Techniques for image-based inspection of dialysis access sites

Abstract

A dialysis access site system can operate to generate a treatment recommendation for treating a condition of an access site based on an image of the access site. The dialysis access site system can be a device having at least one processor and a memory coupled to the at least one processor. The memory can include instructions that, when executed by the at least one processor, can cause the at least one processor to receive an access site image comprising an image of a dialysis access site of a patient, determine access site information for the dialysis access site based on at least one access site feature determined from the access site image, the access site information being indicative of a condition of the dialysis access site, and determine a treatment recommendation for the dialysis access site based on the access site information.

Description

Technical Field

[0001] This disclosure generally relates to a process for examining the physical characteristics of a part of a patient based on images of that part, and more particularly, to a technique for assessing the condition of a patient's dialysis access site. Background Technology

[0002] Dialysis treatment requires blood to enter the patient's circulatory system via a dialysis access site so that the blood can be treated using a dialysis unit. For peritoneal dialysis (PD), the dialysis access site can be via a catheter. Hemodialysis (HD) treatment requires blood to enter the circulation in an extracorporeal circuit connected to the patient's main cardiovascular circuit via a vascular or arteriovenous (AV) access. Typical HD access types can include arteriovenous fistulas (AVFs) and arteriovenous grafts (AVGs). During HD treatment, blood is drawn from the vascular access through an arterial needle fluidly connected to the extracorporeal circuit and delivered to the HD treatment unit. After treatment with the HD treatment unit, the blood is returned to the vascular access through a venous needle and then back to the patient's cardiovascular circuit.

[0003] Therefore, the health of the patient's access site is paramount to the effectiveness of dialysis treatment. For example, the vascular access should provide adequate blood flow for HD treatment and should be free of serious complications such as severe pain and / or swelling, aneurysms, etc. Traditional vascular access site monitoring techniques typically require a visual examination of the site by a healthcare professional capable of providing diagnostic and treatment recommendations. This monitoring necessitates patient visits to a medical facility and / or home visits by a healthcare professional. Furthermore, despite their expertise, healthcare professionals often lack access to robust databases of patient treatment outcomes to determine optimal treatment recommendations. Consequently, traditional monitoring techniques are inefficient and burdensome for patients, especially those receiving treatment at home.

[0004] It is precisely because of these and other considerations that this improvement may be useful. Summary of the Invention

[0005] This summary is provided to present a simplified description of selected concepts, which will be further described in the detailed description below. This summary is not intended to necessarily identify key or essential features of the claimed subject matter, nor is it intended to help determine the scope of the claimed subject matter.

[0006] According to various aspects of the described embodiments, an apparatus may include at least one processor and a memory coupled to said at least one processor. The memory may include instructions that, when executed by said at least one processor, cause said at least one processor to receive a access site image including at least one image of a patient's dialysis access site, determine access site information for a dialysis access based on at least one access site feature determined from the access site image, the access site information indicating the condition of the dialysis access site, and determine a treatment recommendation for the dialysis access site based on the access site information.

[0007] In some embodiments of the device, the instructions, when executed by the at least one processor, enable the at least one processor to receive access site description information and to determine access site information based on at least one access site feature and the access site description information. In various embodiments of the device, the dialysis access site includes one of an arteriovenous fistula (AVF) or an arteriovenous graft (AVG).

[0008] In some embodiments of the device, the instructions, when executed by at least one processor, can cause at least one processor to provide a pathway site image to a computational model to determine at least one pathway site feature. In an exemplary embodiment of the device, the instructions, when executed by at least one processor, can cause at least one processor to provide pathway site information to a computational model to determine a treatment recommendation.

[0009] In some embodiments of the device, the at least one pathway site feature may include at least one of size, color, shape, or the presence of anomalies. In various embodiments of the device, the pathway site image is captured via a client computing device. In some embodiments of the device, instructions, when executed by at least one processor, may cause at least one processor to determine a classification of the pathway site based on pathway site classification information. In various embodiments of the device, the classification may include a score and at least one treatment action. In an exemplary embodiment of the device, the treatment recommendation may include analytical information indicating at least one treatment outcome associated with the treatment recommendation.

[0010] According to various aspects of the described embodiments, a method may include receiving a access site image including at least one image of a patient's dialysis access site, determining access site information for the dialysis access site based on at least one access site feature determined from the access site image, the access site information indicating the condition of the dialysis access site, and determining a treatment recommendation for the dialysis access site based on the access site information.

[0011] In some embodiments of the method, the method may include receiving access site description information and determining access site information based on at least one access site feature and the access site description information. In some embodiments of the method, the dialysis access site may include one of an arteriovenous fistula (AVF) or an arteriovenous graft (AVG).

[0012] In some embodiments of the method, the method may include providing a pathway site image to a computational model to determine at least one pathway site feature. In some embodiments of the method, the method may include providing pathway site information to a computational model to determine a treatment recommendation.

[0013] In some embodiments of the method, the at least one pathway site feature may include at least one of size, color, shape, or the presence of anomalies. In some embodiments of the method, the pathway site image may be captured via a client computing device. In some embodiments of the method, the method may include determining a pathway site classification based on pathway site classification information. In some embodiments of the method, the classification may include a score and at least one treatment action. In some embodiments of the method, the treatment recommendation may include analytical information indicating at least one treatment outcome associated with the treatment recommendation. Attached Figure Description

[0014] As an example, a specific embodiment of the disclosed machine will now be described with reference to the accompanying drawings, in which:

[0015] Figure 1 A first exemplary operating environment according to this disclosure is shown;

[0016] Figure 2 Exemplary pathway site classification information according to this disclosure is shown;

[0017] Figure 3 A second exemplary operating environment according to this disclosure is shown;

[0018] Figure 4 A third exemplary operating environment according to this disclosure is shown;

[0019] Figure 5 The logical flow according to this disclosure is shown; and

[0020] Figure 6 An embodiment of a computing architecture according to this disclosure is shown. Detailed Implementation

[0021] This embodiment will now be described more fully below with reference to the accompanying drawings, in which several exemplary embodiments are illustrated. However, the subject matter of this disclosure can be implemented in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to make this disclosure thorough and complete, and are intended to convey the scope of the subject matter to those skilled in the art. In the drawings, the same reference numerals consistently refer to the same elements.

[0022] As mentioned above, dialysis treatment requires at least one dialysis access site for accessing the patient's circulatory system. Peritoneal dialysis (PD) can use access sites including PD catheters. Hemodialysis (HD) can use access sites including arteriovenous (AV) fistulas (AVFs), AV grafts (AVGs), or HD catheters. An AVF is an artery that is surgically connected to a vein, while an AVG is a surgically placed synthetic material catheter that connects an artery to a vein.

[0023] The health of the access site is crucial for successful dialysis treatment. Monitoring the access site can involve identifying various characteristics of the access site that can indicate complications, abnormalities, etc. Non-limiting examples of access site characteristics may include blood flow rate, color, size, shape, presence and / or severity of pain, inflammation, aneurysm, venous stenosis, thrombosis, etc. Furthermore, monitoring may include identifying changes between current and previous access site characteristics, determining trends in the access site (e.g., whether inflammation is increasing or decreasing), etc. Based on access site characteristics, a treatment plan can be determined to monitor and / or treat access site abnormalities.

[0024] Routine methods for monitoring and assessing patient access site characteristics typically involve clinical monitoring, including physical examination of the access site by a healthcare professional. Clinical assessment may include visual examination, palpation, and / or auscultation. This clinical monitoring requires patient visits to a healthcare facility and / or home visits by a healthcare professional. Requiring physical assessments can be burdensome and difficult for patients to perform, especially in severe cases where it may be necessary over a short period (e.g., daily). Furthermore, patient adherence to subsequent instructions regarding monitoring abnormal access sites may be relatively low when visits to a healthcare facility and / or visits by a healthcare professional are required.

[0025] If an abnormality is detected, healthcare professionals can recommend treatment and / or further evaluation by an experienced physician. While physicians and other healthcare professionals are highly experienced in diagnosing and treating pathway abnormalities, they lack access to a robust repository of population-based treatment outcomes, which may enable them to access treatment options more effectively.

[0026] Therefore, some embodiments may provide a process for image-based examination of dialysis access sites using population-based treatment information. For example, in various embodiments, the access site analysis process may receive images of the access site. For instance, a patient may use a personal computing device (e.g., a smartphone, tablet, etc.) to take images of their access site and send the images to the access site analysis platform. The access site analysis process may use computational models to process the images to determine access site characteristics, such as size, color, presence of abnormalities, etc.

[0027] In some embodiments, the patient may provide descriptive information about the pathway site that may be associated with the image. Generally, descriptive information about the pathway site may include information describing or otherwise indicating the characteristics of the pathway site, such as the presence and / or severity of pain, inflammation, aneurysm, etc. The pathway site analysis process may feed pathway site features and / or descriptive information to a computational model to determine treatment recommendations for the pathway site based on these features and / or descriptive information. In various embodiments, the computational model used in the pathway site analysis process may be trained using actual patient information and / or images of individual patients and / or patient groups (e.g., patients with chronic kidney disease (CKD) and / or end-stage renal disease (ESRD)).

[0028] In some embodiments, the pathway site analysis process can be used to remotely monitor, analyze, steer, and / or similarly treat a patient's pathway sites to improve pathway site longevity and care by using a combination of digital imaging, trend, intervention, and outcome information. In some embodiments, the pathway site analysis process can be an internet-based, software-as-a-service (SaaS), and / or cloud-based platform that can be used by patients or healthcare teams to monitor a patient's clinical care and can be used to provide expert third-party assessments, for example, as a subscription to a healthcare provider or other types of service.

[0029] For example, the access site analysis process can be operated in conjunction with a "patient portal" or other types of platforms that patients and healthcare teams can use to exchange information. For instance, a dialysis treatment center manages patients receiving treatment at home and center patients receiving treatment at the treatment center. Patients may be at various stages of kidney disease, such as chronic kidney disease (CKD), end-stage renal disease (ESRD), etc. Patients at home may periodically (e.g., daily, weekly, monthly, etc.) or as needed (e.g., based on the occurrence and / or changes of abnormalities) use a smartphone or other personal computing device to take images of their access sites, such as catheter sites, AVF sites, AVG sites, etc. According to some embodiments, these images can be uploaded to a patient portal or other platform and routed to a dialysis access site analysis system operable to perform the access site analysis process. Similarly, photographs of access sites of center patients can be taken by patients and / or clinical staff and uploaded to a patient portal for access by the access site analysis system.

[0030] In some embodiments, patient images may be stored in a repository or other database, including but not limited to a Healthcare Information System (HIS), an Electronic Medical Record (EMR) system, etc. Images in the repository may be cataloged and indexed by patients, including key clinical information, population statistics, medical history, and / or similar data to be processed at the patient and / or pathway level by a pathway site analysis system. Depending on applicable regulations, protocols, and / or similar provisions, such as the Health Insurance Portability and Accountability Act of 1996 (HIPAA), using patient image information at the population level may require the removal of Protected Health Information (PHI) and / or other information that identifies the patient.

[0031] Access site analysis systems can be operated to compare recent images of a patient with previous images using imaging analysis techniques configured according to some embodiments to automatically identify trends and changes in patient access sites. Changes and / or trends may involve various access site characteristics, including but not limited to color, size, shape, location of the patient's access site, skin features, vascular system features, patient-reported information such as touch sensitivity, pulse, temperature, pain, and / or the like. In some embodiments, the access site analysis system can provide assessments or diagnoses and / or one or more treatment recommendations that can be offered to a healthcare team.

[0032] The healthcare team can then review the recommendations and accept, reject, or modify interventions for patients. Healthcare team interventions can be logged and stored in a repository at both the patient and group levels so they can be tracked to monitor success rates and outcomes, thereby providing further training data for computational models used according to some embodiments.

[0033] Therefore, access site analysis systems can use computational models that continuously learn and monitor results and success rates, and provide feedback, treatment recommendations, and diagnoses to clinical nursing teams using population-level analysis. Population-level analysis can segment based on various attributes such as age, gender, disease status, national population, regional population, access site type, access site condition, or abnormalities.

[0034] For example, a pathway site analysis system may be able to provide recommended treatments based on information associated with patients who have similar medical histories and pathway site abnormalities, including, for example: intervention recommendation 1, which has been tried on N number of patients and has a 40% success rate on similar patients; intervention recommendation 2, which has a 25% success rate on similar patients; and / or intervention recommendation 3, which has been tried on X patients in your geographic area and has an 80% success rate on similar patients.

[0035] Furthermore, some embodiments can provide a process for automatically classifying access site conditions. For example, various embodiments may include an access site analysis process operable to classify the stage of an aneurysm, such as an AVF aneurysm. As previously mentioned, conventional systems typically require in-person visual examination of aneurysms or other abnormalities. In various embodiments, images captured by the patient or healthcare provider at the access site can be analyzed via a computational model operable to determine the classification, stage, categorization, or other definition of the access site. For example, access sites can be categorized on a scale of 0 (virtually no health risk) to 3 (requiring urgent care). In this way, the access site analysis process can be used to automatically classify patient access sites, such as AVFs and / or AVGs, and suggest actions as necessary, thereby reducing or even eliminating the burden on human healthcare professionals to perform these tasks and provide timely diagnoses during patient in-person visits.

[0036] Therefore, the dialysis access site analysis process according to some embodiments can provide a number of technical advantages and features superior to conventional systems, including improvements in computational technology. One non-limiting example of a technical advantage may include an automated process using digital images employing, for example, artificial intelligence (AI) and / or machine learning (ML) processes to examine access sites. Another non-limiting example of a technical advantage may include allowing remote analysis of patient access sites without requiring in-person visual examination by healthcare professionals, reducing or even eliminating the need for healthcare professionals to visit the patient / be visited by the patient. In yet another non-limiting example of a technical advantage, the access site analysis process according to some embodiments may use population-based patient outcomes and success rates of similar or identical conditions, as determined by AI and / or ML computational models, to determine the treatment course for access site conditions. Other technical advantages are provided in this detailed description. The embodiments are not limited to this context.

[0037] Figure 1 An example of an operating environment 100, which may represent some embodiments, is shown. For example... Figure 1 As shown, the operating environment 100 may include a dialysis pathway site analysis system 105. In various embodiments, the dialysis pathway site analysis system 105 may include a computing device 110 communicatively coupled to a network 170 via a transceiver 160. In some embodiments, the computing device 110 may be a server computer or other type of computing device.

[0038] According to some embodiments, the computing device 110 can be configured to manage operational aspects of the path location analysis process, etc. Although Figure 1 Only one computing device 110 is shown in the diagram, but the embodiments are not limited thereto. In various embodiments, the functions, operations, configurations, data storage functions, applications, logical units, etc., described with respect to computing device 110 may be executed and / or stored therein by one or more other computing devices (not shown) coupled to computing device 110, for example, via network 170 (e.g., one or more of client devices 174a-n). A single computing device 110 is depicted for illustrative purposes only to simplify the diagram. The embodiments are not limited to this context.

[0039] According to some embodiments, computing device 110 may include processor circuitry that may include and / or have access to various logic units for performing processes. For example, processor circuitry 120 may include and / or have access to path location analysis logic unit 122. Processing circuitry 120, path location analysis logic unit 122, and / or portions thereof may be implemented in hardware, software, or a combination thereof. As used herein, the terms “logic unit,” “component,” “layer,” “system,” “circuit,” “decoder,” “encoder,” “control loop,” and / or “module” are intended to refer to computer-related entities, hardware, combinations of hardware and software, software, or software in execution, examples of which are provided by exemplary computing architecture 600. For example, a logic unit, circuit, or module can be and / or may include, but is not limited to, a process running on a processor, a processor, a hard disk drive, multiple storage drives (optical and / or magnetic storage media), an object, an executable file, thread execution, a program, a computer, a hardware circuit, an integrated circuit, an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a digital signal processor (DSP), a field-programmable gate array (FPGA), a system-on-a-chip (SoC), a memory cell, a logic gate, a register, a semiconductor device, a chip, a microchip, a chipset, a software component, a program, an application, firmware, a software module, computer code, a control loop, a computational model or application, an AI model or application, an ML model or application, a proportional-integral-derivative (PID) controller, variations thereof, any combination of the foregoing, and / or such.

[0040] although Figure 1 The pathway location analysis logic unit 122 shown is within the processor circuitry 120, but the embodiment is not limited thereto. For example, the pathway location analysis logic unit 122 and / or any of its components may be located within an accelerator, processor core, interface, separate processor die, fully implemented as a software application (e.g., pathway location analysis application 150) and / or the like.

[0041] Memory cell 130 may include various types of computer-readable storage media and / or systems in the form of one or more high-speed memory cells, such as read-only memory (ROM), random access memory (RAM), dynamic RAM (DRAM), double data rate DRAM (DDRAM), synchronous DRAM (SDRAM), static RAM (SRAM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, polymer memory such as ferroelectric polymer memory, austenite memory, phase change or ferroelectric memory, silicon oxide-nitride-silicon oxide (SONOS) memory, magnetic cards or optical cards, device arrays such as redundant array of independent disk drives (RAID), solid-state storage devices (e.g., USB storage, solid-state drives (SSDs), and any other type of storage media suitable for storing information. Additionally, memory cell 130 may include various types of computer-readable storage media in the form of one or more low-speed memory cells, including internal (or external) hard disk drives (HDDs), floppy disk drives (FDDs), and optical disk drives for reading or writing removable optical discs (e.g., CD-ROMs or DVDs), solid-state drives (SSDs), and / or the like.

[0042] According to some embodiments, memory unit 130 may store various types of information and / or applications used in the pathway site analysis process. For example, memory unit 130 may store pathway site images 132, pathway site description information 134, computational models 136, pathway site information 138, pathway site classification information 140, treatment recommendations 142, and / or pathway site analysis applications 150. In some embodiments, some or all of the pathway site images 132, pathway site description information 134, computational models 136, pathway site information 138, pathway site classification information 140, treatment recommendations 142, and / or pathway site analysis applications 150 may be stored in one or more data stores 172a-n that can be accessed by computing device 110 via network 170. For example, one or more data stores 172a-n may be or may include HIS, EMR systems, dialysis information systems (DIS), picture archiving and communication systems (PACS), Centers for Medicare & Medicaid Services (CMS) databases, US Kidney Data System (USRDS), proprietary databases, and / or the like.

[0043] In some embodiments, for example via a pathway site analysis application 150, the pathway site analysis logic unit 122 may be operable to analyze patient pathway site images 132 using one or more computational models 136 to determine pathway site information 138 (e.g., diagnosis) and / or treatment recommendations 142. The pathway site images 132 may include digital or other electronic files comprising pictures and / or videos of pathway sites and / or other parts of the patient. Images may be stored as image files, such as *.jpg, *.png, *.bmp, *.tif, etc. In some embodiments, images may be or may include video files, such as *.mp3, *.mp4, *.avi, etc. Patients, healthcare providers, caregivers, or other individuals may use any capable device, such as a smartphone, tablet, laptop, personal computer (PC), camera, camcorder, etc., to capture the images.

[0044] Users such as patients and / or healthcare professionals can send, transmit, upload, or otherwise provide pathway site images 132 to the pathway site analysis system 105 via a client device 174a communicatively coupled to computing device 110 via network 170. For example, the pathway site analysis application may be or may include a website, internet interface, portal, or other web-based application that facilitates the uploading of digital pathway site images 132 for storage in memory unit 130 and / or data storage 172a-n. In some embodiments, patient client devices 174a-n may operate a client application (e.g., a mobile application or “app”) operable to communicate with the pathway site analysis application 150 to provide the pathway site images 132. In some embodiments, patients may upload digital pathway site images 132 through a patient portal of a dialysis clinic or other healthcare provider. The pathway site analysis application 150 may be communicatively coupled to the patient portal to receive images from there. Embodiments are not limited to this context.

[0045] In addition, the patient or healthcare provider may provide access site description information 134 that describes the characteristics of the access site. Typically, access site description information 134 may include any type of text, audio, visual, and / or similar data that can indicate the characteristics of the access site, in addition to the access site image 132. For example, access site description information 134 may include descriptions of pain, swelling, color, size, blood flow information, duration of condition or characteristic, age of the access site, type of access site, patient vital signs, and / or similar descriptions. In various embodiments, access site description information 134 may be associated with one or more access site images 132, for example, as metadata, within one or more medical record entries, and / or similar descriptions. For example, access site analysis application 150 may create a record for access site image 132 that includes or references the associated access site description information 134. In this way, access site analysis application 150 may access information describing access site image 132 and / or providing context to access site image 132.

[0046] Access site analysis application 150 can analyze access site image 132 and / or access site description information 134 to determine access site information 138. Typically, access site information 138 can include diagnosis, classification, categorization, access site features, or other analytical results determined by analyzing access site image 132 and / or access site description information 134. For example, access site information 138 can include access site features of access site image 132, including but not limited to color, size, shape, access site elements (e.g., crusting, bleeding, and / or the like), and / or other information that can be identified from analyzing access site image 132. In another example, access site information 138 can include a diagnosis or other classification of the access site, such as a health diagnosis, grade or other classification level, indication of the presence and / or severity of an abnormality, and / or the like. For example, access site analysis application 150 can use access site analysis procedures according to some embodiments (e.g., using computational model 136) to determine the presence and / or severity of an access site aneurysm.

[0047] In some embodiments, the pathway site analysis application 150 may use one or more computational models 136 to analyze the pathway site image 132 and / or pathway site description information 134 to determine pathway site information 138 and / or treatment recommendations 142. Examples of computational models 136 may include ML models, AI models, neural networks (NN), artificial neural networks (ANN), convolutional neural networks (CNN), deep learning (DL) networks, deep neural networks (DNN), recurrent neural networks (RNN), combinations thereof, variations thereof, and / or the like. Embodiments are not limited to this context. For example, a CNN may be used to analyze the pathway site image 132, where the pathway site image 132 (or more specifically, an image file) is the input, and the pathway site information 138 (e.g., including pathway site features) and / or treatment recommendations may be the output.

[0048] In various embodiments, the pathway site analysis application 150 can use different computational models 136 for different parts of the pathway site analysis process. For example, an image analysis computational model can be used to process pathway site images 132. In another example, a treatment recommendation computational model can be used to process pathway site information 138 and / or pathway site classification information 140 (see, for example, Figure 3 This generates a treatment recommendation 142. In some embodiments, a computational model 136 may be used to analyze the pathway site image 132, pathway site description information 134, pathway site information 138, and / or pathway site classification information 140 to determine a treatment recommendation. The embodiments are not limited to this context.

[0049] Computational model 136 may include one or more models trained to analyze images, and particularly pathway site images 132. For example, in various embodiments, computational model 136 may be trained to analyze pathway site images 132 to determine pathway site features and / or other information that can be used to diagnose pathway sites using patient-based and / or population-based pathway site images. The computational model may include one or more models trained to analyze pathway site information 138 and / or pathway site classification information 140 to determine treatment recommendations 142. For example, patient-based training may include training computational model 136 using pathway site images 132 of a specific patient and information indicating condition, abnormalities, or other information that can be used to determine pathway site information 138 and / or treatment recommendations 142. In another example, population-based training may include training computational model 136 using pathway site images 132 of a specific patient population (e.g., geographic region, disease state, condition, different skin color, different types of pathway sites, different ages of pathway sites, etc.) and information indicating condition, abnormalities, or other information that can be used to determine pathway site information 138 and / or treatment recommendations 142.

[0050] In various embodiments, the pathway site classification information 140 may include information that can be used to classify, categorize, grade, or otherwise indicate the condition of the pathway site. Figure 2 Exemplary pathway site classification information according to some embodiments is shown. For example... Figure 2 As shown, classification information 205 may include access site information (e.g., vascular access information), scores, and actions associated with each score category. Vascular access information may include access site information 138 determined by access analysis application 150 through analysis of access site images 132 and / or access site description information 134 using computational model 136. Figure 2 As shown, non-limiting examples of access site information 132 may include the presence of scabs, scab nature, presence / severity of pain, presence / severity of swelling, new pain, new swelling, presence of necrotic areas, presence of erythema, murmur / thrill status, AVF / AVG status (e.g., stiffness higher than AVF / AVG), presence of aneurysm, aneurysm characteristics (e.g., stable, increased size, skin condition higher than aneurysm, etc.), palpation information, and / or the like. Therefore, some embodiments can operate to automatically classify the stages of access site (e.g., AVF / AVG) aneurysms. Although in Figure 2 The text describes specific levels or fractions and actions, but the embodiments are not limited to these, such as... Figure 2 The classification information 205 depicted is for illustrative purposes only. According to some embodiments, other classifications, grades, ratings, and / or similar methods may be used.

[0051] In various embodiments, the pathway site analysis application 150 can analyze the pathway site information 138 (e.g., information indicating characteristics of the pathway site) based on the pathway site information (e.g., classification information 205) provided in the pathway site classification information (e.g., classification information 205) to determine the pathway site information 138 in the form of a diagnosis (e.g., a score) and / or treatment recommendation 142 (e.g., an action). In some embodiments, the pathway site analysis application 150 can use a computational model 136, a table lookup matching process, a pattern matching process, a search process, a combination thereof, etc., to determine the pathway site information 138 (e.g., diagnosis, score, etc.) and / or treatment recommendation 142 (e.g., an action).

[0052] The access site analysis application 150 can generate treatment recommendations 142 based on access site information 138. Treatment recommendations 142 may include procedures for treating and / or monitoring the access site. For example, treatment recommendation 142 may indicate that the access site is safe for use during dialysis procedures (e.g., needle insertion). In another example, treatment recommendation 142 may indicate instructions for clinical interventions, follow-ups, limiting or eliminating access site use, medications, additional actions to assess the access site and / or abnormalities, etc. In various embodiments, treatment recommendations 142 may be provided to healthcare professionals for patient treatment, for example, via network 170 to client devices 174a-n and / or data storage 172a-n accessible to healthcare professional users. For example, healthcare professional users may access patient portals, EMR systems, or other interfaces to obtain patient information to view access site images 132, access site description information 134, access site information, treatment recommendations 142, patient healthcare records including or related to any of the above, and / or similar information.

[0053] Figure 3 An example of an operating environment 300, which may represent some embodiments, is shown. For example... Figure 3 As shown, the operating environment 300 may include a patient computing device 374, such as a smartphone, tablet, portable computing device, etc. The computing device 374 may execute a access site application 352. In some embodiments, the access site application 352 may be or may include a mobile application, client application, web-based application, and / or the like, for interacting (e.g., directly or via the patient portal 330) with the dialysis access site analysis system 305 configured according to various embodiments.

[0054] Users can capture or otherwise access images of the access site or other parts of the patient 332. For example, a user can take one or more photographs and / or videos of the access site (e.g., slowly moving the camera around the access site to obtain multiple views of the access site). In some embodiments, video frames of the access site can be converted into multiple images.

[0055] The access site application 352 may allow a user to input access site description information 334 describing image 332 and / or other personal characteristics. In some embodiments, the access site application 352 may provide text boxes, checkboxes (e.g., to indicate the presence of a condition), selection objects, or other graphical user interface (GUI) objects for inputting the access site description information 334. In some embodiments, the access site application 352 may facilitate the capture of image 332. For example, a user may open the access site application 352 and the access site application 352 may provide image capture capabilities (e.g., using the camera of computing device 374). In some embodiments, image 332 may include or may be associated with image information, including size indicators, color indicators, shape selectors, and / or the like. For example, a ruler or scale may be included in the image or used to determine size information. In another example, a color indicator may be used as a reference and / or to determine the color of a portion of the patient included in image 332. In another example, the shape selector can be used to select, draw, or otherwise highlight a portion of the patient in image 332 (e.g., the patient can draw a circle or other shape around a passage site, pain source, hardness area, discoloration area, change area, and / or such area).

[0056] Image recording 360 can be uploaded to patient portal 330. In some embodiments, image recording 360 may include image 332, pathway site description information 360, and / or other patient information. For example, image recording 360 may include computing device 374 information, user identification information, user certificate information, healthcare provider information, timestamp information, image quality information, etc. In some embodiments, patient portal 330 may store image recording 360 in patient information repository 372. In some embodiments, repository 372 may be or may include a patient record database, such as a DIS, EMR system, etc. In an exemplary embodiment, patient portal 330 and patient information repository 372 may be part of healthcare provider system 350. For example, patient portal 330 and patient information repository 372 may be used by dialysis clinics or multiple dialysis clinics operated by a healthcare provider to provide patient care and manage patient healthcare information.

[0057] In various embodiments, patient portal 330 or other systems may modify image record 360 to generate a modified image record 362. For example, for use as group-specific information, image record 362 may remove identification information that could be used to identify the patient associated with image record 360. In another example, the healthcare provider associated with patient portal 330 may include its own information, such as data and timestamps received by image record 360, changes made to image record 360, healthcare provider information, and / or the like. In some embodiments, image record 362 may be modified to a format corresponding to records and / or other information stored in repository 372.

[0058] The dialysis access site analysis system 305 can access image recordings 362 via a healthcare provider system 350. For example, the dialysis access site analysis system 305 can operate as a service to healthcare providers, such as subscription services and / or Software as a Service (SaaS) providers. According to some embodiments, the dialysis access site analysis system 305 can analyze image recordings 362 and generate treatment recommendations 342 (e.g., see...). Figure 1 , 4 (and 6). In various embodiments, treatment recommendations 342 may be provided to healthcare providers, for example, by being stored in a repository 372 along with patient records. In some embodiments, the dialysis access site analysis system 305 may use image records 362 to train a computational model 336. Alternatively or additionally, the dialysis access site analysis system 305 may use other data, such as CMS databases, USRDS databases, third-party clinical data, computer clinical data, etc., to train the computational model.

[0059] Figure 4 An example of an operating environment 400, which may represent some embodiments, is shown. For example... Figure 4As shown, the pathway site analysis process 405 may include accessing a pathway site image 432 of a pathway site 402 having various elements 404a-n. For example, the first element 404a may include a crust, while the second element 404n may include the color of the pathway site. Pathway site descriptive information 434 may also be accessed, providing descriptive information associated with the pathway site 402, such as symptoms, changes, vital signs, etc. The pathway site image 432 and / or the pathway site descriptive information 434 may be provided to a computational model 436a. In some embodiments, the computational model 436a may include a CNN or other computational model operable to analyze the pathway site image to determine pathway site features 410 based on the analysis of visual elements of the pathway site image 432. For example, the computational model 436a may be trained to determine the color or color differences of the pathway site region (e.g., looking for redness, darkness, contrast with surrounding areas of the patient, etc.). In another example, the computational model 436a may be trained to determine elements 404a-n within the pathway site image 432, such as pathway sites, aneurysms, discolored areas, shiny skin areas, etc. The embodiments are not limited to this context.

[0060] In various embodiments, computational model 436a may analyze pathway site image 432 alone or in combination with pathway site description information 434. For example, computational model 436a may detect conditions (e.g., inflammation) with a specific confidence level. Computational model 436a may examine pathway site description information 434 to determine whether inflammation has been indicated to increase the confidence level for identifying inflammation as a pathway site feature and / or training computational model 436a. In another example, computational model 436a may indicate areas where crusting may occur in response to pathway site description information 434 describing crusting in a pathway site.

[0061] In some embodiments, computational model 436a may compare the pathway site image 432 with any previous image of the pathway site to determine certain pathway site features 410. In this way, computational model 436a may determine trends (e.g., increased element size, increased inflammation, decreased redness, decreased gloss and / or the like), changes (e.g., the presence of new abnormalities, absence of a previous condition, color changes, shape changes and / or the like), and other determinations that may be made based on viewing a series of images taken at different times.

[0062] In some embodiments, the pathway site image 132 may undergo manual review 470 by a healthcare professional. The results of the manual review 470 may be provided to the computational model 436a for analysis and / or training purposes and / or as pathway site features 410.

[0063] Access site features 410 and access site description information 434 can be provided as access site information 438 to computational model 436b. In various embodiments, computational model 436b can operate to determine treatment recommendations 442 based on access site information 438. In some embodiments, computational model 436b can compare access site image 432 and / or access site information with any previous image or information associated with the access site to determine changes, trends, and / or other determinations based on historical patient information.

[0064] In various embodiments, treatment recommendation 442 may include and / or may be based on one or more diagnostic features 452a-n, including but not limited to trends 452a, changes 452b, scores 452c, etc. For example, trend 452a may determine that inflammation has been decreasing over the first three image sampling periods, indicating that treatment may be effective. In another example, a color change 452b at the pathway site may indicate the emergence of a new condition or abnormality. In yet another example, treatment recommendation 442 may include a score 452c or other diagnostic classifications (e.g., see...). Figure 3 ).

[0065] In various embodiments, treatment recommendation 442 may include analytical information 454, such as indicating outcomes, success rates, treatment types, etc., associated with other patients and / or patient groups. For example, treatment recommendation 442 may include analytical information 454 indicating that treatment A for group B with condition C has a 20% success rate and complications X, Y, and Z, while treatment M for group N with condition C has a 30% success rate and complication X. As determined by computational model 436b, optimized treatment recommendations 442 for patients can be determined. For example, computational model 436b can determine one or more most successful treatments (e.g., based on success rate) for patients with the same abnormality, the same group, the same region, pathway site characteristics, pathway site information, combinations thereof, and / or the like. Analytical information 454 may be provided based on various patient characteristics, such as age, sex, pathway site type, pathway site age, abnormality, diagnosis, etc., based on relevance to the patient. For example, analytical information 454 related to patient groups, pathway site types, and / or the like may be provided. In this way, healthcare professionals can use population-based outcomes and success rates to more comprehensively evaluate treatment recommendations.442

[0066] This document includes one or more logical flows that represent exemplary methods for performing novel aspects of the disclosed architecture. Although, for simplicity of explanation, the one or more methods shown herein are illustrated and described as a series of actions, those skilled in the art will understand and appreciate that these methods are not limited to a specific order of actions. Accordingly, some actions may occur in a different order and / or concurrently with other actions shown and described herein. For example, those skilled in the art will understand and appreciate that methods may alternatively be represented as a series of interrelated states or events, such as those shown in a state diagram. Furthermore, for novel embodiments, not all behaviors shown in the methods are necessary. Boxes indicated by dashed lines may be optional boxes in the logical flow.

[0067] The logical flow can be implemented in software, firmware, hardware, or any combination thereof. In software and firmware embodiments, the logical flow can be implemented using computer-executable instructions stored on a non-transitory computer-readable medium or a machine-readable medium. Embodiments are not limited to this context.

[0068] Figure 5 An embodiment of logic flow 500 is illustrated. Logic flow 500 may represent some or all of the operations performed by one or more embodiments described herein, such as computing device 110. In some embodiments, logic flow 500 may represent some or all of the operations of a pathway location analysis process according to some embodiments.

[0069] In box 502, logic flow 500 may receive a patient image. For example, pathway site analysis application 150 may receive a pathway site image 132 stored in a healthcare provider's data repository. In box 504, logic flow 500 may receive pathway site description information. For example, pathway site analysis application 150 may receive pathway site description information 134 associated with the patient image received in box 502. In some embodiments, the patient and pathway site description information may be included in the same patient record stored, for example, in a healthcare provider's database.

[0070] In block 506, logic flow 500 can determine access site information. For example, access site analysis application 150 can use a computational model configured according to some embodiments to process access site image 132 and / or access site description information 134 to determine vascular access information 138. In some embodiments, access site information 138 may include a diagnosis or other determination of the condition of the access site, including indications of features (color, size, abnormalities, etc.) and / or classifications (e.g., scores and associated actions). In block 508, logic flow 500 can provide treatment recommendations. For example, access site analysis application 150 can generate treatment recommendations 508 for access sites determined by processing vascular access information using a computational model configured according to some embodiments. Treatment recommendations may include actions such as monitoring, healthcare provider assessment, medication, continuing / discontinuing needle use, etc.

[0071] In some embodiments, logic flow 500 may receive feedback at box 510. For example, a healthcare provider may provide treatment outcomes and / or similar information related to the treatment process for a patient and / or treatment group, such as treatments associated with treatment recommendations generated in box 508. In another example, a healthcare provider may provide feedback related to the accuracy of vascular access information, access site features, etc., generated by computational model 136. Feedback may take various forms, such as images, text descriptions, clinical data, outcome information, and / or similar information.

[0072] In various embodiments, a computational model can be trained in block 512 logic flow 512. For example, pathway site analysis application 150 can use feedback received in block 510 to train computational model 136. In this way, according to some embodiments, computational models operable to determine pathway site information and / or treatment recommendations can continuously learn and improve their accuracy, confidence level, breadth of analysis, etc.

[0073] Figure 6 Embodiments of an exemplary computing architecture 600 suitable for implementing the various embodiments described above are illustrated. In various embodiments, the computing architecture 600 may include or be implemented as part of an electronic device. In some embodiments, the computing architecture 600 may represent, for example, computing device 110. The embodiments are not limited to this context.

[0074] As used herein, the terms “system,” “component,” and “module” are intended to refer to computer-related entities, hardware, combinations of hardware and software, software, or software in execution, examples of which are provided by the exemplary computing architecture 600. For example, a component can be, but is not limited to, a process running on a processor, a processor, a hard disk drive, multiple storage drives (optical and / or magnetic storage media), an object, an executable file, an execution thread, a program, and / or a computer. As an example, an application running on a server and the server itself can both be components. One or more components may reside in a process and / or an execution thread, and components may reside on a single computer and / or be distributed across two or more computers. Furthermore, components can communicatively couple to each other to coordinate operation through various types of communication media. Coordination may involve one-way or two-way exchange of information. For example, components may transmit information in the form of signals transmitted through a communication medium. This information can be implemented as signals assigned to various signal lines. In such an assignment, each message is a signal. However, alternative embodiments may employ data messages. Such data messages can be sent through various connections. Exemplary connections include parallel interfaces, serial interfaces, and bus interfaces.

[0075] The computing architecture 600 includes various common computing elements, such as one or more processors, multi-core processors, coprocessors, memory units, chipsets, controllers, peripherals, interfaces, oscillators, timing devices, video cards, audio cards, multimedia input / output (I / O) components, power supplies, etc. However, embodiments are not limited to those implemented by the computing architecture 600.

[0076] like Figure 6 As shown, the computing architecture 600 includes a processing unit 604, a system memory 606, and a system bus 608. The processing unit 604 can be a commercially available processor and can include dual-microprocessors, multi-core processors, and other multiprocessor architectures.

[0077] System bus 608 provides interfaces to processing unit 604 for system components, including but not limited to system memory 606. System bus 608 can be any of several types of bus structures that can be further interconnected to memory bus (with or without memory controller), peripheral bus, and local bus using any of a variety of commercially available bus architectures. Interface adapters can be connected to system bus 608 via slot architecture. Example slot architectures may include, but are not limited to, Accelerated Graphics Port (AGP), Card Bus, (Extended) Industry Standard Architecture ((E)ISA), Micro Channel Architecture (MCA), NuBus, Peripheral Component Interconnect (Extended) (PCI(X)), PCI Express, PCMCIA, etc.

[0078] System memory 606 may include various types of computer-readable storage media in the form of one or more high-speed memory cells, such as read-only memory (ROM), random access memory (RAM), dynamic RAM (DRAM), double data rate DRAM (DDRAM), synchronous DRAM (SDRAM), static RAM (SRAM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, polymer memory such as ferroelectric polymer memory, austenite memory, phase change or ferroelectric memory, silicon oxide-nitride-silicon oxide (SONOS) memory, magnetic cards or optical cards, device arrays such as redundant array of independent disk drives (RAID), solid-state memory devices (e.g., USB memory, solid-state drive (SSD)), and any other type of storage media suitable for storing information. Figure 6 In the illustrated embodiment, system memory 606 may include non-volatile memory 610 and / or volatile memory 612. The basic input / output system (BIOS) is stored in non-volatile memory 610.

[0079] Computer 602 may include various types of computer-readable storage media in the form of one or more low-speed memory cells, including internal (or external) hard disk drive (HDD) 614, floppy disk drive (FDD) 616 for reading or writing to removable disk 611, and optical disk drive 620 (e.g., CD-ROM or DVD) for reading or writing to removable optical disk 622. HDD 614, FDD 616, and optical disk drive 620 may be connected to system bus 608 via HDD interface 624, FDD interface 626, and optical drive interface 628, respectively. HDD interface 624 for external drive implementation may include at least one or both of Universal Serial Bus (USB) and IEEE 1114 interface technologies.

[0080] The drive and associated computer-readable medium provide volatile and / or non-volatile storage for data, data structures, computer-executable instructions, etc. For example, multiple program modules may be stored in the drive and memory units 610, 612, including an operating system 630, one or more application programs 632, other program modules 634, and program data 636. In one embodiment, one or more application programs 632, other program modules 634, and program data 636 may include, for example, various applications and / or components of the computing device 110.

[0081] Users can input commands and information into computer 602 through one or more wired / wireless input devices (such as keyboard 638 and pointing device such as mouse 640). These and other input devices are typically connected to processing unit 604 via input device interface 642 coupled to system bus 608, but may also be connected via other interfaces.

[0082] Monitor 644 or other types of display devices are also connected to system bus 608 via an interface such as video adapter 646. Monitor 644 can be internal or external to computer 602. In addition to monitor 644, computer typically includes other peripheral output devices, such as speakers, printers, etc.

[0083] Computer 602 can operate in a networked environment using logical unit connections to one or more remote computers, such as remote computer 648, via wired and / or wireless communications. Remote computer 648 can be a workstation, server computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer-to-peer device, or other public network node, and typically includes many or all of the elements described with respect to computer 602; however, for brevity, only memory / storage device 650 is shown. The illustrated logical unit connections include wired / wireless connections to a local area network (LAN) 652 and / or a larger network, such as a wide area network (WAN) 654. Such LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can connect to global communication networks, such as the Internet.

[0084] Computer 602 is operable to communicate with wired and wireless devices or entities using IEEE 802 series standards, such as wireless devices operable in wireless communication (e.g., IEEE 802.16 air modulation technology). This includes at least Wi-Fi (or Wireless Fidelity), WiMax, and Bluetooth™ wireless technologies. Therefore, communication can be a predefined structure like a traditional network, or simply self-organizing communication between at least two devices. Wi-Fi networks use radio technologies known as IEEE 802.11x (a, b, g, n, etc.) to provide secure, reliable, and fast wireless connectivity. Wi-Fi networks can be used to interconnect computers, connect to the Internet, and connect to wired networks (using IEEE 802.3 related media and functions).

[0085] This document has set forth numerous specific details to provide a thorough understanding of the embodiments. However, those skilled in the art will understand that the embodiments can be practiced without these specific details. In other instances, well-known operations, components, and circuits have not been described in detail so as not to obscure the embodiments. It will be understood that the specific structural and functional details disclosed herein may be representative and do not necessarily limit the scope of the embodiments.

[0086] Some embodiments may use the terms “coupled” and “connected” along with their derivatives for description. These terms are not synonyms for each other. For example, some embodiments may use the terms “connected” and / or “coupled” to indicate that two or more elements are in direct physical or electrical contact with each other. However, the term “coupled” may also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0087] Unless otherwise expressly stated, terms such as “processing,” “computing,” “operation,” and “determining” refer to the actions and / or processes of a computer or computing system or similar electronic computing device that manipulate and / or convert data representing physical quantities (e.g., electrons) in the registers and / or memory of the computing system into other data similarly represented in the memory, registers, or other similar information storage, transmission, or display devices of the computing system. Embodiments are not limited to this context.

[0088] It should be noted that the methods described herein need not be performed in the order described or in any particular order. Furthermore, the various activities described with respect to the methods defined herein can be performed serially or in parallel.

[0089] While specific embodiments have been shown and described herein, it should be understood that any arrangement calculated to achieve the same purpose may replace the specific embodiments shown. This disclosure is intended to cover any and all modifications or variations of the various embodiments. It should be understood that the above description is illustrative and not restrictive. By reading the above description, those skilled in the art will understand combinations of the above embodiments and other embodiments not specifically described herein. Therefore, the scope of the various embodiments includes any other application using the above compositions, structures, and methods.

[0090] Although the subject matter has been described in language specific to structural features and / or methodological actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as exemplary forms for implementing the claims.

[0091] As used herein, elements or operations described in the singular and beginning with the words "a" or "an" should be understood to not exclude plural elements or operations unless such exclusion is explicitly stated. Furthermore, references to "an embodiment" in this disclosure are not intended to exclude the existence of additional embodiments that also include the described features.

[0092] The scope of this disclosure is not limited to the specific embodiments described herein. In fact, various other embodiments and modifications of this disclosure, besides those described herein, will be readily apparent to those skilled in the art based on the foregoing description and drawings. Therefore, such other embodiments and modifications are intended to fall within the scope of this disclosure. Furthermore, although this disclosure has been described in the context of specific implementations for specific purposes in specific environments, those skilled in the art will recognize that its use is not limited thereto, and that this disclosure can advantageously achieve any number of purposes in any number of environments. Therefore, the claims set forth below should be interpreted in accordance with the full scope and spirit of this disclosure as set forth herein.

Claims

1. A device comprising: at least one processor; a memory coupled to the at least one processor, the memory comprising instructions that, when executed by the at least one processor, cause the at least one processor to: receive a site image comprising at least one image of a dialysis access site of a patient, access a computational model trained using population-based images of access sites of at least one patient population and corresponding access site information indicative of a condition of the access sites to determine a diagnosis of the dialysis access site based on at least one access site feature determined from the population-based images, provide the site image to the computational model to determine a diagnosis of the dialysis access site of the patient, and determine a treatment recommendation for a dialysis access site based on the access site information.

2. The apparatus of claim 1, wherein, the instructions, when executed by the at least one processor, cause the at least one processor to: receive site description information, and determine the diagnosis based on the at least one access site feature and the site description information.

3. The apparatus of claim 1, wherein, the dialysis access site comprises one of an arteriovenous fistula (AVF) or an arteriovenous graft (AVG).

4. The apparatus of claim 1, wherein, the instructions, when executed by the at least one processor, cause the at least one processor to provide the diagnosis to a treatment recommendation computational model to determine the treatment recommendation.

5. The apparatus of claim 1, wherein, the at least one access site feature comprises at least one of a size, a color, a shape.

6. The apparatus of claim 1, wherein, the at least one access site feature comprises a presence of an abnormality.

7. The apparatus of claim 1, wherein, the site image is captured via a client computing device.

8. The apparatus of claim 1, wherein, the instructions, when executed by the at least one processor, cause the at least one processor to determine a classification of the access site based on access site classification information.

9. The apparatus of claim 8, wherein, the classification comprises a score and at least one treatment action.

10. The apparatus of claim 1, wherein, the treatment recommendation comprises analytics information indicative of at least one treatment outcome associated with the treatment recommendation.

11. A method comprising: receiving a site image comprising at least one image of a dialysis access site of a patient; accessing a computational model trained using population-based images of access sites of at least one patient population and corresponding access site information indicative of a condition of the access sites to determine a diagnosis of the dialysis access site based on at least one access site feature determined from the population-based images; providing the site image to the computational model to determine a diagnosis of the dialysis access site of the patient; and determining a treatment recommendation for a dialysis access site based on the diagnosis.

12. The method of claim 11, wherein, the method comprising: receiving site description information; and determining the diagnosis based on the at least one access site feature and the site description information.

13. The method of claim 11, wherein, the dialysis access site comprises one of an arteriovenous fistula (AVF) or an arteriovenous graft (AVG).

14. The method of claim 11, wherein, the method comprising providing the diagnosis to a computational model to determine the treatment recommendation.

15. The method of claim 11, wherein, the at least one access site feature comprises at least one of a size, a color, a shape.

16. The method of claim 11, wherein, the at least one access site feature comprises a presence of an abnormality.

17. The method of claim 11, wherein, The access site image is captured via a client computing device.

18. The method of claim 11, wherein, The method includes determining a classification of the access site based on access site classification information.

19. The method of claim 18, wherein, The classification includes a score and at least one treatment action.

20. The method of claim 11, wherein, The treatment recommendation includes analysis information indicative of at least one treatment outcome associated with the treatment recommendation.

Images