Priority Claim:

[0001] This application claims priority from the provisional application numbered 202141010133 filed with Indian Patent Office, Chennai on 10 ^th March 2021 and post-dated to 10 ^th September 2021 entitled “ Clinical decision support model for assessing foot conditions and wounds’", the entirety of which is expressly incorporated herein by reference.

PREAMBLE TO THE DESCRIPTION:

[0002] The following specification particularly describes the invention and the manner in which it is to be performed:

DESCRIPTION OF THE INVENTION

Technical field of the invention

[0003] The present invention relates to approaches for assessing wound in patients, and more particularly for assessing wound in the patients who are suffering from Type-2 diabetes and resulting conditions.

Background of the invention

[0004] As may be understood, a substantial proportion of the population in India is suffering from diabetes. Diabetes in a majority of cases results in development of foot related conditions, such as a Diabetic Foot Ulcer. However, any failure to detect and treat such conditions in a timely manner may result in amputation. [0005] Although appropriate intervention techniques may be employed to prevent amputation, such techniques are usually commonplace in advanced medical institutions but may not be available for remote or rural locations. In such locations even though a certain level of medical care is performed, the clinicians may not apply podiatric clinical recommendations and protocols that are employed in metropolitan cities in India. Non-availability of appropriate care in the semi-urban and rural areas leads to delayed or frequent visits by the patients to tertiary care hospitals in the metro cities, leading to late diagnosis and high costs, and in the end non-healing ulcers and amputations.

[0006] As described above, diabetes may impact conditions of patients’ feet, which have to be accordingly managed. Failure to manage or take appropriate intervention measures may lead to amputation. The fact that such intervention techniques are usually commonplace in advanced medical institutions in metros, does not benefit rural or remote locations which may also have a substantial population which may require adequate treatment and support. Such issues may get further compounded due to clinicians or medical personnel not being informed or trained of the correct podiatric clinical recommendations and protocols that are to be employed while managing foot ulcers or such similar conditions.

[0007] It may be noted that even in cities where appropriate interventions may be provided to ailing patients, such interventions have to be performed under the guidance and instruction of podiatric specialists. In such cases, decision as to the appropriate intervention to be affected is determined and based on a visual inspection and physical examination conducted by the podiatric specialists. This again may be not be possible to conduct through teleconsultations, and hence, becomes largely dependent on the presence and availability of the specialists.

[0008] Furthermore, there do not exist any appropriate approaches that may preempt the occurrence or onset of foot related conditions. As a result, onset or occurrence of a foot ulcer may be prolonged or even prevented if appropriate interventions, such as offloading through custom orthotics, custom footwear, or off the shelf orthotics for patients use. However, no effective approaches presently exist which may efficiently assess posture, gait related attributes of the feet of a diabetic patient to determine likelihood of onset of foot injuries and neither do they provide a prescriptive footwear for overcoming such conditions.

[0009] For instance, a patent application number US10303796B2 provides a wound assessing method and system to provide a convenient, quantitative mechanism for diabetic foot ulcer assessment. The method for assessing chronic wounds and ulcers comprises capturing an image of a body part including a wound area and analysing the image to extract a boundary of the wound area. The system performs colour segmentation within the boundary, wherein the wound area is divided into a plurality of segments, each segment being associated with a colour indicating a healing condition of the segment and the wound area is evaluated.

[0010] For instance, a patent application number US20200330028A1 provides a system and method for facilitating analysis of a wound in a target subject, wherein the method comprises obtaining one or more digital images of at least a portion of the wound; extracting a plurality of feature vectors from the one or more digital images; and identifying, using a first trained deep neural network, a type of wound tissue based on the plurality of extracted feature vectors.

[0011] Hence there is a need for a system and method for training a clinical decision support model for assessing foot conditions and any chronic wound ulcers.

Summary of the invention

[0012] The present invention discloses a system comprising a training system and a training data repository connected through a network. The training system further comprises a clinical decision support model, wherein the clinical decision support model is trained based on an image dataset of wounds and on images depicting various posture related aspects. Further, the training system comprises a processor to execute the computer executable instructions for training the clinical decision support model. The processor further includes a single computing entity or a combination of multiple computing entities or processing units.

[0013] The training system further comprises an image analysis engine, wherein the image analysis engine further comprises a combination of hardware and programming module to implement a variety of functionalities, and a processing resource to execute the instructions. The image analysis engine further comprises a training wound data unit and training posture data unit, wherein the training wound data unit comprises an image dataset of wounds and the image analysis engine processes the training wound data to determine the wound attributes.

[0014] According to the present invention, the clinical decision support model is trained based on the posture data, wherein the posture data includes attributes pertaining to multiple posture related parameters. The image analysis engine further analyses the images of the training posture data to determine the posture attributes. The training engine trains the clinical decision support model based on the wound attributes and the posture attributes. Upon training the clinical decision support model, the system is utilized for analysing the wounds of a given patient and their posture to determine likelihood of occurrence of any injury.

[0015] The system further comprises a training data repository through a network, wherein the training data repository is integrated within the system. The network can be a private network or a public network, wherein the network can further be a wired network, a wireless network, or a combination of a wired and wireless network.

[0016] Further, the system discloses a computing system, wherein the clinical decision support model is implemented within the computing system. The computing system comprises a clinical assessment system, wherein the clinical assessment system communicates with a clinical environment over a communication network. The clinical assessment system further comprises a processor and a detection engine, wherein the detection engine processes and analyses the target wound data and target posture data obtained from the clinical environment. The target wound data contains at least one image of the wound captured for a patient seeking medical attention for foot injuries, wherein the target wound data is obtained by capturing at least one image from one or more image capturing device, and the captured image is saved as target wound data. The target wound data is subsequently shared with the computing system for analysis. Further, the target posture data contains at least one image of foot of the patient depicting gait and posture of the foot.

[0017] Further, the detection engine further provides multiple intervention approaches, wherein the intervention approaches comprise a mapping between a determined stage of the wound and the corresponding intervention measure. The detection engine analyses the target posture data to recommend appropriate solutions for gait correction and prevent occurrence of any wounds/ulcers. The detection engine further comprises posture corrective measures, wherein the posture corrective measures contain a variety of suggestive actions to be prescribed for a patient to either prolong or prevent occurrence of any foot injuries.

[0018] The present invention is advantageous as it provides a system and method to facilitate assessment of posture related attributes, drive transformation in foot management through the novel clinical decision support system (CDSS) enabled through artificial intelligence driven diagnostics, preventive, curative and rehabilitative care. Further, the present invention prevents amputation in above 80% of the patients suffering from any chronic ulcer. The system enables monitoring and management of foot health in the clinic or at home, using conventional computing devices, such as any electronic device- enabled conversational application combined with an image capturing device to generate high-resolution images and videos of the foot and the gait of the patient.

[0019] Further, the system provides a comprehensive objective transparent assessment of the patient wound healing process and results in harmonizing the care process across geographies, hence improving the quality of the care even for remote and rural areas where the access of specialists is not available. Another advantage of the present invention is that the system facilitates ease of use by any clinician at any part of the world, having a network connection and any electronic device with local language support.

Brief description of drawings

[0020] Systems and/or methods, in accordance with examples of the present subject matter are now described, by way of example, and with reference to the accompanying figures, in which:

[0021] FIG. 1 illustrates a system for training a clinical decision support model.

[0022] FIG. 2 illustrates a clinical decision support system for analyzing wound related attributes and foot posture and gait related attributes.

[0023] FIG. 3 illustrates an Al pipeline architecture for posture and gait assessment. [0024] FIG. 4 illustrates an exemplary method for cleaning up an image.

[0025] FIG. 5 illustrates an exemplary flow depicting various stages of training or learning by the clinical assessment system.

[0026] FIG. 6 illustrates an exemplary network environment depicting a cloudbased implementation of the approaches as described in the present invention.

DETAILED DESCRIPTION

[0027] In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components.

[0028] FIG. 1 illustrates a system for training a clinical decision support model, wherein the system (100) comprises a training system (102) for training a clinical decision support model (110). The system (100) further comprises a training data repository (104) connected through a network (106). The training system (102) further comprises a clinical decision support model (110), wherein the clinical decision support model (110) is trained based on an image dataset of wounds and on images depicting various posture related aspects. Further, the training system (102) comprises a processor (108) to execute multiple computer executable instructions for training the clinical decision support model (102). The processor (108) further includes a single computing entity or a combination of multiple computing entities or processing units.

[0029] The clinical decision support model (110) is trained using the training data, wherein the training data is acquired from various data sources. According to an embodiment of the invention, the training system (102) is in communication with the training data repository (104) through the network (106). Although depicted as a network accessible resource, the training data repository (104) is integrated within the training system (102) without limiting the scope of the present subject matter.

[0030] According to an embodiment of the invention, the network (106) can be a private network or a public network and is implemented as a wired network, a wireless network, or a combination of a wired and wireless network. The network (106) also includes a collection of individual networks, interconnected with each other and functioning as a single large network, such as the Internet. Further, the individual networks include, but are not limited to, Global System for Mobile Communication (GSM) network, Universal Mobile Telecommunications System (UMTS) network, Personal Communications Service (PCS) network, Time Division Multiple Access (TDMA) network, Code Division Multiple Access (CDMA) network, Next Generation Network (NGN), Public Switched Telephone Network (PSTN), Long Term Evolution (LTE), and Integrated Services Digital Network (ISDN), according to an embodiment of the invention.

[0031] Further, the processor (108) executes multiple computer executable instructions for training the clinical decision support model (110). The processor (108) is implemented as a single computing entity or as a combination of multiple computing entities or processing units. The training system (102) further includes an image analysis engine (112), wherein the image analysis engine (112) (referred to as engine 112) is a combination of hardware and programming, for example, programmable instructions to implement a variety of functionalities, according to an embodiment of the invention. The hardware and programming are implemented in several different ways, wherein the programming for the engine (112) include executable instructions, by the processor (108) and such instructions are be stored on a non-transitory machine-readable storage medium which is coupled either directly with the training system (102) or indirectly through networked means, according to an embodiment of the invention.

[0032] According to an embodiment of the invention, the engine (112) includes a processing resource (not shown in FIG. 1), for example, either a single processor or a combination of multiple processors, to execute such instructions. A non- transitory machine-readable storage medium stores the instructions, wherein the processor (108) executes the instructions, according to an embodiment of the invention. Additionally, the engine (112) is implemented as electronic circuitry, according to an embodiment of the invention.

[0033] The training system (102) further comprises training wound data unit (114) and training posture data unit (116), wherein the training wound data unit (114) further comprises an image dataset of wounds caused due to foot ulcers in patients, according to an embodiment of the invention. The training wound data unit (114) comprises various images of the wounds that are annotated to identify one or more wound related attributes. The wound related attributes include, but are not limited to, identification of wound area, wound bed, wound edges, wound perimeter, and certain patient indications. Each of such wound related attributes indicates the progression of the wound (i.e., foot ulcer), which consequently require varying levels of wound management techniques and interventions. Further, the image dataset of wounds includes the annotations, wherein the annotations are digitally inscribed onto the images of the data set, or indicated through any other appropriate digital mechanisms. Such variations are only exemplary implementations and included within the scope of the present subject matter. [0034] For training, the image analysis engine (112) processes the training wound data unit (114) to determine the wound attributes which are stored in a wound attribute unit (118), wherein, the wound attribute unit (118), as described above, includes wound area, wound bed, wound edges, wound perimeter, and certain patient indications. According to an embodiment of the invention, the wound attribute unit (118) further includes additional information pertaining to a patient, without limiting the scope of the subject matter in any manner.

[0035] Further, the image analysis engine (112) performs multiple operations on the captured images including image cleanup, vectorization and enrichment, which as will be described in the following paragraphs results in prediction of ulceration, healing ability, rate of wound healing, and wound closure.

[0036] Similarly, the clinical decision support model (110) is trained based on the training posture data unit (116), wherein the posture data unit (116) includes the attributes pertaining to a plurality of posture related parameters. The clinical decision support model (110) is trained based on the images depicting the gait abnormality or any other structural abnormality of the foot. The images are supplemented with additional information including indications associated with the patient, Plantar Pressure Scans and 3D scans. The image analysis engine (112) further analyzes the images of the training posture data unit (116) to determine the posture attributes, which are stored in the posture attributes unit (120). Upon obtaining the wound attributes from the wound attribute unit (118) and the posture attributes from the posture attributes unit (120), the engine (122) trains the clinical decision support model (110) based on the wound attributes and the posture attributes.

[0037] Upon training the clinical decision support model (110) the clinical decision support model (110) analyzes the wounds of a given patient or analyze their posture to determine the likelihood of occurrence of any injury. [0038] FIG. 2 illustrates the clinical decision support system for analyzing the wound related attributes, foot posture and gait related attributes, wherein the clinical decision support system further comprises a computation system (200) in which the clinical decision support model (110) is implemented. The computing system (200) comprises a clinical assessment system (202) (hereinafter referred to as the assessment system 202), wherein the assessment system (202) communicates with a clinical environment (204) over a communication network (206). According to an embodiment of the invention, the communication network (206) is similar to the network (106) of the training system (100).

[0039] The assessment system (202) further comprises a processor (208) and a detection engine (210) to analyze the wound and posture data. The assessment system (202) comprises a clinical environment (204), wherein the clinical environment (204) facilitates evaluation of the patients including patients undergoing diabetes treatment, according to an embodiment of the invention. The system (202) obtains the target wound data from a target wound data unit (212) and target posture data from a target posture data unit (214) of the clinical environment (204). Upon obtaining the target wound data and target posture data, the detection engine (210) analyzes the target wound data and the target posture data, wherein the target wound data unit (212) comprises at least one image of wound captured for a patient seeking medical attention for foot injuries.

[0040] Subsequently, the images present in the target wound data unit (212) is obtained by capturing an image from at least one image capturing device. The plurality of images captured by the image capturing device are stored in the target wound data unit (212) as target wound data and is subsequently shared with the system (202) for analysis. Similarly, the target posture data of the target posture data (214) comprises at least one image of foot of patient depicting gait and posture of the foot. [0041] Further, the detection engine (210) analyzes the target wound data present in the target wound data unit (212) to determine the attributes of the wound to which the target wound data corresponds to, based on the trained clinical decision support model (110). According to an embodiment of the invention, the wound attributes include wound area, wound bed, wound edges, wound perimeter? and certain patient indications. Based on the analysis, the detection engine (210) thereafter ascertains the stage of the wound corresponding to the target wound data.

[0042] Further, the detection engine (210) provides multiple intervention approaches obtained from intervention approaches unit (216), wherein the intervention approaches unit (216) further comprises intervention approaches in the form of a mapping between a determined stage of the wound and the corresponding intervention measure that is to be undertaken. According to an embodiment of the invention, the intervention approaches include recommendations for various foot and wound management and amputation prevention methods-? and various advanced dressing techniques.

[0043] Similarly, the detection engine (210) analyzes the target posture data from the target posture data unit (214) to recommend appropriate solutions for gait correction and prevent occurrence of any wounds/ulcers. According to an embodiment of the invention, the detection engine (210) determines the presence of any gait related abnormalities or related conditionsT and based on the analysis, the detection engine (210) accordingly determines appropriate solutions for gait correction and prevents occurrence of any wounds/ulcers from the posture corrective measures in the posture corrective measures unit (218). The posture corrective measures unit (218) includes a variety of suggestive actions to be prescribed for a patient to either prolong or prevent occurrence of any foot injuries for a patient. According to an embodiment of the invention, the suggestive actions include, but are not limited to custom footwear and orthotics for diabetic or nondiabetic foot and ankle conditions, prescription footwear, or similar accessories. A continuous feedback loop to be implemented within the clinical assessment system (202) to enable an opportunity for periodic updates to the classification of the decision support system and prediction ability, further improving care quality with time, according to an embodiment of the invention.

[0044] Although described in the context of the diabetes and foot ulcers, the above- mentioned approaches implemented by the system (202) are used for preventing any type injuries that results from incorrect posture or gait of any individual irrespective of whether they would be suffering from diabetes or not.

[0045] According to an embodiment of the invention, the system (100), in the context of assessing posture related attributes, drive transformation in foot management through the novel Clinical Decision Support System (CDSS) enabled through Al-driven diagnostics, preventive, curative and rehabilitative care.

[0046] The system (100) helps to prevent amputation in 80% of the patients suffering from any chronic ulcers. The system (100) helps in monitoring and management of foot health in the clinic or at home using conventional computing devices such as electronic devices, wherein a conversational application along with a structural camera is used to generate high-resolution images and videos of the foot and the gait of the patient. Further, the system provides a comprehensive objective transparent assessment of the patient’s wound healing process and results in harmonizing the care process across geographies, hence improving the quality of the care even for remote and rural areas where the access of specialists is not available. The aspects of the system (100) can be used by any clinician anywhere in the world through a network connection and an electronic device, where a local language support and other features enable widespread acceptance and use.

[0047] Further, the present invention implemented through the clinical assessment system (202), enables the physician to diagnose, monitor and manage the ailment, through the Al-based clinical decision support model (110). According to an embodiment of the invention, the aforesaid approaches are integrated into the eCommerce platform, recommending the products appropriate to the condition, diagnosis, including wound dressing materials, offloading devices, footwear, splints and therapeutic devices. The clinical assessment system (202) also enables to capture of data for designing customized insoles or footwear, which shall be further 3D printed or milled on Computer-Aided Design (CAD)/ Computer-Aided Manufacturing (CAM) and delivered to the patient or the attending physician.

[0048] The different approaches implemented through the clinical assessment system (202) facilitates staging, predicting and managing various foot conditions and ulcers. Furthermore, the different approaches are easy to use and to deploy, which in turn facilitates widespread adaptation without incurring costs for specialized equipment. According to an embodiment of the invention, the system (202) enables raising the intervention skills through ‘Tele-Podiatry’. Further, the clinical assessment system (202) recommends and generates a prescription for custom foot orthosis, and offloading footwear.

[0049] FIG. 3 illustrates an Al pipeline architecture for posture and gait assessment, wherein the pipeline architecture comprises an image cleanup stage wherein image preprocessing algorithms process the image captured by an image capturing device to standardize the image and prepare the image for feature extraction. Further, in vectorization stage, the preprocessed image of transformed into matrices for Al model application. The features of the image are enriched in a feature enrichment stage wherein, feature enrichment is performed to gain multidimensional view of the image. Further, in the intelligence stage, Al math models are used for classification of the images, wherein the classification and regression model application classify the image data. In the presentation stage, the processed image which is converted into usable format is used to showcase the final output that can be used by the downstream models.

[0050] FIG. 4 illustrates an exemplary method for cleaning up an image, as an embodiment of the inventio. Consider an image captured by an image capturing device, and the captured image requires clean up. The system (100) receives the image from a doctor and the dead zone in the image is eliminated. Further, the image is preprocessed to convert the image to standard dots per inch (DPI) size. The image is further processed to achieve tilt correction where the tilt in the image is corrected followed by correction of contrast in the image. Further, using image sharpening, the image is sharpened and the processed image is prepared for the system (100) to be used.

[0051] FIG. 5 illustrates an exemplary flow depicting various stages of training or learning by the clinical assessment system according to an embodiment of the invention, wherein the clinical assessment system (202) facilitates real-time scoring by recognizing the data using models and files into inbound data and enriching the data using mathematical frameworks and functions. Further, the data is used by the clinical assessment system (202) to classify the data and predict various foot conditions and ulcers. The results are validated and feedback is provided by the clinical assessment system (202). The clinical assessment system (202) further uses a long-term learning loop to aggregate the data, where the feedback and other data are used to create mapping using big data and the clinical assessment system (202) learns the data using new associations and bayes. Using the processed data, the clinical assessment system (202) creates new models to process the data.

[0052] FIG. 6 illustrates an exemplary network environment depicting a cloudbased implementation of the approaches as described in the present description, wherein the Amazon Simple Storage Service provides image data storage through a web service interface. The image data from the Amazon Simple Storage Service (S3) is processed by the Amazon Elastic Compute Cloud (EC2) cloud-computing platform, wherein the image data is processed through computer applications. The data processing step comprises auto-scaled Elastic Compute Cloud (EC2) nodes, wherein the auto scaling helps to ensure that a correct number of EC2 instances are available to handle the load of the application. The auto-scaled Elastic Compute Cloud (EC2) nodes comprises an image vectorizer to pre-process the image data and transform it into matrices for Al model application. A feature enricher, enriches the features of the image to create a multi-dimensional view of the image. Further, an image extractor then uses Al math models are used for classification and extraction of the image and a presenter to present the processed image that can be used by the downstream models. The presented image is stored in another Amazon Simple Storage Service, which is in connection with the Amazon Simple Storage Service having raw image data.

[0053] The present invention provides a method for training a clinical decision support model (110) on various wound related parameters obtained from images, posture and gait related parameters for wound management and posture and gait management. According to an embodiment of the invention, the clinical decision support model once trained based on various wound related parameters determines wound characteristics (wound area, wound bed, wound edge and peri wound area) and accordingly recommend appropriate wound management functions. According to an embodiment of the invention, the clinical decision support model once trained based on posture and gait related parameters predicts the likelihood of any foot injury to occur and recommend an appropriate offloading footwear or foot orthotics.

[0054] The present invention provides a system (100) to facilitate assessment of posture related attributes, drive transformation in foot management through the novel clinical decision support system (CDSS) enabled through artificial intelligence driven diagnostics, preventive, curative and rehabilitative care. Further, the system (100) facilitates prevention of amputation in above 80% of the patients suffering from any chronic ulcers including diabetic foot ulcer.

[0055] The system (100) enables monitoring and management of foot health in the clinic or at home, using conventional computing devices, such as any electronic device- enabled conversational application combined with an image capturing device to generate high-resolution images and videos of the foot and the gait of the patient. Further, the system (100) provides a comprehensive objective transparent assessment of the patient wound healing process and results in harmonizing the care process across geographies, hence improving the quality of the care even for remote and rural areas where the access of specialists is not available. Another advantage of the present invention is that the system facilitates ease of use by any clinician at any part of the world, having a network connection and any electronic device with local language support.

[0056] The present approaches are further described in the context of a training phase and a testing phase. In the context of machine learning, training involves subjecting a machine learning model with training data. Once trained, certain patterns or determinations are based on the training data. Such determinations are implemented within the testing phase. The machine learning model is implemented through machine-executable code on a processor-based computing system. According to an embodiment of the invention, the machine learning model is a susceptibility detection model based on which drug resistance of a target strain of a pathogen is ascertained.

[0057] To this end, initially, an image dataset of wounds is obtained based on which the clinical decision support model is be trained. The images of the wounds are annotated to identify the wound related attributes. Examples of such wound related attributes include, but are not limited to, identification of wound area, wound bed, wound edges, wound perimeter, and certain patient indications. Each of such wound related attributes indicates the progression of the wound (i.e., foot ulcer), which consequently require varying levels of wound management techniques and interventions. With respect to the annotations, such annotations are either digitally inscribed onto the images of the data set or indicated through any other appropriate digital mechanisms. Such variations are only exemplary implementations and included within the scope of the present subject matter.

[0058] According to an embodiment of the invention, the clinical decision support model is be trained based on a plurality of posture related parameters. The clinical decision support model is trained based on images depicting the posture and gait abnormality or any other structural abnormality of the foot. The images are supplemented with other types of information, examples of which include, clinical signs or indications associated with the patient, Plantar Pressure Scans, 3D scans, and such.

[0059] Once the clinical decision support model is trained, it is implemented within a computing-based assessment system, according to an embodiment of the invention. The assessment system is utilized for analyzing a captured image of wound or a foot ulcer. Based on the analysis, the assessment system classifies the wound. Thereafter, the assessment system further suggests wound care protocols or other interventions. The wound care protocols or other interventions are determined based on a mapping or a correlation between predefined wound classifications and corresponding wound care protocols or other interventions.

[0060] According to an embodiment of the invention, the assessment system is useful for analyzing the foot image to determine presence of any gait related abnormalities or related conditions. Based on the analysis, the assessment system recommends appropriate solutions for gait correction and prevent occurrence of any wounds/ulcers. Although described in the context of the diabetes and foot ulcers, the clinical decision support model (110) is trained to prevent any type injuries that results from incorrect posture or gait of any individual irrespective of whether they would be suffering from diabetes or not.

[0061] It may be noted that the description and figures merely illustrate the principles of the present subject matter. It will thus be appreciated that various arrangements that embody the principles of the present subject matter, although not explicitly described or shown herein, may be devised from the description, and are included within its scope. Moreover, all statements herein reciting principles, aspects, and examples of the present subject matter, as well as specific examples thereof, are intended to encompass equivalents thereof.

[0062] Although examples and embodiments for the present disclosure have been described in language specific to structural features and/or methods, it is to be understood that these aspects are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed and explained as examples of the present disclosure. Reference numbers