Negative and / or positive pressure therapy devices and methods with natural language interfaces

Abstract

A negative and / or positive pressure therapy system can include a therapy device with a pressure source configured to provide a pressure therapy to a wound site covered by a wound dressing and a controller configured to control operation of the pressure source. The system can include a storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to receive a natural language query associated with provision of the pressure therapy, the natural language query being issued by a user of the therapy device, using one or more machine learning models trained solely with data provided by a manufacturer of the therapy device, process the natural language query and determine a response, and provide the response to one or more of the user or the controller.

Description

[0001] NEGATIVE AND / OR POSITIVE PRESSURE THERAPY DEVICES AND METHODS WITH NATURAL LANGUAGE INTERFACES

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0003] This application claims priority to UK Patent Application Nos. GB 2403957.0 filed on March 20, 2024, GB 2409875.8 filed on July 8, 2024, and GB 2414397.6 filed on October 1, 2024, each of which is incorporated by reference in its entirety.

[0004] Technical Field

[0005] Embodiments described herein relate to apparatuses, systems, and methods for the treatment of wounds, for example using dressings in combination with negative and / or positive pressure therapy.

[0006] Description of the Related Art

[0007] Modern clinical wound care on mammals is carried out by individuals whose experience and training ranges from highly experienced clinicians specializing in the subject matter to carers and patients who have no formal training and can be classed as a lay user. Wound care is carried out in all manner of clinical settings ranging from specialized medial units to the home of individual and the center of a battlefield. In the last two decades wound care medical devices have become more complex than simple dressing often including an electronic controller to control the device. More focus has also been placed on preparing wounds and tissue sites and preventing wounds from occurring. Modern wound care medical devices range from active therapy devices (e.g. topical negative pressure, electrical stimulation devices, ultrasonic therapy) wound measurement, assessment and monitoring devices (e.g. infection monitoring devices using optical including UV and infrared, temperature and pH technologies), wound bed preparation devices (e.g. waterjet scalpels, cold plasma wands) and wound prevention devices (patient pressure monitors, patient position sensors). All these devices present a challenge to the human factors experts in designing simple to use yet safe user interfaces that can cater for multiple languages and levels of expertise. Further, with the challenges in resourcing medical care it is often difficult for carers to contact an expert or peer in order to help troubleshoot issues. Many different types of wound dressings are known for aiding in the healing process of a human or animal. These different types of wound dressings include many different types of materials and layers, for example, gauze, pads, foam pads or multi-layer wound dressings. Topical negative pressure (TNP) therapy, sometimes referred to as vacuum assisted closure, negative pressure wound therapy, or reduced pressure wound therapy, is widely recognized as a beneficial mechanism for improving the healing rate of a wound. Such therapy is applicable to a broad range of wounds such as incisional wounds, open wounds, and abdominal wounds or the like. TNP therapy assists in the closure and healing of wounds by reducing tissue edema, encouraging blood flow, stimulating the formation of granulation tissue, removing excess exudates and may reduce bacterial load. Thus, reducing infection to the wound. Furthermore, TNP therapy permits less outside disturbance of the wound and promotes more rapid healing.

[0008] SUMMARY

[0009] A negative and / or positive pressure therapy system can include a therapy device with a pressure source configured to provide a pressure therapy to a wound site covered by a wound dressing, a controller configured to control operation of the pressure source, and a communication circuitry configured to facilitate wireless communication with the therapy device. The system can include a storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to receive from the communication circuitry information associated with provision of the pressure therapy. The instructions can cause the one or more processors to receive a natural language query associated with provision of the pressure therapy. The natural language query can be issued by a user of the therapy device. The instructions can cause the one or more processors to, using one or more machine learning models trained solely with data provided by a manufacturer of the therapy device, process the natural language query and determine a response. The instructions can cause the one or more processors to provide the response to one or more of the user or the controller. The therapy device can provide negative pressure wound therapy.

[0010] The negative and / or positive pressure therapy system of any of the preceding paragraphs and / or any of the systems, apparatuses, or devices disclosed herein can include one or more of the following features. The response can include a set of instructions for adjusting operation of the pressure source. Provision of the response to the controller can cause the controller to adjust operation of the pressure source. The controller can deactivate or activate the pressure source. The natural language query can relate to one or more of status of the therapy device or status of the wound dressing. The controller can be configured to provide an alert associated with provision of the pressure therapy. The natural language query can be associated with the alert. The response can include instructions for remedying the alert.

[0011] The negative and / or positive pressure therapy system of any of the preceding paragraphs and / or any of the systems, apparatuses, or devices disclosed herein can include one or more of the following features. The pressure source can include a negative pressure source configured to provide negative pressure therapy to the wound site. The natural language query can be associated with selecting the wound dressing from a plurality of wound dressings suitable for the therapy device. The information can include one or more images of the wound site. The response can include one or more of a type, shape, and size of the wound dressing suitable for provision of the pressure therapy to the wound site. The one or more images can include a contour of an incision to be made on the wound site. The response can be determined based on the contour of the incision to made on the wound site. Determination of the response can include generating a shape of the wound dressing that matches a shape of the wound site. Provision of the response can include displaying the shape of the wound dressing overlaid on the wound site. Provision of the response can include displaying the wound dressing overlaid on the wound site.

[0012] The negative and / or positive pressure therapy system of any of the preceding paragraphs and / or any of the systems, apparatuses, or devices disclosed herein can include one or more of the following features. Provision of the response can include displaying the response. The one or more processors can be located in one or more servers. The natural language query can include one or more of speech or text. The information can include one or more of image data or data collected by one or more sensors.

[0013] A method of controlling a negative and / or positive pressure therapy system can include, by a therapy device, providing a pressure therapy to a wound site covered by a wound dressing from a pressure source. The pressure source can be controlled by a controller. The method can include, by one or more processors located remotely from the therapy device, receiving a natural language query associated with provision of the pressure therapy. The natural language query can be issued by a user of the therapy device. The method can include, by one or more processors located remotely from the therapy device, using one or more machine learning models trained solely with data provided by a manufacturer of the therapy device. The method can include, by one or more processors located remotely from the negative pressure wound therapy device, processing the natural language query and determining a response. The method can include, by one or more processors located remotely from the negative pressure wound therapy device, providing the response to one or more of the user or the controller. The therapy device can provide negative pressure wound therapy.

[0014] The method of any of the preceding paragraphs and / or any of the methods disclosed herein can include one or more of the following features. The response can include a set of instructions for adjusting operation of the pressure source. Providing the response to the controller can cause adjusting operation of the pressure source. Adjusting operation of the pressure source can include deactivating or activating the pressure source. The natural language query can relate to one or more of status of the therapy device or status of the wound dressing. The method can include, by the therapy device, providing an alert associated with provision of the pressure therapy. The natural language query can be associated with the alert. The response can include instructions for remedying the alert.

[0015] The method of any of the preceding paragraphs and / or any of the methods disclosed herein can include one or more of the following features. The method can include processing the natural language query and determining a response based on one or more images of the wound. The natural language query can be associated with selecting the wound dressing from a plurality of wound dressings suitable for the therapy device. The response can include one or more of a type, shape, and size of the wound dressing suitable for providing the negative pressure therapy to the wound site. The one or more images can include a contour of an incision to be made on the wound site. The response can be determined based on the contour of the incision to made on the wound site. Providing the response can include displaying the wound dressing overlaid on the wound site. Determining the response can includes generating a shape of the wound dressing that matches a shape of the wound site. Providing the response can include displaying the shape of the wound dressing overlaid on the wound site.

[0016] A negative and / or positive pressure therapy system can include a therapy device with a pressure source configured to provide a negative pressure therapy to a wound site covered by a wound dressing, a controller configured to control operation of the pressure source, and a communication circuitry configured to facilitate wireless communication with the therapy device. The system can include a storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to, with one or more machine learning models, initiate an interactive session in a baseline state, the interactive session in the baseline state utilizing the one or more machine learning models trained solely with data provided by a manufacturer of the therapy device to provide responses to natural language queries issued by a user of the therapy device. The instructions can cause the one or more processors to receive from the communication circuitry information associated with provision of the pressure therapy. The instructions can cause the one or more processors to update a state of the interactive session, the interactive session in the updated state comprising the baseline state and further including the information associated with provision of the pressure therapy. The instructions can cause the one or more processors to receive a natural language query associated with provision of the pressure therapy, the natural language query being issued by the user of the therapy device. The instructions can cause the one or more processors to, with the one or more machine learning models trained solely with data provided by the manufacturer of the therapy device and using the information associated with provision of the pressure therapy, process the natural language query and determine a response. The instructions can cause the one or more processors to provide the response to one or more of the user or the controller. The therapy device can provide negative pressure wound therapy.

[0017] The negative and / or positive pressure therapy system of any of the preceding paragraphs and / or any of the systems, apparatuses, or devices disclosed herein can include one or more of the following features. Information associated with provision of the pressure therapy can include at least one of knowledge level of the user, data collected by one or more sensors, or a change to a parameter of the pressure therapy over a period of time. Determining the response can include assigning a higher priority to information associated with the baseline state than to the information associated with provision of the pressure therapy.

[0018] A medical system can include a medical device comprising a treatment module configured to provide a treatment to a patient, a controller configured to control operation of the treatment module, and a communication circuitry configured to facilitate wireless communication with the medical device. The system can include a storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to receive from the communication circuitry information associated with provision of the treatment. The instruction can cause the one or more processors to receive a natural language query associated with provision of the treatment. The natural language query can be issued by a user of the medical device. The instruction can cause the one or more processors to, using one or more machine learning models trained solely with data provided by a manufacturer of the medical device, process the natural language query and determine a response. The instruction can cause the one or more processors to provide the response to one or more of the user or the controller.

[0019] Disclosed herein are kits that include the therapy device of any of the preceding paragraphs and / or any of the devices, apparatuses, or systems disclosed herein and one or more wound dressings.

[0020] Any of the features, components, or details of any of the arrangements or embodiments disclosed in this application, including without limitation any of the apparatus embodiments and any of the negative pressure wound therapy embodiments disclosed herein, are interchangeably combinable with any other features, components, or details of any of the arrangements or embodiments disclosed herein to form new arrangements and embodiments.

[0021] BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figures 1 A and IB illustrate negative pressure wound therapy systems.

[0023] Figure 2A is an isometric view of a negative pressure wound therapy device and canister, showing the canister detached from the pump assembly of the device.

[0024] Figure 2B is a back view of the negative pressure wound therapy device shown in Figure 2 A.

[0025] Figure 2C illustrates a top surface of the negative pressure wound therapy device shown in Figure 2 A, showing a user interface.

[0026] Figure 3 illustrates a schematic of a control system of a negative pressure wound therapy device.

[0027] Figure 4 illustrates another negative pressure wound therapy system.

[0028] Figures 5A, 5B, and 5C illustrate a canisterless negative pressure wound therapy device. Figures 6A-6E and 7A-7B illustrate negative pressure wound therapy systems with a natural language interface.

[0029] Figures 8A-8D illustrate selection of suitable wound dressings for application of negative pressure wound therapy.

[0030] Figures 9A-9C and 10 illustrate selection and placement of suitable wound dressings for application of negative pressure wound therapy.

[0031] Figures 11-14 illustrate supports for selection and placement of suitable wound dressings for application of negative pressure wound therapy.

[0032] Figure 15 illustrates the options for handsets that form part of the regulated information and instructions.

[0033] Figure 16 illustrates an augmented image of the wound identifying the position and percentage of certain bacteria and viable tissue.

[0034] DETAILED DESCRIPTION

[0035] Embodiments disclosed herein relate to systems and methods of treating and / or monitoring a wound. Some embodiments of the negative pressure wound therapy devices disclosed herein can include a negative pressure source configured to be connected and / or fluidically coupled, via a fluid flow path, to a wound covered by a wound dressing and provide negative pressure to a wound.

[0036] Throughout this specification reference is made to a wound. The term wound is to be broadly construed and encompasses open and closed wounds in which skin is torn, cut or punctured or where trauma causes a contusion, or any other superficial or other conditions or imperfections on the skin of a patient or otherwise that benefit from pressure treatment. A wound is thus broadly defined as any damaged region of tissue where fluid may or may not be produced. Examples of such wounds include, but are not limited to, abdominal wounds or other large or incisional wounds, either as a result of surgery, trauma, sterniotomies, fasciotomies, or other conditions, dehisced wounds, acute wounds, chronic wounds, subacute and dehisced wounds, traumatic wounds, flaps and skin grafts, lacerations, abrasions, contusions, bums, diabetic ulcers, pressure ulcers, stoma, surgical wounds, trauma and venous ulcers or the like. Embodiments of systems and methods disclosed herein can be used with topical negative pressure (“TNP”) or reduced pressure therapy systems. Briefly, negative pressure wound therapy assists in the closure and healing of many forms of “hard to heal” wounds by reducing tissue oedema, encouraging blood flow and granular tissue formation, or removing excess exudate and can reduce bacterial load (and thus infection risk). In addition, the therapy allows for less disturbance of a wound leading to more rapid healing. TNP therapy systems can also assist in the healing of surgically closed wounds by removing fluid. TNP therapy can help to stabilize the tissue in the apposed position of closure. A further beneficial use of TNP therapy can be found in grafts and flaps where removal of excess fluid is important and close proximity of the graft to tissue is required in order to ensure tissue viability.

[0037] As used herein, reduced or negative pressure levels, such as -X mmHg, represent pressure levels relative to normal ambient atmospheric pressure, which can correspond to 760 mmHg (or 1 atm, 29.93 inHg, 101.325 kPa, 14.696 psi, etc.). Accordingly, a negative pressure value of -X mmHg reflects pressure that is X mmHg below 760 mmHg or, in other words, a pressure of (760-X) mmHg. In addition, negative pressure that is “less” or “smaller” than X mmHg corresponds to pressure that is closer to atmospheric pressure (for example, -40 mmHg is less than -60 mmHg). Negative pressure that is “more” or “greater” than -X mmHg corresponds to pressure that is further from atmospheric pressure (for example, -80 mmHg is more than -60 mmHg). In some cases, local ambient atmospheric pressure is used as a reference point, and such local atmospheric pressure may not necessarily be, for example, 760 mmHg.

[0038] Systems and methods disclosed herein can be used with other types of treatment in addition to or instead of reduced pressure therapy, such as irrigation, ultrasound, heat or cold, neuro stimulation, or the like. In some cases, disclosed systems and methods can be used for wound monitoring without application of additional therapy. Systems and methods disclosed herein can be used in conjunction with a dressing, including with compression dressing, reduced pressure dressing, or the like.

[0039] A healthcare provider, such as a clinician, nurse, or the like, can provide a TNP prescription specifying, for example, the pressure level or time of application. However, the healing process is different for each patient and the prescription may affect the healing process in a way the clinician or healthcare provider did not expect at the time of devising the prescription. A healthcare provider may try to adjust the prescription as the wound heals (or does not heal), but such process may require various appointments that can be time consuming and repetitive. Embodiments disclosed herein provide systems, devices, or methods of efficiently adjusting TNP prescriptions and delivering effective TNP therapy.

[0040] Wound Therapy System

[0041] Figure 1A schematically illustrates a negative pressure wound treatment system 100’ (sometimes referred to as a reduced or negative pressure wound therapy system, a TNP system, or a wound treatment system). In any implementations disclosed herein, though not required, the negative pressure wound treatment system 100’ can include a wound filler 102 placed on or inside a wound 104 (which may be a cavity). The wound 104 can be sealed by a wound cover 106, which can be a drape, such that the wound cover 106 can be in fluidic communication with the wound 104. The wound filler 102 in combination with the wound cover 106 can be referred to as a wound dressing. A tube or conduit 108’ (also referred to herein as a flexible suction adapter or a fluidic connector) can be used to connect the wound cover 106 with a wound therapy device 110’ (sometimes as a whole or partially referred to as a “pump assembly”) configured to supply reduced or negative pressure. The conduit 108’ can be a single or multi lumen tube. A connector can be used to removably and selectively couple a conduit or tube of the device 110’ with the conduit 108’.

[0042] In any of the systems disclosed herein, a wound therapy device can be canisterless, wherein, for example and without limitation, wound exudate is collected in the wound dressing or is transferred via a conduit for collection at another location. However, any of the wound therapy devices disclosed herein can include or support a canister.

[0043] Additionally, with any of the wound therapy systems disclosed herein, any of the wound therapy devices can be mounted to or supported by the wound dressing or adjacent to the wound dressing. The wound filler 102 can be any suitable type, such as hydrophilic or hydrophobic foam, gauze, inflatable bag, and so on. The wound filler 102 can be conformable to the wound 104 such that the wound filler 102 substantially fills the cavity of the wound 104. The wound cover 106 can provide a substantially fluid impermeable seal over the wound 104. The wound cover 106 can have a top side and a bottom side. The bottom side can adhesively (or in any other suitable manner) seal with the wound 104, for example by sealing with the skin around the wound 104. The conduit 108 or any other conduit disclosed herein can be formed from polyurethane, PVC, nylon, polyethylene, silicone, or any other suitable material.

[0044] The wound cover 106 can have a port (not shown) configured to receive an end of the conduit 108. In some cases, the conduit 108 can otherwise pass through or under the wound cover 106 to supply reduced pressure to the wound 104 so as to maintain a desired level of reduced pressure in the wound 104. The conduit 108 can be any suitable article configured to provide at least a substantially sealed fluid flow pathway or path between the wound therapy device 110’ and the wound cover 106, so as to supply the reduced pressure provided by the wound therapy device 110’ to wound 104.

[0045] The wound cover 106 and the wound filler 102 can be provided as a single article or an integrated single unit. In some cases, no wound filler is provided and the wound cover by itself may be considered the wound dressing. The wound dressing can then be connected, via the conduit 108, to a source of negative pressure of the wound therapy device 110’. In some cases, though not required, the wound therapy device 110’ can be miniaturized and portable, although larger conventional negative pressure sources (or pumps) can also be used.

[0046] The wound cover 106 can be located over a wound site to be treated. The wound cover 106 can form a substantially sealed cavity or enclosure over the wound. The wound cover 106 can have a film having a high water vapor permeability to enable the evaporation of surplus fluid, and can have a super absorbing material contained therein to safely absorb wound exudate. In some cases, the components of the TNP systems described herein can be particularly suited for incisional wounds that exude a small amount of wound exudate.

[0047] The wound therapy device 110’ can operate with or without the use of an exudate canister. In some cases, as is illustrated, the wound therapy device 110’ can include an exudate canister. In some cases, configuring the wound therapy device 110’ and conduit 108’ so that the conduit 108’ can be quickly and easily removed from the wound therapy device 110’ can facilitate or improve the process of wound dressing or pump changes, if necessary. Any of the pump assemblies disclosed herein can have any suitable connection between the conduit 108’ and the pump.

[0048] The wound therapy device 110’ can deliver negative pressure of approximately -80 mmHg, or between about -20 mmHg and -200 mmHg. Note that these pressures are relative to normal ambient atmospheric pressure thus, -200 mmHg would be about 560 mmHg in practical terms. In some cases, the pressure range can be between about -40 mmHg and -150 mmHg. Alternatively, a pressure range of up to -75 mmHg, up to -80 mmHg or over -80 mmHg can be used. Also in some cases a pressure range of below -75 mmHg can be used. Alternatively, a pressure range of over approximately -100 mmHg, or even -150 mmHg, can be supplied by the wound therapy device 110’.

[0049] As will be described in greater detail below, the negative pressure wound treatment system 100’ can be configured to provide a connection 332 to a separate or remote computing device 334. The connection 332 can be wired or wireless (such as, Bluetooth, Bluetooth low energy (BLE), Near-Field Communication (NFC), WiFi, or cellular). The remote computing device 334 can be a smartphone, a tablet, a laptop or another standalone computer, a server (such as, a cloud server), another pump device, or the like.

[0050] The wound therapy device 110’ can transmit data to a cloud 690 that may host one or more cloud-based servers 692. The cloud 690 may host and process the data and provide one or more responses. The cloud 690 can communicate with the remote computing device 334, which can receive the data from the wound therapy device 110’. The cloud 690 can host an Artificial Intelligence (Al) system that may be configured for natural language processing to assist with operation of the wound therapy device 110’ or provision of therapy, as described herein. The Al system can include one or more NLP models as described herein.

[0051] The wound therapy device 110’ may wirelessly transmit data to the remote computing device 334, and the remote computing device 334 can upload the data received from the wound therapy device 110’ to the cloud 690 for processing. The cloud 690 can transmit response(s) back to the remote computing device 334.

[0052] Figure IB illustrates another negative pressure wound treatment system 100. The negative pressure wound treatment system 100 can have any of the components, features, or other details of any of the other negative pressure wound treatment system disclosed herein, including without limitation the negative pressure wound treatment system 100’ illustrated in Figure 1A or the negative pressure wound treatment system 400 illustrated in Figure 4, in combination with or in place of any of the components, features, or other details of the negative pressure wound treatment system 100 shown in Figure IB and / or described herein. The negative pressure wound treatment system 100 can have a wound cover 106 over a wound 104 that can seal the wound 104. A conduit 108, such as a single or multi lumen tube can be used to connect the wound cover 106 with a wound therapy device 110 (sometimes as a whole or partially referred to as a “pump assembly”) configured to supply reduced or negative pressure. The wound cover 106 can be in fluidic communication with the wound 104.

[0053] With reference to Figure IB, the conduit 108 can have a bridge portion 130 that can have a proximal end portion and a distal end portion (the distal end portion being closer to the wound 104 than the proximal end portion, and an applicator 132 at the distal end of the bridge portion 130 forming the flexible suction adapter (or conduit) 108. A connector 134 can be disposed at the proximal end of the bridge portion 130, so as to connect to at least one of the channels that can extend along a length of the bridge portion 130 of the conduit 108 shown in Figure IB. A cap 140 can be coupled with a portion of the conduit 108 and can, in some cases, as illustrated, be attached to the connector 134. The cap 140 can be useful in preventing fluids from leaking out of the proximal end of the bridge portion 130. The conduit 108 can be a Soft Port manufactured by Smith+Nephew. As mentioned, the negative pressure wound treatment system 100 can include a source of negative pressure, such as the wound therapy device 110, capable of supplying negative pressure to the wound 104 through the conduit 108. Though not required, the wound therapy device 110 can also include a canister or other container for the storage of wound exudates and other fluids that can be removed from the wound.

[0054] The wound therapy device 110 can be connected to the connector 134 via a conduit or tube 142. In use, the applicator 132 can be placed over an aperture formed in a wound cover 106 that is placed over a suitably-prepared wound or wound 104. Subsequently, with the wound therapy device 110 connected via the tube 142 to the connector 134, the wound therapy device 110 can be activated to supply negative pressure to the wound. Application of negative pressure can be applied until a desired level of healing of the wound is achieved.

[0055] The bridge portion 130 can comprise an upper channel material or layer positioned between an upper layer and an intermediate layer, with a lower channel material or layer positioned between the intermediate layer and a bottom layer. The upper, intermediate, and lower layers can have elongate portions extending between proximal and distal ends and can include a material that is fluid-impermeable, for example polymers such as polyurethane. It will of course be appreciated that the upper, intermediate, and lower layers can each be constructed from different materials, including semi-permeable materials. In some cases, one or more of the upper, intermediate, and lower layers can be at least partially transparent. In some instances, the upper and lower layers can be curved, rounded or outwardly convex over a majority of their lengths.

[0056] The upper and lower channel layers can be elongate layers extending from the proximal end to the distal end of the bridge portion 130 and can each preferably comprise a porous material, including for example open-celled foams such as polyethylene or polyurethane. In some cases, one or more of the upper and lower channel layers can be comprised of a fabric, for example a knitted or woven spacer fabric (such as a knitted polyester 3D fabric, Baltex 7970.RTM., or Gehring 879.RTM.) or a nonwoven material, or terry-woven or loop-pile materials. The fibers may not necessarily be woven, and can include felted and flocked (including materials such as Flotex.RTM.) fibrous materials. The materials selected are preferably suited to channeling wound exudate away from the wound and for transmitting negative pressure or vented air to the wound site, and can also confer a degree of kinking or occlusion resistance to the channel layers. In one example, the upper channel layer can include an open-celled foam such as polyurethane, and the lower channel layer can include a fabric. In another example, the upper channel layer is optional, and the system can instead be provided with an open upper channel. The upper channel layer can have a curved, rounded or upwardly convex upper surface and a substantially flat lower surface, and the lower channel layer can have a curved, rounded or downwardly convex lower surface and a substantially flat upper surface.

[0057] The fabric or material of any components of the bridge portion 130 can have a three- dimensional (3D) structure, where one or more types of fibers form a structure where the fibers extend in all three dimensions. Such a fabric can in some cases aid in wicking, transporting fluid or transmitting negative pressure. In some cases, the fabric or materials of the channels can include several layers of material stacked or layered over each other, which can in some cases be useful in preventing the channel from collapsing under the application of negative pressure. The materials used in some implementations of the conduit 108 can be conformable and pliable, which can, in some cases, help to avoid pressure ulcers and other complications which can result from a wound treatment system being pressed against the skin of a patient.

[0058] The distal ends of the upper, intermediate, and lower layers and the channel layers can be enlarged at their distal ends (to be placed over a wound site), and can form a "teardrop" or other enlarged shape. The distal ends of at least the upper, intermediate, and lower layers and the channel layers can also be provided with at least one through aperture. This aperture can be useful not only for the drainage of wound exudate and for applying negative pressure to the wound, but also during manufacturing of the device, as these apertures can be used to align these respective layers appropriately.

[0059] In some implementations, a controlled gas leak 146 (sometimes referred to as gas leak, air leak, or controlled air leak) can be disposed on the bridge portion 130, for example at the proximal end thereof. This air leak 146 can comprise an opening or channel extending through the upper layer of the bridge portion 130, such that the air leak 146 is in fluidic communication with the upper channel of the bridge portion 130. Upon the application of suction to the conduit 108, gas (such, as air) can enter through the gas leak 146 and move from the proximal end of the bridge portion 130 to the distal end of the bridge portion along the upper channel of the bridge portion 130. The gas can then be suctioned into the lower channel of the bridge portion 130 by passing through the apertures through the distal ends of the upper, intermediate, and lower layers.

[0060] The air leak 146 can include a filter. Preferably, the air leak 146 is located at the proximal end of the bridge portion 130 so as to minimize the likelihood of wound exudate or other fluids coming into contact and possibly occluding or interfering with the air leak 146 or the filter. In some instances, the filter can be a microporous membrane capable of excluding microorganisms and bacteria, and which may be able to filter out particles larger than 45 pm. Preferably, the filter can exclude particles larger than 1.0 pm, and more preferably, particles larger than 0.2 pm. Advantageously, some implementations can provide for a filter that is at least partially chemically-resistant, for example to water, common household liquids such as shampoos, and other surfactants. In some cases, reapplication of vacuum to the suction adapter or wiping of the exposed outer portion of the filter may be sufficient to clear any foreign substance occluding the filter. The filter can be composed of a suitably-resistant polymer such as acrylic, poly ethersulfone, or polytetrafluoroethylene, and can be oleophobic or hydrophobic. In some cases, the gas leak 146 can supply a relatively constant gas flow that does not appreciably increase as additional negative pressure is applied to the conduit 108. In instances of the negative pressure wound treatment system 100 where the gas flow through the gas leak 146 increases as additional negative pressure is applied, preferably this increased gas flow will be minimized and not increase in proportion to the negative pressure applied thereto. Further description of such bridges, conduits, air leaks, and other components, features, and details that can be used with any implementations of the negative pressure wound treatment systems disclosed herein are found in U.S. Patent No. 8,801,685, which is incorporated by reference in its entirety as if fully set forth herein.

[0061] Any of the wound therapy devices (such as, the device 110 or 110’) disclosed herein can provide continuous or intermittent negative pressure therapy. Continuous therapy can be delivered at above 0 mmHg, -25 mmHg, -40 mmHg, -50 mmHg, -60 mmHg, -70 mmHg, -80 mmHg, -90 mmHg, -100 mmHg, -120 mmHg, -125 mmHg, -140 mmHg, -160 mmHg, -180 mmHg, -200 mmHg, or below -200 mmHg. Intermittent therapy can be delivered between low and high negative pressure set points (sometimes referred to as setpoint). Low set point can be set at above 0 mmHg, -25 mmHg, -40 mmHg, -50 mmHg, -60 mmHg, -70 mmHg, -80 mmHg, -90 mmHg, -100 mmHg, -120 mmHg, -125 mmHg, -140 mmHg, -160 mmHg, -180 mmHg, or below -180 mmHg. High set point can be set at above -25 mmHg, -40 mmHg, -50 mmHg, -60 mmHg, -70 mmHg, -80 mmHg, -90 mmHg, -100 mmHg, -120 mmHg, -125 mmHg, -140 mmHg, -160 mmHg, -180 mmHg, -200 mmHg, or below -200 mmHg. During intermittent therapy, negative pressure at low set point can be delivered for a first time duration, and upon expiration of the first time duration, negative pressure at high set point can be delivered for a second time duration. Upon expiration of the second time duration, negative pressure at low set point can be delivered. The first and second time durations can be same or different values.

[0062] In operation, the wound filler 102 can be inserted into the cavity of the wound 104, and wound cover 106 can be placed so as to seal the wound 104. The wound therapy device 110’ can provide negative pressure to the wound cover 106, which can be transmitted to the wound 104 via the wound filler 102. Fluid (such as, wound exudate) can be drawn through the conduit 108’ and stored in a canister. In some cases, fluid is absorbed by the wound filler 102 or one or more absorbent layers (not shown).

[0063] Wound dressings that can be utilized with the pump assembly and systems of the present application include Renasys-F™, Renasys-G™, Renasys AB™, and Pico™ Dressings available from Smith+Nephew. In certain cases, foam or gauze can be used to fill the wound, particular when it is important to fill a wound cavity. Further description of such wound dressings and other components of a negative pressure wound therapy system that can be used with the pump assembly and systems of the present application are found in U.S. Patent Publication Nos. 2012 / 0116334, 2011 / 0213287, 2011 / 0282309, 2012 / 0136325, U.S. Patent No. 9,084,845, and International Patent Publication No. WO2021 / 069642, each of which is incorporated by reference in its entirety as if fully set forth herein. In some cases, other suitable wound dressings can be utilized.

[0064] More generally, any of the wound dressings described herein can be utilized without application of negative pressure. For instance, the wound dressing can be an AULEVYN™, OPSITE™, ACTICOAT™, or DURAFIBER™ dressing manufactured by Smith+Nephew. For example, ALLEVYN™ dressing is a moist wound environment dressing that is used to treat the wound without the use of negative pressure.

[0065] In some instances, a wound dressing can deliver an effective dose of nitric oxide (NO) to a wound. Nitric oxide influences blood vessel vasodilation, stimulates angiogenesis, influences the host immune response, and demonstrates potent, broad spectrum antimicrobial activity and anti-biofilm activity. Due to these multiple roles, nitric oxide demonstrates a potent effect on tissue and increased amounts of NO may support the acceleration of healing in wounds, particularly chronic wounds. Under normal conditions, nitric oxide, a free radical, is short-lived and converted to a more stable chemical species within seconds of production. Thus, for example, if gaseous nitric oxide contacts air, the gaseous nitric oxide will be rapidly oxidized to generate nitrogen dioxide (NO2). Accordingly, it may be difficult to maintain high concentrations of nitric oxide within a wound dressing or other similar structure for a prolonged period of time. Therefore, a device or a wound dressing having one or more layers containing more stable compositions may effectively generate nitric oxide over time upon activation, for the stable and sustained delivery of nitric oxide to biological tissues.

[0066] A wound dressing for delivering nitric oxide may include a cover layer configured to form a seal around a wound, an activator layer, a dry nitric oxide source layer, the dry nitric oxide source layer free or relatively free of liquid, and an acquisition distribution layer. The wound dressing may further comprise a masking layer configured to at least partially limit visualization of the wound. The dry nitric oxide source layer may comprise a nitrite salt. The nitrite salt may comprise sodium nitrite. The activator layer may be positioned above the nitric oxide source layer. In some embodiments, the nitric oxide source layer may be positioned above the activator layer. The acquisition distribution layer may be positioned between the activator layer and the dry nitric oxide source layer. The activator layer may comprise a hydrogel or a xerogel. The wound dressing may comprise a second dry nitric oxide source layer. The wound dressing may be configured to generate nitric oxide when the wound dressing is placed over a wound. In some instances, the wound dressing may be configured to not generate nitric oxide prior to placement over a wound. The wound dressing may be used in conjunction with provision of negative pressure wound therapy.

[0067] Figures 2A-2C show the negative pressure wound therapy device 110. As illustrated, a pump assembly 160 and canister 162 can be connected, thereby forming the wound therapy device 110. With reference to Figure 2C, the pump assembly 160 can include an interface panel 170 having a display 172, one or more indicators 174, or one or more controls or buttons, including, for example and without limitation, a therapy start and pause button 180 or an alarm / alert mute button 182. The interface panel 170 can have one or more input controls or buttons 184 (three being shown) that can be used to control any functions of the pump assembly 160 or the interface panel 170. For example and without limitation, one or more of the buttons 184 can be used to turn the pump assembly 160 on or off, to start or pause therapy, to operate and monitor the operation of the pump assembly 160, to scroll through menus displayed on the display 172, or to control or perform other functions. In some cases, the command buttons 184 can be programmable, and can be made from a tactile, soft rubber.

[0068] Additionally, the interface panel 170 can have visual indicators 186 that can indicate which of the one or more buttons 184 is active. The interface panel 170 can also have a lock / unlock control or button 188 that can be configured to selectively lock or unlock the functionality ofthe various buttons (e.g., buttons 184) or the display 172. For example, therapy setting adjustment can be locked / unlocked via the lock / unlock control 188. When the lock / unlock button 188 is in the locked state, depressing one or more of the various other buttons or the display will not cause the pump assembly 160 to change any display functions or performance functions of the device. This way, the interface panel 170 will be protected from inadvertent bumping or touching of the various buttons or display. The interface panel 170 can be located on an upper portion of the pump assembly 160, for example and without limitation on an upward facing surface of the pump assembly 160.

[0069] The display 172, which can be a screen such as an LCD screen, can be mounted in a middle portion of the interface panel 170. The display 172 can be a touch screen display. The display 172 can support playback of audiovisual (AV) content, such as instructional videos, and render a number of screens or graphical user interfaces (GUIs) for configuring, controlling, and monitoring the operation of the pump assembly 160.

[0070] The one or more indicators 174 can be lights (such as, LEDs) and can be configured to provide a visual indication of alarm conditions and or a status of the pump. For example and without limitation, the one or more indicators 174 can be configured to provide a visual indication of a status of the pump assembly 160 or other components of the negative pressure wound treatment system 100, including without limitation the conduit 108 or the wound cover 106 (such as, to provide an indication of normal operation, low battery, a leak, canister full, blockage, overpressure, or the like). Any one or more suitable indicators can be additionally or alternatively used, such as visual, audio, tactile indicator, and so on.

[0071] Figure 2B shows a back or rear view of the wound therapy device 110 shown in the Figure 2A. As shown, the pump assembly 160 can include a speaker 192 for producing sound. For example and without limitation, the speaker 192 can generate an acoustic alarm in response to deviations in therapy delivery, non-compliance with therapy delivery, or any other similar or suitable conditions or combinations thereof. The speaker 192 can provide audio to accompany one or more instructional videos that can be displayed on the display 172.

[0072] The pump assembly 160 can be configured to provide easy access (such as, an access door on the casing of the pump assembly) to one or more filters of the pump assembly 160, such as antibacterial filters. This can enable a user (such as, a healthcare provider or patient) to more easily access, inspect or replace such filters. The pump assembly 160 can also include a power jack 196 for providing power to the pump assembly 160 or for charging and recharging an internal power source (such as, a battery). Some implementations of the pump assembly 160 can include a disposable or renewable power source, such as one or more batteries, so that no power jack is needed. Capacity, health, charging current, or the like of the power source can be monitored. The pump assembly 160 can have a recess 198 formed therein to facilitate gripping of the pump assembly 160.

[0073] The canister 162 can hold fluid aspirated from the wound 104. For example, the canister 162 can have an 800 mL (or approximately 800 mL) capacity, or from a 300 mL or less capacity to a 1000 mL or more capacity, or any capacity level in this range. The canister 162 can include a tubing for connecting to the conduit 108 in order to form a fluid flow path. The canister 162 can be replaced with another canister, such as when the canister 162 has been filled with fluid. With reference to Figure 2A, the wound therapy device 110 can include a canister inlet tube 142 (also referred to herein as a dressing port connector) in fluid communication with the canister 162. For example and without limitation, the canister inlet tube 142 can be used to connect with the conduit 108.

[0074] The canister 162 can be selectively coupleable and removable from the pump assembly 160. With reference to Figure 2A, in some cases, a canister release button 202 can be configured to selectively release the canister 162 from the pump assembly 160. One or more microphones (positioned on the pump assembly 160 or externally, such as in the remote computing device 334) can detect clicking of the canister release button 202 to facilitate detection of canister placement, removal, or replacement. With reference to Figure 2B, the canister 162 can have one or more fill lines or graduations 204 to indicate to the user and amount of fluid or exudate stored within the canister 162.

[0075] The wound therapy device 110 can have a handle 208 that can be used to lift or carry the wound therapy device 110. The handle 208 can be coupled with the pump assembly 160 and can be rotatable relative to the wound therapy device 110 so that the handle can be rotated upward for lifting or carrying the wound therapy device 110 or the pump assembly 160, or rotated into a lower profile in a more compact position when the handle is not being used. In some cases, the handle 208 can be coupled with the pump assembly 160 in a fixed position. The handle 208 can be coupled with an upper portion of the pump assembly 160 or can be removable from the wound therapy device 110.

[0076] Figure 3 illustrates a schematic of a control system 300 that can be employed in any of the wound therapy devices described herein, such as in the wound therapy device 110. Electrical components can operate to accept user input, provide output to the user, operate the pressure source, provide connectivity, and so on. A first processor (such as, a main controller 310) can be responsible for user activity, and a second processor (such as, a pump controller 370) can be responsible for controlling another device, such as a pump 390.

[0077] An input / output (I / O) module 320 can be used to control an input and / or output to another component or device, such as the pump 390, one or more sensors (for example, one or more pressure sensors 325 configured to monitor pressure in one or more locations of the fluid flow path), or the like. For example, the I / O module can receive data from one or more sensors through one or more ports, such as serial (for example, I2C), parallel, hybrid ports, and the like. Any of the pressure sensors can be part of the wound therapy device or the canister. In some cases, any of the pressure sensors 325 can be remote to the wound therapy device, such as positioned at or near the wound (for example, in the dressing or the conduit connecting the dressing to the wound therapy device). In such implementations, any of the remote pressure sensors can communicate with the I / O module over a wired connection or with one or more transceivers 340 over a wireless connection.

[0078] The main controller 310 can receive data from and provide data to one or more expansion modules 360, such as one or more USB ports, SD ports, Compact Disc (CD) drives, DVD drives, FireWire ports, Thunderbolt ports, PCI Express ports, and the like. The main controller 310, along with other controllers or processors, can store data in memory 350 (such as one or more memory modules), which can be internal or external to the main controller 310. Any suitable type of memory can be used, including volatile or non-volatile memory, such as RAM, ROM, magnetic memory, solid-state memory, Magnetoresistive random-access memory (MRAM), and the like.

[0079] The main controller 310 can be a general purpose controller, such as a low-power processor or an application specific processor. The main controller 310 can be configured as a “central” processor in the electronic architecture of the control system 300, and the main controller 310 can coordinate the activity of other processors, such as the pump controller 370, one or more communications controllers 330, and one or more additional processors 380. The main controller 310 can run a suitable operating system, such as a Linux, Windows CE, VxWorks, etc.

[0080] The pump controller 370 can control the operation of a pump 390, which can generate negative or reduced pressure. The pump 390 can be a suitable pump, such as a diaphragm pump, peristaltic pump, rotary pump, rotary vane pump, scroll pump, screw pump, liquid ring pump, diaphragm pump operated by a piezoelectric transducer, voice coil pump, and the like. The pump controller 370 can measure pressure in a fluid flow path, using data received from one or more pressure sensors 325, calculate the rate of fluid flow, and control the pump. The pump controller 370 can control the pump actuator (such as, a motor) so that a desired level of negative pressure is achieved in the wound 104. The desired level of negative pressure can be pressure set or selected by the user. The pump controller 370 can control the pump (for example, pump motor) using pulse-width modulation (PWM) or pulsed control. A control signal for driving the pump can be a 0-100% duty cycle PWM signal. The pump controller 370 can perform flow rate calculations and detect alarms. The pump controller 370 can communicate information to the main controller 310. The pump controller 370 can be a low- power processor.

[0081] The pump controller 370 can monitor activity of the pump 390. For example, speed of a pump actuator (such as, motor), duty cycle of the pump actuator, or the like can be monitored. Activity can be indicative of the flow rate and can be utilized for detection of blockage, leakage, canister full, or the like.

[0082] Any of the one or more communications controllers 330 can provide connectivity (such as, a wired or wireless connection 332). The one or more communications controllers 330 can utilize one or more transceivers 340 for sending and receiving data. The one or more transceivers 340 can include one or more antennas, optical sensors, optical transmitters, vibration motors or transducers, vibration sensors, acoustic sensors, ultrasound sensors, or the like. Any of the one or more transceivers 340 can function as a communications controller. In such case, the one or more communications controllers 330 can be omitted. Any of the one or more transceivers 340 can be connected to one or more antennas that facilitate wireless communication. The one or more communications controllers 330 can provide one or more of the following types of connections: Global Positioning System (GPS), cellular connectivity (for example, 2G, 3G, LTE, 4G, 5G, or the like), NFC, Bluetooth connectivity (or BLE), radio frequency identification (RFID), wireless local area network (WLAN), wireless personal area network (WPAN), WiFi connectivity, Internet connectivity, optical connectivity (for example, using infrared light, barcodes, such as QR codes, etc.), acoustic connectivity, ultrasound connectivity, or the like. Connectivity can be used for various activities, such as pump assembly location tracking, asset tracking, compliance monitoring, remote selection, uploading of logs, alarms, and other operational data, and adjustment of therapy settings, upgrading of software or firmware, pairing, and the like.

[0083] Any of the one or more communications controllers 330 can provide dual GPS / cellular functionality. Cellular functionality can, for example, be 3G, 4G, or 5G functionality. The one or more communications controllers 330 can communicate information to the main controller 310. Any of the one or more communications controllers 330 can include internal memory or can utilize memory 350. Any of the one or more communications controllers 330 can be a low-power processor.

[0084] The control system 300 can store data, such as GPS data, therapy data, device data, and event data. This data can be stored, for example, in memory 350. This data can include patient data collected by one or more sensors. The control system 300 can track and log therapy and other operational data. Such data can be stored, for example, in the memory 350.

[0085] Using the connectivity provided by the one or more communications controllers 330, the control system 300 can upload any of the data stored, maintained, or tracked by the control system 300 to a remote computing device, such as the device 334. The control system 300 can also download various operational data, such as therapy selection and parameters, firmware and software patches and upgrades, and the like (for example, via the connection to the device 334). The one or more additional processors 380, such as processor for controlling one or more user interfaces (such as, one or more displays), can be utilized. In some cases, any of the illustrated or described components of the control system 300 can be omitted depending on an embodiment of a wound monitoring or treatment system in which the control system 300 is used.

[0086] A motion sensor 328 can monitor motion of a wound therapy device. The motion sensor 328 can be one or more an accelerometer of gyroscope.

[0087] Any of the negative pressure wound therapy devices described herein can include one or more features disclosed in U.S. Patent No. 9,737,649 or U.S. Patent Publication No. 2017 / 0216501, each of which is incorporated by reference in its entirety.

[0088] Multiple Dressing Negative Wound Therapy

[0089] Figure 4 illustrates another negative pressure wound treatment system 400. The system 400 can include a wound therapy device capable of supplying negative pressure to the wound site or sites, such as wound therapy device 110. The wound therapy device 110 can be in fluidic communication with one or more wound dressings 406a, 406b (collectively referred to as 406) so as to supply negative pressure to one or more wounds, such as the wounds 104a and 104b. A first fluid flow path can include components providing fluidic connection from the wound therapy device 110 to the first wound dressing 406a. As a non-limiting example, the first fluid flow path can include the path from the wound dressing 406a to the wound therapy device 110 or the path from the first wound dressing 406a to an inlet 446 of a branching attachment (or connector) 444 in fluidic connection with the wound therapy device 110. Similarly, a second fluid flow path can include components providing fluidic connection from the wound therapy device 110 to the second wound dressing 406b.

[0090] The system 400 can be similar to the system 100 with the exception that multiple wounds 104a and 140b are being treated by the system 400. The system 400 can include any one or more of the components of the system 100, which are illustrated in Figure 4 with appended letter “a” or “b” to distinguish between the first and second wounds (such as, the wounds 104a and 104b, the covers 106a and 106b). As illustrated, the system 400 can include a plurality of wound dressings 406a, 406b (and corresponding fluid flow paths) in fluidic communication with the wound therapy device 110 via a plurality of suction adapters, such as the adapter 108. The suction adapters can include any one or more of the components of the adapter 108, which are illustrated in Figure 4 with appended letter “a” or “b” to distinguish between the first and second wounds (such as, the bridge portions 130a and 130b, the connectors 134a and 134b, and the caps 140a and 140b).

[0091] The wound therapy device 110 can be fluidically coupled via the tube 142 with the inlet 446 of the connector 444. The connector 444 can be fluidically coupled via branches 445a, 445b and tubes or conduits 442a, 442b with the connectors 134a, 134b, which can be fluidically coupled with the tubes or conduits 130a, 130b. The tubes or conduits 130a, 130b can be fluidically coupled with the wound dressings 406a, 406b. Once all conduits and dressing components are coupled and operably positioned, the wound therapy device 110 can be activated, thereby supplying negative pressure via the fluid flow paths to the wounds 104a, 104b. Application of negative pressure can be applied until a desired level of healing of the wounds 104a, 104b is achieved. Although two wounds and wound dressing are illustrated in Figure 4, some implementations of the wound therapy device 110 can provide treatment to a single wound (for instance, by closing the unused branch 445a or 445b of the connector 444) or to more than two wounds (for instance, by adding branches to the connector 444).

[0092] The system 400 can include one or more features disclosed in U.S. Patent Publication No. 2020 / 0069850, International Publication No. WO2018 / 167199, International Publication No. WO2018 / 167199, or International Publication No. W02023 / 072704, each of which is incorporated by reference in its entirety. Canisterless Pump Assembly

[0093] Figures 5 A, 5B, and 5C illustrate perspective, front, and rear views of a TNP or negative pressure wound therapy (NPWT) device 500 (sometimes referred to as a wound therapy device). The wound therapy device 500 can include a housing 502 and a mounting component 510 (such as an attachment). The mounting component 510 can be removably attached to the housing 502, such that the wound therapy device 500 can be used with or without the mounting component 510. For example, Figure 5C illustrates the wound therapy device 500 without the mounting component 510. The mounting component 510 can be designed to allow the wound therapy device 500 to be mounted on another object such as, but not limited to, a user’s person. The mounting component 510 can include a clip 504 designed to retain the mounting component 510 on a user’s outerwear, such as on a user’s pocket, a pouch, a belt, a flap, or otherwise.

[0094] The housing 502 (sometimes referred to as “outer housing”) can contain or support components of the wound therapy device 500. The housing 502 can be formed from one or more portions, such as a front portion 502A and a rear portion 502B, which can be removably attached to form the housing 502.

[0095] The housing 502 can include a user interface 512 which can be designed to provide a user with information (for example, information regarding an operational status of the wound therapy device 500). The user interface 512 can include one or more indicators, such as icons 514, which can alert the user to one or more operating or failure conditions of the reduced pressure wound therapy system.

[0096] The wound therapy device 500 can include one or more user input features, such as button 516, designed to receive an input from the user for controlling the operation of the wound therapy device 500. A single button can be present which can be used to activate and deactivate the reduced pressure wound therapy device or control other operating parameters of the wound therapy device 500.

[0097] The wound therapy device 500 can include a connector 530 for connecting a tube or conduit to the wound therapy device 500. The connector 530 can be used to connect the wound therapy device 500 to a wound dressing.

[0098] The wound therapy device 500 can be a canisterless device. The wound dressing can retain fluid (such as, exudate) aspirated from the wound. Such a dressing can include a filter, such as a hydrophobic filter, that prevents passage of liquids downstream of the wound dressing (toward the wound therapy device 500).

[0099] The wound therapy device 500 can include a cover 518, as illustrated in Figure 5C and which can be removable. The cover 518 can cover a cavity (not shown) in which one or more power sources, such as batteries, for powering the wound therapy device 500 are positioned.

[0100] The wound therapy device 500 can include one or more controllers or other electronic components described herein. The wound therapy device 500 can be similar to the Pico™ negative pressure wound therapy device manufactured by Smith+Nephew. In some cases, the pump of the wound therapy device 500 can be periodically activated and deactivated in order to conserve power. Leaks can be detected based on monitoring one or more of pressure in the fluid flow path or duty cycle of the pump, and the pump can be automatically deactivated (or stopped) in response to detecting a leak of particular intensity. The wound therapy device 500 can be configured to operate for a limited duration (or lifetime), such as 7 days or less, 10 days, or 14 days or more.

[0101] Any of the negative pressure wound therapy devices described herein can include one or more features, including leak detection, blockage detection, canister full detection, power source monitoring, operation for a limited duration, disclosed in U.S. Patent No. 8,843,327, titled “CANISTER STATUS DETERMINATION” and issued September 23, 2014, U.S. Patent No. 9,408,954, titled “SYSTEMS AND METHODS FOR CONTROLLING OPERATION OF NEGATIVE PRESSURE WOUND THERAPY APPARATUS” and issued August 9, 2016, U.S. Patent No. 9,737,649, titled “SYSTEMS AND METHODS FOR APPLYING REDUCED PRESSURE THERAPY” and issued August 22, 2017, U.S. Patent No. 10,912,870, titled “CANISTER FLUID LEVEL DETECTION IN REDUCED PRESSURE THERAPY SYSTEMS” and issued February 9, 2021, U.S. Patent Publication No. 2019 / 0231939, U.S. Patent No. 8,734,425 titled, “PRESSURE CONTROL APPARATUS” and issued May 27, 2014, U.S. Patent No. 8,905,985 titled, “SYSTEMS AND METHODS FOR CONTROLLING OPERATION OF A REDUCED PRESSURE THERAPY SYSTEM’ and issued December 9, 2014, U.S. Patent No. 9,084,845 titled, “REDUCED PRESSURE THERAPY APPARATUSES AND METHODS OF USING SAME” and issued July 21, 2015, U.S. Patent No. 9,427,505 titled, “NEGATIVE PRESSURE WOUND THERAPY APPARATUS” and issued August 30, 2016, U.S. Patent No. 10,737,002, titled “PRESSURE SAMPLING SYSTEMS AND METHODS FOR NEGATIVE PRESSURE WOUND THERAPY” and issued on August 11, 2020, International Patent Publication No. WO 2022 / 223645, titled “CANISTER STATUS DETERMINATION FOR NEGATIVE PRESSURE WOUND THERAPY DEVICES,” International Patent Publication No. WO 2023 / 110376, titled “SMART BATTERY PACK WITH POWER SAVING MODES FOR NEGATIVE PRESSURE WOUND THERAPY DEVICES,” which are incorporated by reference in their entireties.

[0102] Any of the negative pressure wound therapy devices described herein can perform calibration and self-testing as described in U.S. Patent Publication No. 2023 / 0037943 titled “SELF-TESTING FOR NEGATIVE PRESSURE WOUND THERAPY DEVICES,” which is incorporated by reference in its entirety.

[0103] Natural Language Interfaces

[0104] Use of TNP devices can be complex, confusing, and cumbersome for a user, such as, a health care provider or patient. Existing TNP devices provide users with a user guide which would anticipate certain scenarios and list instructions on what to do next. Such guides can be voluminous and difficult to interpret, particularly, by non-experts. It can be advantageous to simplify the treatment process and reduce the need for expert intervention and product support interactions by providing a system that makes the treatment duration more autonomous and accurate. Such TNP system can utilize generative Al, such as natural language processing (NLP), to automatically monitor device-related sensors and user inputs in real time and respond by alerting the user to anomalous readings, respond to user inquiries, or alert the user to changes in the system status or needs for intervention. Additionally, the system can associate case data with patient outcomes by collecting and storing therapy data for further analysis.

[0105] NLP model(s) (such as, one or more large language models (LLMs)) can be trained with regulated medical device information (which can be stored in a database) about the use and operation of a therapy system, such as any of the negative pressure wound therapy systems described herein. Thus, responses to user’s inquiries can be based on and limited to such regulated information in order to be in compliance with various medical device or healthcare laws. Regulated information can be provided by the manufacturer of the TNP system, such as Smith+ Nephew, and may include one or more of user manual, repair manual, functional description of the operation of the system, catalogue of system accessories (such as, dressings), catalogue of spare parts, instructions for use (such as, instructional videos), list of indications and contra indications, information regarding other compatible products, or information regarding follow up treatments. Regulated information can include safe levels associated with provision of therapy. The NLP training database can be provided by the manufacturer only and regulated by the manufacturer through controls to prevent changes being made to change or add to the data, such as, cyber attacks or bad actors. In some cases, the database will be digitally locked on a version and encrypted. Any changes to the NLP training database would need to go through strict approval process carried out by subject matter experts. For example, making a change may require a multi-disciplinary team of experts to approve the change before implementation. Where a change may affect the safe use of the product the change may first need to be approved by a governmental regulatory body or a notified body. As such all information in the NLP training database would be verified or validated by the manufacturer so that it conforms to all regulatory requirements. In addition to such regulated information, NLP model(s) can provide responses based on specific data captured during provision of therapy (such as, image data, sensor data, or historical data, which can be captured over one or more time durations), as described herein with respect to contextual window(s).

[0106] As described herein, the user can provide voice prompts, text, or images (such as, photos, drawings, or video) for processing by the NLP (s), which in turn provide one or more responses. For example, one or more responses can include instructions for changing one or more therapy settings, selecting and applying a particular dressing, or replacing a canister. The instructions can be provided directly to the negative pressure wound therapy device and can be executed by one or more controllers of the device. As another example, one or more responses can include an interactive series of instructions that may require a further response from the user.

[0107] Figure 6A illustrates application of negative pressure therapy to a wound covered by a wound dressing 640 with a TNP system 600 that includes the NPWT device 500 (which can be a Pico™ device manufactured by Smith+Nephew). The NPWT device 500 can apply negative pressure wound therapy to a wound of a patient 610 covered by a wound dressing 640. The NPWT device 500 can communicate negative pressure to the wound via a fluid flow path that may include a conduit 630, a port 660 (such as, SoftPort manufactured by Smith+Nephew), and the wound dressing 640. The TNP system 600 can include the remote computing device 334 that communicates with the cloud 690. The cloud 690 can execute one or more NLP models for assisting with the application of negative pressure wound therapy. The remote computing device 334 may be operated by a user and can allow the user to request information regarding operation of the NPWT device 500 or provision of therapy based on one or more of data sensed by one or more sensors of the TNP system 600 (such as, pressure, motion (for instance, accelerometer or gyroscope), etc.), status data, image data, verbal prompts, or the like.

[0108] The remote computing device 334 can provide a user interface (UI) that facilitates interactions with the user. The UI can be a web interface, an app, or the like. Advantageously, the UI can be designed for ease of use, ensuring that users can conveniently type, speak, select, or transmit information as well as view, hear, or read the responses. Different user accounts can be supported, and user authentication can be implemented to control access to different features or personal data.

[0109] With reference to Figure 6A, the UI (which can be called “Pico Al”) can include an option 672 for determining status of the NPWT device 500 or provision of therapy, an option 674 for taking and uploading a photo to the cloud 690, and an option 676 for asking a question. These options can be selected using voice commands, by touch, or the like.

[0110] Executable code that implements the UI may be interface with the one or more NEP models being implemented by the cloud 690. This can be accomplished using an application programming interface (API) that communicates with the cloud 690. The API can be executed by the remote computing device 334. The API can make HTTP requests and receive response data. The API can implement rate limiting and error responses. Proper error handling mechanisms of the API can ensure that any issues within the API or the UI are gracefully managed. Logging can be implemented for debugging or monitoring performance. The API can implement data authentication (such as, by using API key(s)).

[0111] Since communication will be taking place over the Internet, it can be important to implement robust security measures. These can include HTTPS for secure communication, handling user data responsibly, and ensuring compliance with data privacy regulations (such, as GDPR). The cloud 690, such as one or more servers 692, can execute application logic that processes user requests (or queries), communicates with the one or more NLP models, and transmits response(s) to the remote computing device 334. The application logic can be built using various programming languages and frameworks (like Node.js, Python, etc.). The NLP models can be executed on one or more servers of the provider of the TNP system 600 or a third party.

[0112] One or more databases can be implemented in the cloud 690 for storing user data, conversation histories, or any other relevant information. The database(s) can ensure data integrity and security.

[0113] The architecture of the TNP system 600 may be scalable, especially if a large number of users is expected. This can be achieved with load balancing, efficient caching strategies, or optimizing API call patterns to avoid unnecessary costs or delays.

[0114] As described herein, the NLP model(s) can be trained on information related to the specific proprietary treatment device(s), method(s) of treatment, and if-then data developed by the manufacturer of the treatment device(s). The NLP model(s) can be revision controlled with traceability to episode of training and training datasets, system configuration and ancillary software and hardware, and black box validation testing. Product control data can be traceable to the manufacturer, for instance, via a specific serial number and documentation stored by the manufacturer.

[0115] The user can request information regarding status of the NPWT device 500. The NPWT device 500 can automatically monitor device-related sensors and user inputs in real time and generate an indication or alert, as described herein. For instance, the NPWT device 500 can provide an indication of normal operation, low battery, blockage, a leak, canister full, blockage, overpressure, or the like. The user may request information related to the status of a NPWT device 500, for instance, responsive to the indication. To request information, the user may be able to interact with the UI on the remote computing device 334, as described herein.

[0116] The user may request a status of the NPWT device 500 via the UI, and the request can be transmitted to the cloud 690, processed in the cloud, and response regarding the status can be transmitted from the cloud 690 and provided to the user (such as, via the UI). The request may be received as natural language voice command, text, or image. The response may be displayed (such as, via the remote computing device 334) or provided in audio format. The request submitted may be associated with the patient 610 (each patient may be assigned a unique patient identification number). The request may include the patient identification number and be processed by the cloud 690 based on a specific patient identification number. Furthermore, the cloud 690 may respond to the request by taking into account previous interactions related to the patient 610 (such as, provide a contextual window as described herein). As such, patient data may be aggregated in the database that is only accessed by the NLP model(s) when a request relates to the specific patient or device treatment episode. When a device is associated with a new patient, the previous patient’s data may be deleted or rendered inaccessible by the NLP model(s).

[0117] The response can include one or more instructions or information regarding operation of the NPWT device 500 or provision of therapy, status, modification of therapy settings, or the like. The NPWT device 500 may determine wound therapy levels based on a determination of various sensor information gathered by the NPWT device 500 wherein the information may be transmitted to a remote computing device 334 or the cloud-based server 692.

[0118] Table 1 provides examples of interactions with the TNP system 600. Table 1 provides a column with requests made by the user, responses provided by the NLP model(s), and inputs used by the NLP model(s) to provide the responses as well as actions communicated by the cloud server 690 to the device or a third party. Table 1 assumes that negative pressure wound therapy is being provided by a canisterless device, such as the device 500.

[0119] Table 1 : Example interactions with a canisterless TNP system

[0120]

[0121] As is noted in connection with example #2, the cloud 690 can issue instructions or commands directly to the NPWT device 500, for instance, to turn off (or deactivate) the negative pressure source when minor leak is being remedied. As is noted in connection with example #3, the cloud 690 can communicate with third parties, such as the clinician.

[0122] In some instances, the NPWT device 500 can override a command issued by the cloud 690 or a user action may be required to confirm the command before the NPWT device 500 executes the commands. This can be performed for reasons of safety or compliance. For example, a user may be asked to confirm turning off the negative pressure source, such as, by pressing a button (for instance, the button 180 or 516). As another example, the NPWT device 500 may override the command in case an alarm continues to be reasserted.

[0123] Table 2 provides examples of interactions with a TNP system 600 that includes a device with a canister that provides negative pressure wound therapy (such as, the device 110). Table 2 provides a column with requests made by the user, responses provided by the NLP model(s), and inputs used by the NLP model(s) to provide the responses as well as actions communicated by the cloud server 690 to the device or a third party. As described herein, the messages may take multiple formats, such as, audible spoken in the language of choice, text or icons on a screen of the device, or a separate device with any text being in the language of choice.

[0124] Table 2: Example interactions with a TNP system that utilizes a canister

[0125]

[0126] As is noted in connection with example #4, the cloud 690 can issue instructions or commands directly to the NPWT device 500, for instance, to turn off (or deactivate) the negative pressure source when canister is being replaced and turn on (or activate) the negative pressure source after to restart therapy after the canister has been replaced. Examples #2 and #3 illustrate the cloud 690 instructing the NPWT device 500 to set alerts to replace the canister and for charging the battery, respectively. In connection with example #3, the cloud 690 can instruct the NPWT device 500 to modify the battery alarm threshold indicative of low battery condition. The cloud 690 can determine the duration of time needed for charging the battery based on one of more of the current charge level, temperature, battery condition, usage. Example #7 illustrates the cloud 690 instructing the device 500 to generate an alert when 2 hours of battery charge remain. As is noted in connection with example #6, the cloud 690 can communicate with third parties, such as the healthcare provider or service and repair.

[0127] Responsive to raising an alert or providing another type of output, the cloud 690 can contact (for instance, by phone, email, SMS, or the like) a patient’s healthcare provider to communicate the alert or another type of output. The cloud 690 can communicate the alert or another type of output to a computing device of one or more of the healthcare provider or another party. The cloud 690 can facilitate a two-way communication with the healthcare provider or another party and can relay information to the user of the device 500. The cloud 690 can facilitate communication between the healthcare provider or another party and a third party, for instance, to order further medical equipment, schedule medical tests, or the like.

[0128] The system 600 can be configured to detect the type of user interacting with the system, such as healthcare provider or patient. The system 600 can make such detection based on the requests being provided by the user. For instance, a healthcare provider would likely provide more sophisticated requests than a patient. In addition, a level of sophistication of the healthcare provider can be detected, such as, expert clinician, non-expert clinician, nurse, or the like. The system 600 can adjust its responses based on the detection of the type of the user. The user may identify the user’s level of education or proficiency with the system and the system may respond using language that is meaningful to the particular user. For example, the user may identify as a non-skilled and therefore the responses may be adjusted to provide more explanation using simpler, less technical language.

[0129] Figures 6B to 6E are example illustrations of interactions between the user and the TNP system 600. An example of a user input illustrated with user input dialog box 670A, as shown in Figure 6B. The user can request (for instance, using a voice command or using a text command) the status of the dressing 640. The user can provide the request to the remote computing device 334, which can transmit the request to the cloud 690 for processing. The cloud 690 can provide a response as illustrated by the output dialog box 680A. The response can be based on data collected by one or more sensors (such as, pressure) and one or more photos of the dressing provided to the cloud 690. The output dialog box 680A can provide a response related to the status of the dressing, such as the dressing being about 40% full. The output dialog box 680A may include stepwise instructions requesting further information from a user.

[0130] Another example interaction is illustrated in Figure 6C. The user can request explanation of what it means for the device 500 to have all visual indicators off, as shown in the input dialog box 670B. The response can indicate that the power source has been depleted, as is illustrate in the output dialog box 680B. The response can offer to provide further instructions for changing the power source. The one or more NLP models can provide information regarding procedural steps to execute a dedicated task. As is illustrated in the output dialog box 680B further actions can be suggested and an offer to guide the user through performing such further actions can be made.

[0131] Figure 6D illustrates example interaction involving an alert generated by the NPWT device 500. Information regarding the alert can be provided to the user without prior request from the user (which is indicated by an empty input dialog box 670C). As is described herein, the cloud 690 can receive information from the NPWT device 500 (such as, sensor status, indication, or alerts). The cloud 690 can process the information and provide an explanation to the user. As is illustrated in the output dialog box 680D, the information can indicate that the dressing is full and needs to be changed and an offer to schedule an appointment with a healthcare provider.

[0132] Figures 7A and 7B illustrate provision of status of the NPWT device 500 or therapy in response to the user’s request for status (as explained in connection with Figure 6B) or in response to an alert (as explained in connection with Figures 6D and 6E). Status can be provided on the UI of the remote computing device 334. UI status screen 734 can illustrate indicators 736 of the NPWT device 500, specifically highlight indicator 738 that provides an alert, or provide illustration of pressure at the wound over time 740. Control 742 can provide the opportunity to type text for communication to the cloud 690.

[0133] The user may interact with the UI status screen 734. For example, the user may select (such as, touch) the indicator 738 and receive information from the cloud 690 about the alert and how to resolve the alert. For example, the user can select the indicator 738 and ask “Why is it red?” The user may select any of the status indicators 736 and receive information from the cloud 690. The user may similarly select the illustration of pressure 740 (or select any specific region) and receive information about application of pressure to the wound. The cloudbased server 692 determines, based on previous processed information, status indication with respect to identification of specific event triggers.

[0134] As described herein, the NLP model(s) can be configured to understand and process the context in which a TNP system 600 (or any other device described herein) is operating. For instance, the example interactions in Tables 1 and 2 illustrate contextual awareness of the NLP model(s). Answers can be tailored for a specific user (such as, a patient or healthcare provider) and provided in context of the interaction with the user. This may be referred to as providing a contextual window, which can be tailored for the user. The NLP model(s) can be configured to provide a contextual window for each user. To provide contextual window(s), the NPL model(s) can be configured to track the passage of time.

[0135] A contextual window can be created for a particular user when a TNP system 600 (or any other device described herein) is being set up to deliver therapy to a patient. Previous contextual window(s) can be deleted, and a new contextual window can be created using regulated device information, as described herein. In some instances, instead of deleting the contextual window for a previous user, data related to such contextual window can be saved and reloaded when another therapy session for the previous patient is started (or a previous therapy session is restarted). Advantageously, contextual windows can be created and tailored for a particular patient therapy session (or care episode). Starting with regulated information at the time of creation of a contextual window, the data set being used by the NLP model(s) can grow based on the interactions with the user. That is, regulated information can serve as baseline information at the initiation of the contextual window, and additional information is learned as the patient care episode is progressing. Responses or recommendations provided by the NLP model(s) can be adjusted taking into account such context as well as safe levels associated with provision of therapy (which can be part of the baseline information).

[0136] Baseline information can be partitioned from the additional information learned during the patient’s care episode in order to preserve integrity of regulated information that serves as baseline information. Regulated information can be updated (for instance, by a manufacturer), which can result in formation of a new baseline information. Instead of deleting an active contextual window created prior to the update, such portioning can allow maintaining such active contextual window by updating its baseline information. Advantageously, a contextual window’s baseline additional information associated with a particular patient can “grow” separately from any updates or changes to the baseline information.

[0137] A contextual window can be configured based on the education or knowledge level of the user, which may be provided by the user or a third party (for example, as a response to a prompt). Interactions with the user (such as, responses or questions) can be tailored to match the user’s education or knowledge level. Additional details are provided herein in connection with disclosure for type of user. In some cases, contextual windows can be configured based on a patient’s medical condition, which may be provided by a patient or third party or determined using one or more sensors that can include, for instance, one or more pressure sensors, motion sensors (for example, accelerometer or gyroscope), etc. Medical condition can include one or more of the patient’s mobility (such as, mobile or sedentary), exudate levels (such as, high or low), vitals (such as, good or poor), or the like.

[0138] A contextual window can, responsive to determining a reduction of exudate levels, suggest transition from negative pressure wound therapy with a canister (such as, with a Renasys negative pressure wound therapy device manufactured by Smith+Nephew) to canisterless negative pressure wound therapy (such as, with a Pico™ negative pressure wound therapy device manufactured by Smith+Nephew). Such determination can be made based on, for instance, directly monitoring the flow rate in a fluid flow path (or level of fluid in the canister) and detecting reduction in the flow rate over a period of time (or detecting static level of fluid in the canister over a period of time). Additionally or alternatively, the determination can be made by indirectly monitoring the flow rate, for instance, by monitoring a number of canister changes and detecting a reduction in the number of canister changes over a period of time. Additional details of transitioning to canisterless therapy are disclosed in International Patent Publication No. WO 2023 / 072704, which is incorporated by reference in its entirety.

[0139] A contextual window can suggest additional or alternative adjustments to the therapy. For instance, the contextual window can recommend adjusting the negative pressure setpoint or transitioning to intermittent (or continuous) negative pressure wound therapy. As an example, the contextual window can suggest an increase (or decrease) of the negative pressure setpoint responsive to determining that the user has previously increased (or decreased) the negative pressure setpoint. The contextual window can inquire whether the user is not experiencing discomfort or pain prior to increasing the negative pressure setpoint. In another instance, the contextual window can recommend decreasing the negative pressure setpoint in case the user is experiencing pain. In some cases, such decrease can be made automatically as a safety mechanism for protecting the patient’s health (for example, if blood is detected in the fluid flow path, if patient’s vital signs deteriorate, or the like).

[0140] In some instances, information can be weighted differently by the NLP model(s) during processing of a query and determining a response. One or more of the regulated information or prescribed therapy settings (such as, the negative pressure set point, dressing type, dressing size, etc.) can be assigned a higher weighting than information obtained via a contextual window during a therapy session for a particular user. This can be advantageous for maintaining provision of therapy within the constraints of the regulated information. For example, the regulated information can include the golden rule for a dressing fit whereby the wound should be completely covered by a dressing including an overlap of the dressing onto the wound periphery in order to achieve a good seal. Consistent with this rule, for a Pico™ dressing manufactured by Smith+Nephew, it may be desirable to choose a dressing size that is slightly larger than the wound size so that the benefits of negative pressure therapy are extended to the periwound area. Therapy settings can include information that a Pico™ dressing has been prescribed for negative pressure wound therapy and the above dressing size rule can be assigned a higher weight and utilized by the NLP model(s) (for example, in response to a query related to how to place the dressing on a wound).

[0141] As another example, suppose that a user issues the following query: “Provide me a simple explanation for changing the canister.” A response to this query can be more weighted to using the exact wording, images, or video from the regulated information (such as, from instructions for use) than to using simplified language that may have been determined to be appropriate for a particular user during a care episode (for example, due to the user’s education or knowledge level).

[0142] As yet another example, the user may ask for the wireless compliance license number for the device. The user may open a dialogue using a particular foreign language and may be asked whether the user would like the license number for the region associated with that language. On confirmation of the region required by the user, the NLP may provide the exact legal information provided in the instructions for use and labeling related to the wireless licensing compliance for the device. Such information may be verbal (such as, spoken via a loud speaker) or one or more of text or image data on a graphical display, or one or more of text or image data sent to a printer and printed on paper for the user. As such, the user may ask for an exact recitation from the instructions for use and legal labelling information that such a device is required to provide in order to comply with the laws of the region of use.

[0143] As yet another example, suppose that a user asks a question that contradicts with the regulated information. The user may ask: “What does the orange light mean on the top of the device?” According to the regulated information, the device may not have an orange status light. However, there may be information obtained via a contextual window during interactions with the user that the user has previously asked about an orange light (for instance, due to the user being color blind). The response generated by the NLP model(s) can be weighted to the explanation of the status lights according to the regulated information. For instance, the response can ask the user to confirm the color stating there is no orange light.

[0144] As yet another example, the regulated information may state that the battery life is 12 hours. Based on information obtained via a contextual window during a care episode for a particular user (such as, current draw, battery health, or temperature of operation), it may be determined that the battery could last 14 hours. In responding to a question about the battery life from the user, the weighting of the response can be higher towards the 12-hour limit as specified by the regulated information. Thus, the NLP model(s) can provide the following response: “The expected battery life is 12 hours. Under your current use conditions, this may extend by up to X minutes” (wherein X can be 30 minutes or less or more, 1 hour or less or more, etc.). That is, the answer can be biased to the regulated information.

[0145] In yet another example a TNP device may also irrigate the wound by controlling the flow of an irrigant solution (such as, saline or other physiologically therapeutic solutions) into the dressing. As such the user may ask the how long the current irrigant supply will last before it is empty. Based on information obtained via a contextual window during a care episode for a particular user (such as, therapy setting including irrigant flow rates, previous irrigant reservoir changes fluid changes, or pauses in therapy) it may be determined the current irrigant supply could last 24hrs. In responding to a question about the irrigant life from the user, the weighting of the response can be higher towards the 22-hour limit as specified by the regulated information. This difference may account for tolerance or operational parameter effects that may impact on the flow rate that have been determined by the manufacturer during development and testing of the device. Thus, the NLP model(s) can provide the following response: “The expected irrigant supply life is 22 hours. Under your current use conditions, this may extend by up to X minutes” (wherein X can be 30 minutes or less or more, 1 hour or less or more, etc.). That is, the answer can be biased to the regulated information.

[0146] Figures 8 A to 8D provide example illustrations of selecting appropriate wound dressings for application of negative pressure wound therapy. The cloud 690 can receive one or more photos of the wound (such as, an incision) or data related to wound anatomy or topology in order to recommend a suitable dressing type, form, and size for treating the wound. These interactions can be performed after the wound has already been formed (such as, after an operation) or before the wound has been formed (such as, before the operation). While examples in Figures 8 A to 8D relate to incision sites (prior to the operation) or incisions (after the operation), similar approaches can be used for treating any wound site prior to the operation or after the operation. The term wound site is to be broadly construed and encompasses any region of tissue prior to operation or after the operation, including closed or open wounds (which encompasses any incision sites or incisions). In some implementations, a wound site can be treated with negative pressure wound therapy prior to the surgical procedure. For example, the NPWT device 500 can be utilized, as is illustrated in Figures 6A-6E or Figure 7A. As described herein, Pico™ dressing can be utilized for applying negative pressure pre- operatively. The advantages of treating the wound site with negative pressure wound therapy include, among others, increased perfusion, reduction in oedema, disinfection, or decontamination. In some cases, positive pressure can be applied pre-operatively in addition to or instead of applying negative pressure and any of the examples described herein can apply positive pressure alone or in combination with negative pressure.

[0147] Such pre-operative treatment of the wound site (sometimes referred to as tissue conditioning) can improve overall wound healing outcomes. For instance, most surgical infections are a result of the patient’s own dermal flora contaminating the wound. By increasing blood flow prior to the surgery, the tissue can be primed to be able to rapidly supply the body’s own defensive biochemistry and nutrients for cells. By reducing the bioburden on the patient’s skin there may be a smaller chance that sufficient flora can enter the wound (for instance, the incision) and cause an infection. Keeping the tissue elastic and flexible through optimising moisture content can reduce stress on wound closure modalities (such as, sutures, clips, or glue), thus reducing the chance of dehiscence.

[0148] Any of the negative pressure wound therapy devices, such as the NPWT device 500, can treat not only the wound site area, but also the periphery of the wound site for a wider zone of treatment. Accordingly, a suitable dressing may be larger than the wound site area and should be sized correctly.

[0149] With reference to Figure 8A, to select a suitable wound dressing for an incision site 820 (or more generally a wound site), the user may ask “What size dressing do I need for the incision site?” The system may instruct the user to obtain one or more images of the wound (or area where the wound will be formed) as well as the periphery. For instance, the instructions may be “Hold the camera over the incision (or likely incision) so that the entire incision (or likely incision) along with the anatomic location are in view and wait for a dressing outline to appear then press the button to take an image.” The user may obtain image(s) of the incision site 820 and surrounding anatomy 810. In a pre-operative scenario, the user may obtain image(s) of the likely incision line, which can be physical or virtual. The image(s) can be uploaded to the cloud 690 and the NLP model(s) can process the image(s) to determine the size and shape of the wound site and its periphery and recommend a suitable dressing size and shape. The NLP model(s) can utilize (such as, be trained with) parameters provided by the wound dressing manufacturer for determining the optimum fit of a dressing to a wound site. For instance, the parameters can indicate that the minimum width of adhesive in contact with the skin on the periphery of the wound site less than 1.0 mm, less than 5.0 mm, less than 10.0 mm, etc. Parameters can be dependent on the type of pressure sensitive adhesive (such as, silicone or acrylic), reactive curing adhesive (such as, cyanoacrylate, epoxy, polyurethane, etc.), the type of dressing (NPWT, traditional adhesive, primary vs secondary), or the anatomical location (joint, torso, head etc.). For a wound dressing that delivers negative pressure to a wider zone of treatment (such as, the Pico™ dressing), the parameters can relate to the optimum width of intact skin surrounding the wound site that should receive the therapy.

[0150] NLP model(s) that determine the size and shape of the wound site and its periphery and recommend a suitable dressing size and shape can perform image processing and recognition to identify and classify one or more patterns or features in the image(s). For example, the NLP model(s) can identify the likely incision line(s) (which may be physically drawn on the skin of a patient or drawn in the image(s), as described herein). NLP model(s) can include one or more of convolutional neural networks (CNNs), deep residual networks (ResNet), Inception-v3 (GoogleNet), VGG16 (Visual Geometry Group), or YOLO (You Only Look Once). In some implementations, Eulerian video magnification can be utilized by the NLP model(s), as described in U.S. Patent No. 11,791,030, which is attached as Appendix A and incorporated by reference in its entirety. As described herein, the NLP model(s) can be trained solely with data provided by a manufacturer of the negative pressure wound therapy device. Such data can include correspondence between various different wound sites and dressing types and sizes.

[0151] In some implementations, the image(s) can include infrared (IR) image(s) that can facilitate identifying the size and shape of the wound site. The IR image(s) can be used by the NLP model(s) to determine the shape and size, for instance, of the wound site. In some instances, the size and shape of the wound site can be determined by the user using a ruler 950 as described herein or a utility installed on the remote computing device. This information can be provided to the NLP model(s), for instance, verbally by the user.

[0152] While a zone of treatment (with negative pressure) of at least 50 mm from the edge of the wound site may have a positive impact on blood flow, tissue moisture, and mechanical stress on the tissue, for some parts of the anatomy it may not be possible to attain such a zone of treatment (for instance, in case of anatomical openings or overall size of a body part). In such situations, the shape and size of the zone of treatment (and consequently of the recommended dressing) can be adjusted by the NLP model(s). For example, while the NLP model(s) can be trained on data that indicates that 50 mm is the minimum goal, but the image data may drive a compromise between optimal treatment and dressing types or sizes available in the manufacturer's catalogue or the user’s own supplies. For instance, the user may provide verbal feedback to the NLP model(s) that only certain size dressings are available, and the NLP model(s) can process the image data to determine the most suitable dressing to use of those dressings that are available.

[0153] In some instances, pre-operative planning and treatment can include the following steps: • Surgeon (or another healthcare provider) draws (physically or virtually) on the patient’s intact skin line(s) marking where the surgeon intends to make the incision.

[0154] • Surgeon takes image(s) of the intact incision site including the line(s).

[0155] • The image(s) (or description of the intact incision site) alone or along with information regarding the size of the line(s) is provided to the NLP model(s).

[0156] • NLP model(s) determine and provide a recommendation of suitable dressing (such as, type and size of the dressing, such as present a stock keeping unit (SKU) code or product code for the particular dressing), optionally, along with an augmented image showing the dressing positioned over the incision site with the line(s).

[0157] • Surgeon selects the dressing and applies the dressing as indicated to the incision site.

[0158] • Pre-operative treatment of the incision site is initiated.

[0159] Alternatively, in certain cases, pre-operative planning and treatment can include the following steps:

[0160] • Surgeon (or another healthcare provider) takes image(s) of the patient’s proposed incision site.

[0161] • Surgeon draws (physically or virtually) on the image(s) proposed incision line(s).

[0162] • The image(s) (or description of the intact incision site) alone or along with information regarding the size of the line(s) is provided to the NLP model(s).

[0163] • NLP model(s) determine and provide a recommendation of a suitable dressing (such as, type and size of the dressing), optionally, along with an augmented image showing the dressing positioned over the incision site with the line(s).

[0164] • Surgeon selects the dressing and applies the dressing as indicated to the incision site.

[0165] • Pre-operative treatment of the incision site is initiated.

[0166] In some cases, anatomical or topological data collected by sensor(s), such as light detection and ranging (LIDAR) sensor(s) or scanner(s), can be uploaded to the cloud 690 to facilitate with the selection of the dressing. Such anatomical or topological data can be used by the NLP model(s). The remote computing device 334 may be equipped with various sensors (such as, image sensors, LIDAR sensors or scanners, etc.) for determining wound site dimensions. The NLP model(s) can utilize the one or more image(s), anatomical or topological data, and manufacturer’s data regarding dressing sizes and shapes (such as, catalogue data) to provide a suitable dressing recommendation. For instance, the dressing recommendation can be in the form of “Use a 10cmx30cm PICO dressing with product code 66802013.” As is illustrated in Figure 8B, the particular recommended dressing can be overlaid on the incision site 820 in real time to provide the user with a visual representation of how the dressing would be placed over the incision site. The overlay 830 can be illustrated in the UI of the remote computing device 334. The system can provide instructions for placing the dressing (such as, video instructions).

[0167] The NLP model(s) can generate or recommend a dressing with an optimum shape of the dressing. Such shape can match the shape of the wound site. The generated shape can be overlaid on the dressing in real time (such as, on a display of the remote computing device 334). This can allow the user to cut the dressing to the optimal shape, as described herein.

[0168] In some instances, the shape may be printed out to actual scale on a standard desktop printer and then overlaid on the dressing to act as a template for the clinician to draw around or cut around. As such, a physical template can be created to aid the user on shaping the dressing. In further examples, the NLP model(s) can generate G-Code or other suitable Code to operate a numerical control of a manufacturing machine, such as, a laser cutter, a milling machine, or a 3D printer, in order for the dressing to be cut out, shaped, or produced according to the shape defined by the NLP model(s). In certain cases, a single dressing may not be sufficient to cover the area required and, in such cases, multiple shaped dressing may be combined to cover the therapy site on the patient.

[0169] Figures 8C and 8D illustrate another example of selecting a suitable dressing for an incision site 850 in a different part of the body. In this case, the particular recommended dressing size can be 15x30cm (product code 66802017).

[0170] A wound filler or a wound dressing for standalone use or for use with a different form of therapy can be similarly selected. Examples of such wound fillers and dressing are described herein. A wound filler can be used when it is important to get a good fit to the wound site itself so that the dressing seals the wound site and stays in place as the patient moves, rather than stick a dressing to the wound site periphery. Figure 9A illustrates selecting a suitable dressing using augmentation. The user may upload image(s) of a wound site 940 to the cloud 690, which can determine a segmented region 930 for placing a wound dressing. Additional data, such as data related to the anatomical features, can be provided as described herein. The segmented region 930 can be determined based on recognizing the features of the wound site 940. The segmented region 930 can include the wound site 940 and region(s) surrounding the wound site, as described herein. The segmented region 930 can be overlaid in real time on the UI of a remote computing device 920, thus providing an augmented view. The user can adjust the size, shape, or positioning of the segmented region 930 in the augmented view. Recommendations on the dressing dimensions, shape, and form to fit the segmented region can be provided, as described herein. Instructions for placing the dressing can also be provided.

[0171] Figure 9B illustrates similar environment as Figure 9A with the addition of a ruler 950 to assist with determining the segmented region 930. One or more NLP models being executed in the cloud 690 can perform image processing based on the measurements provided by the ruler 950 in order to accurately determine the segmented region 930. The ruler 950 can include a markings to help determine the dimensions of the wound site 940. The ruler 950 can include a color grid to verify the color of the wound site 940. Also illustrated is a support 960 for fixing the remote computing device during the process of selecting a suitable dressing for the wound site 940. The device support 960 may be adjustable (such as, pivotable) for adequate placement of the remote computing device 920. The device support 960 can include one or more of a stand, holder, mount, arm, or the like. The device support 960 and the remote computing device 920 can be manipulated by a user (such as, a health care professional).

[0172] Figure 9C further illustrates a user 970 interacting with the cloud 690 using voice commands. For instance, voice commands can be directed to the remote computing device 920 and relayed to the cloud 690. The user 970 may upload image(s) of the wound site 940 to the cloud 690. The user 970 may provide further information regarding the condition of the wound site.

[0173] Figure 10 illustrates placing of a suitable wound dressing using artificial reality (AR). A user 1070 wearing an AR headset 1030 (or another AR device) can size a wound dressing 1020 based on instructions being received from the cloud 690. The instructions can be generated based on image(s) 1010. The user 1070 can be guided in an augmented reality space in which, for example, a dressing template or the wound site can be displayed to the user to facilitate preparation of the wound dressing 1020. The user 1070 can have actual visibility of the reality with an augmented heads up display overlaying information showing where to cut the wound dressing 1020 (for instance, foam or gauze) and how to orientate and position the dressing on the wound. Guidance can be provided in a hands-free manner. The wound dressing 1020 being prepared or positioned can be overlaid on one or more of the template or the wound site in the view provided by the headset 1030. This can allow the user 1070 to follow the template or the wound site for more accurate preparation and placement of the wound dressing 1020.

[0174] Figure 11 illustrates placing of a suitable wound dressing on a wound site of a patient 1120 using AR or augmentation. As described in connection with Figures 9A to 9C, the user 970 can prepare and place the wound dressing 1020 on the wound site using the remote computing device supported by a support 1160. Alternatively or additionally, as is described in connection with Figure 10, the user can prepare and place the wound dressing 1020 on the wound site using the AR headset 1030. The support 1160 (shown as a stand) can include articulating arm(s) positioning the remote computing device 920.

[0175] Figure 12 illustrates preparation of the wound dressing 1020. A segmentation (or guide) 1210 can be presented to the user for assisting with the preparation of the wound dressing 1020. The guide 1210 can be a virtual guide overlay ed on the wound dressing 1020. In some cases, the guide 1210 can be physical or a combination of physical and virtual guide. The cloud 690 may provide the guide 1210 to assist the user to cut the wound dressing to the determined shape and dimensions. Additional or different visual, audible, or tactile aids can provided to the user for preparation and placement of the wound dressing 1020.

[0176] Figure 13 A illustrates a support 1160 for positioning the remote computing device 920. The support 1160 is illustrated as a mobile stand that may be rolled to different positions. The support 1160 may include one or more articulating arms for supporting the remote computing device 920. A user may utilize the remote mobile devices in a hands-free manner using the support 1160.

[0177] Figure 13B illustrates another support 1260. Similarly to the support 1160, the support 1260 can be a mobile stand with articulating arms. Multiple devices or tools can be positioned on the arms, such as a first electronic device 1330A, a magnifier 1330B, a second electronic device 1330C, and a measuring apparatus 1330D (such as, a ruler). Additional or alternative devices or tools can be supported by the support 1260.

[0178] Figure 13C illustrates another support 1360. The support 1360 can be a mobile stand that can propel itself. The support 1360 can propel itself based on one or more instructions received from an external device (for instance, wirelessly received). The support 1360 can include an electrical motor and battery pack enabling the support 1360 to propel itself. The support 1360 may operate autonomously. The support 1360 may include one or more motorized articulating arms for supporting the remote computing device 920. The support 1360 may include one or more sensors 1340, such as a camera. The support 1360 can include one or more sensors for assisting with the selection of a wound dressing, such as, one or more LIDAR sensors or scanners.

[0179] Figure 14 illustrates another support 1460. While the support 1460 can be similar to the support 1360, the support 1460 can be equipped with features that printing a wound dressing 1410 of a suitable size, shape, and form. For example, the support 1460 can include one or more additive printers (or 3D printers). The support 1460 can create the wound dressing 1410 from scratch or size and shape a wound dressing template to match the determined dimensions and shape of the wound dressing or the wound site. The support 1460 can receive instructions from the cloud 690 (or from the remote computing device 920) to prepare a suitable wound dressing. The support 1460 can utilize the one or more additive printers to accurately cut the wound dressing to the provided dimensions and shape. The support 1460 can subsequently dispense the wound dressing.

[0180] In some implementations, Al system trained with regulated medical device information to provide NLP interface(s) may be used to communicate and interact with, water jet and plasma ablation debridement systems that enable a clinician to remove dead and necrotic tissue and debris from a wound. When using such systems, the success of the procedure is often down to the skill of the user. The user must make expert judgment to select the appropriate disposable hand piece and power setting on the device to ensure a good outcome.

[0181] As such, the user can ask the Al system to suggest appropriate settings for the type of procedure, anatomical location, or type of debris to be removed. For instance, the user can ask: “I have a small diabetic ulcer to debride on the foot of a patient and it has some very dry eschar that needs removing - which handset and machine setting should I use?” In response, based on the technical performance and operational data, the NLP model(s) can provide a response for a particular hand piece part number and device settings (which may be confirmed both verbally and on the display of the device). The NLP model(s) may also provide the option for the clinician to accept the device setting via the user interface. Thus, in this particular example based on the information provided by the clinician about the procedure, from six options of handsets illustrated in Figure 15, the response may in the language of the clinician: “We recommend the VERSAJET II Plus disposable handset 66800045 and recommend starting on setting 5 on the device and fine adjusting the setting based on performance.”

[0182] In some cases, as illustrated by 1502 in Figure 15, the product code or an image of the recommended handset may be displayed on the screen of the device or on another device running an associate application (such as, a smart phone running an app that the clinician has logged into). The clinician may then ask to describe this particular handset. An example response from the NLP model(s) may be: “This handset is ideal for removing non-viable tissue as in the wound described it has a 45-degree angled cutting tip and an 8mm wide cutting window and is ideal for debriding small wounds.”

[0183] During the procedure, the clinician may verbally interact with the device without the need for taking the clinician’s focus off the procedure. For instance, the clinician may ask: “How long until the saline runs out?” Based on the technical data contained database, the elapsed time of operation for the current saline supply, and the settings the device controller, the NLP model(s) can determine a timing for when the saline is expected to run out and provide a response (such as, a verbal announcement or display the response).

[0184] Wound diagnostic or wound status devices can be interacted with in a similar manner using an Al system trained with regulated medical device information that provides NLP interface(s) for the user. Such devices may use image capture to determine the status or clinical diagnosis of the state of the wound. For instance, UV fluorescence can be used to determine the bacterial load in a wound. The user may ask for assistance with interpretation of the data or image, such as: “How much of the wound is colonized with bacteria and which types of bacteria are present?” Based on the technical data contained in database and analysis of the image of the wound, the NLP model(s) will provide a response (such as, both verbal description and a display of the types of bacteria present and the percentage area of the wound associated with each type of bacteria. The NLP model(s) may provide and augment image of the wound perimeter filled with colored regions showing the different bacteria types via different colors and also provide a percentage area for each bacteria type, such as illustrated in Figure 16. In addition to or alternatively, the user may ask for the image to be sent to a printer, transmitted by email to an email address or associated with an electronic medical record for the patient (or otherwise electronically transmitted).

[0185] In some implementations, wound prevention devices can be interacted with in a similar manner using an Al system trained with regulated medical device information to provide NLP interface(s) for the user. For example, such devices can monitor patient position over time or monitor patient pressure on a surface over time to provide information to a caregiver on when a patient should have their position changed to prevent pressure injury. A number of patients on a ward may have their data sent to a central monitoring or nursing station. Due to other tasks pending, the clinician may ask the question: “Which patients will need turning in the next 10 minutes?” Based on the technical data contained in the database and an analysis of individual patient data, the NLP model(s) can provide a list of the patients (such as, both verbally and on a graphical display). The clinician may further ask the NLP model(s) to send the list to a phone or portable tablet or print the list so that it is available during the ward visit and no patient is missed. Alternatively, the clinician may request that the individual patients be identified by illuminating an alert on a patient monitor device (such as, provide an audible alert on each patients monitor device).

[0186] Other Variations

[0187] Although some embodiments describe negative pressure wound therapy, the systems, devices, and / or methods disclosed herein can be applied to other types of therapies usable standalone or in addition to TNP therapy. Systems, devices, and / or methods disclosed herein can be extended to any medical device, and in particular any wound monitoring and / or treatment device. For example, systems, devices, and / or methods disclosed herein can be used with devices that provide one or more of ultrasound therapy, oxygen therapy, neurostimulation, microwave therapy, active agents, antibiotics, antimicrobials, or the like. Such devices can in addition provide TNP therapy. As another example, systems, devices, and / or methods disclosed herein can be used with a wound debridement system, patient monitoring system, or the like. The systems and methods disclosed herein are not limited to medical devices and can be utilized by any electronic device.

[0188] Any of transmission of data described herein can be performed securely. For example, one or more of encryption, HTTPS protocol, secure VPN connection, error checking, confirmation of delivery, or the like can be utilized.

[0189] While certain examples relate to the use of NLP model(s) or LLM(s), other types of Al or machine learning model(s) can be additionally or alternatively used.

[0190] Any value of a threshold, limit, duration, etc. provided herein is not intended to be absolute and, thereby, can be approximate. In addition, any threshold, limit, duration, etc. provided herein can be fixed or varied either automatically or by a user. Furthermore, as is used herein relative terminology such as exceeds, greater than, less than, etc. in relation to a reference value is intended to also encompass being equal to the reference value. For example, exceeding a reference value that is positive can encompass being equal to or greater than the reference value. In addition, as is used herein relative terminology such as exceeds, greater than, less than, etc. in relation to a reference value is intended to also encompass an inverse of the disclosed relationship, such as below, less than, greater than, etc. in relations to the reference value.

[0191] Features, materials, characteristics, or groups described in conjunction with a particular aspect, embodiment, or example are to be understood to be applicable to any other aspect, embodiment or example described herein unless incompatible therewith. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and / or all of the steps of any method or process so disclosed, can be combined in any combination, except combinations where at least some of such features and / or steps are mutually exclusive. The protection is not restricted to the details of any foregoing embodiments. The protection extends to any novel one, or any novel combination, of the features disclosed in this specification (including any accompanying claims, abstract and drawings), or to any novel one, or any novel combination, of the steps of any method or process so disclosed.

[0192] While certain embodiments have been described, these embodiments have been presented by way of example only, and are not intended to limit the scope of protection. Indeed, the novel methods and systems described herein may be embodied in a variety of other forms. Furthermore, various omissions, substitutions and changes in the form of the methods and systems described herein may be made. Those skilled in the art will appreciate that in some embodiments, the actual steps taken in the processes illustrated and / or disclosed may differ from those shown in the figures. Depending on the embodiment, certain of the steps described above may be removed, others may be added. For example, the actual steps and / or order of steps taken in the disclosed processes may differ from those shown in the figure. Various components illustrated in the figures or described herein may be implemented as software and / or firmware on a processor, controller, ASIC, FPGA, and / or dedicated hardware. The software or firmware can include instructions stored in a non-transitory computer-readable memory. The instructions can be executed by a processor, controller, ASIC, FPGA, or dedicated hardware. Hardware components, such as controllers, processors, ASICs, FPGAs, and the like, can include logic circuitry. Furthermore, the features and attributes of the specific embodiments disclosed above may be combined in different ways to form additional embodiments, all of which fall within the scope of the present disclosure.

[0193] Moreover, the various illustrative logical blocks and modules described in connection with the embodiments disclosed herein can be implemented or performed by a machine, such as a machine learning service server, a DSP, an ASIC, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A machine learning service server can be or include a microprocessor, but in the alternative, the machine learning service server can be or include a controller, microcontroller, or state machine, combinations of the same, or the like configured to generate and publish machine learning services backed by a machine learning model. A machine learning service server can include electrical circuitry configured to process computer-executable instructions. Although described herein primarily with respect to digital technology, a machine learning service server may also include primarily analog components. For example, some or all of the modeling, simulation, or service algorithms described herein may be implemented in analog circuitry or mixed analog and digital circuitry. A computing environment can include any type of computer system, including, but not limited to, a computer system based on a microprocessor, a mainframe computer, a digital signal processor, a portable computing device, a device controller, or a computational engine within an appliance, to name a few. The elements of a method, process, routine, or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a machine learning service server, or in a combination of the two. A software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of a non-transitory computer-readable storage medium. An illustrative storage medium can be coupled to the machine learning service server such that the machine learning service server can read information from, and write information to, the storage medium. In the alternative, the storage medium can be integral to the machine learning service server. The machine learning service server and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In the alternative, the machine learning service server and the storage medium can reside as discrete components in a user terminal (for example, access device or network service client device).

[0194] User interface screens illustrated and described herein can include additional and / or alternative components. These components can include menus, lists, buttons, text boxes, labels, radio buttons, scroll bars, sliders, checkboxes, combo boxes, status bars, dialog boxes, windows, and the like. User interface screens can include additional and / or alternative information. Components can be arranged, grouped, displayed in any suitable order.

[0195] Conditional language used herein, such as, among others, “can,” “could”, “might,” “may,” “e.g.,” and the like, unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain embodiments include, while other embodiments do not include, certain features, elements and / or states. Thus, such conditional language is not generally intended to imply that features, elements and / or states are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without author input or prompting, whether these features, elements and / or states are included or are to be performed in any particular embodiment. The terms “comprising,” “including,” “having,” and the like are synonymous and are used inclusively, in an open-ended fashion, and do not exclude additional elements, features, acts, operations, and so forth. Also, the term “or” is used in its inclusive sense (and not in its exclusive sense) so that when used, for example, to connect a list of elements, the term “or” means one, some, or all of the elements in the list. Further, the term “each,” as used herein, in addition to having its ordinary meaning, can mean any subset of a set of elements to which the term “each” is applied. Additionally, the words “herein,” “above,” "below," and words of similar import, when used in this application, refer to this application as a whole and not to any particular portions of this application.

[0196] Conjunctive language, such as the phrase “at least one of X, Y and Z,” unless specifically stated otherwise, is to be understood with the context as used in general to convey that an item, term, etc. may be either X, Y, or Z, or a combination thereof. Thus, such conjunctive language is not generally intended to imply that certain embodiments require at least one of X, at least one of Y and at least one of Z to each be present.

[0197] Language of degree used herein, such as the terms “approximately,” “about,” “generally,” and “substantially” as used herein represent a value, amount, or characteristic close to the stated value, amount, or characteristic that still performs a desired function or achieves a desired result. For example, the terms “approximately”, “about”, “generally,” and “substantially” may refer to an amount that is within less than 10% of, within less than 5% of, within less than 1% of, within less than 0.1% of, and within less than 0.01% of the stated amount. As another example, in certain embodiments, the terms “generally parallel” and “substantially parallel” refer to a value, amount, or characteristic that departs from exactly parallel by less than or equal to 15 degrees, 10 degrees, 5 degrees, 3 degrees, 1 degree, or 0.1 degree.

[0198] Unless otherwise explicitly stated, articles such as “a” or “an” should generally be interpreted to include one or more described items. Accordingly, phrases such as “a device configured to” are intended to include one or more recited devices. Such one or more recited devices can also be collectively configured to carry out the stated recitations.

[0199] Although the present disclosure includes certain embodiments, examples and applications, it will be understood by those skilled in the art that the present disclosure extends beyond the specifically disclosed embodiments to other alternative embodiments and / or uses and obvious modifications and equivalents thereof, including embodiments which do not provide all of the features and advantages set forth herein. Accordingly, the scope of the present disclosure is not intended to be limited by the specific disclosures of preferred embodiments herein, and may be defined by claims as presented herein or as presented in the future.

Claims

WHAT IS CLAIMED IS:

1. A negative and / or positive pressure therapy system comprising: a therapy device comprising: a pressure source configured to provide a pressure therapy to a wound site covered by a wound dressing; a controller configured to control operation of the pressure source; and a communication circuitry configured to facilitate wireless communication with the therapy device; and a storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to: receive from the communication circuitry information associated with provision of the pressure therapy; receive a natural language query associated with provision of the pressure therapy, the natural language query being issued by a user of the therapy device; using one or more machine learning models trained solely with data provided by a manufacturer of the therapy device, process the natural language query and determine a response; and provide the response to one or more of the user or the controller.

2. The system of any one of the preceding claims, wherein the response comprises a set of instructions for adjusting operation of the pressure source.

3. The system of any one of the preceding claims, wherein provision of the response to the controller causes the controller to adjust operation of the pressure source.

4. The system of claim 3, wherein the controller deactivates or activates the pressure source.

5. The system of any one of the preceding claims, wherein the natural language query relates to one or more of status of the therapy device or status of the wound dressing.

6. The system of any one of the preceding claims, wherein the controller is configured to provide an alert associated with provision of the pressure therapy, wherein the natural language query is associated with the alert, and wherein the response comprises instructions for remedying the alert.

7. The system of claim 1, wherein the pressure source comprises a negative pressure source configured to provide negative pressure therapy to the wound site.

8. The system of any one of the preceding claims, wherein: the natural language query is associated with selecting the wound dressing from a plurality of wound dressings suitable for the therapy device; the information includes one or more images of the wound, the one or more images optionally including a contour of an incision to be made on the wound site; and the response comprises one or more of a type, shape, or size of the wound dressing suitable for provision of the pressure therapy to the wound site, optionally, the response being determined based on the contour of the incision to be made on the wound site.

9. The system of claim 8, wherein: determination of the response further comprises generating a shape of the wound dressing that matches a shape of the wound site; and provision of the response comprises displaying the shape of the wound dressing overlaid on the wound site.

10. The system of claim 8 or 9, wherein provision of the response comprises displaying the wound dressing overlaid on the wound site.

11. The system of any one of the preceding claims, wherein provision of the response comprises displaying the response.

12. The system of any one of the preceding claims, wherein the one or more processors are located in one or more servers.

13. The system of any one of the preceding claims, wherein the natural language query comprises one or more of speech or text.

14. The system of any one of the preceding claims, wherein the information includes one or more of image data or data collected by one or more sensors.

15. A method of controlling a negative and / or positive pressure therapy system, the method comprising: by a therapy device, providing a pressure therapy to a wound site covered by a wound dressing from a pressure source, the pressure source being controlled by a controller; and by one or more processors located remotely from the therapy device: receiving a natural language query associated with provision of the pressure therapy, the natural language query being issued by a user of the therapy device; using one or more machine learning models trained solely with data provided by a manufacturer of the therapy device, processing the natural language query and determining a response; and providing the response to one or more of the user or the controller.

16. The method of any one of the preceding claims, wherein the response comprises a set of instructions for adjusting operation of the pressure source.

17. The method of any one of the preceding claims, wherein providing the response to the controller causes adjusting operation of the pressure source, and, optionally, wherein adjusting operation of the pressure source comprises deactivating or activating the pressure source.

18. The method of any one of the preceding claims, wherein the natural language query relates to one or more of status of the therapy device or status of the wound dressing.

19. The method of any one of the preceding claims, further comprising, by the therapy device, providing an alert associated with provision of the pressure therapy, wherein the naturallanguage query is associated with the alert, and, optionally, wherein the response comprises instructions for remedying the alert.

20. The method of any one of the preceding claims, wherein: the method comprises processing the natural language query and determining a response based on one or more images of the wound; the natural language query is associated with selecting the wound dressing from a plurality of wound dressings suitable for the therapy device, the one or more images optionally including a contour of an incision to be made on the wound site; and the response comprises one or more of a type, shape, or size of the wound dressing suitable for providing the pressure therapy to the wound site, optionally, the response being determined based on the contour of the incision to be made on the wound site; and providing the response comprises displaying the wound dressing overlaid on the wound site.

21. The method of claim 20, wherein: determining the response further comprises generating a shape of the wound dressing that matches a shape of the wound site; and providing the response comprises displaying the shape of the wound dressing overlaid on the wound site.

22. A negative and / or positive pressure therapy system comprising: a therapy device comprising: a pressure source configured to provide a pressure therapy to a wound site covered by a wound dressing; a controller configured to control operation of the pressure source; and a communication circuitry configured to facilitate wireless communication with the therapy device; and a storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to:with one or more machine learning models, initiate an interactive session in a baseline state, the interactive session in the baseline state utilizing the one or more machine learning models trained solely with data provided by a manufacturer of the therapy device to provide responses to natural language queries issued by a user of the therapy device; receive from the communication circuitry information associated with provision of the pressure therapy; update a state of the interactive session, the interactive session in the updated state comprising the baseline state and further including the information associated with provision of pressure therapy; receive a natural language query associated with provision of the pressure therapy, the natural language query being issued by the user of the therapy device; and with the one or more machine learning models trained solely with data provided by the manufacturer of the therapy device and using the information associated with provision of pressure therapy, process the natural language query and determine a response; and provide the response to one or more of the user or the controller.

23. The system of claim 22, wherein the information associated with provision of the pressure therapy comprises at least one of knowledge level of the user, data collected by one or more sensors, or a change to a parameter of the pressure therapy over a period of time.

24. The system of any one of claims 22 or 23, wherein determining the response comprises assigning a higher priority to information associated with the baseline state than to the information associated with provision of the pressure therapy.

25. A medical system comprising: a medical device comprising: a treatment module configured to provide a treatment to a patient; a controller configured to control operation of the treatment module; and a communication circuitry configured to facilitate wireless communication with the medical device; anda storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to: receive from the communication circuitry information associated with provision of the treatment; receive a natural language query associated with provision of the treatment, the natural language query being issued by a user of the medical device; using one or more machine learning models trained solely with data provided by a manufacturer of the medical device, process the natural language query and determine a response; and provide the response to one or more of the user or the controller.

Images