air leak in the face mask;

[0052] Figure 10E This is an example interface that allows users to graphically select the location where a mask leak is occurring;

[0053] Figure 10F After the user selects the area where a mask leak has already occurred Figure 10B Example interface in the document;

[0054] Figure 11A This is a sample slider interface for collecting subjective data on the impact of air leaks;

[0055] Figure 11B This is an example slider interface for collecting subjective data on patients' satisfaction with face masks;

[0056] Figure 11C This is a sample interface for collecting patient demographic data;

[0057] Figure 11D is an exemplary diagram of a mask that can be inserted depending on the type selected to collect discomfort and air leakage;

[0058] Figure 12 It is a tree diagram of the feedback data collected to determine the design of the face mask;

[0059] Figure 13 It is a flowchart of the process for collecting feedback data from patients to determine the characteristics of the face mask; and

[0060] Figure 14 This is a diagram of a system that produces modified interfaces based on collected feedback data.

[0061] This invention allows for various modifications and alternatives. Some representative embodiments have been shown by way of example in the accompanying drawings and will be described in detail herein. However, it should be understood that the invention is not limited to the specific forms disclosed. Rather, the invention is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention as defined by the appended claims. Detailed Implementation

[0062] This invention can be embodied in many different forms. Representative embodiments are shown in the accompanying drawings and will be described in detail herein. This invention is an example or illustration of the principles of the invention and is not intended to limit the broad aspects of the invention to the illustrated embodiments. In this regard, elements and limitations disclosed, for example, in the abstract, summary, and detailed description but not expressly set forth in the claims should not be incorporated into the claims individually or collectively by means of implication, inference, or otherwise. For the purposes of this detailed description, unless specifically stated otherwise, the singular includes the plural and vice versa; and the word “comprising” means “including but not limited to.” Furthermore, for example, approximate words such as “about,” “almost,” “substantially,” “approximately,” etc., may be used herein to mean “at,” “close to,” or “nearly at,” or “within 3-5%,” or “within acceptable manufacturing tolerances,” or any logical combination thereof.

[0063] This invention relates to a system and method for collecting feedback data from a face mask selected by a user of a respiratory pressure therapy device. The size of the face mask is determined based on facial data collected from the user. An interface is presented to the user to collect feedback data regarding the determined face mask size. The data is analyzed to further refine the design of face masks for similar patients based on factors such as operational data, patient demographics, and patient facial features.

[0064] Figure 1 A system is shown that includes a patient 10 wearing a full-face mask (FFM) patient interface 100, which receives a positive pressure air supply from an airway pressure therapy (RPT) device 40. The air from the RPT device 40 is humidified in a humidifier 60 and delivered to the patient 10 along an air circuit 50.

[0065] Figure 2 A patient interface 100 according to one aspect of the present technology is depicted, the patient interface including the following functional aspects: a sealing forming structure 160, an inflation chamber 120, a positioning and stabilizing structure 130, an air vent 140, a forehead support 150, and a connection for connecting to Figure 1 One form of connection port 170 of the air circuit 50. In some forms, functional aspects may be provided by one or more physical components. In some forms, a single physical component may provide one or more functional aspects. In use, the sealing formation 160 is arranged around the inlet of the patient's airway to facilitate the supply of positive pressure air to the airway.

[0066] In one embodiment of this technology, the sealing-forming structure 160 provides a sealing-forming surface and may additionally provide a cushioning function. The sealing-forming structure 160 according to this technology may be constructed from a soft, flexible, and resilient material such as silicone. In one embodiment, the sealing-forming portion of the non-invasive patient interface 100 includes a pair of nasal sprays or nasal pillows, each spray or pillow being configured and arranged to form a seal with the corresponding nostril of the patient's nose.

[0067] The nasal pillow according to this technology includes: a truncated cone, at least a portion of which forms a seal on the bottom surface of the patient's nose; a handle; and a flexible region on the bottom surface of the truncated cone that connects the truncated cone to the handle. Furthermore, the structure connecting the nasal pillow according to this technology includes a flexible region adjacent to the bottom of the handle. The flexible regions can work together to facilitate a universal connection structure that can adapt to relative movement of both the truncated cone and the structure connecting the nasal pillow with displacement and angle. For example, the position of the truncated cone can be axially moved toward the structure connecting the handle.

[0068] In one embodiment, the non-invasive patient interface 100 includes a sealing forming portion that, during use, forms a seal on the upper lip region (i.e., the upper lip) of the patient's face. In another embodiment, the non-invasive patient interface 100 includes a sealing forming portion that, during use, forms a seal on the chin region of the patient's face.

[0069] Preferably, in the area forming a seal during use, the inflation chamber 120 has a periphery shaped to complement the surface contours of a normal person's face. During use, the boundary edges of the inflation chamber 120 are positioned very close to the adjacent surfaces of the face. Actual contact with the face is provided by the sealing structure 160. The sealing structure 160 may extend along the entire periphery of the inflation chamber 120 during use.

[0070] Preferably, the sealing structure 160 of the patient interface 100 of this technology can be kept in a sealed state during use by positioning and stabilizing structure 130.

[0071] In one embodiment, the patient interface 100 includes a ventilation port 140 configured and arranged to allow flushing of exhaled carbon dioxide. In one embodiment of the present technology, the ventilation port 140 includes a plurality of holes, such as about 20 to about 80 holes, or about 40 to about 60 holes, or about 45 to about 55 holes.

[0072] Figure 3A A front view of a human face is shown, including the inner canthus, nasal alae, nasolabial folds, upper and lower lips, upper and lower lips, and the corners of the mouth. The mouth width, the sagittal plane dividing the head into left and right portions, and direction indicators are also shown. The direction indicators indicate radial inward / outward and upward / downward directions. Figure 3B A side view of the human face is shown, including the glabella, bridge of the nose, nasal ridge, nasal protuberance, subnasal point, upper and lower lips, supramental point, ridge point, and upper and lower ear bases. Directional indicators for up / down and front / back directions are also shown. Figure 3C A bottom view of the nose with several identified features is shown, including the nasolabial folds, lower lip, vermilion border of the upper lip, nostrils, lower point of the nasal septum, columella, nasal protuberance, long axis of the nostrils, and central sagittal plane.

[0073] Below is Figures 3A-3C A more detailed explanation of the facial features shown.

[0074] Alar: The outer wall or "wing" of each nostril (plural: alar)

[0075] Alar tip: the outermost point on the ala of the nose.

[0076] Nasal wing curve (or nasal apex) point: the last point on the baseline of each nasal wing curve, found in the crease formed by the junction of the nasal wing and the cheek.

[0077] Auricle: The entire visible external part of the ear.

[0078] Columella: A strip of skin that separates the nostrils and extends from the nasal protuberance to the upper lip.

[0079] Columellar angle: The angle between a line drawn through the midpoint of the nostril and a line drawn perpendicular to the Frankfort plane (the two lines intersect at the lower point of the nasal septum).

[0080] The glabella (between the eyebrows): Located on the soft tissue, it is the most prominent point in the sagittal plane at the midline of the forehead.

[0081] Nostrils (or nasal eyes): Approximately oval-shaped openings that form the entrance to the nasal cavity. The singular form of nostril (nare) is nasal nasal (naris). The nostrils are separated by the nasal septum.

[0082] Nasolabial folds or nasolabial folds: Skin folds or grooves that extend from each side of the nose to the corners of the mouth, separating the cheeks from the upper lip.

[0083] Nasolabial angle: The angle between the columella and the upper lip (which intersects at the lower point of the nasal septum).

[0084] Base point below the ear: the lowest point where the auricle attaches to the facial skin.

[0085] Base point on the ear: the highest point where the auricle attaches to the facial skin.

[0086] Nasal protuberance: The most prominent point or tip of the nose, which can be identified in a side view of the rest of the head.

[0087] The philtrum is the midline groove that extends from the lower border of the nasal septum to the top of the upper lip.

[0088] Prechin point: Located on the soft tissue, at the midpoint of the front part of the chin.

[0089] Nasal ridge: The nasal ridge is the midline protrusion of the nose that extends from the bridge of the nose to the nasal protuberance.

[0090] Sagittal plane: A vertical plane that divides the body into right and left halves from front (front) to back (back).

[0091] Nasal bridge point: Located on the soft tissue, it is the most concave point covering the nasolabial fold area.

[0092] Septal cartilage (nose): The nasal septal cartilage forms part of the septum and separates the anterior part of the nasal cavity.

[0093] Posterosuperior lateral lamina: the point at the lower edge of the base of the nasal ala, where the base of the nasal ala joins the skin of the upper (superior) lip.

[0094] Subnasal point: Located on the soft tissue, at the junction of the columella and the upper lip in the midsagittal plane.

[0095] Supramental point: The point on the midline of the lower lip where the greatest concavity occurs between the midpoint of the lower lip and the premental point of the soft tissue.

[0096] As will be explained below, there are several key dimensions from the face that can be used to select the patient interface (such as...). Figure 1 The dimensions of the mask (10) in this example. In this example, there are three dimensions, including face height, nose width, and nose depth. Figures 3A-3B Line 3010, representing the height of the face, is shown. (As in...) Figure 3B As can be seen, facial height is the distance between the bridge of the nose and the suprachin. Figure 3A The line 3020 in the middle represents the width of the nose, which lies between the left and right alar points of the nose. Figure 3B The line 3030 in the middle indicates the depth of the nose.

[0097] Figure 4A An exploded view of the components of an example RPT device 40 according to one aspect of the present technology is shown. The RPT device includes mechanical, pneumatic and / or electrical components and is configured to perform one or more algorithms, such as any of the methods described herein in whole or in part. Figure 4B A block diagram of an example RPT device 40 is shown. Figure 4C A block diagram of the electrical control components of an example RPT device 40 is shown. The upstream and downstream directions are indicated by reference to a blower and a patient interface. The blower is defined as upstream of the patient interface and the patient interface as downstream of the blower, regardless of the actual flow direction at any given moment. Items 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 airflow for delivery to a patient's airway, for example, to treat one or more respiratory conditions.

[0098] The RPT device may have an outer housing 4010, which is composed of two parts: an upper part 4012 and a lower part 4014. Furthermore, the outer housing 4010 may 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 may include a handle 4018.

[0099] The pneumatic path of the RPT device 40 may include one or more air path components, such as an inlet air filter 4112, an inlet silencer 4122, a pressure generator 4140 (e.g., a blower 4142) capable of supplying positive pressure air, an outlet silencer 4124, and one or more transducers 4270, such as a pressure sensor 4272, a flow sensor 4274, and a motor speed sensor 4276.

[0100] One or more air path components may be housed within a detachable, separate structure, referred to as pneumatic block 4020. Pneumatic block 4020 may be housed within an outer housing 4010. In one embodiment, pneumatic block 4020 is supported by, or forms part of, a chassis 4016.

[0101] RPT device 40 may include a power supply 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. A separate controller may be provided for the treatment device. Electrical components 4200 may be mounted on a single printed circuit board assembly (PCBA) 4202. In an alternative form, RPT device 40 may include more than one PCBA 4202. Other components, such as one or more protection circuits 4250, transducers 4270, data communication interfaces 4280, and storage devices, may also be mounted on the PCBA 4202.

[0102] The RPT device may include one or more of the following components in an integral unit. In an alternative form, one or more of the following components may be configured as separate units.

[0103] One form of RPT device according to the present technology may include one or more air filters 4110. In one embodiment, an inlet air filter 4112 is positioned at the beginning of the pneumatic path upstream of the pressure generator 4140. In another embodiment, an outlet air filter 4114, such as an antibacterial filter, is positioned between the outlet of the pneumatic block 4020 and the patient interface 100.

[0104] One form of the RPT device according to the present technology may include one or more silencers 4120. In one form of the present technology, the inlet silencer 4122 is positioned in the pneumatic path upstream of the pressure generator 4140. In one form of the present technology, the outlet silencer 4124 is positioned between the pressure generator 4140 and... Figure 1 The pneumatic path between the patient interface 100.

[0105] In one form of this technology, the pressure generator 4140 for generating a positive pressure airflow or air supply is a controllable blower 4142. For example, the blower 4142 may include a brushless DC motor 4144 having one or more impellers. These impellers may be located in a volute. The blower may deliver an air supply, for example, at a rate up to about 120 liters per minute and at a positive pressure ranging from about 4 cm H2O to about 20 cm H2O, or in other forms up to about 30 cm H2O. The blower may be as described in any of the following patents or patent applications, which are incorporated herein by reference in their entirety: U.S. Patent No. 7,866,944; U.S. Patent No. 8,638,014; U.S. Patent No. 8,636,479; and PCT Patent Application No. WO 2013 / 020167.

[0106] The pressure generator 4140 is controlled by the treatment device controller 4240. In other words, the pressure generator 4140 may be a piston-driven pump, a pressure regulator (e.g., a compressed air reservoir) connected to a high-pressure source, or a bellows.

[0107] According to one aspect of the present technology, the air circuit 4170 is a conduit or tube that is constructed and arranged in use to allow a pressurized airflow to travel between two components (such as 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 pressurization chamber 120 of the patient interface 100.

[0108] In one embodiment of this technology, an anti-backflow valve 4160 is positioned between the humidifier 60 and the pneumatic block 4020. The anti-backflow valve is constructed and arranged to reduce the risk of water flowing upstream from the humidifier 60 to, for example, the electric motor 4144.

[0109] The power supply 4210 may be located inside or outside the outer housing 4010 of the RPT device 40. In one embodiment of the invention, the power supply 4210 supplies power only to the RPT device 40. In another embodiment of the invention, the power supply 4210 supplies power to both the RPT device 40 and the humidifier 60.

[0110] The RT system may include one or more transducers (sensors) 4270 configured to measure one or more of any number of parameters relating to the RT system, its patient, and / or its environment. The transducers may be configured to generate output signals representing the one or more parameters that the transducer is configured to measure.

[0111] The output signal can be one or more of the following: electrical signal, magnetic signal, mechanical signal, visual signal, optical signal, sound signal, or any number of other signals known in the art.

[0112] The transducer can be integrated with another component of the RT system, with one exemplary arrangement being that the transducer is inside the RPT device. The transducer can also be essentially a 'standalone' component of the RT system, with an exemplary arrangement being that the transducer is outside the RPT device.

[0113] A transducer can be configured to transmit its output signal to one or more components of an RT system, such as an RPT device, a local external device, or a remote external device. An external transducer can be located, for example, on a patient interface or in an external computing device such as a smartphone. An external transducer can be positioned, for example, on an air circuit such as the patient interface or form part of it.

[0114] One or more transducers 4270 may be configured and arranged to generate signals representing air characteristics, such as flow rate, pressure, or temperature. The air may be an airflow from the RPT device to the patient, an airflow from the patient to the atmosphere, ambient air, or anything else. The signal may represent the characteristics of the airflow at a specific point, such as the airflow in the pneumatic path between the RPT device and the patient. In one form of the art, one or more transducers 4270 are located in the pneumatic path of the RPT device, such as downstream of the humidifier 60.

[0115] According to one aspect of this technology, one or more transducers 4270 include a pressure sensor in fluid communication with a pneumatic path. Examples of suitable pressure sensors are transducers from the HONEYWELL ASDX series. Alternative suitable pressure sensors are transducers from the GENERAL ELECTRIC NPA series. In one implementation, the pressure sensor is located in the air circuit 4170 adjacent to the outlet of the humidifier 60.

[0116] Microphone pressure sensor 4278 is configured to generate an acoustic signal representing pressure changes within air circuit 4170. The acoustic signal from microphone 4278 can be received by central controller 4230 for sound processing and analysis configured by one or more algorithms described below. Microphone 4278 can be directly exposed to the air circuit for greater sound sensitivity, or it can be encapsulated behind a thin layer of flexible membrane material. This membrane can protect microphone 4278 from heat and / or humidity.

[0117] Data from these transducers 4270 (such as pressure sensor 4272, flow sensor 4274, motor speed sensor 4276, and microphone 4278) can be collected periodically by the central controller 4230. This data typically relates to the operating status of the RPT device 40. In this example, the central controller 4230 encodes this data from the sensors in a proprietary data format. The data can also be encoded in a standardized data format.

[0118] In one embodiment of this technology, the RPT device 40 includes one or more input devices 4220 in the form of buttons, switches, or dials to allow personnel to interact with the device. The buttons, switches, or dials can be physical devices or software devices accessed via a touchscreen. In one embodiment, the buttons, switches, or dials can be physically connected to an external housing 4010, or in another embodiment, they can communicate wirelessly with a receiver electrically connected to a central controller 4230. In one embodiment, the input devices 4220 can be configured or arranged to allow personnel to select values ​​and / or menu options.

[0119] In one form of this technology, the central controller 4230 is one or more processors adapted to control the RPT device 40. Suitable processors may include x86 Intel processors, processors based on those from ARM Holdings, etc. The processor can be a microcontroller, such as the STM32 series from ST Microelectronics. In some alternative forms of this technology, a 32-bit RISC CPU, such as the STR9 series from ST Microelectronics, or a 16-bit RISC CPU, such as the MSP430 series from Texas Instruments, can also be used. In one form of this technology, the central controller 4230 is a dedicated electronic circuit. In another form, the central controller 4230 is an application-specific integrated circuit (ASIC). In yet another form, the central controller 4230 includes discrete electronic components. The central controller 4230 can be configured to receive input signals from one or more transducers 4270, one or more input devices 4220, and the humidifier 60.

[0120] The central controller 4230 can be configured to provide output signals to one or more output devices 4290, treatment device controller 4240, data communication interface 4280 and humidifier 60.

[0121] In some forms of this technology, the central controller 4230 is configured to implement one or more methods described herein, such as one or more algorithms represented as computer programs stored in a non-transitory computer-readable storage medium in memory. In some forms of this technology, the central controller 4230 may be integrated with the RPT device 40. However, in some forms of this technology, some methods may be performed by a remote device such as a mobile computing device. For example, a remote positioning device may determine control settings for the ventilator or detect respiratory-related events by analyzing stored data such as from any of the sensors described herein. As mentioned above, all data and operations from external sources or the central controller 4230 are generally proprietary to the manufacturer of the RPT device 40. Therefore, data from sensors and any other additional operational data are generally not accessible to any other device.

[0122] In one form of this technology, a data communication interface is provided and connected to a central controller 4230. The data communication interface can be connected to a remote external communication network and / or a local external communication network. The remote external communication network can be connected to a remote external device, such as a server or database. The local external communication network can be connected to a local external device, such as a mobile device or a health monitoring device. Therefore, the local external communication network can be used by the RPT device 40 or the mobile device to collect data from other devices.

[0123] In one embodiment, the data communication interface is part of the central controller 4230. In another embodiment, the data communication interface 4280 is separate from the central controller 4230 and may include an integrated circuit or processor. In one embodiment, the remote external communication network is the Internet. The data communication interface can connect to the Internet using wired communication (e.g., via Ethernet or fiber optic) or wireless protocols (e.g., CDMA, GSM, 2G, 3G, 4G / LTE, LTE Cat-M, NB-IoT, 5G New Radio, satellite, Beyond 5G). In one embodiment, the local external communication network 4284 utilizes one or more communication standards, such as Bluetooth or consumer infrared protocols.

[0124] Example RPT device 40 includes integrated sensors and communication electronics, such as Figure 4C As shown. Older RPT devices can be updated with sensor modules that may include communication electronics for transmitting the collected data. Such sensor modules can be attached to the RPT device and thus transmit operational data to the remote analysis engine 130.

[0125] Some implementations of the disclosed acoustic analysis techniques can be based on cepstral analysis using audio signals from sensors such as the audio sensor 4278. The audio signals can reflect user physiological states such as sleep or breathing, as well as operational data from the RPT. The cepstral spectrum can be considered as the inverse Fourier transform of the logarithmic spectrum of the forward Fourier transform of the decibel spectrum, etc. This operation essentially transforms the convolution of the impulse response function (IRF) and the sound source into an additive operation, making it easier to consider or remove the sound source to isolate the IRF data for analysis. Cepstral analysis techniques are described in detail in the scientific papers entitled "Cepstral: A Processing Guide" (Childers et al., IEEE Transactions on Physics, Vol. 65, No. 10, October 1977) and Randall RB, Frequency Analysis, Copenhagen: Bruel & Kjaer, p. 344 (1977, revised 1987). The application of cepstral analysis in the identification of components of respiratory therapy systems is described in detail in PCT Publication No. WO2010 / 091462 entitled “Acoustic Detection for Respiratory Treatment Apparatus”, the entire contents of which are incorporated herein by reference.

[0126] As mentioned earlier, respiratory therapy systems typically include an RPT device, a humidifier, an air delivery duct, and a patient interface, such as... Figure 1 The components shown are examples of those used in RPT devices. Various types of patient interfaces are available for a given RPT device, such as nasal pillows, nasal forks, nasal masks, nasal and mouth (oronasal) masks, or full-face masks. Additionally, different types of air delivery conduits may be used. To provide improved control over the treatment delivered to the patient interface, treatment parameters, such as pressure and exhaust flow rate in the patient interface, can be analyzed, measured, or estimated. In earlier systems, knowledge of the type of component used by the patient, as explained below, could be used to determine the optimal interface for the patient. Some RPT devices include a menu system that allows the patient to select the type of system component, including the patient interface being used, such as brand, form, model, etc. Once the patient has entered the component type, the RPT device can select the appropriate operating parameters of the airflow generator that best matches the selected component. Data collected by the RPT device can be used to evaluate the effectiveness of supplying pressurized air to the patient by a specific selected component (e.g., the patient interface).

[0127] This technology includes analytical methods capable of separating acoustic mask reflections from other system noises and responses, including but not limited to blower sounds. This allows for the identification of differences between acoustic reflections from different masks (typically defined by mask shape, construction, and materials) and enables the identification of different masks without user or patient intervention.

[0128] An example method for identifying a face mask is to sample the output sound signal y(t) generated by microphone 4278 at at least a Nyquist rate (e.g., 20 kHz), calculate the cepstrum based on the sampled output signal, and then separate the reflection component of the cepstrum from the input signal component of the cepstrum. The reflection component of the cepstrum includes the acoustic reflection of the input sound signal from the face mask and is therefore referred to as the "acoustic signature" or "face mask signature" of the face mask. This acoustic feature is then compared to a predefined or predetermined database of pre-measured acoustic features obtained from a system containing known face masks. Optionally, some criteria can be set to determine appropriate similarity. In one example implementation, the comparison can be performed based on a single maximum data peak in the cross-correlation between the measured and stored acoustic features. However, the method can be improved by comparing several data peaks, or alternatively, the comparison can be performed on a unique set of extracted cepstrum features.

[0129] According to this technology, the data associated with the reflection component can then be compared with similar data from previously identified mask reflection components (such as mask reflection components contained in a memory or database of mask reflection components).

[0130] As described above, the RPT device 40 can provide data on the patient interface type and operational data. Operational data can be correlated with mask type and patient-related data to determine the effectiveness of a particular mask type. For example, operational data reflects the duration of use of the RPT device 40 and whether the use provides effective treatment. The type of patient interface can be correlated with the level of patient compliance or treatment effectiveness determined from the operational data collected from the RPT device 40. This relevant data can be used to better identify effective interfaces for new patients requiring respiratory therapy from similar RPT devices. This selection is combined with facial dimensions obtained from a facial scan of the new patient to aid in interface selection.

[0131] Therefore, this technology allows patients to obtain a patient interface, such as a mask, more quickly and conveniently by integrating data collected from the use of RPT devices associated with different mask groups with the individual patient's facial features determined by the scanning process. The scanning process allows patients to quickly measure their facial anatomy from the comfort of their own homes using a computing device such as a desktop computer, tablet, smartphone, or other mobile device. The computing device can then receive recommendations for the appropriate patient interface size and type after analyzing the patient's facial dimensions and data from a general patient group associated with different interfaces. Facial data can also be collected in other ways, such as from pre-stored facial images. Such facial data is stored and associated with information concerning the patient and operational data from the RPT device.

[0132] In this example, facial data can be collected using an app that can be downloaded from the manufacturer's or a third-party server to a smartphone or tablet with an integrated camera. Upon launch, the app provides visual and / or audio instructions. Following the instructions, the user (i.e., the patient) can stand in front of a mirror and press the camera button on the user interface. The activation process can then capture a series of images of the user's face, and then, for example, obtain facial dimensions for selecting the interface within approximately a few seconds (based on processor analysis of these images). Once the mask is selected and used with the RPT 40, as will be explained below, this app can be used to collect feedback from the user.

[0133] Users / patients can capture images or a series of images of their facial structure. Instructions provided by an application stored on a computer-readable medium, such as when executed by a processor, detect various facial landmarks within the images, measure and scale the distances between these landmarks, compare these distances with data records, and recommend an appropriate patient interface size. Therefore, automated devices for consumers can allow for accurate patient interface selection, such as at home, enabling consumers to determine the size without trained personnel.

[0134] Figure 5 An example system 200, which can be implemented to collect patient interface feedback data from patients, is depicted. System 200 may also include automatic facial feature measurement and patient interface selection. System 200 generally includes one or more of a server 210, a communication network 220, and a computing device 230. The server 210 and the computing device 230 can communicate via the communication network 220, which may be a wired network 222, a wireless network 224, or a wired network with a wireless link 226. In some versions, the server 210 can 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 can share information and / or process tasks. System 200 can be implemented to, for example, allow the automatic purchase of patient interfaces, such as... Figure 1 The system 100 includes a face mask, wherein the process may include an automated size determination process, described in more detail herein. For example, a customer may order a face mask online after running a face mask selection process that automatically identifies the appropriate mask size through image analysis of the customer's facial features combined with operational data from other face masks and RPT operational data from patient groups using different types and sizes of face masks. The system 200 will continue to collect feedback data after the face mask has been used by the patient.

[0135] Server 210 and / or computing device 230 may also be compatible with, for example, similar to Figure 1The RPT 40 shown communicates with the RPT 250 of the respiratory therapy device. In this example, the RPT 250 collects operational data, mask leakage, and other relevant data related to patient use to provide feedback related to mask usage. Data collected from the RPT 250 is used in the patient database 260 and correlated with individual patient data. The patient interface database 270 includes data on different types and sizes of interfaces, such as masks available for new patients. The patient interface database 270 may also include acoustic feature data for each mask type, enabling the determination of the mask type based on audio data collected from the respiratory therapy device. A mask analysis engine, executed by server 210, is used to correlate and determine the effective mask size and shape based on individual face size data, and to determine the appropriate effectiveness based on operational data collected by the RPT 250, which includes the entire patient population. For example, effective compliance can be demonstrated by the minimum detectable leakage and treatment plan (e.g., mask on / off time and frequency of on / off events), the number of overnight apneas, AHI level, pressure settings used on the device, and maximum compliance with the prescribed pressure settings. This data can be correlated with facial size data of new patients. As will be explained, server 210 collects data from multiple patients stored in database 260 and corresponding mask size and type data stored in database 270 to select an appropriate mask based on the best mask best suited to the scanned facial size data collected from the new patient, and the best operating data for patients with similar facial size, sleep behavior data, and demographics to the new patient. This data is supplemented by additional feedback in the form of subjective data input by the patient using RPT device 250 and operating data from RPT device 250 associated with the patient interface or mask.

[0136] The computing device 230 may be a desktop or laptop computer 232 or a mobile device, such as a smartphone 234 or a tablet computer 236. Figure 6 A general architecture 300 of computing device 230 is depicted. Computing device 230 may include one or more processors 310. Computing device 230 may also include a display interface 320, a user control / input interface 331, sensors 340 and / or sensor interfaces for one or more sensors, inertial measurement units (IMUs) 342 and non-volatile memory / data storage devices 350.

[0137] Sensor 340 may be one or more cameras (e.g., CCD charge-coupled devices or active pixel sensors) integrated into computing device 230, such as cameras provided in smartphones or laptop computers. Alternatively, if computing device 230 is a desktop computer, device 230 may include interfaces for use with external cameras (such as...)Figure 5 The webcam 233 depicted herein is coupled to a sensor interface. Other exemplary sensors that can be integrated with or external to a computing device and may be used to assist the methods described herein include stereo cameras for capturing three-dimensional images, or photodetectors capable of detecting reflected light from lasers or strobe / structured light sources.

[0138] User control / input interface 331 allows the user to provide commands or responses to prompts or instructions provided to the user. This can be, for example, a touchpad, keyboard, mouse, microphone, and / or speaker.

[0139] Display interface 320 may include a monitor, LCD panel, etc., to display prompts, output information (such as facial measurements or interface size recommendations), and other information, such as capture displays, as described in further detail below.

[0140] The memory / data storage device 350 may be the internal memory of a computing device, such as RAM, flash memory, or ROM. In some embodiments, the memory / data storage device 350 may also be external memory linked to the computing device 230, such as an SD card, server, USB flash drive, or optical disc. In other embodiments, the memory / data storage device 350 may be a combination of external and internal memory. The memory / data storage device 350 includes stored data 354 and processor control instructions 352 for the instruction processor 310 to perform specific tasks. The stored data 354 may include data received by the sensor 340 (such as captured images) and other data provided as part of an application. The processor control instructions 352 may also be provided as part of the application.

[0141] As described above, facial images can be captured by a mobile computing device such as a smartphone 234. An appropriate application running on computing device 230 or server 210 can provide three-dimensional correlated facial data to aid in the selection of a suitable mask. This application can use any suitable facial scanning method. Such applications may include Capture from StandardCyborg (https: / / www.standardcyborg.com / ), an application from Scandy Pro (https: / / www.scandy.co / products / scandy-pro), a Beauty3D application from Qianxun3d (http: / / www.qianxun3d.com / scanpage), Unre 3D FaceApp (http: / / www.unre.ai / index.php?route=ios / detail), and an application from Bellus3D (https: / / www.bellus3d.com / ). Detailed procedures for facial scanning are included in the techniques disclosed in WO 2017000031, which are incorporated herein by reference in their entirety.

[0142] One such application is an application for facial feature measurement and / or patient data collection 360, which may be an application downloadable to a mobile device such as a smartphone 234 and / or a tablet 236. Application 360 may also collect facial features and data of patients already wearing masks to better gather feedback from such masks. Application 360, which may be stored on a computer-readable medium such as a memory / data storage device 350, includes program instructions for causing processor 310 to perform certain tasks related to facial feature measurement and / or patient interface sizing adjustment. The application also includes data that can be processed by algorithms of automated methods. Such data may include data records, reference features, and correction factors, as explained in further detail below.

[0143] Application 360, executed by processor 310, measures patient facial features using two-dimensional or three-dimensional images and, based on the obtained measurements, selects appropriate patient interface sizes and types from a set of standard dimensions. The method can generally be characterized as comprising three or four distinct phases: a pre-capture phase, a capture phase, a post-capture image processing phase, and a comparison and output phase.

[0144] In some cases, the application for facial feature measurement can control the processor 310 to output a visual display including reference features on the display interface 320. Users can position features adjacent to their facial features, such as through camera movement. The processor can then capture and store one or more images of the facial features associated with the reference features when certain conditions (such as alignment conditions) are met. This can be done with the aid of a mirror. A mirror reflects the displayed reference features and the user's face back to the camera. The application then controls the processor 310 to identify certain facial features within the image and measure the distances between them. Through image analysis processing, a scaling factor can then be used to convert the facial feature measurements (which may be pixel counts) into standard interface measurements based on the reference features. Such values ​​may be, for example, standard units of measurement, such as meters or inches, and values ​​expressed in such units are suitable for mask sizes.

[0145] Additional correction factors can be applied to the measurements. Facial feature measurements can be compared to a data record that includes measurement ranges corresponding to different patient interface sizes for specific patient interface forms (such as nose shields and FFM). A recommended size can then be selected and output as a recommendation to the user / patient based on the comparison results. This process can be conveniently implemented within the comfort of any preferred user position. The application can execute the method within seconds. In one example, the application executes the method in real time.

[0146] During the pre-capture phase, the processor 310 specifically assists the user in establishing appropriate conditions for capturing one or more images for resizing processing. Some of these conditions include, for example, appropriate lighting and camera orientation caused by an unstable hand holding the computing device 230, as well as motion blur.

[0147] Users can easily download applications for performing automatic measurement and sizing at computing device 230 from a server such as a third-party application storage server to their computing device 230. When downloaded, such applications can be stored on the computing device's internal non-volatile memory (such as RAM or flash memory). Computing device 230 is preferably a mobile device, such as a smartphone 234 or a tablet computer 236.

[0148] When a user launches the application, processor 310 may prompt the user for patient-specific information, such as age, gender, weight, and height, via display interface 320. However, processor 310 may prompt the user for this information at any time, such as after measuring the user's facial features and after the user has used a mask with an RPT (Receiving Patient-Specific Transmission Device). Processor 310 may also present tutorials, which may be presented in an audible and / or visual manner, as provided by the application, to help the user understand their role during the process. These prompts may also require information about the type of patient interface, such as nose or full face, and the type of device the patient interface will be used with. Furthermore, during the pre-capture phase, the application may infer patient-specific information based on information already collected by the user (such as after receiving captured images of the user's face) and based on machine learning techniques or artificial intelligence. Other information may also be collected via the interface, as described below.

[0149] When the user is ready to continue (this can be indicated by user input or in response to a prompt via user control / input interface 331), processor 310 activates sensor 340 according to processor control instruction 352. Sensor 340 is preferably a forward-facing camera of the mobile device, located on the same side of the mobile device as display interface 320. The camera is generally configured to capture two-dimensional images. Mobile device cameras that capture two-dimensional images are ubiquitous. This technology utilizes this ubiquity to avoid the burden on the user to obtain dedicated equipment.

[0150] Approximately simultaneously with the activation of sensor / camera 340, processor 310 presents a capture display on display interface 320 according to instructions from the application. This capture display may include a live camera motion preview, reference features, a target frame, and one or more status indicators or any combination thereof. In this example, the reference feature is centered on the display interface and has a width corresponding to the width of display interface 320. The vertical position of the reference feature may be such that its top edge is adjacent to the top edge of display interface 320 or its bottom edge is adjacent to the bottom edge of display interface 320. A portion of display interface 320 will display a live camera motion preview 324, which typically displays the user's facial features captured by sensor / camera 340 in real time if the user is in the correct position and orientation.

[0151] The reference feature is a (predetermined) feature known to the computing device 230 and provides the processor 310 with a reference frame that allows the processor 310 to scale the captured image. The reference feature can preferably be a feature other than the user's facial or anatomical features. Therefore, during the image processing phase, the reference feature helps the processor 310 determine when certain alignment conditions are met, such as during the pre-capture phase. The reference feature can be a Quick Response (QR) code or a known example or marker that can provide the processor 310 with certain information, such as scaling information, orientation, and / or any other desired information that can optionally be determined from the structure of the QR code. The QR code can have a square or rectangular shape. When displayed on the display interface 320, the reference feature has a predetermined size, such as in millimeters or centimeters, the value of which can be encoded into the application and transmitted to the processor 310 at an appropriate time. The actual size of the reference feature 326 can vary between various computing devices. In some versions, the application can be configured to be specific to a particular computing device model, where the size of the reference feature 326 is known when displayed on a specific model. However, in other embodiments, the application may instruct the processor 310 to obtain certain information from the device 230, such as display size and / or scaling characteristics, which allows the processor 310 to calculate the real-world / actual size of the reference feature displayed on the display interface 320 via scaling. In any case, the actual size of the reference feature displayed on the display interface 320 of such a computing device is generally known prior to post-capture image processing.

[0152] Along with the reference features, the target frame can be displayed on the display interface 320. The target frame allows the user to align certain components within the capture display 322, which is desirable for successful image capture.

[0153] Status indicators provide users with information about the process status. This helps ensure that users do not make significant adjustments to the sensor / camera positioning before image capture is complete.

[0154] Therefore, when the user holds the display interface 320 parallel to the facial feature to be measured and presents the user display interface 320 to a mirror or other reflective surface, the reference feature is highlighted and overlaid on the real-time image seen by the camera / sensor 340 and reflected by the mirror. This reference feature can be fixed near the top of the display interface 320. The reference feature is highlighted at least partially in this way so that the sensor 340 can clearly see it, and the processor 310 can easily identify the feature. Additionally, the reference feature can overlay the real-time view of the user's face, which helps avoid user confusion.

[0155] The user can also be instructed by the processor 310 via the display interface 320, by audible instructions via the speaker of the computing device 230, or by prior instruction from a tutorial, to position the display interface 320 in the plane of the facial feature to be measured. For example, the user can be instructed to position the display interface 320 so that it faces forward in the plane aligned with the specific facial feature to be measured and is placed below, against, or adjacent to the user's chin. For example, the display interface 320 can be positioned aligned with the self-illuminating and upper-illuminating planes. Since the final captured image is two-dimensional, plane alignment helps ensure that the scale of the reference feature 326 is equally applicable to facial feature measurement. At this point, the distances between the mirror and the user's two facial features and the display will be approximately the same.

[0156] When a user is positioned in front of a mirror and the display interface 320, including reference features, is roughly aligned with the plane of the facial features to be measured, the processor 310 checks specific conditions to help ensure adequate alignment. As previously mentioned, an exemplary condition that can be established by the application is that all reference features must be detected within the target frame 328 in order to proceed. If the processor 310 detects that the reference features are not fully within the target frame, the processor 310 can disable or delay image capture. The user can then move their face along with the display interface 320 to maintain planarity until the reference features displayed in the live motion preview are within the target frame. This facilitates optimized alignment of the facial features and the display interface 320 relative to the mirror used for image capture.

[0157] When processor 310 detects all reference features within the target frame, it can read the IMU 342 of the computing device to detect the device tilt angle. For example, IMU 342 may include an accelerometer or gyroscope. Therefore, processor 310 can evaluate the device tilt, for example, by comparing it to one or more thresholds to ensure it is within an appropriate range. For example, if it is determined that the computing device 230, and therefore the display interface 320 and the user's facial features, are tilted in any direction within approximately ±5 degrees, the process can proceed to the capture phase. In other embodiments, the sustained tilt angle can be within approximately ±10 degrees, ±7 degrees, ±3 degrees, or ±1 degree. If excessive tilt is detected, a warning message can be displayed or issued to correct the unwanted tilt. This is particularly useful in helping users prevent or reduce excessive tilt, especially in the front-to-back direction, which, if not corrected, can become a source of measurement error because the captured reference image will not have an appropriate aspect ratio.

[0158] Once the alignment has been determined by the processor 310 to be application-controlled, the processor 310 proceeds to the capture phase. The capture phase preferably occurs automatically once the alignment parameters and any other prior conditions are met. However, in some embodiments, the user can initiate capture in response to a prompt to do so.

[0159] When image capture is initiated, processor 310 captures n images via sensor 340, preferably more than one image. For example, processor 310 may capture approximately 5 to 20 images, 10 to 20 images, or 10 to 15 images via sensor 340, etc. The number of captured images can be time-based. In other words, the number of captured images can be based on the number of images at a predetermined resolution that sensor 340 can capture during a predetermined time interval. For example, if image sensor 340 can capture 40 images at a predetermined resolution in 1 second, and the predetermined time interval for capture is 1 second, then sensor 340 will capture 40 images for processor 310 to process. The number of images can be user-defined, determined by server 210 based on artificial intelligence or machine learning of detected environmental conditions, or based on a desired accuracy target. For example, more images may be needed if high accuracy is required. Although it is preferable to capture multiple images for processing, a single image can be successfully used to obtain accurate measurements. However, more than one image allows for the acquisition of averaged measurements. This can reduce errors / inconsistencies and increase accuracy. The image can be placed by the processor 310 into the storage data 354 of the memory / data storage device 350 for post-capture processing.

[0160] Once an image is captured, processor 310 processes it to detect or identify facial features / landmarks and measure the distances between them. The resulting measurements can be used to recommend a suitable patient interface size. This processing can alternatively be performed by server 210 receiving the transmitted captured image and / or on the user's computing device (e.g., a smartphone). Processing can also be performed by a combination of processor 310 and server 210. In one example, the recommended patient interface size may be primarily based on the user's nose width. In other examples, the recommended patient interface size may be based on the user's mouth and / or nose size.

[0161] The processor 310, controlled by the application, retrieves one or more captured images from stored data 354. The processor 310 then extracts the images to identify each pixel of the two-dimensional captured image. The processor 310 then detects certain pre-defined facial features within the pixel composition.

[0162] The detection can be performed by the processor 310 using edge detection techniques (such as Canny, Prewitt, Sobel, or Robert edge detection). These edge detection techniques / algorithms help identify the location of certain facial features within the pixel structure that correspond to the actual facial features of the patient presented for image capture. For example, the edge detection technique can first identify the user's face within the image and also identify the pixel locations within the image corresponding to specific facial features, such as each eye and its edges, the mouth and its corners, the left and right nostrils, the supramental point, the glabella, and the left and right nasolabial folds, etc. The processor 310 can then label, tag, or store the specific pixel location of each of these facial features. Alternatively, or if such detection by the processor 310 / server 210 is unsuccessful, the pre-defined facial features can be manually detected and labeled, tagged, or stored by an operator through the user interface of the processor 310 / server 210 to view access to the captured image.

[0163] Once the pixel coordinates of these facial features are identified, the application controls the processor 310 to measure the pixel distances between certain identified features. For example, this distance can typically be determined by the number of pixels per feature and may include scaling. For instance, measurements between the left and right nostrils can be used to determine the pixel width of the nose and / or to determine the pixel height of the face. Other examples include pixel distances between each eye, between the corners of the mouth, and between the left and right nasolabial folds to obtain additional measurement data for specific structures like the mouth. Further distances between facial features can be measured. In this example, specific facial dimensions are used in the patient interface selection process.

[0164] Once pixel measurements of pre-specified facial features are obtained, an anthropometric correction factor can be applied to those measurements. It should be understood that, as described below, the correction factor can be applied before or after the scaling factor. The anthropometric correction factor can correct for errors that may occur during the automated process, errors that can be observed to occur consistently from patient to patient. In other words, without the correction factor, the automated process alone may result in consistent results between patients, but the results may lead to a certain amount of dimensional errors in the patient interface. Correction factors extracted empirically from overall testing can shift the results closer to the true measurements, helping to reduce or eliminate dimensional errors. Since each patient's measurement and dimensional data is transmitted from the corresponding computing device to server 210, this data can be further processed in the server to improve the correction factor, thus the correction factor can be improved or refined in accuracy over time. The anthropometric correction factor can also vary between patient interface forms. For example, the correction factor for a specific patient seeking FFM may differ from the correction factor when seeking a nasal mask. This correction factor can be derived from mask purchase tracking, for example, by monitoring mask returns and determining the dimensional difference between replacement and returned masks.

[0165] To apply these facial feature measurements to patient interface size determination, whether or not they are corrected by anthropometric correction factors, these measurements can be scaled from pixel units to other values ​​that accurately reflect the distances between patient facial features presented for image capture. Reference features can be used to obtain one or more scaling values. Thus, processor 310 similarly determines the dimensions of the reference features, which may include measurements of the pixel width and / or pixel height (x and y) of the entire reference feature (e.g., pixel count). More detailed measurements can also be determined of the pixel dimensions of the numerous squares / dots comprising the QR code reference feature and / or the pixel area occupied by the reference feature and its constituent parts. Therefore, each square or dot of the QR code reference feature can be measured pixel-wise to determine a scaling factor based on the pixel measurement of each dot, and then averaged across all measured squares or dots. This improves the accuracy of the scaling factor compared to a single measurement of the full size of the QR code reference feature. However, it should be understood that regardless of what measurements are taken of the reference feature, these measurements can be used to scale the pixel measurements of the reference feature to the corresponding known size of the reference feature.

[0166] Once the processor 310 has measured the reference feature, it calculates a scaling factor according to the control of the application. The pixel measurement of the reference feature is correlated with the known corresponding size of the reference feature (e.g., reference feature 326 displayed by the display interface 320 for image capture) to obtain a conversion or scaling factor. This scaling factor can be in the form of length / pixel or region / pixel A2. In other words, the known size can be divided by the corresponding pixel measurement (e.g., count).

[0167] The processor 310 then applies a scaling factor to the facial feature measurement (pixel count) to transform the measurement from the pixel units into other units that reflect the distances between the patient's actual facial features suitable for determining the mask size. This typically involves multiplying the scaling factor by the pixel count of the distances between the facial features in relation to the mask size.

[0168] For each captured image, repeat these measurement and calculation steps for both facial features and reference features until each image in the group has scaled and / or corrected facial feature measurements.

[0169] The processor 310 can then optionally average the corrected and scaled measurements from the set of images to obtain final measurements of the patient's facial anatomy. Such measurements can reflect the distances between the patient's facial features.

[0170] During the comparison and output phase, the results from the post-capture image processing phase can be directly output (displayed) to interested individuals or compared with data records to obtain automatic recommendations for patient interface sizes.

[0171] Once all measurements have been determined, the processor 310 can display the results (e.g., the tie value) to the user via the display interface 320. In one implementation, this can terminate the automated process. The user / patient can record these measurements for further use.

[0172] Alternatively, the final measurement values ​​can be automatically or at the user's command via communication network 220 from computing device 230 to server 210. 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.

[0173] In another embodiment, processor 310 compares a final facial feature measurement reflecting the distance between actual facial features of the patient with patient interface size data, such as in a data record. The data record may be part of an application for automated facial feature measurement and patient interface size determination. The data record may include, for example, a lookup table accessible to processor 310, which may include patient interface sizes corresponding to ranges of facial feature distances / values. Multiple tables may be included in the data record, many of which may correspond to a specific form of patient interface and / or a specific model of patient interface provided by the manufacturer.

[0174] An exemplary process for selecting a patient interface identifies key landmarks from a facial image captured by the method described above. In this example, the initial association with a potential interface involves facial landmarks, which include features defined by… Figures 3A-3B The lines 3010, 3020, and 3030 represent facial height, nose width, and nose depth. These three facial landmark measurements are collected by the application to help, for example, select the size of a compatible face mask using the lookup table mentioned above.

[0175] As described above, after selecting or customizing a face mask for a patient, operational data for each RPT can be collected for a large number of patients. This can include usage data based on when each patient uses the RPT. Therefore, compliance data, such as the time and frequency of patient use of the RPT within a predetermined time period, can be determined based on the collected operational data. Leakage data can be determined from the analysis of operational data (such as flow data or pressure data). Face mask switching data using acoustic signal analysis can be exported to determine whether a patient has switched masks. RPT can be used based on internal or external audio sensors (such as... Figure 4B The microphone 4278 in the image uses cepstral analysis as described above to determine the mask type. Alternatively, for earlier masks, operational data can be used to determine the mask type by correlating the collected acoustic data with the acoustic characteristics of a known interface.

[0176] In this example, patient input feedback data can be collected via a user application running on computing device 230 or smartphone 234. The user application may be part of or a separate application of user application 360 that instructs the user to obtain facial landmark features. This may also include subjective data obtained via a questionnaire with questions designed to collect data on comfort preferences, whether the patient is a mouth or nose breather (e.g., questions such as “Do you wake up with a dry mouth?”), and the mask material is preferably, for example, silicone, foam, fabric, or gel. For example, patient input can be collected by the patient responding to subjective questions via a user application related to the comfort of the patient interface. Other questions may relate to relevant user behaviors, such as sleep characteristics. For example, subjective questions may include questions such as “Do you wake up with a dry mouth?”, “Are you a primary breather?”, or “What are your comfort preferences?” Such sleep information may include sleep duration, how the user sleeps, and external influences such as temperature and pressure factors. Subjective data can be as simple as a numerical rating of comfort or more detailed responses. This subjective data can also be collected from a graphical interface. For example, leakage from the interface can be collected from a user selecting a portion of the graphical representation of the interface. The collected patient input data can be assigned to… Figure 6 The patient database contains 260 patients. Subjective input data from patients can be used as feedback on mask design and features for future reference. Other subjective data related to patient psychological safety can be collected. For example, questions such as whether a patient experiences claustrophobia with that particular mask, or how psychologically comfortable a patient feels wearing the mask next to their bed partner, can be asked, and input can be collected.

[0177] Other data sources can be collected outside of RPT use that may be relevant to a particular mask. This could include patient demographics such as age, sex, or location; AHI severity indicating the level of sleep apnea experienced by the patient. Other data could include the prescribed pressure settings for new patients using the RPT device.

[0178] After selecting an interface, system 200 continues to collect operational data from RPT 250. The collected data is added to databases 260 and 270. Feedback from new patients can be used to refine recommendations for better mask options. For example, if operational data determines that a recommended mask has a high level of leakage, an alternative mask type can be recommended to the patient. Through feedback loops, the selection algorithm can be improved to learn specific aspects of facial geometry that may be best suited for a particular mask. This correlation can be used to improve mask recommendations for new patients with that facial geometry. Therefore, the collected data and associated mask type data can provide additional updates to mask selection and design criteria. Consequently, the system can provide additional insights to improve the selection or design of masks for patients.

[0179] In addition to mask selection, this system allows for analysis of mask selection in relation to the effectiveness and compliance of respiratory therapy. Additional data allows for optimization of respiratory therapy based on data traversed through a feedback loop.

[0180] Machine learning can be applied to provide correlations between mask types and features, and to increase compliance with respiratory therapy. These correlations can be used to select or design features for new mask designs. This machine learning can be performed by server 210. A mask analysis algorithm can be learned using a training dataset based on outputs of favorable operational outcomes and inputs including patient demographics, mask size and type, and subjective data collected from patients. Machine learning can be used to discover correlations between desired mask features and predictive inputs such as face size, patient demographics, operational data from the RPT device, and environmental conditions. Machine learning can employ techniques such as neural networks, clustering, or traditional regression techniques. Test data can be used to test different types of machine learning algorithms and determine which one has the best accuracy in predicting correlations.

[0181] The model used to select the best interface can be determined by [the relevant authority / organization]. Figure 5 The system continuously updates with new input data. Therefore, as the analysis platform is used more extensively, the model can become more accurate.

[0182] As mentioned above, Figure 5 Part of the system involves using the RPT (Recommended Face Mask Test) to recommend an interface to the patient. A second function of the system is a feedback data collection process that gathers data for future mask design or adjustments. Once a patient has been provided with a recommended mask and has been using it for a period of time, such as two days, two weeks, or another period, the system can monitor RPT usage and collect additional data. Based on this collected data, if it is determined that the mask is not performing to a high standard based on poor data indicating leakage, rejection compliance, or unsatisfactory feedback, the system can re-evaluate the mask selection and update the database 260 and machine learning algorithms with the patient's results. The system can then recommend a new mask to suit the newly collected data. For example, if a relatively high leakage rate is determined based on data based on acoustic features or other sensors, the patient may experience jaw drooping during REM sleep, which can signal the need for a different type of interface, such as a full-face mask instead of the initially chosen nose-only or smaller full-face mask.

[0183] The system can also adjust recommendations in response to satisfactory tracking data. For example, if operational data indicates no leakage from the selected full-face mask, the routine can suggest trying a smaller mask for a better experience. Follow-up recommendations can be provided using trade-offs between style, material, variation, and relevance to patient preferences to maximize adherence. These trade-offs can be determined through an input tree displayed to the patient by the application. For example, if a patient indicates skin irritation is a problem in the potential problem menu, a graph showing the potential irritation location on a facial image can be displayed to collect data as the specific location of the irritation from the patient. Specific data can provide a better relevance to the optimal mask for a particular patient.

[0184] This process allows for the collection of feedback data and its correlation with facial feature data, providing mask designers with data for designing other masks. This data is collected by applications such as 360 or others. Figure 5 As part of another application executed by a computing device such as computing device 230 or mobile device 234, feedback information related to the mask can be collected.

[0185] The 360 ​​app can collect initial patient information and provide security measures to protect data such as password settings. Once a patient has created an application and associated the 360 ​​app with a specific patient identity, the app can collect feedback data.

[0186] If facial data has already been collected for the patient, the 360 ​​app will continue to collect additional data. If no prior facial data has been collected for the patient, the 360 ​​app will offer the patient the option to collect facial data. Figure 7A An interface 700 of an application displaying a facial image 710 is shown. The patient can capture the facial image 710, similar to the facial scanning process described above regarding mask selection. After displaying the facial image 710, a facial mesh can be created. Figure 7B A second interface 720 is shown displaying a facial mesh 712 created based on a facial image 710. Facial data can then be exported from the facial mesh 710, stored, and sent to a server 210 for storage. Figure 5 Database 260 in the database.

[0187] The 360 ​​application collects all relevant data from patients through other interfaces displayed to evaluate the characteristics of the mask design. Figure 7CA sleep data collection interface 730 is shown, allowing the collection of subjective patient data related to sleep quality. This data can be collected and correlated with target sleep data or related operational data collected by the aforementioned RPT. Interface 730 includes a question 732 related to sleep position. Interface 730 includes options for the user to choose from, including a supine option 734, a prone option 736, and a lateral option 738. If the user is unsure, they can select an uncertain option 740. Therefore, interface 730 collects sleep position data relevant to a specific user.

[0188] Figure 7D Another sleep interface 750 is shown for collecting sleep type information. Interface 750 includes a question 752 about sleep type. Interface 750 includes options for the user to choose from, including a light sleeper option 754, a moderate sleeper option 756, and a deep sleeper option 758. If the user is unsure, they can select the unsure option 760. Therefore, interface 750 collects sleep type data related to a specific user.

[0189] The 360 ​​app also collects information about the current face mask used by the patient. Figure 8A Interface 800 includes options for a nose-only mask or a nose and mouth mask. Therefore, the user can either select option 802 for a nose-only mask or option 804 for a nose and mouth mask. In this example, options 802 and 804 include helpful graphics describing the interface type. This selection will indicate an additional interface specific to the manufacturer and interface model. After the patient makes the selection, a display allows the patient to choose the mask brand. Figure 8B The face mask brand selection interface 810 is shown. Interface 810 includes selection 812 for manufacturer A, selection 814 for manufacturer B, selection 816 for manufacturer C, and selection 818 for manufacturer D. The application allows access to all interface models for each manufacturer AD and will provide this information for subsequent interfaces, allowing selection of a specific interface from the selected manufacturer AD.

[0190] Figure 8C An interface 820 for selecting a face mask model is shown. The selection in interface 820 is made by... Figure 8B The manufacturer selected in interface 810 is determined. Interface 820 lists the options for each applicable model provided by the manufacturer, such as selecting 822, 824, 826, and 828.

[0191] After selecting the mask model, the 360 ​​app displays interface 830 to determine the size of the mask padding, such as... Figure 8D As shown. Interface 830 includes from Figure 8CThe interface 820 displays a graphic image 832 showing the model of the face mask selected. Graphic image 832 indicates where the user determines the size of the interface. Interface 830 includes small size selection 834, medium size selection 836, and large size selection 838.

[0192] Alternatively, the 360 ​​app can be programmed to identify a face mask by analyzing a graphic image of the mask and comparing that image with identification data about known face mask models. Figure 9A An instruction interface 900 is shown, providing options for obtaining automatic visual identification of the face mask. Figure 9B A photo interface 910 is shown that allows capturing images 912 of a face mask. Figure 9C A photo interface 920 is shown, displaying a captured image 912 of the face mask.

[0193] The 360 ​​app also includes an interface that collects data to determine which face mask is being used. Figure 9D The short-term use interface 930 determines whether a face mask is the only one used by displaying questions 932 related to face mask use over the past 30 days. Interface 930 can display a graphic of the face mask model previously selected by the user. The user can select "Yes" 934 or "No" 936 to indicate that another face mask has been used. Application 360 can also provide input to collect data about previous face masks.

[0194] Figure 9E An interface 940 is shown to determine whether a face mask is the only one in long-term use by displaying a question 942 related to face mask use. Interface 940 can display a graphic of the interface model previously selected by the user. The user can select "Yes" selection 944 or "No" selection 946 to indicate that a different face mask has been used.

[0195] The 360 ​​app can also identify comfort feedback data from patients. Figure 10A An interface 1000 is displayed to determine if there is any discomfort from the face mask. Question 1002 is displayed, asking the patient if they are experiencing any discomfort from the face mask. The patient can choose option 1004 or option 1006.

[0196] If the patient selects option "Yes" (1006), then as follows: Figure 10BThe interface 1010, which displays a visual discomfort indicator, is shown. Interface 1010 displays an image 1020 of facial features. Image 1020 can be selected from general facial images based on the patient's gender or other characteristics. Alternatively, image 1020 can be a personalized facial image, which, if captured by application 320, can be stored on a portable computing device or accessed from a database of previously captured patient facial images. A mask-shaped location grid 1022 covers the patient's facial image 1020. A selection list 1024 is displayed, describing five potential discomfort areas, including: a) bridge of the nose; b) upper side of the nose; c) lower side of the nose / corner of the nose; d) sides / corners of the mouth; and e) jaw / lower lip. The location grid 1022 includes lines defining five regions 1030, 1032, 1034, 1036, and 1038 corresponding to the regions described in list 1024, to help the patient locate the discomfort areas. Each of regions 1030, 1032, 1034, 1036, and 1038 represents the contact area between the face and the mask. The user can select one or more discomfort areas in list 1024. The list of discomfort areas and the corresponding areas in grid 1022 are then highlighted. In this example, the positional mask is specific to the entire mask, but other types of masks, such as support-type masks, may have different positional grids 1022 with discomfort areas specific to the mask type.

[0197] Figure 10C An example of the interface 1010 is shown when the patient has already selected an area of ​​discomfort. In this example, the patient has selected the upper side of the nose in list 1024. This selection is therefore highlighted. The area 1032 of the grid 1022 representing the upper side of the nose is also highlighted, thereby showing the area of ​​discomfort relative to the facial image 1020.

[0198] The 360 ​​app can also identify leak feedback data from patients. Figure 10D An interface 1050 is shown to determine whether there is any air leakage in the seal between the mask and the face. Question 1052 is displayed, asking the patient if they are experiencing any leakage from the mask. The patient can choose either option 1054 or option 1056.

[0199] If the patient selects "Yes" option 1056, then as follows Figure 10EThe interface 1060, which displays a visual indication of discomfort, is shown. Interface 1060 displays an image 1070 of the patient, which can be stored on a portable computing device if captured by application 320 or accessed from a database of previously captured images of the patient's face. A mask-shaped location grid 1072 covers the patient's facial image 1070. A selection list 1074 is displayed, describing five areas of potential air leakage, including: a) bridge of the nose; b) upper side of the nose; c) lower side of the nose / corner of the nose; d) sides / corners of the mouth; and e) jaw / lower lip. The location grid 1072 includes lines defining five areas 1080, 1082, 1084, 1086, and 1088 corresponding to the areas described in list 1074, to help the patient identify leaks between the mask and their face in areas 1080, 1082, 1084, 1086, and 1088 representing the contact area between the face and the mask. The user can select one or more discomfort areas in list 1074. Then highlight the list of inappropriate items and the corresponding areas in grid 1072.

[0200] Figure 10F An example of interface 1060 is shown when the patient has already selected an area of ​​discomfort. In this example, the patient has selected the upper part of the nose in list 1074. This selection is therefore highlighted. Area 1082 of grid 1072 is also highlighted, thus showing the area of ​​discomfort relative to facial image 1070.

[0201] Figure 11A An interface 1100 is shown for collecting subjective feedback data from patients regarding the impact of air leaks. If the user... Figure 10E If option 1056 is selected in interface 1050, then interface 1100 is displayed. Interface 1100 includes question 1102, which asks the patient to provide a numerical scale indicating how bothered they are by the air leak. Interface 1100 includes a scale 1104 ranging from 0 (not bothered) to 10 (very bothered). The patient can select slider 1106, which displays numerical input from the scale shown in the image of interface 1100. Other similar interfaces can be provided for other questions, such as those related to discomfort in a specific area or region of the face.

[0202] Figure 11B An interface 1150 is shown that collects subjective feedback data from patients regarding their satisfaction with their current face mask. Interface 1150 includes a question 1152 asking the patient if they would recommend a specific face mask model on a numerical scale. Interface 1150 includes a scale 1154 ranging from 0 (unlikely) to 10 (likely). The patient can select a slider 1156 that displays numerical input from the scale shown in the image of interface 1150.

[0203] Figure 11C This is an example interface 1160 that can be displayed to collect patient demographic data. Interface 1160 includes an age selection field 1162, a gender selection field 1164, and a race field 1166. Patients can then use fields 1162, 1164, and 1166 to enter their age, gender, and race data. This data can be collected to aid in the analysis of mask designs related to patient demographics.

[0204] Figure 11D is an example profile diagram that can be inserted for collecting discomfort and leaks, depending on the criteria used to determine, for example... Figure 10B The discomfort or certainty shown is as follows Figure 10C The selected mask type is shown in the interface generated by the leak. Figure 11D illustrates a series of five different overlay graphics 1170, 1172, 1174, 1776, and 1178 representing the shapes of different masks. For example, overlay graphics 1170, 1176, and 1178 represent different types of nose-only masks. Overlay graphics 1172 and 1174 represent different types of masks and nose masks. Based on the user's selection of the mask, the appropriate graphics 1170, 1172, 1174, 1776, and 1178 will be inserted.

[0205] Figure 12 A tree diagram 1200 shows the data collected by the sample application 360 described herein. Input 1210 requests which options best describe the user. Input 1210 can include users of vendor-made masks 1212, users of third-party-made masks 1214, and users without a current mask 1216. If the user identifies themselves as a user of a vendor-made mask or a user of a third-party-made mask, input 1220 determines whether the mask covers the nose or the nose and mouth. Data collection then collects data 1222 related to sleep position. If the user indicates they are not currently using a mask, the routine directly collects data 1222 related to sleep position. Input 1224 collects data on whether the user has difficulty placing their arms over their head. Input 1226 determines whether the user has difficulty breathing through their nose. Input 1228 determines whether the user suffers from nasal dryness. Input 1230 determines whether the user experiences claustrophobia. Input 1232 determines whether the user uses face cream at night.

[0206] Input 1234 determines the user's gender, as different genders typically have different facial features. The user can choose male or female. If the user refuses to answer, input 1236 determines the user's gender at birth. The user can answer male, female, or refuse to answer. If the user answers male by inputting 1234 or 1236, input 1238 determines whether the user has facial hair. The routine then presents a set of gender-common questions, including input 1240 related to whether the face or skin is easily irritated, input 1242 regarding whether the user wears glasses, input 1244 regarding whether the user has a bed partner, input 1246 regarding whether the user is concerned about the appearance of wearing a mask 1248, and input 1250 regarding whether the user has difficulty falling asleep. As described above, the collected data can be used to recommend or select appropriate masks for the user. The collected data can also be categorized and correlated with other user-specific data to provide guidance for the design of new masks relevant to specific patient subgroups or the general patient population.

[0207] For example, patient input data could indicate mask leakage in a specific area, such as the upper side of the nose. Leakage can be confirmed via operational data from the RPT device. This data can then be correlated with facial data involving the upper side of the nose. Analysis can be performed to adjust the mask size to minimize leakage by lengthening the edge of the mask at the junction with the upper side of the nose. Another example could be patient input data indicating discomfort with the mask on the upper side of the nose. This data can then be correlated with facial data involving the upper side of the nose. Analysis can be performed to adjust the mask size to minimize discomfort by shortening the edge of the mask at the junction with the upper side of the nose. Of course, the data can also be provided to a healthcare provider to recommend different sizes or types of masks to reduce discomfort or leakage. Alternatively, the data can be used to modify the mask initially selected by the patient to fit the patient individually.

[0208] Patient data and supplementary data collected from the aforementioned applications can be transformed or processed during the data processing steps, such as data from... Figure 5 The operating data of the RPT device 250 is used to help design an improved interface for the user. A mirror image (surface topography) of the face can be scanned to produce interfaces such as face masks. However, such patient interfaces are not necessarily ideal because certain areas of the sealing zone on the face may require different levels of sealing force, be more sensitive to tight headband pressure, or be more likely to leak at that location due to complex facial geometry. These finer details related to performance and comfort are considered along with additional processing that leads to a more optimized face mask design.

[0209] In one example, relaxed-state geometry data from a relaxed-state data collection can be used to attempt to provide an indication of the deformed-state geometry when it cannot be directly measured or is unavailable. Simulation software can be used for post-processing of the relaxed data to simulate the deformed state. Examples of suitable simulation software may include, but are not limited to, ANSYS, which performs the conversion from 'relaxed' to 'deformed' state geometry data in the relaxed data.

[0210] Additional facial images can be captured to determine the relaxation and deformation states of the facial geometry. Using the 'relaxation' and 'deformation' states of the geometric data, finite element software (such as ANSYS) can be used to calculate approximate pressure values ​​experienced between the patient interface contact area and the patient's face during the simulated stress. Alternatively, pressure data can be collected separately via pressure mapping. Therefore, based on the relaxation state data collection, the deformed geometry and the experienced pressure can be estimated.

[0211] Using measured data, geometric data, or pressure data, areas or features on a patient's face that require special consideration can be identified and addressed in specific feature treatments. Optionally, data from any combination of measurement sources can provide a comprehensive model that includes both geometric and pressure datasets to further refine the design's goals for comfort, efficacy, and compliance.

[0212] The face is not a static surface. More appropriately, it adapts to and modulates its interaction with external conditions, such as forces from the patient interface, air pressure on the face, and gravity. By taking these interactions into account, additional benefits are gained in providing optimal seal and comfort for the patient. Three examples illustrate this process.

[0213] First, since users wearing these patient interfaces will experience CPAP pressure, this knowledge can be used to enhance the comfort and seal of the patient interface. Simulation software, along with known properties such as soft tissue properties or elastic modulus, can help predict the deformation that the lower surface will experience under specific pneumatic pressures within the patient interface.

[0214] For groups involving any of the following facial locations, the tissue characteristics may be known and may be clustered: supragingival margin, glabella, nasal root, nasal tip, mid-philtrum, upper lip margin, lower lip margin, lower labial groove, labial fold, mental eminence, subchinum, forehead eminence, supraorbital margin, lateral glabella, lateral nose, infraorbital margin, subzygomatic bone, lateral nostrils, nasolabial ridge, supracanine, subcanine, mental tubercle ant., mid-lateral orbit, supraarticular, zygomatic bone, lateral, supra-M2, masseter, occlusal line, sub-M2, angle of the mandible, and middle angle of the mandible.

[0215] For example, soft tissue thickness is known from an anthropometry database for at least one of the following facial features: nasal tip, mid-philetrum, chin-lip fold, chin protuberance, infraorbital region, subzygomatic region, lateral nostrils, nasolabial ridge, upper canines, and lower canines. Certain locations, such as the infraorbital region, subzygomatic region, lateral nostrils, nasolabial ridge, upper canines, and lower canines, are situated on either side of the face.

[0216] Known tissue characteristics at any one or more of these locations may include soft tissue thickness, force-based modulus data, deflection, modulus and thickness, soft tissue thickness ratio information, and any one or more of body mass index (BMI).

[0217] Second, when the CPAP patient interface is strapped to the face, the skin surface on the patient's face undergoes significant deformation. Using initial 3D measurements of the geometry of the head and face in a relaxed state, changes in the surface can be predicted using knowledge of the skin / soft tissue properties discussed above and simulation software. This technique can be an iterative optimization process coupled with the design process.

[0218] Third, given the sleeping position, the skin surface may shift due to gravity. Predicting these changes using knowledge of skin and soft tissue properties and simulation software can help design more robust, comfortable, and high-performance patient interfaces across various sleeping positions. Data relating to geometric changes from upright to supine positions can be collected and used from one or more facial regions of interest, such as the nasal root, nasal tip, philtrum, labial fold, infraorbital region, lateral nostrils, nasolabial ridge, upper canines, and lower canines.

[0219] Finite element analysis (FEA) software (such as ANSYS) can be used to calculate approximate pressure values ​​experienced between the interface contact area and the user's face. In one form, the input can include the geometry of the face in a 'relaxed' and 'deformed' state, and features of the face at different locations (e.g., the measured elastic modulus, or substructures with known characteristics such as stiffness). Using such input, a finite element (FE) model of the face can be constructed, which can then be used to predict one or more responses of the face to the input (such as deformation or load response). For example, the FE model of the face can be used to predict the deformable shape of the face for a given pressure level in the patient interface (e.g., a pressure level of 15 cm H2O). In some forms, the FE model can also include a model of the patient interface or a portion thereof, such as a liner, including the geometry of the liner and its properties (e.g., mechanical properties such as the elastic modulus). Such a model can predict the deformation of the liner when internal loads are applied to it, such as the application of CPAP pressure, and the resulting interaction between the liner and the face, including the load / pressure therebetween, and the deformation of the face. Specifically, the change in distance at each point between the relaxed and deformed states, along with the corresponding tissue properties, can be used to predict the stress experienced at a given point (e.g., at the cheek).

[0220] Certain areas or features on the face may require special consideration. Identifying and adjusting these features can improve the overall comfort of the interface. Based on the data collection and estimation techniques discussed above, appropriate features can be applied to a customized patient interface.

[0221] In addition to the aforementioned indicators of pressure sensitivity, pressure compliance, shear sensitivity, and shear compliance, special consideration can be given to facial hair, hairstyle, and extreme facial landmarks (e.g., prominent bridge of the nose, sunken cheeks, etc.). As used herein, "shear sensitivity" refers to a patient's perception of shear, while "shear compliance" refers to how willing or compliant a patient's skin is to move along or comply with shear.

[0222] Figure 13 This is a feedback data collection routine that can run for one or more specific time periods after the patient initially selects the interface. For example, a tracking routine can run for the first two days after using the interface with RPT. Figure 13The flowchart in the diagram represents exemplary machine-readable instructions for collecting and analyzing feedback data to select features of an interface optimized for respiratory pressure therapy for different patient types. In this example, the machine-readable instructions include an algorithm for execution via the following steps: (a) a processor; (b) a controller; and / or (c) one or more other suitable processing devices. This algorithm can be embodied as software stored on a tangible medium such as flash memory, CD-ROM, floppy disk, hard disk, digital video (DVD) disc, or other storage devices. However, those skilled in the art will readily understand that the entire algorithm and / or portions thereof can alternatively be executed by devices other than a processor and / or implemented in a known manner using firmware or dedicated hardware (e.g., via application-specific integrated circuits [ASIC], programmable logic devices [PLD], field-programmable logic devices [FPLD], programmable gate arrays [FPGA], discrete logic, etc.). For example, any or all components of the interface can be implemented by software, hardware, and / or firmware. Furthermore, some or all of the machine-readable instructions represented by the flowchart can be implemented manually. Additionally, although referenced... Figure 13 The flowchart shown describes the example algorithm, but those skilled in the art will readily understand that many other methods can be used to implement the example machine-readable instructions. For example, the execution order of the blocks can be changed, and / or some of the described blocks can be modified, eliminated, or combined.

[0223] As will be explained below, Figure 13 The routines provided can offer suggestions for design modifications to different characteristics of interfaces, such as those in contact with facial regions. This data can also be continuously updated to support example machine learning-driven engines.

[0224] The routine first determines whether facial data has already been collected for the patient (1310). If facial data has not yet been collected, the routine activates application 360 to request the use of, for example, Figure 5 Mobile devices such as mobile device 234 running the above application scan the user's face (1312).

[0225] After collecting facial image data (1312), or if facial data has been stored from a previous scan, the routine accesses the operational data collected from the RPT within a set time period, such as 2 days (1314). Of course, other appropriate time periods, greater or less than two days, can be used as the time period for collecting operational data and other relevant data from the RPT. For example, Figure 2 The system can collect compiled objective data from two days of use, such as usage time or leaked data from RPT 250.

[0226] Furthermore, subjective feedback data such as sealing, comfort, and general liking / disliking can be collected from the interface of the user application 360 executed by the computing device 230 (1316). As described above, subjective data can be collected via an interface that presents questions to the patient. Therefore, subjective data can include answers related to discomfort or leakage, as well as psychological safety questions, such as whether the patient is psychologically comfortable with the mask. Other data can be collected based on the visual display of the mask relative to an image of the face.

[0227] The routine then correlates objective and subjective data with the selected mask type and the patient's facial scan data (1318). In the case of good results, the routine identifies operational data indicating high patient compliance, low leakage, and good subjective outcome (1320). The routine then updates the database and learning algorithm with the successful mask characteristics or features based on the relevant data (1322). If the results are not good, the routine also analyzes the relevant data and determines whether the results can be improved by adjusting the characteristics of the interface (1324). The routine then recommends changes to the features based on the analysis (1326). For example, the procedure might suggest thickening the portion of the mask that connects to the nose to prevent detection or reporting of leakage. The routine then stores the results by updating the database and learning algorithm (1322).

[0228] Figure 14 Based on from Figure 5 The data collection system 200 collects data to produce an example production system 1400 with a modified interface. The server 210 provides the analysis module 1420 with operational data collected from the RPT device group 1410 and subjective data collected by the application 230 from the patient group 1412.

[0229] Analysis module 1420 includes access to interface database 270, which contains data related to different models of face masks used by one or more different manufacturers. Analysis module 1420 may include machine learning routines to provide suggested changes to the characteristics or features of an interface for a specific patient or used by a subgroup of a patient population. For example, collected operational and patient input data, along with facial image data, may be input into analysis module 1420 to provide new features for the face mask design. Manufacturing data, such as CAD / CAM files used for existing interface designs, is stored in database 1430. Modified designs are generated by the analysis module and transmitted to manufacturing system 1440 to produce face masks with modifications in dimensions, sizes, materials, etc. In this example, manufacturing system 1440 may include processing machines, molding machines, printing systems, etc., for producing face masks.

[0230] To provide a more efficient method for manufacturing custom parts than additive manufacturing, the molding tools in manufacturing system 1440 can be rapidly prototyped (e.g., 3D printed) based on proposed modifications. In some examples, rapid 3D printing tools can provide a cost-effective method for manufacturing low-volume parts. Soft tools made of aluminum and / or thermoplastics are also possible. Compared to steel tools, soft tools provide a smaller number of molded parts and are cost-effective.

[0231] Hard tooling can also be used in the manufacture of custom parts. Hard tooling may be necessary when producing interfaces with advantageous volumes based on collected feedback data. Hard tooling can be made from various grades of steel or other materials used in the molding / machining process. The manufacturing process can also involve fabricating any part of the patient interface using any combination of rapid prototyping, soft tooling, and hard tooling. The construction of the tooling can also differ within the tool itself, using any or all types of tools; for example, half of the tooling that defines more general features of the part can be made by hard tooling, while half of the tooling that defines the custom part can be made by rapid prototyping or soft tooling. Combinations of hard or soft tooling are also possible.

[0232] Other manufacturing techniques may include multi-point injection molding for interfaces with different materials within the same component. For example, a patient interface liner may include different materials or grades of softness in different areas of the patient interface. Thermoforming (e.g., vacuum forming) may also be used, which involves heating a plastic sheet and evacuating the sheet onto a tooling mold, then cooling the sheet until it takes the shape of the mold. This is a viable option for molding components for custom nasal masks. In yet another form, a custom patient interface frame (or any other suitable component, such as a headgear or its parts, such as a hardener) may be produced using an initially stretchable material. A patient “male mold” may be manufactured using one or more of the techniques described herein, on which a stretchable “template” component may be placed to shape the component to fit the patient. The custom component may then be ‘cured’ to shape the component into a state that is no longer stretchable. An example of such a material may be a thermosetting polymer, which is initially stretchable until it reaches a specific temperature (after which it irreversibly cures); or a thermosoftening plastic (also known as a thermoplastic), which becomes stretchable above a specific temperature. Custom fabric weaving / knitting / forming may also be used. Aside from using yarn instead of plastic, this technology is similar to 3D printing. The structure of the fabric component can be knitted into any three-dimensional shape, making it ideal for manufacturing custom helmets.

[0233] As used herein, the terms “component,” “module,” “system,” etc., generally refer to a computer-related entity, or hardware (e.g., a circuit), a combination of hardware and software, software, or an entity associated with an operating machine having one or more specific functions. For example, a component can be, but is not limited to, a processor (e.g., a digital signal processor), a microprocessor, an object, an executable file, an execution thread, a program, and / or a process running on a computer. As an illustration, an application running on a controller and the controller itself can both be components. One or more components may reside within a process and / or an execution thread, and components may be located on a single computer and / or distributed across two or more computers. Furthermore, a “device” can take the form of specially designed hardware; general-purpose hardware specifically manufactured to perform specific functions by executing software thereon; software stored on a computer-readable medium; or a combination thereof.

[0234] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. Furthermore, the terms “including / includes,” “having / has,” “with,” or variations thereof are used in the detailed description and / or claims, and these terms are intended to be inclusive in a manner similar to the term “comprising.”

[0235] One or more elements, aspects, or steps or any part thereof from any one of claims 1-28 may be combined with one or more elements, aspects, or steps or any part thereof from any other claims 1-28 or a combination thereof to form one or more additional implementations and / or claims of the present invention.

[0236] Although the invention has been described with reference to one or more specific embodiments or implementations, those skilled in the art will recognize that many changes can be made thereto without departing from the spirit and scope of the invention. Each of these implementations and their obvious variations is considered to fall within the spirit and scope of the invention. It is also conceivable that further or alternative implementations of various aspects of the invention may combine any number of features from any implementation described herein, for example, in the alternative implementations described below.

Claims

1. A method of collecting data related to a patient interface for a respiratory pressure therapy device, the method comprising: associating facial image data from a patient with the patient; collecting operational data of the respiratory pressure therapy device used by the patient wearing the patient interface, wherein the operational data is collected via sensors and the operational data is indicative of a leak of the patient interface or a length of time the patient uses the respiratory pressure therapy device; collecting subjective patient input data from the patient regarding the patient interface; associating characteristics of the patient interface with the facial image data, operational data, and subjective patient input data; and adjusting the characteristics of the patient interface based on the facial image data, operational data, and subjective patient input data to generate a patient interface design specific to the patient.

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

3. The method of claim 1 or 2, wherein, 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.

4. The method of claim 1 or 2, wherein the facial image data is retrieved from a mobile device having an application for capturing an image of the patient’s face.

5. The method of claim 1 or 2, further comprising displaying a facial image with an inserted image of the patient interface and collecting subjective data from the patient based on a location on the inserted image of the patient interface.

6. The method of claim 5, wherein, the subjective data is collected by displaying questions in an interface on a mobile device.

7. The method of claim 6, wherein, the interface displays a sliding scale to input the patient’s answers.

8. The method of claim 1 or 2, wherein the facial image data includes a facial height, a nasal width, and a nasal depth.

9. The method of claim 1 or 2, further comprising adjusting a characteristic of the patient interface to prevent a leak, wherein the characteristic is associated with contact between a facial surface and the patient interface.

10. The method of claim 1 or 2, further comprising adjusting a characteristic of the patient interface to increase comfort, wherein the characteristic is associated with contact between a facial surface and the patient interface.

11. The method of claim 1 or 2, further comprising collecting facial image data of a second patient similar to the patient, operational data of a respiratory pressure therapy device used by the second patient, and subjective data input by the second patient regarding a characteristic of the patient interface.

12. The method of claim 1 or 2, further comprising: collecting facial image data, operational data, and subjective patient input data from a plurality of patients including the patient; and applying machine learning to determine types of operational data, subjective data, and facial image data related to a characteristic to adjust the characteristic of the patient interface.

13. A system comprising: a control system including one or more processors; and a memory having machine-readable instructions stored thereon; wherein the control system is coupled to the memory and implements the method of any one of claims 1 to 12 when the machine executable instructions in the memory are executed by at least one of the one or more processors of the control system.

14. A system for communicating one or more indications to a user, the system comprising a control system configured to implement the method of any one of claims 1 to 12.

15. A computer program product comprising instructions which, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 12.

16. The computer program product of claim 15, wherein the computer program product is a non-transitory computer readable medium.

17. A system for collecting feedback data from a patient using a patient interface that interfaces with a respiratory pressure therapy device, the system comprising: a storage device that stores a facial image of the patient; a data communication interface that communicates with the respiratory pressure therapy device to collect operational data from the patient while using the patient interface, wherein the operational data is collected via sensors and the operational data is indicative of a leak of the patient interface or a length of time the patient uses the respiratory pressure therapy device; a patient data collection interface that collects subjective patient input data from the patient relating to the patient interface; and an analysis module operable to correlate characteristics of the patient interface with facial image data relating to the facial image, the operational data, and the subjective patient input data, and adjust the characteristics of the patient interface based on the facial image data, the operational data, and the subjective patient input data to generate an interface design specific to the patient.

18. The system of claim 17, further comprising a manufacturing system that produces the patient interface specific to the patient based on design data from the generated interface design.

19. The system of claim 17 or 18, wherein the patient interface is a mask.

20. The system of claim 17 or 18, wherein 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.

21. The system of claim 17 or 18, further comprising a mobile device that executes an application to capture the facial image of the patient.

22. The system of claim 17 or 18, wherein the patient data collection interface displays a facial image with an inserted image of the patient interface and collects subjective data from the patient based on a location on the inserted image of the patient interface.

23. The system of claim 22, wherein the subjective data is collected by displaying questions in an interface on a mobile device.

24. The system of claim 23, wherein the interface displays a sliding scale to input answers of the patient.

25. The system of claim 17 or 18, wherein the facial image data comprises a facial height, a nasal width, and a nasal depth.

26. The system of claim 17 or 18, wherein a characteristic of the patient interface is adjusted to prevent leaks, wherein the characteristic is associated with contact between a facial surface and the patient interface.

27. The system of claim 17 or 18, wherein a characteristic of the patient interface is adjusted to increase comfort, wherein the characteristic is associated with contact between a facial surface and the patient interface.

28. The system of claim 17 or 18, further comprising a machine learning module operable to determine operational data, subjective data, and facial image data from a plurality of patients associated with the characteristic in order to adjust the characteristic of the patient interface.

Images