Evaluation of patient status and medical device performance post-implant

Abstract

Techniques for remotely monitoring a patient and a corresponding medical device are described. The remote monitoring includes providing an interactive session configured to allow a user to navigate a plurality of sub-sessions, determining a first set of data items from a first sub-session, the first set of data items containing image data, determining a second set of data items from a second sub-session of the interactive session, determining an anomaly based at least in part on the first set of data items and the second set of data items, and outputting a post-implant report of the interactive session.

Description

Technical Field

[0001] This disclosure relates to medical devices, and in some specific instances to computing devices (e.g., mobile devices) configured to evaluate a patient’s recovery from the implantation of a medical device and / or to evaluate the performance of a medical device currently implanted in a patient. Background Technology

[0002] Medical devices can be used to treat a variety of medical conditions. Example medical devices include implantable medical devices (IMDs), such as cardiac or cardiovascular implantable electronic devices (CIEDs). An IMD, sometimes referred to as an "implantable medical device," can be a device implanted in a patient at a surgically or procedurally prepared implantation site. An IMD can include diagnostic devices configured to diagnose various diseases in a patient, monitor the patient's health status, etc. Alternatively or additionally, an IMD can also be configured to deliver electrical stimulation therapy to a patient via electrodes such as implantable electrodes, wherein the device can be configured to stimulate the heart, nerves, muscles, brain tissue, etc. In any case, an IMD may include a battery-powered component in some cases, such as when referring to implantable pacemakers, implantable cardioverter defibrillators (ICDs), other electrical stimulators including spinal cord stimulators, deep brain stimulators, nerve stimulators, and muscle stimulators, infusion devices, cardiac and other physiological monitors, cochlear implants, etc. In such cases, the battery-powered component of the IMD can be implanted at the surgical or procedurally prepared implantation site. In addition, related devices such as thin medical electrical leads or drug delivery catheters can extend from the IMD to other subcutaneous implantation sites, or in some cases to deeper parts of the body, such as to organs or various other implantation sites.

[0003] Although preparation and implantation are performed in a sterile area, and the IMD component is packaged in a sterile container or sterilized before being introduced into the sterile area, there is still a risk of introducing microorganisms into the surgical site. Therefore, implantation clinicians typically apply disinfectants or antiseptics to the skin at the surgical site before surgery, apply them directly to the site before the incision closes, and prescribe oral antibiotics for the patient to take during recovery. Despite these precautions, infection can still occur.

[0004] Therefore, infections associated with implanted medical devices (IMDs) remain a public health and economic issue. If an IMD-related infection occurs, device removal is often the only appropriate course of action. Furthermore, once an infection is present at one site, it can migrate, for example, along the lead or catheter to the location where the lead and / or catheter were implanted. For instance, removing a long-term implanted lead or catheter in response to such an infection can be very difficult. Aggressive systemic medical therapy is used to treat such infections. However, early detection of IMD-related infections can allow for early intervention, thereby reducing device removal.

[0005] In some cases, patients who have had certain medical devices implanted, such as CIEDs, require post-implantation follow-up consultations by a healthcare professional (HCP). HCP visits typically occur anytime from a few days to a few weeks after implantation. The HCP usually performs a wound examination and may initiate a device inquiry session to determine performance metrics of the CIED. In most cases, up to 90% or more, these visits are insignificant and brief. However, post-implantation follow-up can still constitute a necessary checkpoint for the HCP for the patient. In some cases, this follow-up may uncover potential infections or device-related complications that may require clinical intervention. Summary of the Invention

[0006] While actual follow-up consultations conducted by healthcare professionals (HCPs) are often relatively short, these visits can still place a burden on patients' lives, doctors' offices, and the healthcare system as a whole. Aspects of this disclosure relate to one or more computing devices having a processing circuitry system in which the processing circuitry is configured to facilitate or simulate a virtual registration of a patient, such as a virtual follow-up or other health check, in which the patient and / or doctor can examine the status of a medical device including an implantable medical device (IMD) and / or the patient themselves.

[0007] The processing circuitry of the one or more computing devices can implement various tools and techniques (hereinafter referred to as "tools," processor systems, or processing circuitry systems) to provide virtual registration for patients. The processing circuitry system can be configured to offer patients the option to participate in interactive sessions (e.g., virtual registration processes, interactive registration sessions, interactive reporting processes, etc.) as part of post-implantation assessment. For these interactive sessions, patients can remotely participate in interactive reporting sessions, such as from a physician's office environment or other HCP environments. In some instances, the processing circuitry system of a mobile or portable computing device can be configured to manage interactive sessions, enabling users to efficiently navigate these sessions from any remote location. Additionally, the processing circuitry system can communicate patient and / or medical device data between various computing devices (e.g., end-user mobile devices, camera devices, wearable devices, edge devices, etc.). In some instances, the processing circuitry system can be configured to manage interactive sessions to ensure proper interaction with the registration tool, enabling the system to accurately determine whether the patient and / or IMD have any complications. The processing circuitry system can communicate such information via a network and / or by implementing various communication protocols.

[0008] In some cases, the processing circuitry system can implement interactive sessions in a secure environment, such as on an authenticated mobile computing device and / or on a secure data network. In some instances, the processing circuitry system can implement interactive sessions on a mobile device configured to perform one or more of the various techniques disclosed herein, with or without the assistance of other devices (e.g., network devices). That is, the mobile device can operate various software tools configured to perform a virtual registration process. The patient can then conduct the entire session (e.g., multiple sub-sessions of an interactive session) of the virtual interactive registration session without network access or with limited network usage, such as when using wireless communication with an edge device (e.g., an IoT device with additional processing resources to assist or perform various registration functions). The mobile device can synchronize the virtual registration data with other network devices at a later point in time after the registration session (e.g., multiple sub-sessions of an interactive session) has concluded. In this way, the HCP can access data at said time, where it may not be important for the HCP to access such data in real-time or near real-time while the patient is conducting a particular registration session (e.g., multiple sub-sessions of an interactive session).

[0009] According to the technology disclosed herein, a processing circuitry system is configured to provide a comprehensive user interface (UI) to a user (e.g., a patient), wherein the UI is configured to guide the user through an interactive session and / or assessment process. The processing circuitry system of the computing device can provide the UI to the user by generating UI program data and / or accessing UI program data from memory. In some cases, the processing circuitry system can access UI program data from a separate computing device within a virtual registration computing system. In some cases, the processing circuitry system of the computing device can customize UI program data for each specific user or user category. In some cases, the processing circuitry system can customize UI program data by deploying various artificial intelligence (AI) algorithms and / or machine learning (ML) models of the medical device corresponding to a specific user or user category, configured to determine a UI reflecting a specific user or user category. In any case, the processing circuitry system can be configured to provide the UI to a user of a user-operated computing device via a display device.

[0010] In some instances, the UI may include interactive UI registration elements (e.g., UI tiles) configured to systematically guide patients through a virtual registration process. These UI registration elements may be configured to proactively assist specific patients in providing specific patient input to the system. Patient input may contain specific types and quantities of information. In some instances, the processing circuitry system may use this information to, for example, identify various patient conditions, such as device pocket infection, or otherwise identify abnormalities in the medical device and / or the patient. In some instances, the processing circuitry system may deploy AI and / or ML models to evaluate input received through the UI to determine the patient's health status and / or the status of one or more medical devices, including the IMD. In another instance, the processing circuitry system may communicate input from the patient to the HCP. The processing circuitry system may then receive input from the HCP. In this case, the processing circuitry system may determine the patient's health status and / or the status of one or more medical devices based on the HCP input. In any case, the processing circuitry system may train AI and / or ML models based on patient input and / or HCP input, where the processing circuitry system may, in some cases, obtain HCP input based on patient input (e.g., uploaded images of the implantation site, ECG waveforms, etc.). Therefore, the processing circuitry system can utilize information from multiple sources to determine various diseases of a patient. Although described with reference to a comprehensive UI, the technology of this disclosure is not limited thereto, and it will be understood that UI elements can be implemented as independent UIs involving a subset of the UI elements of this disclosure. That is, the processing circuitry system of the computing device may not contain all UI elements of a single UI program, and in some cases may contain additional UI elements configured to provide various other registration functions.

[0011] In some instances, UI registration elements can include general patient status registration elements, physiological parameter registration elements, medical device registration elements, and site examination elements, such as wound examination elements. The processing circuitry system can acquire information related to these various discrete registration elements and determine the patient's health status, such as the patient's IMD status. In some cases, patients can periodically perform such virtual checks to examine the status of medical devices or implanted sites. That is, even after multiple virtual registration sessions (e.g., multiple sub-sessions of an interactive registration session) have been performed, which are mandated or recommended by the HCP following the patient's surgical event, the patient can still undergo a health check.

[0012] Interactive reporting sessions can replace and / or supplement HCP field visits in some cases. In some instances, the processing circuitry system of this disclosure can use the results of examinations performed by a computing device to determine whether to provide instructions to the patient, and in some cases to physicians or other HCPs regarding the need for a field visit, or alternatively, whether the patient's IMD wound recovery is proceeding as expected. Additionally, the processing circuitry system can implement one or more sub-sessions of the interactive session to determine whether one or more medical devices are operating within acceptable limits, etc. In some cases, the processing circuitry system can obtain information from the user via a computing device such as a mobile phone device and evaluate said information via another computing device such as an edge device or a web server. In this case, the edge device can deploy AI and / or ML models trained based on medical device data, patient data, and / or heuristic data obtained from the network. In some cases, the processing circuitry system can train AI or ML models based on data obtained from the user's computing device and / or data obtained directly from the patient's medical device. In this case, those medical devices can be configured to communicate with both the edge device and the user's computing device.

[0013] In one instance, this disclosure provides a method for monitoring a patient with an intramural disorder (IMD), the method comprising: providing an interactive session via a computing device, the interactive session being configured to allow a user to navigate multiple sub-sessions, the multiple sub-sessions including at least a first sub-session and a second sub-session different from the first sub-session, wherein the first sub-session includes capturing image data via one or more cameras; determining a first set of data items via the computing device based on the first sub-session of the interactive session, the first set of data items containing the image data; determining a second set of data items via the computing device based on the second sub-session of the interactive session, the second set of data items being different from the first set of data items and including one or more of: data obtained from the IMD, at least one physiological parameter of the patient, or user input data; determining an abnormality corresponding to at least one of the patient or the IMD based at least in part on the first set of data items and the second set of data items; and outputting a post-implantation report of the interactive session via the computing device, wherein the post-implantation report includes an indication of the abnormality and an indication of the amount of time that has occurred since the date of implantation of the IMD.

[0014] In another instance, this disclosure provides a system for monitoring a patient with an implantable medical device (IMD), the system comprising: a memory configured to store image data; and one or more processors in communication with the memory, the processors being configured to: provide an interactive session configured to allow a user to navigate a plurality of sub-sessions, the plurality of sub-sessions including at least a first sub-session and a second sub-session different from the first sub-session, wherein the first sub-session includes capturing the image data via one or more cameras; determine a first set of data items based on the first sub-session of the interactive session, the first set of data items containing the image data; determine a second set of data items based on the second sub-session of the interactive session, the second set of data items being different from the first set of data items and including one or more of: data obtained from the IMD, at least one physiological parameter of the patient, or user-input data; determine an abnormality corresponding to at least one of the patient or the IMD based at least in part on the first set of data items and the second set of data items; and output a post-implantation report of the interactive session, wherein the post-implantation report includes an indication of the abnormality and an indication of the amount of time that has occurred since the date of implantation of the IMD.

[0015] This disclosure also provides a non-transitory computer-readable medium comprising instructions that cause a programmable processor to perform any of the techniques described herein. In one example, this disclosure provides a non-transitory computer-readable storage medium having instructions stored thereon that, when executed, cause one or more processors to: provide an interactive session to a user, the interactive session being configured to allow the user to navigate a plurality of sub-sessions, the plurality of sub-sessions including at least a first sub-session and a second sub-session different from the first sub-session, wherein the first sub-session includes capturing image data via one or more cameras; determine a first set of data items based on the first sub-session of the interactive session, the first set of data items containing the image data; determine a second set of data items based on the second sub-session of the interactive session, the second set of data items being different from the first set of data items and including one or more of: data obtained from an IMD, at least one physiological parameter of a patient, or user input data; determine an abnormality corresponding to at least one of the patient or the IMD based at least in part on the first set of data items and the second set of data items; and output a post-implantation report of the interactive session, wherein the post-implantation report includes an indication of the abnormality.

[0016] This disclosure also provides means for performing any of the techniques described herein.

[0017] This summary is intended to provide an overview of the subject matter described in this disclosure. It is not intended to provide an exclusive or exhaustive explanation of the systems, apparatus, and methods described in detail in the following drawings and specification. Further details of one or more embodiments of this disclosure are set forth in the following drawings and specification. Other features, objects, and advantages will become apparent from the specification and drawings and from the claims. Attached Figure Description

[0018] Figure 1 An environment for an example monitoring system in conjunction with a patient, based on one or more technologies disclosed herein, is shown.

[0019] Figure 2 This demonstrates one or more techniques disclosed herein. Figure 1 A functional block diagram of an example configuration of an example computing device.

[0020] Figure 3 This includes demonstrating one or more techniques disclosed herein. Figure 1 Block diagram of an example network system, including example computing devices, networks, edge devices, and servers, or 2.

[0021] Figure 4 This demonstrates one or more techniques disclosed herein. Figure 1Functional block diagram of an example configuration of a medical device and / or 3.

[0022] Figure 5 It is based on one or more technologies of this disclosure Figure 1 , 2 Or, a visual representation of the example user interface (UI) of an example computing device (or 3).

[0023] Figure 6 It is a UI visualization that initiates an interactive session interface based on one or more techniques disclosed herein.

[0024] Figure 7 It is a UI visualization of an example menu interface based on one or more technologies disclosed herein.

[0025] Figure 8 This is a flowchart illustrating an example method of utilizing UI input and data processing according to one or more techniques disclosed herein.

[0026] Figure 9 Based on one or more technologies disclosed herein, according to the user's... Figure 7 The UI visualization of the sample patient status interface presented is based on the request for the patient status interface shown in the image.

[0027] Figure 10 This is a UI visualization of an example patient status interface based on one or more techniques disclosed herein.

[0028] Figure 11 It is a UI visualization of an example physiological parameter examination interface based on one or more techniques of this disclosure.

[0029] Figure 12 It is a UI visualization of an example physiological parameter examination interface based on one or more techniques of this disclosure.

[0030] Figure 13 This is an example device for inspecting the UI visualization of an interface based on one or more techniques of this disclosure.

[0031] Figure 14 This is an example device for inspecting the UI visualization of an interface based on one or more techniques of this disclosure.

[0032] Figure 15 This is a UI visualization of an interface for inspecting an example part of one or more techniques according to this disclosure.

[0033] Figure 16 This is a flowchart illustrating an example method of utilizing imaging techniques according to one or more techniques disclosed herein.

[0034] Figure 17This is a UI visualization of an interface for inspecting an example part of one or more techniques according to this disclosure.

[0035] Figure 18 This is a UI visualization of an interface for inspecting an example part of one or more techniques according to this disclosure.

[0036] Figure 19 This is a flowchart illustrating an example method for capturing images of a body changing over time according to one or more techniques disclosed herein.

[0037] Figure 20 This is a flowchart illustrating an example method for a set of UI interfaces for navigating a virtual registration process according to one or more technologies disclosed herein.

[0038] Figure 21 This is a UI visualization of a complete registration interface based on one or more techniques disclosed herein.

[0039] Figure 22 This is a UI visualization of a complete registration interface based on one or more techniques disclosed herein.

[0040] Figure 23 This is a flowchart illustrating an example method for determining instructions for medical interventions for patients with IMD according to one or more techniques disclosed herein.

[0041] Throughout the specification and drawings, the same reference numerals denote the same elements. Detailed Implementation

[0042] In 2019, an estimated 1.5 million implantable medical devices (IMDs) were implanted globally. According to guidelines from the Heart Rhythm Society (HRS) and the European Heart Rhythm Association (EHRA), each of these implants should be followed up in person within two to twelve weeks. Patient adherence to post-implantation visits improves mortality and patient outcomes. However, patient adherence to these visits ranges from 55% to 80%. In 93% to 99% of these visits, patients experienced no abnormalities (e.g., infection). This means that many of these visits can be performed virtually.

[0043] This disclosure presents a system and method for remote post-implantation site (IMD) monitoring of infection. It is estimated that approximately 0.5% of IMD implants and approximately 2% of IMD replacements develop implantation infections. Early diagnosis of IMD infection can help facilitate effective antibiotic therapy or device removal to treat the infection. This is performed in a hospital post-operative environment where continuous patient monitoring is possible.

[0044] When patients experience any infection-related symptoms such as pain or fever, they are usually followed up with a post-discharge infection diagnosis. However, for some asymptomatic patients who cannot self-report any abnormalities at the implantation site, expert review is required. Since conducting infection reviews for all patients can be cumbersome for both patients and caregivers, remote monitoring of the implantation site is often necessary.

[0045] Generally, this disclosure relates to browser interfaces or mobile device applications that can be operated by various user-facing computing devices, including but not limited to smartphones, tablets, mobile devices, virtual reality (VR), augmented reality (AR), or mixed reality (MR) headsets. The computing device can execute software applications that enable the computing device to perform the various functions described herein, either locally using its computing resources or via cloud computing, such as by transmitting captured data via a network interface to some or all of the backend systems (e.g., server systems) performing the analyses described herein. Additionally, as described herein, some or all of the analyses can be performed via edge computing, such as by transmitting captured data to an edge device (e.g., an IoT device or another computing device). In some instances, the edge device may include user-facing devices or client devices, such as smartphones, tablets, PDAs, and other mobile computing devices. In any case, the backend system may or may not include certain edge devices as part of the backend system. In one instance, a network may engage with one or more edge devices operating at the edge of the backend system to form an intermediary between the user's computing device and various network servers. In such instances, the computing device may perform the various techniques of this disclosure by utilizing edge computing, cloud computing, or a combination thereof. Example combinations of edge computing and cloud computing may include distributed computing or distributed computing systems. In any case, the computing device may perform the techniques of this disclosure in an application, in a tablet computer, and / or in a cloud environment.

[0046] In the cloud-based implementation of this disclosure, a mobile device application can receive various types of analyzed data from a backend system and present the data to the user in the received form or after performing some additional processing or formatting the data locally.

[0047] A computing device executing an application (e.g., a virtual registration process) can perform the various functions described below, whether via local computing resources provided by the computing device, via a cloud-based backend system, or both. In some instances, the computing device can implement the application via a web browser. In some instances, the computing device can perform device checks. In such instances, the computing device can perform one or more queries on one or more medical devices (e.g., IMD, CIED, etc.). Additionally, the computing device can analyze medical device settings, parameters, and performance metrics.

[0048] In some instances, the computing device can perform physiological examinations. In such instances, the computing device can monitor and / or analyze physiological signals detected from a patient, including electrocardiogram (ECG) signals and other health signals that can be recorded (e.g., respiration, impedance, activity, stress, etc.).

[0049] Additionally, the computing device can perform examinations of one or more surgical sites (e.g., implant wounds, implantation sites after implant removal, etc.). In some instances, the computing device can perform image processing on areas indicating implantation sites (e.g., wound sites). In some instances, the computing device can use a camera, or one otherwise communicatively coupled to the computing device, to perform image processing to detect anomalies, such as abnormalities in wound healing and / or by identifying potential infection at the implantation site.

[0050] In some instances, the computing device can perform patient status checks. The application can implement interactive logging, journaling, or diary functions for the patient to answer several key questions about the patient's health information, medications, symptoms, physiological or anatomical measurements, or any relevant patient-reported information.

[0051] In some instances, the tools of this disclosure may use an artificial intelligence (AI) engine and / or a machine learning (ML) model. In some instances, the AI ​​engine may use cohort data for individual examination. The cohorts may comprise any number of groups, including CIED groups comprising CIED patients, age groups, skin pigmentation groups, IMD type groups, etc., or combinations thereof. Additionally, cohort data may be used to train an ML model for individual examination. In the wound examination instance, the tools of this disclosure may invoke image recognition or image processing AI, utilizing wound and infection databases available from various sources (e.g., training using said wound and infection databases).

[0052] To perform an ECG examination, the tools disclosed herein can classify normal rhythms and any potential arrhythmias using an arrhythmia classification AI with a QRS model relative to the patient's demographic characteristics and traits. It will be understood that a QRS model generally refers to a QRS complex containing a combination of various pattern deflections present in a typical ECG (e.g., Q wave, R wave, S wave, etc.).

[0053] To perform the device inspection functions of this disclosure, the application can utilize various communication hardware components of the computing device to query one or more medical devices (e.g., IMDs) to retrieve medical device parameters specific to a particular medical device family. The processing circuitry can be configured to compare the retrieved parameters with settings previously provided by a physician and with comparable medical device families to perform a normality / normal deviation analysis.

[0054] The tools disclosed herein can also provide patient status monitoring functionality using an interactive session with the patient, in which the patient provides elicited input to answer questions related to the patient's health and current condition. In various instances, the tools of this disclosure enable the patient to input information (e.g., status information or results) via text input, selection from pre-filled responses through drop-down menus and / or radio buttons, as shown in one or more of the accompanying drawings. In some non-limiting instances, the tools of this disclosure can output questions to elicit a patient response, based on which the patient can input information such as medication, its dosage, and other prompts.

[0055] Upon completion of a session (e.g., an interactive reporting session), the tools of this disclosure can mark the results on a UI provided via a mobile device application, with a date and timestamp. The tools of this disclosure can enable patients to generate reports for patient records (e.g., as portable document format (PDF) or various other formats), and to transmit reports or selected content of reports to family members or physicians via email or other means (e.g., via file transfer protocol (FTP)).

[0056] In some non-limiting instances, the applications of this disclosure can enable patients to locally save results to a computing device (e.g., a smartphone or tablet) for future comparison, reference, or use as a standalone document. In some cases, the computing device can locally store results for use in a retrieveable session within an application or other application, or as part of a health toolkit implemented on the computing device. In some non-limiting instances, the applications of this disclosure can push reports to a proprietary network (e.g., via an online portal). By pushing reports or other data in this manner, the tools of this disclosure enable HCPs to review patient health information and input data into an electronic medical record (EMR) database or repository. The tools of this disclosure can generate confirmation of HCP receipt based on various criteria (and in some instances, an indication of whether a report has been reviewed by the HCP), and provide such communication to the patient via communication with a mobile device or other patient-accessible computing methods. In some instances, the computing device can be configured to receive an indication of whether a report has been reviewed by the HCP. In such instances, the computing device can be configured to provide the user with the status of the report (e.g., HCP has reviewed, review in progress, etc.) at least in part based on the indication.

[0057] If the tools of this disclosure determine that any of the foregoing examinations or any combination of examinations produced an abnormal result (or an abnormality outside the acceptable normal range), the tools of this disclosure may output a prompt to the patient using a mobile device application. In some instances, the prompt may indicate the abnormality. In some instances, the prompt may include a suggestion or instruction to schedule a follow-up visit for the HCP.

[0058] In some instances, the tools of this disclosure can store session information (e.g., sub-session information, combined session information, etc.) and the results of previous checks (e.g., locally stored on the computing device, stored to a cloud storage resource, or both). The computing device can do this to help patients and / or HCPs track progress or changes regarding the patient's wound healing, the functionality of the medical device, etc. In some instances, the tools of this disclosure can implement a finite-date counter for the application to prevent or deter patients from continuing to use the application after the follow-up window has expired. Aspects of this disclosure implement, for example, two-way communication for contacting physicians, who can communicate using various messages such as "call my office," etc.

[0059] As those skilled in the art will understand, the telemedicine device monitoring disclosed herein represents a significant technological advancement compared to existing implementations. Specifically, the disclosed technology can identify and display customized sets of patient-related content elements and additional enhanced content, thereby improving the efficiency of rapid access to relevant content and allowing users to interact with multiple patient-related content elements (e.g., content tiles, sub-session interfaces, etc.). Furthermore, the disclosed technology can generate health benefits by dynamically determining the presence of anomalies using specific tools deployed and implemented at specific times to achieve the highest accuracy in anomaly detection. It can also present users with relevant control mechanisms that allow intuitive UI manipulation to capture the correct images, correct physiological parameters, correct device query data, and correct patient status updates for achieving the highest accuracy in anomaly detection. Thus, the examples described herein represent a significant improvement in this computer-related technology.

[0060] Other examples disclosed herein also represent improvements in computer-related technologies. For example, camera systems can use enhanced overlays (e.g., wireframes) to allow users to accurately align the implantation site or other parts of the patient's body, enabling consistent and reliable image acquisition. Furthermore, using such enhanced overlays allows computing devices to receive consistent images at specific angles and / or with specific implantation site sizes to determine the patient's healing progress over time based on analysis of the images over time. Another technological improvement involves using stored images of the patient's body (e.g., images taken shortly after surgery) to develop wireframes simulating the implantation site (e.g., transparent augmented reality overlays), allowing the patient to accurately align the implantation site with the wireframe as a guide for capturing images at specific angles and / or sizes, or specific contrast, lighting, zoom, etc. Advantageously, when, for example, the healing scar at the implantation site fits a specific area of ​​the wireframe, the computing device can initiate automatic still image capture of the implantation site. Additionally, in some instances, the monitoring system disclosed herein can be a native system of other software applications, and therefore, similar UI / UX elements can be used to display tiles. Other examples of improvements include the ability to invoke external information sources to provide greater relevance and complexity to post-implantation reports, and, in some instances, the ability to invoke APIs (e.g., language translation APIs, machine learning APIs) to perform additional work within the monitoring system. In one instance, a cloud-deployed API can serve as an accessible endpoint for ML models. Additionally, various ML models or AI engines can be deployed as so-called lightweight versions, configured to run efficiently on resource-constrained devices (e.g., mobile devices, tablets, etc.).

[0061] The ideas disclosed herein exist within the field of computer-related technologies. For example, the display of information in a UI where the relevant data does not necessarily reside locally in a storage device coupled to the relevant display device is practically impossible to replicate outside the field of computer-related technologies. That is, in some cases, the relevant data (e.g., training sets, physiological parameter data, images, etc.) can be stored on a cloud storage device, while in some instances, the relevant data can be stored locally (e.g., on the patient's mobile device) and / or synchronized with a cloud storage device or another device, such as a mobile device for HCP, at a time that is advantageous to the system, in order to convert computing resources (e.g., processing, memory, power resources, etc.). In non-limiting instances, multifaceted information, such as static content tiles, dynamically enhanced content tiles, etc., can be obtained simultaneously or dynamically from different systems, identified in some cases by metadata, and presented simultaneously or dynamically in interactive session UIs and sub-session UIs. In addition, the monitoring system can visually present data through appropriate media and / or at appropriate times on appropriate displays (e.g., on a static schedule or a dynamically updated schedule). Furthermore, the techniques disclosed herein provide, in some instances, anomaly determination techniques that can utilize non-visual sensors, such as thermal imaging via a camera, to detect temperature changes at the implantation site. Furthermore, various data analysis techniques are described for specific instances of synthesizing various data items (e.g., images of the implantation site, device status information, etc.), in which the information source can be optimized to provide specific data relevant to specific technical issues in post-implantation patient monitoring. That is, in some instances, data synthesis provides robust algorithms for identifying anomalies, although the described algorithms are used to obtain and analyze specific portions of the data, such as image data, for potential anomalies.

[0062] Furthermore, it has been noted that designing “human-usable and easily learned computer UIs is a non-trivial problem for software developers” (Dillon, A. (2003), “User Interface Design,” MacMillan Encyclopedia of Cognitive Science, Vol. 4, London: MacMillan, 453-458). The various examples of interactive and dynamic UIs disclosed herein are the result of extensive research, development, improvement, iteration, and testing, and in some instances provide specific ways of acquiring, summarizing, and presenting information on electronic devices. This non-trivial development has resulted in the UIs described herein, which are likely to offer significant cognitive and ergonomic efficiencies and advantages over previous systems. Interactive and dynamic UIs incorporate improved human-computer interaction that can provide users with reduced mental workload / burden, improved decision-making, reduced work stress, and more. For example, a UI with the interactive UI described herein can provide an optimized presentation of patient-specific information from various sources, enabling users to access, navigate, evaluate, and utilize such information more quickly than previous systems that may be slow, complex, and / or difficult to learn, especially for novice users. Therefore, presenting concise and compact information on a specific UI corresponding to a particular patient contributes to the efficient use of available information and the optimized use of the medical devices and virtual examination functions of this disclosure.

[0063] Figure 1 An environment for an example monitoring and / or registration system 100 integrated with patient 4 is illustrated. In some instances, system 100 can implement various patient and medical device monitoring and anomaly detection techniques disclosed herein. System 100 includes one or more medical devices 6 and one or more computing devices 2. Although in some cases, medical device 6 includes an IMD, such as Figure 1 As shown, but the technology disclosed herein is not limited thereto. However, for illustrative purposes, in some cases, the medical device 6 may be simply referred to herein as IMD 6 or one or more IMD 6.

[0064] The computing device 2 may be a computing device with a display that can be viewed by a user. The user may be a physician technician, surgeon, electrophysiologist, clinician (e.g., implantologist), or patient 4. Patient 4 is typically human, but not necessarily human. For example, patient 4 may be an animal requiring continuous monitoring of various health conditions (e.g., cardiac condition, spinal cord condition, etc.). In this case, human caregivers can operate aspects of the disclosed technology that may not be available from user input to the animal patient 4.

[0065] In some cases, computing device 2 may be referred to herein as multiple “computing devices 2”, while in other cases, it may be simply referred to as “computing device 2” where appropriate. System 100 may be implemented in any environment in which at least one of the computing devices 2 can engage with and / or monitor at least one of the implantation sites of the medical device 6. Computing device 2 may engage with and / or monitor the medical device 6, for example, by imaging the implantation site of the medical device 6, according to one or more techniques of the present disclosure. In addition, computing device 2 may query medical device 6 to obtain data from medical device 6, such as performance data, historical data stored in memory, battery strength, impedance, pulse width, pacing percentage, pulse amplitude, pacing mode, internal device temperature, etc. of medical device 6. In some instances, computing device 2 may perform a query sub-session with medical device 6 by establishing wireless communication with one or more of medical devices 6. In some cases, medical device 6 may or may not include an IMD. In one instance, computing device 2 queries the memory of wearable medical device 6 to determine device operating parameters as query data. In another instance, computing device 2 can receive (e.g., acquire) physiological parameters from medical device 6, such as waveforms of physiological parameters, parameter markers (e.g., "detected abnormal ECG"), etc. In another instance, computing device 2 can acquire patient status input into computing device 2 by a user (e.g., patient 4, patient 4's caregiver, etc.). In one instance, a user can input patient status updates through the user interface of computing device 2. In another instance, a user can input patient status updates through another computing device 2, which can then transmit the patient status data to one of the computing devices 2 configured to run an interactive registration session. In such instances, network 10 or edge device 12 can facilitate data exchange between various computing devices 2, medical devices 6, etc., as referenced. Figure 3 Further detailed description.

[0066] In some instances, computing device 2 may include one or more of a cellular phone, a "smartphone", a satellite phone, a laptop computer, a tablet computer, a wearable device, a computer workstation, one or more servers, a personal digital assistant, a handheld computing device, a virtual reality headset, a wireless access point, a motion or presence sensor device, or any other computing device that can run an application that enables the computing device to interact with medical device 6 or with another computing device configured to interact with medical device 6.

[0067] At least one of the computing devices 2 can be configured to communicate with the medical device 6 and optionally other computing devices in the computing device 2 via wired or wireless communication. For example, the computing device 2 can communicate via near field communication (NFC) technology (e.g., inductive coupling, NFC, or other communication technologies that can operate within a range of less than 10-20 cm) and / or far field communication technology (e.g., radio frequency (RF) telemetry according to 802.11). The communication can be performed using a standard set or other communication technologies that operate beyond the range of NFC technology. In some instances, the computing device 2 may include interfaces for providing input to the edge device 12, the network 10, and / or the medical device 6. For example, the computing device 2 may include a user input mechanism, such as a touchscreen, that allows users to store images in a database. In such instances, one of the edge devices 12 may manage the database, and in some cases, the computing device 2 may access the database via the network 10 to perform one or more of the various techniques disclosed herein.

[0068] Computing device 2 may include a user interface (UI) 22. In some instances, UI 22 may be a graphical user interface (GUI), an interactive user interface, etc. In some instances, UI 22 may further include a command-line interface. In some instances, computing device 2 and / or edge device 12 may include a display system (not shown). In such instances, the display system may include system software for generating UI data to be presented for display and / or interaction. In some instances, processing circuitry, such as the processing circuitry of computing device 2, may be available from another device, such as edge device 12 or server 94. Figure 3 One of the computing devices receives UI data, and the computing device 2 can use the UI data to generate system software for displaying and / or interacting with UI data to be presented.

[0069] The computing device 2 can be configured to receive input from a user via a UI 22. The UI 22 may include, for example, a keypad and a display, which may be, for example, a liquid crystal display (LCD) or a light-emitting diode (LED) display. In some instances, the display of the computing device 2 may include a touchscreen display, and the user can interact with the computing device 2 through the display. It should be noted that the user can also interact remotely with the computing device 2 via a network computing device.

[0070] In some instances, UI 22 may further include a keypad. In some instances, UI 22 may include both a keypad and a display. The keypad may take the form of an alphanumeric keypad or a simplified set of keys associated with specific functions. The computing device 2 may additionally or alternatively include a peripheral pointing device, such as a mouse, through which the user interacts with UI 22. In some cases, UI 22 may include a UI utilizing virtual reality (VR), augmented reality (AR), or mixed reality (MR) UIs, such as those implemented via VR, AR, or MR headsets.

[0071] In some instances, the processing circuitry system, for example, the processing circuitry system 20 of the computing device 2 ( Figure 2 ), processing circuit system 64 of edge device 12 Figure 3 ), server 94 processing circuit system 98 ( Figure 3 The processing circuitry system 40 of the medical device 17 can determine the patient 4's identification data, such as authentication data. In one example, the processing circuitry system 20 can identify the IMD information corresponding to IMD 6 based at least in part on the identification data. Thus, the processing circuitry system 20 can determine an interactive session program based at least in part on the IMD information, the interactive session program defining one or more parameters for imaging implantation sites, such as the implantation site of the patient 4. In one example, the interactive session program can define one or more parameters for imaging one or more implantation sites of the patient 4. The interactive session program can include a site inspection sub-session application, a patient status sub-session application, etc. (e.g., a mobile application installed from an app store). In some instances, the interactive session program can further include sub-session procedures (e.g., site inspection sub-session imaging program, patient status sub-session program, physiological parameter sub-session program, etc.) customized for the user of the computing device 2 (e.g., patient 4, HCP, etc.).

[0072] In an illustrative example, system 100 includes a system for monitoring patient 4. The system includes a processor and storage system, as referenced... Figure 2-4 Further details regarding those components are provided. In some instances, the storage device may include a memory, such as the memory device of computing device 2, wherein the memory can be configured to store image data (e.g., image data frames, images of the implantation site, etc.). Additionally, the storage device may be configured to store other data items, such as physiological parameter values, patient status updates, device query data, etc. A processor system, which may include one or more processors, can communicate with at least one of the storage devices configured to store image data.

[0073] In some instances, one of the computing devices 2 may include one or more processors in a processor system implemented in a circuit system, wherein the one or more processors may be configured to provide an interactive session, such as a virtual registration interactive session, via the computing device 2. In such instances, the virtual registration interactive session may be configured to allow a user (e.g., via the computing device 2) to navigate multiple sub-sessions. The multiple sub-sessions may include at least two sub-sessions as part of the interactive session. In one instance, the multiple sub-sessions may include at least a first sub-session and a second sub-session. In such instances, the second sub-session is distinct from the first sub-session. Additionally, the first sub-session may include a sub-session involving the capture of image data via one or more cameras. That is, the first sub-session may include a site examination sub-session. The second sub-session may include a device examination sub-session, a physiological parameter examination sub-session, a patient status sub-session, or other sub-sessions configured to elicit information about patient 4 that is useful in monitoring patient 4 (e.g., an IMD patient). In some cases, the interactive session may include a third and / or fourth sub-session, which includes one or more of a device examination sub-session, a physiological parameter examination sub-session, a patient status sub-session, or other sub-sessions, as described in the specific example sub-sessions herein.

[0074] In an illustrative example, computing device 2 may determine a first set of data items based on a first sub-session of an interactive session. In such an example, the first set of data items includes image data, such as image data frames. That is, computing device 2 may determine the first set of data items using a camera (e.g., Figure 2 The camera 32) captures image data frames and can store the frames in memory. In one instance, the image data may include still image frames of the implantation site of the medical device 6. In another instance, the image data may include still image frames of areas of the patient 4's body near the implantation site, such as where the lead may be routed under the patient 4's skin. In some cases, the computing device 2 may process the image data before storing it as a first set of data items. In one instance, the computing device 2 may deploy an AI engine and / or an ML model trained to identify image anomalies at the implantation site or other body parts of the patient 4. The AI ​​engine and / or ML model may determine anomaly metrics, such as the probability of an anomaly at the implantation site (e.g., confidence value), the type of anomaly, etc. In any case, the computing device 2 may determine that the first set of data items contains image data (e.g., anomaly determination, etc.).

[0075] Additionally, the computing device 2 can determine a second set of data items based on a second sub-session of the interactive session. In this case, the second set of data items may differ from the first set of data items. This is because the second sub-session includes a sub-session configured to obtain complementary or supplementary data related to the first sub-session, rather than serving as a copy of the first sub-session. For illustration, the second set of data items may include one or more of the following: query data obtained from the medical device 17 (e.g., IMD 6), one or more physiological parameters of the patient 4, and / or user input data. In such instances, the computing device 2 can determine an abnormality corresponding to at least one of the patient or IMD based at least in part on the first set of data items and the second set of data items. In one instance, the first set of data items and the second set of data items may indicate various abnormal states. Abnormal states may include device migration, potential infection, healing abnormalities, physiological parameter abnormalities, device parameter abnormalities, patient input indicating sensory abnormalities, etc. Additionally, abnormal states may include healing granulation tissue around the implantation site edge, discharge from the implantation site, inflammation at the implantation site, tissue erosion at or around the implantation site, etc. Therefore, the abnormality corresponding to the patient 4 or IMD 6 may include an abnormality determination based on various abnormal states observed from various data items.

[0076] In one example, computing device 2 can determine ECG changes that indicate device migration and thus increase the likelihood of detecting potential abnormalities from image data, based on physiological parameters obtained through a second sub-session. In this case, computing device 2 can analyze the image data using biases against abnormality detection, or it can include in the post-implantation report a probability (e.g., probability, confidence interval) based on the increased likelihood of potential abnormalities determined according to a first set of data items and a second set of data items. Computing device 2 can output a post-implantation report for the interactive session. In an illustrative example, the post-implantation report may include indications of abnormalities and / or indications of the amount of time that has occurred since the IMD was implanted.

[0077] In some instances, computing device 2 may include a programming head or paddle (not shown). In such instances, computing device 2 can engage with medical device 6 via the programming head. The programming head may be placed close to the patient 4's body near medical device 6 (e.g., near the implantation site of IMD 6). Computing device 2 may include the programming head to improve the quality or security of communication between computing device 2 and medical device 6. Additionally, computing device 2 may include the programming head to improve the quality or security of communication between computing device 2, medical device 6, and / or edge device 12.

[0078] exist Figure 1In illustrative and non-limiting examples, the medical device 6 includes at least one IMD. In such examples, at least one IMD can be implanted outside the chest cavity of the patient 4 (e.g., subcutaneously). Figure 1 (The location of the pectoral muscles shown in the image).

[0079] In some instances, the medical device 6 may be positioned near the pectoral muscles at or just below the level of the patient 4's heart, for example, at least partially within the heart's outline. As used herein, the IMD may include, is, or is a subset of: various devices or integrated systems, such as, but not limited to, implantable cardiac monitors (ICMs), implantable pacemakers, including those for delivering cardiac resynchronization therapy (CRT), implantable cardioverter defibrillators (ICDs), diagnostic devices, cardiac devices, etc. In some instances, the tools of this disclosure may be configured to monitor the function of implants other than CIEDs or the user's adaptation to said implants, such as spinal cord stimulators, deep brain stimulators, gastric stimulators, urinary tract stimulators, other neurostimulators, orthopedic implants, respiratory monitoring implants, etc.

[0080] In some instances, medical device 6 may include one or more CIEDs. In some instances, patient 4 may interact with multiple medical devices 6 simultaneously. In an illustrative example, patient 4 may have multiple IMDs implanted within patient 4's body. In another instance, medical device 6 may include a combination of one or more implantable and / or non-implantable medical devices. Examples of non-implantable medical devices include wearable devices (e.g., monitoring watches, wearable defibrillators, etc.) or any other external medical device configured to obtain physiological data from patient 4.

[0081] In some instances, medical device 6 may include diagnostic medical devices. In one instance, medical device 6 may include a device for predicting heart failure events or detecting worsening heart failure in patient 4. In non-limiting and illustrative instances, system 100 may be configured to measure impedance fluctuations in patient 4 and process impedance data to accumulate evidence of worsening heart failure. In any case, medical device 6 may be configured to determine a health condition associated with patient 4. Medical device 6 may transmit diagnostic data or health status as query data to computing device 2, such that computing device 2 may correlate the query data with image data to determine whether an abnormality (e.g., infection at the implantation site) exists in either medical device 6 (e.g., IMD) or a specific patient 4.

[0082] In some instances, the medical device 6 can operate as a therapy delivery device. For example, the medical device can deliver electrical signals to the heart of the patient 4, such as an implantable pacemaker, cardioverter-defibrillator, and / or defibrillator; a drug delivery device that delivers therapeutic substances to the patient 4 via one or more catheters; or a therapy device that delivers both electrical signals and therapeutic substances. As described herein, the computing device 2 can determine various interactive sessions or at least some aspects of interactive sessions (e.g., program programs, UI programs, etc.) based on the type of medical device implanted in the patient 4 or based on the patient 4's identification information.

[0083] It should be noted that while some example medical devices 6 are described as being configured to monitor cardiovascular health, the technology disclosed herein is not limited thereto, and those skilled in the art will understand that the technology disclosed herein can be implemented in other settings (e.g., neurological, orthopedic, etc.). In some instances, one or more of the medical devices 6 may be configured to perform deep brain stimulation (DBS), spinal cord stimulation (SCS), pelvic stimulation, peripheral nerve stimulation, muscle stimulation, etc.

[0084] Furthermore, while some example medical devices 6 are described as insertable or implantable devices, the technology disclosed herein is not limited thereto, and those skilled in the art will understand that the technology of this disclosure can be implemented with medical devices 6 that are not configured to be insertable or implantable, such as wearable devices or other external medical devices. In a non-limiting example, medical device 6 may include a wearable device (e.g., a smartwatch, a headband, etc.) configured to acquire physiological data (e.g., activity data, heart rate, etc.) and transmit such data to computing device 2, network 10, edge device 12, etc., according to one or more of the various technologies of this disclosure for subsequent use.

[0085] Furthermore, while some example medical devices 6 are described as electrical or electrically active devices, the technology disclosed herein is not limited thereto, and those skilled in the art will understand that in some instances, medical device 6 may include non-electrical or non-electrically active devices (e.g., orthopedic implants, etc.). In any case, medical device 6 may be configured to transmit medical data to computing device 2, such as via telemetry protocols, radio frequency identification (RFID) transmission, etc. Thus, any medical device and / or computing device configured to transmit medical data may be configured to implement the technology disclosed herein.

[0086] In some instances, the medical device 6 can be implanted subcutaneously into the patient 4. Furthermore, in some instances, the computing device 2 can monitor the subcutaneous impedance value obtained from the medical device 6. In some instances, at least one of the medical devices 6 employs Reveal LINQ. TMInsertable cardiac monitor (ICM) or similar devices such as the LINQ developed by Medtronic, Inc. of Minneapolis, Minnesota. TM A version or modified form of ICM. In such instances, the medical device 6 can facilitate relatively long-term monitoring of patients during normal daily activities.

[0087] In non-limiting instances, the medical device 6 may include an IMD configured to operate as a pacemaker, cardioverter and / or defibrillator, or otherwise monitor the electrical activity of the heart of patient 4. In some instances, the medical device 6 may deliver pacing pulses to the heart of patient 4 based on electrical signals sensed within the heart of patient 4.

[0088] In some instances, the medical device 6 can also deliver defibrillation therapy and / or cardioversion therapy via electrodes positioned on at least one lead and / or housing electrode. The medical device 6 can detect cardiac arrhythmias in the heart of the patient 4, such as ventricular fibrillation, and deliver defibrillation therapy to the heart of the patient 4 in the form of electrical pulses. In some instances, the medical device 6 can be configured to deliver a series of therapies, such as pulses with increasing energy levels, until the fibrillation in the heart of the patient 4 stops. In such instances, the medical device 6 can employ one or more fibrillation detection techniques known in the art to detect fibrillation.

[0089] In some instances, system 100 may be implemented in an environment that includes network 10 and / or edge device 12. That is, in some instances, system 100 may operate in the environment of network 10 and / or include one or more edge devices 12. In some cases, network 10 may include edge device 12. Similarly, computing device 2 may include the functionality of edge device 12 and therefore may also be used as an edge device among edge devices 12.

[0090] In some instances, edge device 12 includes a modem, router, Internet of Things (IoT) device or system, smart speaker, screen-enhanced smart speaker, personal assistant device, etc. Additionally, edge device 12 may include user-facing devices or client devices, such as smartphones, tablets, personal digital assistants (PDAs), and other mobile computing devices.

[0091] In instances involving network 10 and / or edge device 12, system 100 can be implemented in a home environment, a hospital environment, or any environment that includes network 10 and / or edge device 12. Example technologies can be used with medical device 6, which can be used with one or more edge devices 12 and... Figure 1 Other devices not described herein (e.g., web servers) communicate wirelessly.

[0092] In some instances, computing device 2 may be configured to communicate with one or more of medical device 6, edge device 12, or network 10, said network operating as those developed by Medtronic Corporation of Minneapolis, Minnesota. Network services such as the internet. In some instances, medical device 6 can... Communicates with computing device 2. In some cases, network 10 may include one or more edge devices among edge devices 12. Network 10 may be and / or include any suitable network, including private networks, personal area networks, intranets, local area networks (LANs), wide area networks, wired networks, satellite networks, cellular networks, peer-to-peer networks, global networks (e.g., the Internet), cloud networks, edge networks, etc. Device networks or combinations thereof, some or all of which may or may not be connected to and / or originate from the Internet. That is, in some instances, network 10 includes the Internet. In an illustrative example, computing device 2 may periodically transmit and / or receive various data items to and / or from one of medical device 6 and / or edge device 12 via network 10.

[0093] Additionally, the computing device 2 can be configured to connect to a cellular base station transceiver (e.g., for 3G, 4G, LTE, and / or 5G cellular network access) and Wi-Fi. TM Access points, because these connections are available. In some instances, cellular base station transceivers may have access to network 10. These various cellular and Wi-Fi... TM Network connectivity may be managed by different third-party entities, which are referred to herein as “carriers”.

[0094] In some instances, system 100 may include one or more databases (e.g., storage device 96) that store various medical data records, group data, image data. In such instances, server 94 (e.g., one or more databases) may be managed or controlled by one or more separate entities (e.g., Internet service provider (ISP) etc.).

[0095] The computing device 2 and / or edge device 12 can be used to configure the operating parameters of the medical device 6. In some instances, the user can use the computing device 2 as a programmer to program measurement parameters, stimulation programs, etc. The computing device 2 can also be configured to program the therapy process, select electrodes to deliver defibrillation pulses, select waveforms for defibrillation pulse or stimulation pulse sequences, select or configure fibrillation detection algorithms, etc. The user can also use the computing device 2 to program aspects of other therapies that can be provided by the medical device 6, such as cardioversion or pacing therapy. In some instances, the user can activate certain features of the medical device 6 by entering a single command via the UI 22 of the computing device 2, such as pressing a single key or combination of keys on the keypad or performing a single-point selection action using a pointing device. In addition, the computing device 2 can operate the interactive session of this disclosure, wherein the interactive session is loaded with programming parameters. The computing device 2 can use such data to determine physiological parameters and / or query data that deviates from the expected values ​​expected by the programming parameters. The computing device 2 can utilize an AI engine and / or an ML model to determine such deviations (e.g., anomalies), wherein the AI ​​engine and / or ML model can be trained based on programming parameters and anomalous data to determine the correlation between such data items.

[0096] In some instances, computing device 2 can be configured to retrieve data from medical device 6. The retrieved data may include values ​​of physiological parameters measured by medical device 6, signs of arrhythmias or other illnesses detected by medical device 6, and physiological signals obtained by medical device 6. In some instances, computing device 2 can retrieve cardiac EGM segments recorded by computing device 2, for example, because computing device 2 determines that an arrhythmia or other illness occurred during said segment, or in response to a request from patient 4 or another user to record said segment.

[0097] In some instances, the user can also use computing device 2 to retrieve information about other sensed physiological parameters of the patient 4, such as activity or posture, from medical device 6. In some instances, edge device 12 can interact with medical device 6 in a manner similar to computing device 2, for example, to program medical device 6 and / or retrieve data from medical device 6.

[0098] System 100, such as the processing circuitry of medical device 6, computing device 2, edge device 12, and / or one or more other computing devices (e.g., remote servers), can be configured to perform the example techniques of this disclosure to determine abnormal states of patient 4 and / or IMD 6 components. In some cases, the processing circuitry system may be referred to herein as a processor system or processing circuitry system. In some instances, the processing circuitry system of system 100 acquires physiological parameters, images, medical device diagnostics, etc., to determine whether to provide an alert to patient 4 and / or HCP.

[0099] In some instances, when patient health data (e.g., images of the implantation site, ECG parameters, etc.) and medical device diagnostic data are combined, system 100, such as the processing circuitry of computing device 2, provides an alert to patient 4 and / or other users, indicating the onset of an abnormality. The alert may be an audible alert generated by medical device 6 and / or computing device 2, a visual alert generated by computing device 2 such as a text prompt or a flashing button or screen, or a tactile alert generated by medical device 6 and / or computing device 2 such as vibration or a vibration pattern. Furthermore, alerts may be provided to other devices, for example, via network 10. Several different levels of alerts may be used based on the severity of the potential infection detected according to one or more of the various techniques disclosed herein.

[0100] In some instances, when patient health data (e.g., images of the implantation site, ECG parameters, etc.) and medical device diagnostic data are combined, system 100, such as the processing circuitry of computing device 2, provides an alert to patient 4 and / or other users, indicating the onset of an abnormality. The process of determining when to issue an alert to patient 4 involves measuring the abnormality (e.g., severity or probability level) against one or more thresholds, as described in more detail below. The alert may be an audible alert generated by medical device 6 and / or computing device 2, a visual alert generated by computing device 2 such as a text prompt or a flashing button or screen, or a tactile alert generated by medical device 6 and / or computing device 2 such as vibration or a vibration pattern. Furthermore, alerts may be provided to other devices, for example, via network 10. Several different levels of alerts may be used based on the severity of the potential abnormality detected by the techniques disclosed herein.

[0101] Figure 2 This is a block diagram illustrating an example configuration of at least one component of a computing device 2. Figure 2 In one example, at least one computing device 2 includes a processing circuit system 20, a communication circuit system 26, a storage device 24, and a UI 22.

[0102] The processing circuitry system 20 may include one or more processors configured to implement functions and / or processing instructions for execution within the computing device 2. For example, the processing circuitry system 20 may be capable of processing instructions stored in the storage device 24. The processing circuitry system 20 may include, for example, a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a complex programmable logic device (CPLD), or an equivalent integrated or discrete logic circuitry system, or a combination of any of the foregoing devices or circuitry systems. Therefore, the processing circuitry system 20 may include any suitable structure, whether in hardware, software, firmware, or any combination thereof, for performing the functions attributed herein to the processing circuitry system 20.

[0103] The trained ML model 30 and / or AI engine 28 can be configured to process and analyze user input (e.g., images of the implantation site, patient status data, etc.), device parameters (e.g., accelerometer data), historical data of the medical device (e.g., medical device 6), and / or physiological parameters, according to certain instances of ML models considered advantageous in this disclosure (e.g., predictive modeling, inference detection, context matching, natural language processing, etc.). Instances of ML models and / or AI engines that can be configured to perform aspects of this disclosure include classifier and non-classifier ML models, artificial neural networks (“NN”), linear regression models, logistic regression models, decision trees, support vector machines (“SVM”), naive or non-naive Bayesian networks, k-nearest neighbor (“KNN”) models, deep learning (DL) models, k-means models, clustering models, random forest models, or any combination thereof. Depending on the implementation, the ML model can be supervised, unsupervised, or, in some cases, a combination of both (e.g., semi-supervised). These models can be trained based on data instructing how a user (e.g., patient 4) interacts with computing device 2. For example, for illustrative purposes only, events or behaviors (such as clicking, viewing, or watching) related to items (e.g., wound images, cameras, videos, physiological parameters, etc.) will be used to describe certain aspects of this disclosure. In another instance, these models and engines can be trained to synthesize data to identify anomalies in patient 4 or medical device 17, and to identify anomalies in patient 4 or medical device 17 based on individual data items.

[0104] In a non-limiting instance, patient 4 may have difficulty capturing images of the implantation site from various angles. This useful data can be shared in health monitoring or computational networks to present optimal results to more than one user based on similar queries and user responses to those queries. For brevity, these aspects may not be described in terms of events or behaviors related to objects (e.g., data objects, such as search strings). In some instances, processing circuitry system 40 may use ML algorithms (e.g., DL algorithms) for example, targeting the implantation site of one of the medical devices 17, to monitor the progress of a healing wound or predict potential infections. In an illustrative and non-limiting instance, AI engine 28 and / or ML model 30 may utilize deep neural networks to locate the implantation site in an image and classify abnormal states. In another instance, AI engine 28 and / or ML model 30 may utilize Naive Bayes and / or decision trees to synthesize (e.g., combine) data items and their analyses (e.g., image analysis and ECG analysis) to obtain a comprehensive anomaly determination for patient 4 and include such a comprehensive determination in reports such as those for patient 4.

[0105] In another instance, AI engine 28 and / or ML model 30 may be loaded with group parameters (e.g., age groups, IMD type groups, skin pigmentation groups, etc.) and combinations of group parameters and trained based on said group parameters. In such instances, AI engine 28 and / or ML model 30 may utilize historical reference queries used for comparison when determining deviations from baseline parameters.

[0106] In addition, depending on various environments and other resource constraints (e.g., processing power, network access, battery life, etc.), computing device 2 can utilize different image processing algorithms and / or data synthesis algorithms, such as AI, ML, DL, digital signal processing, neural networks and / or other technologies.

[0107] In some instances, AI engine 28 can be trained to analyze a patient's gait in the presence of orthopedic implants (e.g., by comparing video data representing the patient with group gait information). In such instances, computing device 2 can deploy AI engine 28 and / or ML model 30 to analyze patient activity to determine the presence of potential anomalies in patient 4 and / or medical device 17 (e.g., IMD 6), such as when the patient's gait is anomalous for AI engine 28 and / or ML model 30, and / or when the patient's gait changes over time to indicate a development or sudden abnormality in patient 4.

[0108] Furthermore, the trained AI engine 28 can be used to learn about patient 4 and their implantation site over time. In this way, the AI ​​engine 28 can provide personalized detection algorithms for detected abnormalities at specific implantation sites. In such instances, the AI ​​engine 28 can be loaded with and trained based on group parameters, using historical reference queries or image comparisons. In this way, the computing device 2 can use different algorithmic approaches (e.g., AI, ML, DL, digital signal processing, neural networks, and / or other techniques) to provide solutions for personalizing the site examination process for patient 4.

[0109] Users such as clinicians or patients can interact with one or more computing devices in computing device 2 through UI 22. UI 22 includes a display (not shown), such as a liquid crystal display (LCD) or a light-emitting diode (LED) display or other type of screen, through which processing circuitry 20 can present health or device-related information, such as cardiac EGM, indications of impedance changes, temperature changes, etc. Additionally, UI 22 may include an input mechanism for receiving input from the user. The input mechanism may include, for example, buttons, a keypad (e.g., an alphanumeric keypad), a peripheral pointing device, a touchscreen, or another input mechanism that allows the user to navigate and input through UI 22 presented by processing circuitry 20 of computing device 2. In one example, UI 22 may allow the user to use the touchscreen of computing device 2 to rotate images and adjust zoom levels (e.g., pinch zoom, gestures, eye tracking, etc.). Furthermore, UI 22 may allow the user to control camera parameters, such as selecting a front or rear camera, lighting, zoom level, focus level, contrast, etc., allowing the user to capture images according to the camera parameters. In another instance, computing device 2 can automatically adjust such parameters with or without initial input from the user.

[0110] In some instances, computing device 2 may include an imaging device. In illustrative examples, computing device 2 may include camera 32 or more cameras 32 (e.g., digital cameras), such as imaging devices. Figure 2 As shown, camera 32 can refer to an assembly of one or more image sensors 34, one or more lenses 36, and one or more camera processors 38 (e.g., an image signal processor). In some instances, processing circuitry system 20 may include camera processor 38.

[0111] In some instances, computing device 2 may include an imaging device, such as camera 32. Camera 32 may be a digital camera built into computing device 2. In some instances, camera 32 may be separate from computing device 2. In such instances, camera 32 may transmit imaging data to computing device 2 and / or other computing devices (e.g., edge device 2). In some instances, computing device 2 may include a charge-coupled device (CCD) chip. The CCD chip may be configured to operate in a spectral response analysis mode using a flash lamp as an excitation (e.g., white light) source. In such instances, computing device 2 may employ the CCD chip to analyze images of the implantation site. In one instance, computing device 2 may employ the CCD chip to provide individual color filtering analysis at different light wavelengths to better detect redness and swelling in different skin tones. That is, computing device 2 may perform color filtering on images to identify anomalies from one or more images. In another instance, computing device 2 may perform color filtering on images to identify anomalies from one or more images. In an illustrative example, the computing device 2 may perform a region comparison of a body region according to one or more of the various techniques of this disclosure to distinguish the implantation site from another region of the body and to use for different skin types (e.g., skin color).

[0112] In some instances, the computing device 2 can use a camera 32 to image the implantation site of the patient 4. In such instances, the storage device 24 of the computing device 2 can store image data (e.g., still images, etc.). In this case, processing circuitry systems, such as the processing circuitry system 20 of the computing device 2 and / or the processing circuitry system 64 of the edge device 12 ( Figure 3 It can communicate with storage device 24.

[0113] In some instances, multiple cameras 32 may be contained within a single computing device 2 (e.g., a mobile phone having one or more front-facing cameras and one or more rear-facing cameras). In some instances, computing device 2 may include a first camera 32 having one or more image sensors 34 and one or more lenses 36, and a second camera 32 having one or more image sensors 34 and one or more lenses 36, etc. It should be noted that while some example techniques herein may be discussed with reference to frames received from a single camera (e.g., from a single image sensor), the techniques disclosed herein are not limited thereto, and those skilled in the art will understand that the techniques disclosed herein can be implemented for any type of camera 32 and combination of camera 32, such as combinations of cameras 32 that may be contained in computing device 2 or otherwise communicatively coupled to computing device 2. In some instances, image sensor 34 refers to one or more image sensors 34 that may contain an image sensor processing circuitry system. In some instances, image sensor 34 includes an array of pixel sensors (e.g., pixels) for capturing a representation of light.

[0114] Although shown (e.g., by dashed lines) as optionally included in computing device 2, the techniques of this disclosure are not limited thereto, and in some cases, camera 32 may be separate from computing device 2, such as a stand-alone camera device or a separate camera system. In any case, camera 32 may be configured to capture images of the implantation site and transmit the image data to processing circuitry system 20 via camera processor 38. In some instances, camera 32 may be configured to implement various scaling levels. In one instance, camera 32 may be configured to perform cropping and / or scaling techniques to achieve a specific scaling level. In some instances, camera 32 may be configured to manipulate the output from image sensor 34 and / or manipulate lens 36 to achieve a specific scaling level.

[0115] In some instances, computing device 2 may include an audio circuitry (not shown) for providing sound notifications, instructions, or other sounds to the user and for receiving voice commands from the user, or both. In some instances, computing device 2 may provide sound notifications instructing the user on the direction of the UI 22 and / or virtual registration process. Additionally, computing device 2 may provide sound notifications indicating when a task has been completed, such as an authentication task (e.g., successful login), an ECG measurement task, or any other task. In another instance, computing device 2 may provide different sound notifications based on specific outcomes. In one instance, computing device 2 may provide a static notification when the outcome of an interactive session indicates that no further appointment is needed (e.g., no potential infection, device operation is correct, physiological parameters are good, etc.), while a louder notification may be provided when the outcome of the interactive session suggests a further appointment. In one instance, computing device 2 may provide a sound notification when the possibility of one or more anomalies is identified. In another instance, computing device 2 may provide a sound notification after identifying a collective anomaly (e.g., after data synthesis). In an illustrative example, computing device 2 can determine collective abnormalities based on potential abnormalities identified at the implantation site and abnormalities based on physiological parameters (e.g., ECG abnormalities). In some cases, when no abnormality is identified in one sub-session (e.g., implantation site abnormality) but an abnormality is identified in another sub-session (e.g., IMD abnormality), computing device 2 can still determine the presence of potentially health-threatening abnormalities, such that analysis of at least two sub-sessions indicates the presence or absence of an abnormality requiring subsequent appointment recommendations. Furthermore, computing device 2 can provide different audio notifications after each sub-session and then provide different audio notifications again after all prohibited sub-sessions (e.g., two sub-sessions, three sub-sessions, etc.) have been completed.

[0116] The communication circuitry 26 may include any suitable hardware, firmware, software, or any combination thereof for communicating with another device, such as the medical device 6. Under the control of the processing circuitry 20, the communication circuitry 26 can receive downlink telemetry from the medical device 6 or the other device, and send uplink telemetry to it. The communication circuitry 26 may be configured to communicate via inductive coupling, electromagnetic coupling, NFC, RF communication, etc. Wi-Fi TM Or other proprietary or non-proprietary wireless communication schemes to transmit or receive signals. The communication circuit system 26 can also be configured to communicate with devices other than the medical device 6 via any of a variety of wired and / or wireless communication and / or network protocols. In some instances, the computing device 2 can communicate via scanning (e.g., TelC, TelB, TelM, etc.). (etc.) to perform telemetry selection.

[0117] Storage device 24 can be configured to store information within computing device 2 during operation. Storage device 24 may comprise a computer-readable storage medium or a computer-readable storage device. In some instances, storage device 24 comprises one or more of short-term memory or long-term memory. Storage device 24 may comprise, for example, read-only memory (ROM), random access memory (RAM), non-volatile RAM (NVRAM), dynamic RAM (DRAM), static RAM (SRAM), magnetic disk, optical disk, flash memory, various forms of electrically erasable programmable ROM (EEPROM) or erasable programmable ROM (EPROM), or any other digital media.

[0118] In some instances, storage device 24 is used to store data indicating instructions executed by processing circuitry system 20. Additionally, storage device 24 may store image data and / or supplementary image data. In some instances, storage device 24 may store image data frames. That is, storage device 24 may store one or more images. In some instances, storage device 24 may store one or more images of the patient 4's body (e.g., images of the implantation site, skin images for skin color analysis, skin surface near the lead wire, etc.), images of physiological parameters (e.g., ECG images), etc. Storage device 24 may be used by software or applications running on computing device 2 to temporarily store information during program execution. Storage device 24 may also store historical medical device data, historical patient data, time-series information (e.g., number of days after IMD implantation, number of days after a specific physiological parameter exceeds a certain threshold, etc.), AI and / or ML training sets, image data, etc.

[0119] The data exchanged between computing device 2, edge device 12, network 10, and medical device 6 may include operating parameters of medical device 6. Computing device 2 may transmit data containing computer-readable instructions to medical device 6. Medical device 6 may receive and execute these computer-readable instructions. In some instances, when implemented by medical device 6, the computer-readable instructions may control medical device 6 to change one or more operating parameters, export collected data, etc. In an illustrative example, processing circuitry system 20 may transmit instructions to medical device 6 requesting it to export collected data (e.g., ECG, impedance values, etc.) to computing device 2, edge device 12, and / or network 10. Computing device 2, edge device 12, and / or network 10 may then receive the collected data from medical device 6 and store it, for example, in storage device 24. Additionally, processing circuitry system 20 may transmit query instructions to medical device 6 requesting it to output operating parameters (e.g., battery level, impedance, pulse width, pacing percentage, etc.).

[0120] In some instances, the computing device 2 may be coupled to an external electrode or to an implantable electrode via a percutaneous lead. In such instances, according to one or more techniques disclosed herein, the computing device 2 may receive and monitor physiological parameters, ECG, etc., from the medical device 6.

[0121] exist Figure 2 In the examples shown herein, the processing circuitry 20 is configured to perform various techniques described herein, such as those described in the references. Figure 5-22 The described techniques. To avoid confusion, the processing circuit system 20 is described as performing various processing techniques prohibited by the computing device 2, but it should be understood that at least some of these techniques can also be performed by other processing circuit systems (e.g., the processing circuit system 40 of the medical device 17). Figure 4 The processing circuitry system 20 (such as the processing circuitry system 98 of server 94, the processing circuitry system 64 of edge device 12, etc.) executes the commands. In an illustrative example, the processing circuitry system 20 may capture images of the implantation site, obtain other data items, output images and / or other data items to an analysis platform for infection detection, determine the presence of potential abnormalities (e.g., infection) based on images and other data items, output a summary of the implantation status containing information on potential abnormalities, and in some cases, transmit the summary of the implantation status containing information on potential infection to another device. In this example, the analysis platform may be a separate program executed by the processing circuitry system 20. In another example, the analysis platform may be a separate program executed alternatively by other processing circuitry systems from the processor system.

[0122] Figure 3 This is a block diagram illustrating an example system 300 comprising one or more example computing devices 2, one or more medical devices 17, a network 10, one or more edge devices 12, and one or more servers 94, according to one or more technologies disclosed herein. In some instances, system 300 is referenced... Figure 1 The described system 100 is an example. In another example, system 300 illustrates an example network system of the managed monitoring system 100. In some instances, the medical device 17 may be... Figure 1 An example of medical device 6. That is, medical device 17 can include IMD, CIED, etc., similar to the reference. Figure 1 As described. Additionally, medical device 17 may include non-implantable medical devices, including wearable medical devices (e.g., smartwatches, wearable defibrillators, etc.).

[0123] Medical device 17 can be configured to transmit data, such as sensed, measured, and / or determined values ​​of physiological parameters (e.g., heart rate, impedance measurement results, fluid index, respiratory rate, activity data, electrocardiogram (EGM), historical physiological data, blood pressure values, etc.) to edge device 12, computing device 2, and / or access point (e.g., gateway). In some instances, medical device 17 can be configured to determine multiple physiological parameters. For example, medical device 17 may include medical device 6 (e.g., IMD) configured to determine respiratory rate values, subcutaneous tissue impedance values, EGM values, etc. The edge device 12 and / or access point device can then transmit the retrieved data to server 94 via network 10.

[0124] In some instances, medical device 17 can transmit data to server 94, edge device 12, or computing device 2 via wired or wireless connections. For example, server 94 can receive data from medical device 17 (e.g., IMD 6, wearable device, etc.) or from edge device 12. In another instance, edge device 12 can receive data from server 94 via network 10. In some instances, edge device 12 can receive data from medical device 17 via network 10 or via wired or wireless connections. In such instances, edge device 12 can determine the data received from server 94, medical device 17, or computing device 2. In some instances, edge device 12 can store the data in its internal storage device 62. The processing circuitry system 64 of edge device 12 may also include an AI engine and / or ML models, as referenced. Figure 2 Describes the AI ​​engine and ML model.

[0125] In this example, medical device 17 can communicate with one of the edge devices 12 via a first wireless connection using communication circuitry 42. In some examples, medical device 17 can communicate with an access point via a second wireless connection using communication circuitry 42. The access point can include a device connected to network 10 via any of a variety of connections such as dial-up, digital subscriber line (DSL), or cable modem connections. In some examples, the access point can be coupled to network 10 via different forms of connections including wired or wireless connections. In some examples, one of the computing devices 2 can be used as an access point for network 10. For example, a user device such as a tablet computer or smartphone can be located in the same location as the patient 4 and can be configured to act as an access point. In any case, computing device 2, edge device 12, and server 94 are interconnected and can communicate with each other via network 10.

[0126] Medical device 17, edge device 12, and / or computing device 2 may be configured to communicate with remote computing resources (e.g., server 94) over network 10 via various connections. The data network (e.g., network 10) may be implemented by server 94 (e.g., data server, deletion server, analysis server, etc.). In one instance, server 94 may include a data server configured to store data and / or perform calculations based on said data. In another instance, server 94 may include a data server configured to store data (e.g., a database) according to one or more of the various techniques disclosed herein and to send the data to another server within server 94 for data analysis, image processing, or other data calculations. In some instances, server 94 may be implemented on one or more host devices, such as blade servers, mid-range computing devices, mainframes, desktop computers, or any other computing devices configured to provide computing services and resources. Protocols and components used for communication over the Internet or any of the above-described types of communication networks are known to those skilled in the art of computer communications and therefore do not require further description herein.

[0127] In some instances, one or more medical devices in medical device 17 may serve as or contain server 94. That is, medical device 17 may contain sufficient storage capacity or processing power to perform the techniques disclosed herein on a single medical device in medical device 17 or on a network of medical devices 17 coordinating tasks via network 10 (e.g., on a private or closed network). In some instances, one of medical devices 17 may contain at least one server among servers 94. For example, a portable / bedside patient monitor may be configured to serve as one of servers 94, and also as one of medical devices 17 configured to obtain physiological parameter values ​​from patient 4.

[0128] In some instances, server 94 can communicate with each medical device in medical device 17 via a wired or wireless connection to receive physiological parameter values ​​and / or device query data from medical device 17. In non-limiting instances, physiological parameter values ​​and / or device query data can be transmitted from medical device 17 to server 94 and / or edge device 12. Server 94 and / or edge device 12 can perform analysis on the data to determine the presence of abnormalities at the implantation site (e.g., the location of one or more IMD components in the body of patient 4). Server 94 and / or edge device 12 can transmit the analysis results to computing device 2 via a communication circuit system for display and / or further processing.

[0129] In some instances, server 94 can be configured to provide a secure storage location for data collected from medical device 17, edge device 12, and / or computing device 2. In some cases, server 94 may include a database storing medical and health-related data. For example, server 94 may include a cloud server or other remote server storing data collected from medical device 17, edge device 12, and / or computing device 2. In some cases, server 94 may use computing device 2 to compile data into web pages or other documents for viewing by trained professionals such as clinicians. Figure 3 In the example shown, server 94 includes storage device 96 (e.g., for storing data retrieved from medical device 17) and processing circuitry 98. (See reference...) Figure 2 As described, computing device 2 may similarly include storage devices and processing circuitry.

[0130] Processing circuitry system 98 may include one or more processors configured to implement functions and / or processing instructions for execution within server 94. For example, processing circuitry system 98 may be capable of processing instructions stored by storage device 96. Processing circuitry system 98 may include, for example, a microprocessor, DSP, ASIC, FPGA, or equivalent integrated or discrete logic circuitry system, or a combination of any of the foregoing devices or circuitry systems. Therefore, processing circuitry system 98 may include any suitable structure, whether in hardware, software, firmware, or any combination thereof, for performing the functions attributed herein to processing circuitry system 98. The processing circuitry system 98 of server 94 and / or the processing circuitry system of computing device 2 may implement any of the techniques described herein to analyze physiological parameters received from medical device 17, for example, to determine the healing progress of patient 4 or the health of medical device 17.

[0131] Storage device 96 may comprise a computer-readable storage medium or a computer-readable storage device. In some instances, storage device 96 comprises one or more of short-term memory or long-term memory. Storage device 96 may comprise, for example, ROM, RAM, NVRAM, DRAM, SRAM, magnetic disk, optical disk, flash memory, various forms of EEPROM or EPROM, or any other digital media. In some instances, storage device 96 is used to store data indicating instructions to be executed by processing circuitry system 98.

[0132] In some instances, one or more computing devices in computing device 2 may be tablets or other smart devices placed by a clinician (or other HCP), through which the clinician can program medical device 17, receive alerts from medical device 17, and / or query medical device 17. For example, the clinician can access data collected by medical device 17 through computing device 2, such as the status of medical conditions used to check when patient 4 is between clinician visits. In some instances, computing device 2 can transmit data about images, infection or other abnormality indicators, training sets, ML models, IMD information, patient identification data, authentication data, etc., to one or more other computing devices 2, edge devices 12, and / or servers 94. Similarly, computing device 2 can receive similar information.

[0133] In another instance, computing device 2 can generate an alert to patient 4 based on anomalies determined by a combination of data items (or forward an alert determined by medical device 17, edge device 12, or server 94), which could allow patient 4 to proactively seek medical help before receiving instructions for medical intervention. Figure 3 In the example shown, server 94 includes storage device 96 (e.g., for storing data retrieved from medical device 17) and processing circuitry 98. (See reference...) Figure 2 As described, computing device 2 may similarly include storage devices and processing circuitry.

[0134] In some instances, a clinician can input instructions for medical intervention for patient 4 into an application executed by computing device 2, such as based on the status of the patient's condition determined by another of computing device 2, medical device 17, edge device 12, server 94, or any combination thereof, or based on other patient data known to the clinician. The patient's condition may include implant status, such as potential infection at the implantation site. The user's computing device 2 can receive instructions via network 10. Computing device 2 can then display a message instructing the medical intervention on a display device.

[0135] In some instances, one of the computing devices 2 can transmit instructions for medical intervention to another computing device within the computing device 2, located by the patient 4 or the patient 4's caregiver. For example, such instructions for medical intervention could include changes to medication dosage, timing, or selection, scheduling a clinician visit, or seeking medical assistance. In this way, the patient 4 can be authorized to take action as needed to address their medical condition, which could help improve the patient 4's clinical outcomes.

[0136] Figure 4This is a functional block diagram illustrating an example configuration of one or more medical devices in a medical device 17 according to one or more technologies disclosed herein. In the illustrated example, medical device 17 includes a processing circuitry 40, a storage device 50, and a communication circuitry 42. Additionally, in some embodiments, medical device 17 may include one or more electrodes 16, an antenna 48, a sensing circuitry 52, a switching circuitry 58, a sensor 62, and a power supply 56. As previously described, medical device 17 may be... Figure 1 One example of medical device 6. That is, medical device 17 may include IMD, CIED, etc., similar to the reference. Figure 1 The medical device 6 shown and described. In another example, the medical device 17 may include a non-implantable medical device, such as a wearable medical device, a medical workstation cart, etc.

[0137] In some instances, one of the medical devices 17 may be a medical device implanted in the patient 4, while another medical device in the medical device 17 may include a camera 32, and thus may perform one or more of the various techniques of this disclosure. That is, according to one or more of the various techniques of this disclosure, one of the medical devices 17 may capture images of the patient 4's body (e.g., the implantation site of the patient 4) via the camera 32.

[0138] Processing circuitry system 40 may include fixed-function circuitry systems and / or programmable processing circuitry systems. Processing circuitry system 40 may include any one or more microprocessors, controllers, DSPs, ASICs, FPGAs, or equivalent discrete or analog logic circuitry systems. In some instances, processing circuitry system 40 may include any combination of multiple components, such as one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, or one or more FPGAs, as well as other integrated or discrete logic circuitry systems. The functionality attributed herein to processing circuitry system 40 may be embodied in software, firmware, hardware, or any combination thereof.

[0139] In some instances, the processing circuit system 40 may include an AI engine 44 and / or an ML model 46. The AI ​​engine 44 and the ML model 46 may be similar to the reference... Figure 2 The AI ​​engines and ML models described. In one instance, ML model 46 may contain one or more DL models, which are trained, for example, on various physiological parameter data such as ECG data.

[0140] exist Figure 4In the non-limiting examples shown, medical device 17 includes a plurality of electrodes 16A-16N (collectively referred to as “electrodes 16”). In some cases, electrodes 16 may be referred to herein as a plurality of “electrodes 16”, while in other cases, they may be simply referred to as “electrodes 16” where appropriate. Electrodes 16 may be disposed within one body layer of patient 4, while at least one other electrode 16 may be disposed within another body layer of patient 4. In some instances, medical device 17 may sense electrical signals associated with depolarization and repolarization of the heart of patient 4 via electrodes 16.

[0141] In some instances, electrode 16 may be configured to be implanted externally in the chest of patient 4. In some instances, the housing of medical device 17 may be used as an electrode in combination with electrodes positioned on leads. In some instances, medical device 17 may be configured to measure impedance changes, ECG morphological changes, etc., within the interstitial fluid of patient 4. For example, medical device 17 may be configured to receive one or more signals indicating subcutaneous tissue impedance. In some instances, computing device 2 may utilize such information to determine abnormalities in IMD 6, such as device migration abnormalities; computing device 2 may use said information based on obtained images of the implantation site to determine the likelihood of an abnormality (e.g., infection) at the implantation site.

[0142] One or more electrodes of electrode 16 may be coupled to at least one lead. In some instances, medical device 17 may employ electrode 16 to provide sensing and / or pacing functions. Electrode 16 may be configured as unipolar or bipolar. Sensing circuitry 52 may be selectively coupled to electrode 16 via switching circuitry 58, for example, to select electrode 16 and the polarity of a known sensing vector controlled by processing circuitry 40 for sensing impedance and / or cardiac signals. Sensing circuitry 52 may sense signals from electrode 16, for example, to generate cardiac EGM or subcutaneous ECG to monitor the post-implantation status of IMD 6. Sensing circuitry 52 may also monitor signals from sensor 54, which may include one or more accelerometers, pressure sensors, temperature sensors, and / or optical sensors. In some instances, sensing circuitry 52 may include one or more filters and amplifiers for filtering and amplifying signals received from electrode 16 and / or sensor 54. In an illustrative example, the computing device 2 can obtain temperature sensor data from IMD 6 to determine the likelihood of device pocket infection based on the obtained image of the implantation site of IMD 6, since a temperature sensor rise at IMD 6 that occurs before temperature rises at other locations in patient 4 may indicate device pocket infection. In some instances, the computing device 2 can obtain thermal images of the implantation site and / or adjacent areas to compare the thermal images with temperature data and determine the presence of abnormalities at the implantation site, such as locations where a temperature rise at IMD 6 leads to temperature rises at other external locations in patient 4.

[0143] In some instances, the processing circuitry 40 may use the switching circuitry 58, for example via a data / address bus, to select which available electrodes among the available electrodes will be used to obtain various measurement results. The switching circuitry 58 may comprise a switch array, switch matrix, multiplexer, transistor array, microelectromechanical switch, or any other type of switching device suitable for selectively coupling the sensing circuitry 58 to selected electrodes. In some instances, the sensing circuitry 52 comprises one or more sensing channels, each of which may include an amplifier. In response to a signal from the processing circuitry 40, the switching circuitry 58 may couple an output from a selected electrode to one of the sensing channels.

[0144] In some instances, one or more channels of the sensing circuitry 52 may include an R-wave amplifier that receives signals from electrode 16. In some instances, the R-wave amplifier may take the form of an automatic gain control amplifier that provides an adjustable sensing threshold based on the measured R-wave amplitude. Additionally, in some instances, one or more channels of the sensing circuitry 52 may include a P-wave amplifier that receives signals from electrode 16. The sensing circuitry 52 can use the received signals to perform pacing and sensing in the heart of patient 4. In some instances, the P-wave amplifier may take the form of an automatic gain control amplifier that provides an adjustable sensing threshold based on the measured P-wave amplitude. Other amplifiers may also be used. In some instances, the sensing circuitry 52 includes channels comprising amplifiers having a passband relatively wider than that of the R-wave or P-wave amplifiers. Signals from selected sensing electrodes selected for coupling to this broadband amplifier can be provided to a multiplexer and then converted by an analog-to-digital converter (ADC) into multi-bit digital signals for storage in storage device 50. The processing circuitry system 40 can employ digital signal analysis techniques to characterize the digitized signals stored in the storage device 50. In some instances, the processing circuitry system 40 can detect and classify arrhythmias from the digitized electrical signals. In some instances, the computing device 2 can obtain physiological parameters (e.g., arrhythmia data) as part of a set of data items through a physiological parameter sub-session. Additionally, the computing device 2 can obtain device performance parameters, such as amplifier performance, ADC performance, etc., as part of a set of data items including query data items through a device inspection sub-session. According to one or more of the various techniques of this disclosure, the computing device 2 can utilize such data items to elucidate and / or inform the analysis of images of the implantation site.

[0145] In some instances, the medical device 17 may include a measurement circuitry system with an amplifier design configured to switch continuously and in real time between multiple different measurement parameters. Additionally, the medical device 17 may activate the sensing circuitry system 52 and / or the switching circuitry system 58 for short periods to conserve power. In one instance, the medical device 17 may use amplifier circuitry, such as a chopper amplifier, based on certain techniques described in U.S. Application No. 12 / 872,552, entitled “Chopper-stabilized Instrumentation Amplifier for Impedance Measurement,” filed August 31, 2010, by Denison et al.

[0146] In some instances, medical device 17 may operate as a therapy delivery device. In such instances, medical device 17 may include leads. The leads may extend to any location within or near the heart or chest of patient 4. In illustrative and non-limiting instances, one of the medical devices 17 may include a single lead extending from one of the medical devices 17 into the right atrium or right ventricle, or two leads extending into the right atrium and right ventricle, respectively.

[0147] In some instances, one of the medical devices 17 may be configured to include a sensing circuit system such as sensing circuit system 52 and one or more sensors such as sensor 54. Additionally, in some instances, one of the computing devices 2 may also be configured to include a sensing circuit system such as sensing circuit system 52 and one or more sensors such as sensor 54. In one instance, one of the computing devices 2 and / or one of the medical devices 17 may include a heart rate sensor, a pulse sensor, a photoplethysmography (PPG) sensor, a blood oxygen saturation (SpO2) sensor, etc.

[0148] The sensing circuitry system 52 can be implemented in one or more processors, such as in the processing circuitry system 40 of the medical device 17 or in one or more processors of the processing circuitry system 20 of the computing device 2. Figure 4 In this example, the sensing circuitry 52 is shown in conjunction with the sensor 54. Similar to the processing circuitry systems 20, 98, 40, 64 and other circuitry systems described herein, the sensing circuitry 52 may be embodied as one or more hardware modules, software modules, firmware modules, or any combination thereof.

[0149] In some instances, at least one of the medical devices 17 may include sensor devices such as activity sensors, heart rate sensors, wearable devices worn by the patient 4, temperature sensors, chemical sensors, impedance sensors, etc. In some instances, one or more other medical devices 17 may be external devices relative to the patient 4's body or external to the medical device 17 implanted within the patient 4. In any case, the medical devices 17 may be coupled to each other via communication circuitry 42, and in some instances may be coupled to computing devices 2, edge devices 12, etc., in a similar manner. In illustrative and non-limiting examples, computing device 2 may acquire temperature sensor data from the temperature sensor on the IMD 6 board and may correlate such data with image data to predict potential abnormalities. In one instance, computing device 2 may correlate an image with an increased body temperature of the patient 4 or the IMD 6 to determine, for example, the presence of infection at the implantation site. In another instance, computing device 2 may acquire chemical data from a chemical sensor, which may indicate lactate formation and pH changes, key indicators of abnormalities such as infection at the IMD 6 implantation site. The computing device 2 can correlate such data based on, for example, baseline values ​​obtained prior to the implantation of the IMD 6. In one instance, impedance monitoring may be useful in detecting changes in device migration, but several days, such as 10 days, may be useful for waiting to allow the impedance to stabilize after the implantation event. In some instances, the computing device 2 can determine that the impedance has stabilized to a baseline value before relying on impedance data to determine the presence of a potential anomaly.

[0150] In one example, computing device 2 can utilize orientation information of medical device 17, such as accelerometer data, to adjust, for example, image processing parameters of computing device 2. In one example, a shadow can be formed based on the orientation of medical device 17 that affects the image processing techniques of this disclosure, allowing the image processing algorithm to adjust the processing techniques based on information about the location of medical device 17 within patient 4. In this case, computing device 2 can receive information such as temperature data and / or orientation data from medical device 2 and utilize such information during image data analysis. That is, computing device 2 can analyze image data received by camera 32 based on information received from medical device 2 to accurately characterize potential anomalies. In a non-limiting and illustrative example, computing device 2 can analyze image data based on a set of reference images of the implantation site uploaded immediately after implantation, wherein the set of reference images may no longer be aligned with the positional state of medical device 2 due to movement of medical device 2, and therefore, computing device 2 can adjust image processing techniques to maintain a certain level of accuracy, while computing device 2 or another device performs anomaly analysis last.

[0151] In one instance, computing device 2 can determine ECG changes that indicate device migration and thus increase the likelihood of detecting a potential abnormality from image data, based on physiological parameters obtained through a second sub-session. In this case, computing device 2 can analyze the image data using biases against abnormality detection, or it can include in the post-implantation report the increased likelihood (e.g., probability, confidence interval) based on the probability of a potential abnormality determined according to a first set of data items and a second set of data items.

[0152] In another instance, computing device 2 can determine the ECG signal and map the ECG signal to the orientation of IMD 6. In some instances, computing device 2 can map the ECG morphology data to the orientation of IMD 6 by identifying deflections in the ECG (e.g., PQRST data) or by comparing ECG morphology data with a population range or group database. When the ECG morphology indicates a shift from the baseline ECG of patient 4, computing device 2 can indicate a device migration anomaly. Device migration anomalies can indicate potential infection anomalies. In this case, when computing device 2 is unsure whether there is a potential infection from the image set, computing device 2 can determine a bias towards anomaly identification based on ECG morphology data. In another instance, computing device 2 can obtain lead impedance information from one or more medical devices in medical device 17 (e.g., IMD 6). Similar to the above, computing device 2 can utilize IMD information (e.g., lead impedance information) as additional input for anomaly detection and / or prediction.

[0153] The communication circuitry 42 may include any suitable hardware, firmware, software, or any combination thereof for communicating with another device such as edge device 12, network computing device (e.g., server), other medical device 17, or sensor and / or computing device 2. Under the control of the processing circuitry 40, the communication circuitry 42 may receive downlink telemetry from edge device 12 or another device and send uplink telemetry to it via internal or external antennas such as antenna 48. Additionally, the processing circuitry 40 may utilize technologies such as those from Medtronic. Network 10 communicates with the network computing device. Antenna 48 and communication circuit system 42 can be configured to communicate via inductive coupling, electromagnetic coupling, NFC, RF communication, etc. Wi-Fi TMOr other proprietary or non-proprietary wireless communication schemes to transmit and / or receive signals. In one example, processing circuitry 40 can provide data to be transmitted uplink via communication circuitry 42 to edge device 12, computing device 2, and / or other devices via network 10. In an illustrative example, computing device 2 can receive signals (e.g., uplink data) from a specific medical device in medical device 17 (e.g., IMD 6). In such an example, computing device 2 can determine information associated with patient 4 and / or a specific medical device in medical device 17 (e.g., IMD 6) based on the signals. In one example, the information may include device information (e.g., IMD information) corresponding to a specific medical device in medical device 17 or corresponding to a set of medical devices 17, wherein the set may include other paired medical devices 17 (e.g., wearable devices, etc.) besides one of IMD 6. In such an example, computing device 2 can initiate a device query session in which computing device 2 receives signals indicating device query data (e.g., battery health status, operating parameters, etc.) from a specific medical device in medical device 17 (e.g., IMD 6).

[0154] In some instances, the processing circuitry 40 may use an address / data bus to provide control signals. In some instances, the communication circuitry 42 may provide data to the processing circuitry 40 via a multiplexer, with the data being received from an external source via antenna 48. In some instances, the medical device 17 may use a wired connection, such as a Universal Serial Bus (USB) connection or an Ethernet connection (e.g., LAN) on network 10, to transmit data to another device.

[0155] In some instances, the processing circuitry 40 can send temperature data or query data from other devices to the edge device 12 via the communication circuitry 42. For example, the medical device 17 can send internal temperature measurements to the edge device 12, where the edge device 12 will then analyze the internal temperature measurements. In such instances, the edge device 12 performs the described processing techniques. Alternatively, the medical device 17 can perform processing techniques and transmit abnormal results to the edge device 12 for reporting purposes, such as providing an alert to patient 4 or another user.

[0156] In some instances, storage device 50 contains computer-readable instructions that, when executed by processing circuitry system 40, cause medical device 17, which includes processing circuitry system 40, to perform various functions attributable to medical device 17 and processing circuitry system 40 herein. Storage device 50 may contain any volatile, non-volatile, magnetic, optical, or electrical medium. For example, storage device 50 may contain ROM, RAM, NVRAM, DRAM, SRAM, magnetic disk, optical disk, flash memory, various forms of EEPROM or EPROM, or any other digital media. As an example, storage device 50 may store programmed values ​​of one or more operating parameters of medical device 17 and / or data collected by medical device 17 for transmission to another device using communication circuitry system 42. As an example, data stored by storage device 50 and transmitted by communication circuitry system 42 to one or more other devices may include electrocardiograms, cardiac EGM (e.g., digitized EGM), and / or impedance values.

[0157] Various components of the medical device 17 are coupled to a power source 56, which may comprise a rechargeable or non-rechargeable battery. A non-rechargeable battery can maintain its charge for several years, while a rechargeable battery can be charged from a receptacle or other external charging device (e.g., inductive charging). In instances involving rechargeable batteries, the rechargeable battery may be charged, for example, once daily, weekly, or annually. In some instances, according to one or more of the various techniques disclosed herein, the power source 56 may be detached from the medical device 17 and implanted in a separate implantation site in the patient 4 where abnormalities can be monitored.

[0158] As described herein, medical device 17 may include medical device 6 (e.g., IMD 6). In such instances, medical device 17 may have a geometry and size designed for ease of implantation and patient comfort. Examples of medical device 17 described in this disclosure may have a volume of 3 cubic centimeters (cm³). 3 or smaller, 1.5cm 3 Or smaller or any volume in between. Additionally, the medical device 17 may include a proximal end and a distal end that are rounded to reduce discomfort and irritation to surrounding tissues after implantation under the skin of the patient 4. An example configuration of the medical device 17 is described, for example, in U.S. Patent Publication No. 2016 / 0310031. The computing device 2 may receive IMD information (e.g., IMD size, whether the ends are rounded, the length of the elongated leads, etc., if any) containing such configuration details of the medical device 17. As described herein, according to one or more of the various techniques of this disclosure, the computing device 2 may utilize IMD information, such as IMD configuration, to train the AI ​​engine 28 and / or the ML model 30 to provide anomaly assessments tailored to the IMD.

[0159] Figure 5 This is an example UI visualization of an example computing device 502 based on one or more technologies of this disclosure. The computing device 502 may be a reference. Figure 1 , 2 An example of one of the computing devices 2 described in 3. According to one or more various techniques of this disclosure, computing device 502 may include one or more cameras 32. As described herein, in some instances, one or more cameras 32 may be separable from computing device 502. Figure 5 In illustrative and non-limiting examples and other examples illustrating computing device 502, computing device 502 may include a mobile handheld device (e.g., a tablet computer, smartphone, etc.). Although shown as a mobile handheld device, the technology of this disclosure is not limited thereto. It will be understood that various other devices and UI visualization elements can be used in various other environments, such as in virtual reality, augmented reality, or mixed reality environments. That is, a user can use the camera 32 of an augmented reality headset to image the implantation site of the patient 4 and navigate one or more of the UIs of this disclosure.

[0160] In some instances, the UI visualization or interface described herein may comprise UI pages or screens of a related UI (e.g., UI 22). In some instances, a user may navigate laterally (e.g., forward, backward, etc.) through various UI pages or screens using navigation buttons (e.g., back, next, scroll buttons, etc.). In some cases, the UI visualization may comprise virtual reality and / or augmented reality visualizations, such as when computing device 502 includes a VR, AR, or MR headset. That is, the UI visualization may be presented as an immersive UI program that a user can interact with in a virtual reality space and / or an augmented reality space. Those skilled in the art will understand that while computing device 502 is shown as different pages of a UI, the computing device may similarly present VR UI elements that a user can navigate to engage in an interactive session, rather than UI pages on a handheld mobile device screen, according to one or more of the various techniques of this disclosure, or at least not inconsistent with one or more of the various techniques of this disclosure.

[0161] In some instances, computing device 502 may (e.g., via UI 22) present an interface 504 containing various login options. In one instance, interface 504 may include a login tile 506 or other login elements (e.g., a camera icon 508). According to one or more techniques of this disclosure, since user input is associated with login tile 506, computing device 502 may receive user input to invoke and / or initiate a virtual registration interactive session.

[0162] In an illustrative example, interface 504 may include a camera icon that first initializes camera 32 for login purposes. Computing device 502 can receive images from camera 32 and authenticate the user based on the received images. In some instances, computing device 502 can perform facial recognition or implantation site (e.g., wound) characteristic recognition. In some instances, patient 4 can attach computing device 502 to the implantation site for NFC or RFID authentication. That is, computing device 502 can receive NFC or RFID indications. Computing device 502 can use such indications to identify and / or authenticate a specific user. In any case, computing device 502 can be accessed via or based on barcodes (e.g., one-dimensional barcodes, two-dimensional barcodes, quick response (QR) codes). TM The interactive session is loaded from storage device 24 by reading or scanning (such as matrix barcodes). In some cases, the barcode may be included in a leaflet given to the patient 4 at the time of implantation or shortly before / after the implantation procedure.

[0163] In some instances, computing device 502 may use one of medical devices 17 to authenticate a user. In this case, medical device 17 may include a wearable device capable of verifying the user (e.g., patient 4, HCP, etc.). In some cases, the wearable device may include a wristband containing barcodes, RFID chips, etc. In this case, the user may tap the medical device 17 to computing device 502 or computing device 502 may scan the medical device 17 in other ways. In some cases, the tap may be a non-contact tap, such as an air tap that maintains a small air gap between the devices. In any case, in a non-limiting example, computing device 502 may receive authentication information from medical device 17 and authenticate the user, such as by allowing the user to proceed to the next interface of an interactive session.

[0164] In some instances, UI 22 may include a button 600 (e.g., a soft key, a hard key, etc.) used as a login element. That is, button 600 may include a multi-function button providing various login options. In one instance, button 600 may include a fingerprint scanner or other biometric scanner. Button 600 may be on the front, back, or any other part of the computing device 502.

[0165] In some instances, computing device 502 may not present interface 504, such as after a user's first login. In such instances, the user can choose "Remember this device," "Remember me," and / or "I am the only associated user of this device." Computing device 502 may receive user input and accordingly discard the login interface for future login events. In some cases, the user may want to re-authenticate for each login, such as when multiple IMD patients use the same computing device 502 for implantation site or other IMD monitoring.

[0166] Figure 6 This is a UI visualization of a startup session interface 602 according to one or more technologies of this disclosure. In some cases, the startup session interface 602 may include a startup session icon 606 and / or a camera icon 608. The camera icon 608 may be similar to camera icon 508, except that once authenticated, the camera icon 608 can be used as a shortcut to start a body part examination sub-session or other sub-sessions of a virtual registration process (e.g., interactive reporting and / or registration sub-sessions). In such instances, the computing device 502 may receive user input for the camera icon 608, and the computing device 502 may then initialize an imaging device (e.g., camera 32) and start a body part examination sub-session (e.g., wound examination sub-session), as referenced. Figure 15-19 As described.

[0167] In some cases, the initiation session interface 602 may include a configuration file interface 604. In some instances, the configuration file interface 604 may contain images of patient 4, images of one or more relevant implantation sites of patient 4, or both. In this way, patient 4 can enjoy a more personalized experience by using the virtual registration UI. In such instances, computing device 502 may access the images from storage device 24 or from another storage device such as via network 10. In some instances, the images may be from a previous site examination sub-session.

[0168] In some instances, virtual checks in an interactive session can be pushed to patient 4's device, such as via a cloud solution. In this case, computing device 502 can receive push notifications from edge device 12 or from another device (e.g., server 94 via network 10). In some cases, push notifications can originate from another user's computing device 2, such as computing device 2 originating from HCP. In some cases, computing device 502 can receive notifications prompting a virtual registration session based on a pre-determined scheduling reminder. In this case, HCP can program a calendar timer to cause computing device 502 to provide push notifications and / or automatically initiate virtual registration sessions (e.g., interactive reporting sessions) upon expiration. In some instances, computing device 502 can provide the user with an instruction to open (e.g., initiate) a virtual registration interactive session after determining a scheduling trigger or push notification (e.g., an HCP push). In some cases, computing device 502 can automatically initiate a virtual registration interactive session after determining a scheduling trigger or push notification. That is, computing device 502 can automatically present... Figure 5 504 error on the interface Figure 6 The interface 602, or in some cases, can be presented by default and referenced. Figure 7-21The interface described is similar to the interface described above. In some cases, computing device 502 can determine whether the user needs to be authenticated first before presenting various other interfaces.

[0169] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can be configured to determine the identification data of patient 4. In one instance, processing circuitry system 20 can determine the identification data of patient 4. The identification data may include one or more of the following: biometric data, RFID data, NFC data, telemetry protocol data, user login information, authentication data, patient name or username data, etc. In any case, the user can input the identification data via computing device 2 and / or via camera 32. In one instance, computing device 2 may include computing device 502 used as a user registration device. In this case, computing device 2 can determine the identification data of patient 4 via input received via elements of interface 504 (e.g., via button 600, where button 600 includes a biometric scanner).

[0170] In some instances, patient 4 may provide authentication data to gain access to perform an interactive session. In some instances, patient 4 may provide biometric data (e.g., facial data, fingerprint data, iris data, voice data, characteristic implantation site data, etc.). In one instance, computing device 2 may include a biometric scanner (e.g., camera 32, fingerprint scanner, etc.) that patient 4 or another user may use to provide authentication / biometric data. In some cases, camera 32 may image the implantation site to identify patient 4, wherein processing circuitry 20 includes an AI engine 28 and / or ML model 30 trained to identify patient 4 with a degree of determinism based on one or more initial images of the implantation site. Processing circuitry 20 may identify patient 4 based on the unique characteristics of the implantation site. In another instance, processing circuitry 20 may authenticate the user based on wireless communication with patient 4's IMD 6 (e.g., NFC data, telemetry protocol data, RFID data, etc.).

[0171] In some instances, patient 4 may or may not be the primary user of computing device 2 for the purpose of participating in and / or navigating the interactive session. In illustrative examples, a user separate from patient 4 may be a user of computing device 2 for the purpose of participating in and / or navigating the interactive session. That is, a user can coordinate with patient 4 while navigating the interactive session on behalf of patient 4. In the illustration, a user separate from patient 4 can log in to access the interactive session. In this case, after authentication to access the interactive session, the user can then identify patient 4. In some instances, the user can identify the patient by taking a photograph of the patient, entering the patient's name, scanning the patient's barcode, imaging the wound site, etc. In illustrative examples, the user can take a photograph of patient 4's face or the implantation site. In any case, computing device 2 can perform facial detection or wound characteristic detection to identify patient 4.

[0172] Processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can deploy image processing tools (e.g., AI engine 28 and / or ML model 30) to perform the authentication process. In one instance, processing circuitry system 20 can train the image processing tools based on patient data, implantation site data, etc. In one instance, when scanning the implantation site, the imaging processing tools can understand, for example, how the implantation site heals over time (e.g., healing trends). Generally, the characteristics of the implantation site can change over time, and therefore processing circuitry system 20 can adjust relevant parts of the recognition algorithm accordingly over time. This is particularly useful when the recognition algorithm of processing circuitry system 20 uses, for example, images of the implantation site to identify and / or verify the user. In this case, processing circuitry system 20 is still able to accurately identify patient 4, even though some time has passed between registration sessions.

[0173] In some cases, when attempting to identify patient 4 via camera 32, processing circuitry system 20 can detect potential anomalies at this stage. In this case, computing device 2 can request additional identification data to correctly and / or accurately identify patient 4. In some cases, processing circuitry system 20 can store authentication data (e.g., two-step authentication data) to storage device 24 to streamline the authentication and identification process for patient 4 in subsequent sessions. In another instance, processing circuitry system 20 can query a database (e.g., storage device 96 of remote server 94) that holds patient data (e.g., username, password, implantation site characteristic data, implantation site image, etc.) via network 10. In this case, processing circuitry system 20 can identify patient 4 based on the patient data after receiving search results from the database. In an illustrative example, processing circuitry system 20 can receive user input indicating the patient's name via UI 22. Processing circuitry system 20 can query the database and identify patient 4 as a known patient of system 100 (e.g., system 300) based on the query results.

[0174] The processing circuitry system 20 can reference patient data (e.g., patient identifiers) to allow the same computing device 2 (or the same algorithm library) to be shared among multiple patients (e.g., in a clinic). As described herein, the computing device 2 can adjust the site inspection algorithm library based on patient data to customize the process and UI visualization to suit each individual patient. In another instance, a generic site inspection algorithm can be deployed to suit all patients of a certain category (e.g., nursing home patients, patients in a specific nursing home, etc.). In this way, the site inspection algorithm can maintain and provide a specific level of consistency for various users in an interactive session, where these users may be part of a common class.

[0175] In some instances, while operating an interactive session simultaneously, multiple computing devices 2 can capture images of the implantation site of a single patient 4 and determine other data items (e.g., query data). That is, this is a technique that can be performed by both the patient 4's computing device 2 and the caregiver's computing device 2 when operating the imaging procedure. In such instances, computing devices 2 can synchronize data and / or analysis results in real time, or in some cases, synchronize data and / or analysis results at a later point in time, such as by waiting until a wireless connection between computing devices 2 becomes available or a network connection becomes available (e.g., via a connection to network 10). In some cases, until computing devices 2 determine to perform the data synchronization process, computing devices 2 can store data locally, such as to storage device 24, or in some cases, to storage device 62 of edge device 12.

[0176] In some instances, after receiving authentication data from the user of the identification imaging program, a processing circuitry, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine the identification data of patient 4. In such instances, the user of the interactive session can include HCP, family members of patient 4, patient 4, etc. For illustration, processing circuitry system 20 can authenticate the user and authorize the user to access the interactive session. Subsequently, processing circuitry system 20 can receive valid input data for identifying patient 4, such as user input, through UI 22. In one instance, the input data includes barcode scan data, selection of patient 4 from a drop-down menu (e.g., by keyword search), manually entered patient information, etc. In any case, computing device 2 can then determine the identification data of patient 4 based on the input, such as by determining the name or ID of patient 4.

[0177] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine IMD information corresponding to one of the medical devices 17 (e.g., IMD 6) of patient 4. In one instance, processing circuitry system 20 can identify IMD information corresponding to a specific medical device in medical device 17 based at least in part on identification data. In some instances, IMD information may include IMD implantation site information, such as the location of the implantation site on patient 4's body, the size and shape of the implantation site, and other information about the implantation site. In another instance, IMD information may include historical data related to the implantation site of the IMD and / or historical data associated with the IMD. In some instances, historical data may include images of the implantation site after implantation surgery, wound characteristics, the shape and size of the implantation site (e.g., wound size), incision information, any history of complications during surgery, implantation date, etc. In some instances, IMD information may further include IMD type information, IMD communication protocol information, estimated orientation of medical device 17 (e.g., IMD 6), data about one or more HCPs (e.g., surgeons, clinicians) responsible for implanting (e.g., inserting) medical device 17 (e.g., IMD 6), information related to one or more methods used by one or more HCPs in sealing the implantation site, images of the implantation site over time, etc. Examples of implantation methods and instruments are described, for example, in U.S. Patent Publication No. 2014 / 0276928. In any case, computing device 2 may determine the presence of a potential abnormality at the implantation site (e.g., the probability that a potential abnormality is an actual abnormality) based on the implantation method and instruments used during the implantation procedure. In one instance, computing device 2 may compare image data of the implantation site with reference image data from a reference image library, wherein the reference images in the library may have been labeled with various details such as implantation methods and instruments (e.g., library metadata). The computing device 2 can determine the abnormality at the implantation site at least in part by referring to a corresponding image from a reference library, the corresponding image containing implantation method and instrument attributes similar to those of the implantation method and instrument attributes that the computing device 2 is imaging at the implantation site.

[0178] In non-limiting and illustrative instances, computing device 502 may initiate an interactive session (e.g., virtual registration) upon prompting by patient 4, at a specific post-implantation date, and / or during or near a clinic visit. In some instances, computing device 502 may cause the user's (e.g., patient 4's) interactive session program to expire after a given time. In another instance, the interactive session may not include an explicit expiration date (e.g., a so-called "evergreen" application).

[0179] In an illustrative example, computing device 502 can identify a patient's follow-up schedule when providing an interactive session. In one example, computing device 502 may receive the follow-up schedule, for example, from one of the computing devices 2 of the HCP, or it may access the follow-up schedule from a database via network 10. The follow-up schedule may define one or more time periods during which computing device 502 is configured to prompt the user for an interactive session. In some instances, the one or more time periods may contain at least one time period corresponding to a predetermined amount of time from the date of implantation of IMD 6. That is, the first time period or at least one of the one or more time periods may be a predetermined time from the date of implantation of IMD (e.g., the number of days from the date of implantation of IMD 6).

[0180] In illustrative examples, the follow-up schedule may include a first time period for which the computing device 502 provides prompts, for example, 15 days after the implantation or removal of the medical device 17 (e.g., IMD 6). In another example, the computing device 502 may include variable time periods that the AI ​​engine 28 and / or ML model 30 can determine for the patient 4, allowing different patients to have different enrollment schedules based on various different criteria. In such examples, the computing device 502 can provide interactive sessions based on the follow-up schedule. In another example, the computing device 502 may, for example, provide prompts to mobile device users to capture image data using the computing device 502 at a predetermined time after implantation that results in an implant-related wound. In some examples, the computing device 502 identifies the follow-up schedule by receiving push notifications from another device via the communication circuitry system 26 and determining a first time period of the follow-up schedule based on the push notifications. In such examples, the push notifications may include HCP pushes received from one of the computing devices 2 of the HCP, such as the HCP corresponding to the patient 4. In some instances, computing device 502 can identify a follow-up schedule by receiving physiological parameters indicating an abnormality (e.g., an abnormal ECG) and determining a first time period of the follow-up schedule based on the abnormal physiological parameters. That is, computing device 2 can determine triggering events for identifying a follow-up schedule containing triggers based on the amount of time elapsed, specific signals such as activity levels or ECGs received from one of the medical devices 17 (e.g., IMD6), or triggers received via network 10 (e.g., computing device 2 of HCP).

[0181] Figure 7This refers to the UI visualization of a menu interface 702 according to one or more technologies disclosed herein. After initiating an interactive session, the computing device 502 can output an interactive UI via UI 22 based on the virtually registered interactive session. In some instances, the computing device 502 can provide a top-level interface containing at least one first interface tile. The first interface tile may correspond to a first sub-session. In this case, the first sub-session may contain a first sub-interface level that is lower than the level of the top-level interface. The top-level UI interface can present multiple tiles from which the user can select. Figure 7 In some instances, the application output of this disclosure includes a UI program containing one or more graphical UI visualization elements (collectively referred to as UI elements or “tiles”).

[0182] Although described as being provided as part of a hierarchical structure with layered levels, it will be understood that the techniques of this disclosure are not limited thereto, and sub-session interfaces may be separable from the first interactive session interface in terms of what the user can consider as the default when initializing the receiving session interface. In instances involving mixed reality environments, computing device 502 may present all interfaces at a single level, where the user can access each individual sub-session interface, for example, by panning the patient 4’s head around the virtual reality user interface. In illustrative and non-limiting instances, the user can access and / or initiate sub-sessions from the virtual reality user interface, where the virtual reality interface may, in some cases, be converted to an augmented reality interface, such as when computing device 502 detects the selection of a first sub-session (e.g., a site inspection sub-session). In this case, according to one or more of the various techniques of this disclosure, computing device 502 may switch to an augmented reality mode in which the user can, for example, image the implantation site of the patient 4 via camera 32 (e.g., a head-mounted camera or another camera communicatively coupled to computing device 502). Once the first sub-session is complete, the computing device 502 can revert to a separate user interface (e.g., a top-level menu interface or a second sub-session interface), which in some cases is again presented in the virtual reality environment. While this document may describe multiple instances of user interaction with the interactive sub-sessions of this disclosure, it will be understood that interactive sub-sessions and sub-sessions can be provided in various environments and are not necessarily described herein for the sake of brevity.

[0183] like Figure 7As illustrated in the illustrative example, the UI elements of interface 702 may include a patient status tile 706, a physiological parameter analysis tile 708, a device examination tile 710, and / or a site examination tile 712. Users (e.g., patient 4, caregiver, physician) can (e.g., via touch input) select any of these tiles to utilize the functionality associated with the description of each such tile. In some instances, UI elements may include interactive graphical units that can be presented to the user through UI 22. In some instances, selecting the camera icon may cause computing device 502 to automatically initiate a site examination sub-session, providing a shortcut to the site examination page accessible via site examination tile 712.

[0184] Additionally, any interface described herein may include a Session ID Tracker tile 704. The Session ID Tracker tile 704 may provide session and / or sub-session tracking information, such as date stamps, timestamps, session ID stamps and / or sub-session ID stamps, user information, etc. The Session ID Tracker may further include historical data about previous sessions (e.g., historical data about one or more previous sub-sessions), such as summaries of previous reports (e.g., session reports, reports detailing anomalous results of one or more sub-sessions, etc.). In any case, the computing device 502 may include such session tracking information when generating new reports for each specific interactive session, each specific sub-session (e.g., sub-reports of a sub-session), etc. The highest-level interface 702 may contain multiple Session ID Tracker tiles 704, such as one for each sub-session.

[0185] Additionally, a separate interface for one or more sub-sessions may contain tracker tiles. When computing device 502 detects the selection of a specific tracker tile, computing device 502 can retrieve historical information about each sub-session and previous sub-session results (e.g., reports, etc.). Computing device 502 may provide a pop-up interface through UI 22 to provide such information, or in some cases, may automatically navigate the user to the reports and / or history interface through UI 22 for further viewing. Furthermore, computing device 502 may export such data (e.g., reports, history, etc.) from the interactive session interface to another interface and / or together to another device (e.g., one of the computing devices 2 of the HCP, one of the servers 94, edge device 12, etc.). In one instance, in response to detecting a user selection of one of the sub-session tracker tiles or interactive session tracker tiles 704, computing device 502 may export a report in response to a detected selection of an export report button (e.g., a soft key). The exported report may contain multiple reports (e.g., sub-session reports) detailing the analysis of multiple data items from multiple sub-sessions, or a compiled report (e.g., interactive session report). In an illustrative example, computing device 502 can detect the selection of sub-session tracker tiles through a sub-session interface, and in response, can generate and / or export a report for a specific sub-session corresponding to a specific interface of an interactive session.

[0186] In another instance, computing device 502 can detect the selection of an interactive session tracker tile (e.g., tracker tile 704) and, in response, can generate and / or export a report corresponding to the interactive session, a report corresponding to a specific sub-session that has been performed to date (if not all sub-sessions), and / or a comprehensive report corresponding to the entire interactive session, as well as any summary reports of individual sub-sessions. In another instance, computing device 502 can generate an aggregated historical report containing any one or more of these reports, such that, in response to detecting the selection of an interactive session tracker tile or other tracker tile, computing device 502 can retrieve historical reports and compile and / or summarize past reports to produce a single post-implantation historical report for export and / or (e.g., via a pop-up interface) display. In this case, computing device 2 of the HCP can receive the post-implantation report via network 10, allowing the HCP to view the patient 4's history and / or a summary of the history (e.g., for medical device 17 corresponding to patient 4).

[0187] Figure 8 This is a flowchart illustrating an example method of implementing a sub-session technique for a virtual registration interactive session according to one or more techniques of this disclosure. The sub-session technique of this disclosure can determine abnormalities at body parts of patient 4 by obtaining various data items and synthesizing based on combinations of data items.

[0188] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can acquire image data related to the body of patient 4 and determine the current state of the implant-related wound on the body of patient 4. In such instances, the image data comprises one or more frames representing images of the body of patient 4. Additionally, in some instances, a portion of the body of patient 4 contains the implantation site of IMD 6, such that the frame represents an image of the implantation site. In an illustrative example, processing circuitry system 20 can prompt a mobile device user (e.g., patient 4) to use the mobile device to capture image data. In such instances, processing circuitry system 20 can prompt a mobile device user at a predetermined time after implantation resulting in an implant-related wound. As described herein, processing circuitry system 20 can further acquire data related to the functionality of one of the medical devices 17 implanted within the body of patient 4. Processing circuitry system 20 can further determine performance metrics of the medical device 17 based on the acquired data (e.g., query data, diagnostic data). In some instances, the processing circuitry system 20 can determine performance metrics of a medical device based on the captured image data, such as images indicating device migration that can in turn affect various performance metrics, such as IMD 6.

[0189] In illustrative examples, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can monitor patient 4. In one example, processing circuitry system 20 can provide an interactive session configured to allow a user to navigate multiple sub-sessions, said multiple sub-sessions including at least a first sub-session and a second sub-session different from the first sub-session, wherein the first sub-session includes capturing image data (802) via one or more cameras 32. In some cases, processing circuitry system 20 can provide an interactive session in response to being pushed to patient 4 via a cloud solution. In one example, the interactive session may include a mobile application pushed to the patient via a cloud solution. In another example, processing circuitry system 20 can provide an interactive session based on scanning a QR code from a leaflet given at or shortly before or after implantation.

[0190] In some cases, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can provide interactive sessions (e.g., a first sub-session, a site examination sub-session, etc.) by: training a session generator based on one or more of the following (e.g., via processing circuitry system 20): group parameters or IMD information; deploying the session generator via the computing device to generate the interactive session; and providing an interactive session that is at least partially personalized for the user as a result of the training via the session generator. Additionally, the session generator can refer to historical query data for comparison when personalizing the interactive session. The session generator may include an AI engine 28 and / or an ML model 30.

[0191] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine a first set of data items (804) based on a first sub-session of an interactive session. In one instance, processing circuitry system 20 can determine a first set of data items containing image data as part of a site inspection sub-session.

[0192] In some instances, the processing circuitry 20 may determine a second set of data items based on a second sub-session of the interactive session. This second set of data items differs from the first set and includes one or more of the following: data obtained from medical device 17 (e.g., IMD 6), at least one physiological parameter of patient 4, or user input data (806). In some instances, the processing circuitry 20 of computing device 2 or computing device 502 may execute a pairing session (e.g., a pairing process) with one or more medical devices 17 (e.g., IMD 6), with another computing device 2, and / or with an edge device 12 (e.g., an IoT device in the home). The pairing session is configured to pair the computing device with the corresponding device (e.g., IMD 6). In some instances, the pairing session may include an authentication process as described herein. In an illustrative example, the mobile computing device may be initialized to communicate with IMD 6, including authentication (e.g., two-step authentication) such that only authorized mobile computing devices can interact with IMD 6. In such instances, in the first case, IMD 6 may transmit a signal to computing device 2 in response to a computing device attempting to pair with IMD 6.

[0193] The user can then perform self-authentication, and if appropriate, IMD 6 can then pair with computing device 2 and initiate bidirectional or unidirectional communication between the devices. IMD 6 can then remember the unique ID of computing device 2 for future authentication (e.g., via hash keys, neural networks, etc.). In any case, computing device 2 can receive information about the IMD during the pairing session. In this case, computing device 2 can receive query data about IMD 6 (e.g., from IMD 6) through the pairing process. In some instances, computing device 2 can store the query data as historical query data for later reference and / or as a training set for AI engine 28 and / or ML model 30. That is, in some cases, IMD information can contain device query data (e.g., historical query data).

[0194] According to one or more of the various techniques disclosed herein, a processing circuitry system, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine anomalies corresponding to at least one of patient 4 and / or IMD 6 based at least in part on a first set of data items and a second set of data items (808). In one example, processing circuitry system 20 can output a post-implantation report for an interactive session, wherein the post-implantation report includes an indication of the anomaly (810). Processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can enable patient 4 to generate reports for their records (e.g., in PDF format or various other formats), send them to family members or doctors via email or FTP, etc. In some instances, the post-implantation report may further include an indication of the amount of time that has occurred since the implantation of IMD 6. In some instances, processing circuitry 20 may determine a post-implantation report by identifying anomalies (e.g., ECG abnormalities) based on a second set of data items and by determining the post-implantation report based at least in part on the anomalies and images. In any case, processing circuitry 20 may determine how to provide feedback to patient 4, such as by using simplified icons or complex results (e.g., depending on HCP preferences). At the end of the interactive session, processing circuitry systems, such as processing circuitry 20 of computing device 2, processing circuitry 64 of edge device 12, processing circuitry 98 of server 94, or processing circuitry 40 of medical device 17, may, in some cases, mark the results with a date and timestamp on UI 22 provided via a mobile device application.

[0195] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can output post-implantation reports to the HCP device via network 10 (e.g., via a bidirectional communication protocol). In one instance, processing circuitry system 20 can output post-implantation reports via network 10 to another device of the user of UI 22 and / or interactive session, where the user may or may not be patient 4.

[0196] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine the completion of an interactive session and provide notification of its completion, such as by providing a confirmation receipt or by marking tiles on the UI 22 interface as having completed a threshold number of sub-sessions. In some instances, processing circuitry system 20 can output post-implantation reported results for display (via a display of computing device 2 or another device, such as one of the medical devices 17 containing a display). In an illustrative example, when processing circuitry system 20 determines that any one or any combination of sub-sessions produces an abnormal result (or an abnormality outside the acceptable normal range), processing circuitry system 20 can output a prompt to patient 4 using a mobile device application. In some instances, the prompt can indicate the abnormality. In other instances, the prompt can contain a recommendation or instruction to schedule a follow-up visit by HCP.

[0197] In some instances, the first set of data items may include image overlays (e.g., augmented reality overlays). Image overlays can be used to add a set of preview frames for specific angle and size references. In such instances, the processing circuitry 20 may output an image overlay at the first sub-interface level. Additionally, when providing a first sub-session, the processing circuitry 20 may detect the selection of a first interface tile and provide the first sub-session of the interactive session. In another instance, the processing circuitry 20 may prompt a user (e.g., patient 4, HCP, etc.) to capture image data using one or more cameras 32 when determining the first set of data items, and subsequently determine at least a portion of the first set of data items (e.g., image data or at least a portion of image data). In any case, the processing circuitry 20 may prompt a mobile device user to capture image data using the mobile device at a predetermined time after implantation that results in an implant-related wound.

[0198] In some instances, the processing circuitry 20 may provide a second sub-session of the interactive session through a second sub-session interface, and may further modify the second interface tiles to (e.g., with checkmarks) indicate the completion of the second sub-session. Alternatively, the processing circuitry 20 may provide a first sub-session of the interactive session after the second sub-session to obtain image data, and may further modify the first interface tiles to indicate the completion of the first sub-session. In some instances, to facilitate user navigation, the processing circuitry 20 may facilitate direct navigation from the second sub-session interface to the first sub-session interface without involving the highest-level interface. In any case, the processing circuitry 20 may also provide a third sub-session of the interactive session after the first or second sub-session, and determine a third set of data items based on the third sub-session of the interactive session, wherein the third set of data items differs from the first set of data items. In such instances, determining the third set of data items may involve the processing circuitry 20 receiving physiological parameter signals and determining the third set of data items based on the physiological parameter signals. It should be noted that the sub-sessions described in this disclosure can be provided and accessed in any order, and in some cases, the processing circuitry system 20 can gradually cancel one or more sub-sessions over a specific time period, such as from a predetermined time after implantation, from a predetermined time after the user completes a specific interactive session, or from the result of a specific interactive session (e.g., implantation site status). In one instance, the processing circuitry system 20 can disable access to the imaging sub-session after a predetermined time following implantation or after a predetermined time following a health status update (e.g., a wound healing according to a planned schedule). In such instances, the processing circuitry system 20 can generate an interactive session to include one of the remaining sets of sub-sessions included with the interactive session at the expected time. In some instances, the processing circuitry system 20 can generate an interactive session to include disabled or gradually canceled sub-sessions (e.g., site examination sub-sessions), such that the disabled sub-sessions are hidden from the user or otherwise inaccessible. The processing circuitry system 20 can provide interactive sessions to include sub-sessions, even if some sub-sessions are presented as inaccessible to the user.

[0199] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can identify anomalies based on various data items. In one instance, processing circuitry system 20 can determine that the anomaly includes a first anomaly. In such instances, processing circuitry system 20 can determine a post-implantation report by outputting a second set of data items to another computing device in computing device 2 via communication circuitry system 26. Processing circuitry system 20 can then receive the results of analysis of any one or more sets of the data item set (e.g., the second data item set) via communication circuitry system 26. The results can indicate that the second set of data items does not indicate the presence of a second anomaly. In such instances, processing circuitry system 20 can determine a post-implantation report based at least in part on the first anomaly and the second set of data items.

[0200] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can provide interactive sessions comprising a third sub-session and a fourth sub-session. In one instance, processing circuitry system 20 can provide a third sub-session containing a physiological parameter sub-session and can provide a fourth sub-session containing a device examination sub-session. In this case, processing circuitry system 20 can determine anomalies by: determining a third set of data items based on the third sub-session, wherein the third set of data items contains at least one physiological parameter of the patient; and determining a fourth set of data items based on the fourth sub-session, wherein the fourth set of data items contains query data. Thus, processing circuitry system 20 can further determine anomalies at least in part based on the third set of data items and / or the fourth set of data items.

[0201] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can initiate a second sub-session after a first sub-session. In one instance, processing circuitry system 20 can determine a first set of data items by receiving a first set of data items via communication circuitry system 26, and can determine a second set of data items by receiving a second set of data items via computing device 2. In some instances, processing circuitry system 20 can determine a second set of data items, which includes information indicating an abnormality in at least one physiological parameter of the patient or an abnormality corresponding to device parameters of one or more medical devices 17. In such instances, processing circuitry system 20 can output at least one of the first or second set of data items to an anomaly determiner for anomaly analysis when an indication of an anomaly is determined, and determine the result of the anomaly analysis, wherein the result indicates an anomaly. In this case, the anomaly determiner can include at least one of AI engine 28 and / or ML model 30. In one instance, one of computing devices 2 can include and deploy an anomaly determiner to determine anomalies at body parts of patient 4. In other words, the processing circuit system 20 can deploy an anomaly determiner to identify anomalies, wherein, as described herein, the anomaly determiner can be trained to identify various anomalies based on image data and other data items.

[0202] In some instances, the processing circuitry system 20 can identify the presence of potential infection at the implantation site as a potential anomaly. That is, the processing circuitry system 20 can determine the presence of potential infection at the implantation site when an anomaly is identified at the implantation site. In some instances, the processing circuitry system 20 can detect potential anomalies at the implantation site based on the analysis of at least one frame. In another instance, the processing circuitry system 20 can determine potential anomalies by transmitting images and other data items to the edge device 12 via the communication circuitry system 26. That is, the computing device 2 can transmit one or more frames of image data to the edge device 12, wherein the frames contain one or more images of the implantation site. Additionally, the computing device 2 can transmit images and / or other data items to the edge device 12, the medical device 17 (e.g., a wearable device, a bedside workstation), and / or the server 94 via the network 10.

[0203] In some instances, computing device 2 can transmit images and / or other data items to another device, such as server 94, via network 10. In this case, server 94 can transmit the images and / or other data items to edge device 12 for further analysis. That is, in some instances, computing device 2 can indirectly transmit data such as image or video data to edge device 12 and / or server 94 via network 10. In one instance, computing device 2 can transmit data to edge device 12, which then performs data processing and / or transmits the data (e.g., edge-processed data) to server 94 for further analysis. In this case, edge device 12 and / or server 94 can determine the presence of potential anomalies based on data (e.g., image data, video data, etc.) received from computing device 2 via communication circuitry 26. In any case, computing device 2 can determine the presence of potential anomalies at the implantation site after receiving potential anomaly information from another device (e.g., edge device 12, server 94, etc.).

[0204] In illustrative examples, edge device 12 and / or server 94 may receive images and / or other data items (e.g., a second set of data items, a third set of data items, a fourth set of data items, etc.) from computing device 2. In some cases, edge device 12 and / or server 94 may perform image processing analysis before transmitting the results of image processing analysis to computing device 2 and / or edge device 12. In some instances, edge device 12 may identify the presence of potential anomalies based on analysis of image data and / or other data items of other sub-sessions. In some instances, edge device 12 may deploy an image processing engine (e.g., via AI engine 28 and / or ML model 30) to determine the presence of potential anomalies. In another instance, edge device 12 may perform some or all of the analysis by means of server 94. That is, in some instances, server 94 or edge device 12 may contain an image processing engine or various analysis tools configured to help detect potential anomalies. Server 94 and / or edge device 12 may contain an image processing engine, as referenced... Figure 2 The AI ​​engine 28 or ML model 30 is described. In one instance, the server 94 or edge device 12 may contain a training set for training one or more image processing engines. The server 94 and / or edge device 12 may perform training on the image processing engine, or in some cases, may assist the computing device 2 in training the image processing engine. In another instance, the server and / or edge device 12 may transfer the training set to the computing device 2. In this case, the computing device 2 may train an image processing algorithm (e.g., via the AI ​​engine 28 and / or ML model 30). In any case, the computing device 2 may determine the presence of potential infection at the implantation site based on the analysis of the image.

[0205] Additionally, when an anomaly is identified, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine the likelihood that a potential anomaly is an actual anomaly (e.g., severity measures, probability measures, etc.). In one instance, processing circuitry system 20 can determine the likelihood that a potential anomaly is an actual anomaly based on information defining the potential anomaly (e.g., the category of the anomaly, the characteristics of the anomaly, the IMD type, etc.). In some cases, processing circuitry system 20 can determine the likelihood by receiving data from another device (e.g., edge device 12, server 94, etc.) indicating the likelihood that a potential anomaly is an actual anomaly, or, in some cases, data indicating that a potential anomaly poses a health risk (whether severe or not). In a non-limiting example, processing circuitry system 20 can determine the likelihood that a potential infection identified based on a set of images represents an actual infection.

[0206] As those skilled in the art will understand, an actual infection (e.g., a genuine infection) can be demonstrated by the presence of an infectious agent that is confirmed or verified at the implantation site. In other words, a potential infection determination is an unconfirmed determination that the implantation site has been infected by an infectious agent. That is, the computing device 2 can determine a potential infection as a possible infection based on data available to the computing device 2, but the computing device 2 may not be able to diagnose an actual infection without additional input indicating that the infection is actually an actual infection. In any case, the computing device 2 can determine the likelihood that a potential infection at the implantation site is an actual infection based at least in part on images and one or more other data items. In addition, actual abnormalities such as healing abnormalities can be demonstrated by actual abnormalities in the healing process, such as confirmation or verification by another source (e.g., HCP).

[0207] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, may use weighting factors (e.g., built-in bias, error range, etc.) when determining the likelihood that a potential anomaly is an actual anomaly. In one instance, processing circuitry system 20 may train AI engine 28 and / or ML model 30 based on a data pool containing patient data, implantation site data, false alarm rate, error range information, etc., to determine the accurate likelihood that a potential anomaly is an actual anomaly. In one instance, when an IMD belongs to a specific type or a specific number of images indicating a potential anomaly, built-in bias may include a bias that tends to identify the potential anomaly as likely to be an actual anomaly.

[0208] Figure 9 It is based on the user's Figure 7 The UI visualization of the patient status interface 902, as shown in the image, is presented in response to a request for the patient status interface. In other words, Figure 9 Showing based on user preferences Figure 1 The screenshot shows a UI visualization of the selection and initiation of the patient status tile in the user-facing mobile device application of this disclosure. Various UI visualizations of this disclosure may include navigation buttons 906A-906N. These navigation buttons may include a back button 906A, a home button 906B, a next button 906C, an end button 906N, etc. In some cases, button 600 may function as a home button 906B, which allows the user to return to the home page of computing device 502 or the home page of the application, such as interface 602 or 702. Interface 902 may include a start session tile 904, which, when selected, can initiate a patient status sub-session configured to trigger or request patient input. In some instances, the patient status interface 902 may serve as a health information hub for patient 4. In one instance, in addition to health information received through computing device 502, computing device 502 may also receive health information from other devices, wearable devices, or other software applications.

[0209] Figure 10 This is a UI visualization of an example patient status interface 1002 based on one or more technologies disclosed herein. Figure 10 Non-limiting examples of patient status questionnaires that can be generated by the backend system or mobile device application of this disclosure are shown. The patient status questionnaire can be used to assess information such as the patient's overall health status, the recovery of specific symptoms from the implant, and medications the patient has recently taken or will take. The patient status interface 1002 can be a UI page that allows the patient or another user to input information about the patient, for example, through free text, drop-down menus, radio buttons, etc. In some instances, the computing device 2 can train the AI ​​engine 28 and / or ML model 30 based on the patient's health information to more accurately determine abnormal information at the implantation site (e.g., the severity of the abnormality type, etc.). In one instance, the computing device 2 can receive user input indicating soreness, redness, etc., at the implantation site. In this case, the AI ​​engine 28 and / or ML model 30 can utilize such information when identifying potential abnormalities. In some cases, the computing device 502 can receive patient health information as audio data, in which case the computing device 502 can train the AI ​​engine 28 and / or ML model 30 based on the audio data.

[0210] As described herein, in some instances, the second sub-session may include a patient status sub-session. In such instances, the processing circuitry system 20 can determine a set of data items via UI 22 based on the patient status sub-session. In one instance, the processing circuitry system 20 can receive user input data based on the second sub-session of the interactive session and determine a second set of data items based on the user input data. The user input data may include one or more of the following: patient-input data, medication information, symptom information, physiological or anatomical measurements. In an illustrative example, the user input data may include the patient's pain level, soreness level, and perception of redness at or near the implantation site. The processing circuitry system 20 can utilize this information to determine, based on image data, whether an abnormality exists at or near the implantation site. In one instance, the processing circuitry system 20 can receive an image of a specific area of ​​the patient's body pointed to by the user, and can indicate, via user input, that the indicated area is sore at a specific level of pain. In some instances, the processing circuitry system 20 may acquire one or more additional images of a body part based on a site inspection sub-session and perform image processing and analysis based on user input and gesture indications (e.g., pointing) to selectively and confidently determine, within specific confidence intervals, that a specific area of ​​the body part contains a potential abnormality. In some cases, the processing circuitry system 20 may indicate potential abnormalities in different areas of the body part (e.g., above the implantation site) even if the patient indicates soreness in another area (e.g., below the implantation site), where the processing circuitry system 20 identifies, based on image data and / or other data items, that a potential abnormality is more likely to be associated with one area (e.g., above the implantation site) than another area (e.g., below the implantation site).

[0211] In some instances, the processing circuitry 20 can input user input data into a risk calculator (e.g., AI engine 28 and / or ML model 30), which is configured to control the frequency at which the patient 4 receives subsequent notifications to image specific body parts of the patient 4. In one instance, when the symptom risk score is high, the processing circuitry 20 may prompt the patient 4 to image body parts more frequently.

[0212] Figure 11 This is a UI visualization of an example physiological parameter checking interface 1102 according to one or more techniques of this disclosure. The physiological parameter checking interface 1102 may include buttons including "Start Physiological Parameter Analysis" 1104, "Previous Parameter" 1106, "Next Parameter" 1108, and a physiological parameter menu. In some cases, the physiological parameter checking interface 1102 displays information based on user selection. Figure 7 The interface for calling or initializing the physiological parameter analysis blocks (e.g., block 708) displayed in the document.

[0213] Figure 12 This is a UI visualization of an example physiological parameter checking interface 1202 according to one or more techniques of this disclosure. In an illustrative example, the physiological parameter checking interface 1202 includes an ECG analysis page. The physiological parameter checking interface 1202, as a non-limiting example, displays two results: a normal ECG analysis 1204 and an abnormal ECG analysis 1208 (e.g., indicated by an abnormality 1210 observed in the ECG). ECGs can be received from medical device 6, medical device 17 (e.g., an IMD), or another device such as a watch, fitness tracker, or other wearable device configured to collect ECG data. In any case, computing device 2 can obtain the ECG data for analysis. In both non-limiting and illustrative examples, the analysis may include a normal result 1206 or an abnormal result 1212, in the case of an abnormal result, an alert may be required to contact a clinic.

[0214] In some instances, a sub-session may include a physiological parameter sub-session. In such instances, the processing circuitry system 20 can determine a set of data items based on the physiological parameter sub-session. In one instance, the processing circuitry system 20 can receive at least one physiological parameter corresponding to patient 4 based on a second sub-session and determine a set of data items based on the at least one physiological parameter. In some instances, the processing circuitry system 20 can receive at least one physiological parameter from one or more medical devices 17 including IMD 6 via communication circuitry system 26. The at least one physiological parameter includes at least one of the following: electrocardiogram (ECG) parameters, respiratory parameters, impedance parameters, core body temperature, skin surface temperature, activity parameters, blood pressure, vital signs, blood glucose levels, rhythm data, and / or pressure parameters. In some instances, the ECG parameter represents an abnormal ECG. In this case, the processing circuitry system 20 can determine the abnormality at a body part of patient 4 based at least in part on the abnormal ECG and, in some cases, in conjunction with image data. The physiological parameter may include health signals retrieved from IMD 6 or from one or more other medical devices 17, such as another IMD or a wearable device including one or more sensors.

[0215] Examples of ECG collection include ECGs collected directly from one of the medical devices 17 (e.g., medical device 6). In some instances, medical device 17 may include wearable devices such as activity trackers, heart rate monitors, pulse monitors, pulse oximeters, and temperature monitors (e.g., core temperature monitors, surface temperature monitors). Additionally, computing device 2 may receive ECGs collected from wearable devices or other ECG devices (e.g., medical device 17). In some instances, computing device 2 may provide a programmed connection to medical device 17 (e.g., via a drop-down menu). Computing device 2 may receive input from patient 4 or HCP indicating a target programmed connection (e.g., wireless connection) to one or more medical devices in medical device 17 via a drop-down menu. In some instances, the virtual registration application of this disclosure includes a device-aware application. That is, computing device 2 may store information about which devices it is communicating with. In some cases, computing device 2 may determine such information through a pairing process. In another instance, computing device 2 may receive information such as information downloaded by a doctor. In some instances, computing device 2 can determine such information based on user selections in drop-down menus (e.g., device drop-down menus).

[0216] In some instances, computing device 2 may include device awareness aspects based on inquiries to one of the medical devices 17. In another instance, computing device 2 may receive device parameters and information pushed by another device, such as via push notification. In some instances, computing device 2 may receive device information from another computing device within computing device 2 operated by HCP, where HCP can fill in the correct information via UI 22.

[0217] In some cases, computing device 2 can receive physiological parameters or physiological parameter analysis results directly from another device or indirectly from another device, such as via network 10. In an illustrative example, the computing device can receive an ECG or an image of an ECG from another device. That is, a scanner program can scan an ECG and upload the scan in any suitable document format. Similarly, a loader program can upload an image of an ECG for use by computing device 2. In some cases, computing device 2 may contain a scanner program and / or a loader program. In this case, computing device 2 can upload physiological parameter information to another device or store the parameter information in an internal storage device (e.g., storage device 24).

[0218] In some instances, circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry state 40 of medical device 17, can detect the selection of a second interface tile before providing a second sub-session, wherein the first interface tile corresponding to the first sub-session and the second interface tile corresponding to the second sub-session are different from each other. In one instance, processing circuitry system 20 can provide a second sub-session of the interactive session in response to the selection of the second interface tile.

[0219] In some instances, the highest-level interface of computing device 502 may include second interface tiles. In another instance, the interface of the first sub-session may include second interface tiles, allowing the user to navigate from the first sub-session to the second sub-session without having to return to the highest-level interface.

[0220] Figure 13 This is a UI visualization of an example device inspection interface 1302 based on one or more technologies of this disclosure. The device inspection interface 1302 displays a UI that can be customized according to user input. Figure 7 The example interface shown in the figure is used to call or initialize the device inspection block (e.g., block 710).

[0221] Figure 14 This is a UI visualization of an example device inspection interface 1402 according to one or more technologies of this disclosure. Calling the device inspection interface 1402 allows the computing device 2 to query the medical device 17 (e.g., IMD 6). In one instance, the computing device 2 can query the medical device 17 via various short-range wireless communication protocols and telemetry. The computing device 2 can populate the device inspection interface 1402 with various parameters of the device inspection section, as shown. In various instances, the backend system of a cloud-based implementation can push the query information to a mobile device, or a mobile device application can initiate the query locally on the mobile device. In any case, the user can audit the performance of the medical device 17 (e.g., IMD 6) by calling the application and sending statistics, such as... Figure 14 As shown. In Figure 14 In some instances, the monitored statistics include, but are not limited to, battery strength, impedance, pulse width, pacing percentage, pulse amplitude, and pacing mode. In some cases, the computing device 2 can automatically schedule routine device checks or follow-ups based on the results of the query.

[0222] In such instances, the sub-sessions of interfaces 1302 and 1402 include a device inspection sub-session, where a processing circuitry, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine a second set of data items. In one instance, processing circuitry system 20 can perform an inquiry to one or more medical devices among the medical devices 17 corresponding to the patient via communication circuitry system 26. The one or more medical devices 17 may include IMD 6 and, in some cases, other medical devices 17, such as wearable monitoring devices. Processing circuitry system 20 can perform the inquiry by establishing a wireless communication connection with the corresponding medical device 17. That is, processing circuitry system 20 can receive the second set of data items via a computing network. In some instances, the computing device can receive medical device inquiry data directly from one or more medical devices 17, from one or more edge devices 12, or any combination thereof via network 10. In any case, processing circuitry system 20 can determine the second set of data items based on the inquiry, wherein the second set of data items includes device inquiry data (e.g., battery, impedance, pulse width, etc.). In some instances, the processing circuitry system 20 can determine a post-implantation report after the device examination sub-session has concluded. That is, the processing circuitry system 20 can determine that the medical device 17 meets one or more performance thresholds based on the set of data items obtained through the device examination sub-session. In one instance, the processing circuitry system 20 can compare query data with data read during implantation. In such instances, the processing circuitry system 20 can determine the post-implantation report based at least in part on data items from the device examination sub-session. Examples of post-implantation reports and the generation of such reports are described herein (e.g., see references). Figure 21-23 ).

[0223] Figure 15 This is a UI visualization of an example part inspection interface 1502 based on one or more techniques disclosed herein. Part inspection interface 1502 displays information based on user input... Figure 7 The selection of the part inspection block shown in the image (e.g., block 712) can invoke or initiate a part inspection sub-session.

[0224] The body part inspection interface 1502 may include a Start Inspection 1504 button and a camera icon 608 button. The camera icon 608 can automatically start the body part inspection sub-session. However, in some instances, the user may want to adjust camera parameters before starting. Although not shown, the body part inspection interface 1502 may include additional options for adjusting various camera parameters. Additionally, the user can adjust camera parameters in real-time while capturing images of the implantation site using the camera. In some instances, camera parameters include adjustments between the front-facing camera and another camera, lighting (e.g., infrared, thermal imaging, flash, etc.), zoom level, focus, contrast, etc. Once ready, the processing circuitry system 20 can receive the user's selection to Start Inspection 1504 via the UI 22 to proceed to the next page (e.g., the interface) of the body part inspection sub-session (e.g., the next graphical interface of the body part inspection UI).

[0225] Figure 16 This is a flowchart illustrating an example method utilizing image acquisition, recognition, and / or image processing techniques according to one or more techniques of this disclosure. For example, refer to... Figure 15 , 17 The interface described above, such as the processing circuitry system 20 of computing device 2, the processing circuitry system 64 of edge device 12, the processing circuitry system 98 of server 94, or the processing circuitry system 40 of medical device 17, can receive UI commands to begin a site examination sub-session (e.g., a wound examination sub-session). In one instance, processing circuitry system 20 can receive a user input instruction to select the start examination icon 1504.

[0226] In the illustrative example, a method for imaging the implantation site (e.g., an image capture process) is described. Camera 32 captures images (1612) of the implantation site or adjacent to one of the medical devices 17 (e.g., IMD 6). Processing circuitry system 20 can capture images at specific time points after implantation of the medical device 17 (e.g., IMD 6). In some instances, a first computing device in computing device 2 can store various images to storage device 24 (1614). Alternatively or additionally, computing device 2 can transmit various images to a secure back-end system. Example back-end systems include edge device 12, server 94, and / or other components of network 10 (e.g., Medtronic). (Network). The backend system's processing circuitry (e.g., processing circuitry 64, processing circuitry 98, etc.) can process various images and / or route images to various other devices. In some instances, processing circuitry 20 can store images to storage device 50 of medical device 17. Similarly, processing circuitry 20 can store such data to storage device 62 of edge device 12 or storage device 96 of server 94.

[0227] The processing circuitry system 20 can guide the user by providing predetermined reminders. These reminders can be pushed to the user's computing device 2. Additionally, when the implantation site shows no signs of healing over time, the HCP (e.g., the prescribing physician) can access an interactive session interface (e.g., a site check sub-session interface) to follow up with the patient 4. That is, the processing circuitry system 20 can identify abnormalities, such as implantation sites showing no signs of healing over time, and therefore can transmit a notification to the HCP's computing device 2, allowing the HCP to access the interactive session interface (e.g., the site check sub-session interface) via UI 22, containing images, physiological parameters, etc.

[0228] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, may deploy ML models (e.g., DL models) and / or AI engines to analyze anomalies from each captured image from the site inspection sub-session as part of the site inspection sub-session. In illustrative and non-limiting examples, the site inspection sub-session may provide three levels of detection: “Presence of anomaly,” “Absence of anomaly,” and “Uncertain.” In one instance, if processing circuitry system 20 detects a highly probable anomaly in any image through the site inspection sub-session, then processing circuitry system 20 may determine the presence of the anomaly at that time. If processing circuitry system 20 determines that no highly probable anomaly exists in any of the images, then processing circuitry system 20 may determine that no anomaly exists at that time. In some instances, processing circuitry system 20 may transmit images from the site inspection sub-session to another computing device in computing device 2 (e.g., computing device 2 of a technician or HCP) for review by a human expert. The "expert" can be a trained professional who can review images of the patient's body and identify potential abnormalities and / or capture relatively clear images of the implantation site. If the human expert detects an abnormality, the patient can be asked to undergo follow-up with the prescribing physician.

[0229] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine thresholds for the presence or absence of anomalies. In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine parameters for site examination sub-sessions, including thresholds for anomaly detection, based on factors such as whether the implantation site has a first implant or a replaced implant, IMD type (e.g., CIED type), skin color, and the age of the monitored patient 4.

[0230] In an illustrative example, processing circuitry system 20 can determine the sensitivity level of a site examination sub-session (e.g., anomaly detection algorithm, etc.). To determine the sensitivity level, processing circuitry system 20 can determine medical device information (e.g., IMD information) regarding medical device 17, physiological parameters (e.g., ECG), etc. In such an example, processing circuitry system 20 can determine the sensitivity level based on the determined medical device information, physiological parameters, etc. In an illustrative and non-limiting example, processing circuitry system 20 can determine the prevalence factors defining the anomalies (e.g., infection) prevalent for a particular type of IMD. In another example, processing circuitry system 20 can determine the influencing factors defining the potential impact of anomalies (e.g., device malfunction, infection, etc.) on patient 4 and medical device 17 (e.g., IMD 6). Processing circuitry system 20 can determine the sensitivity level for generating a more conservative algorithm based on such or other information, which errs in over-detecting rather than under-detecting anomalies. That is, being more conservative and not missing potential anomalies (e.g., infection, IMD malfunction, etc.) may be important because doing so can provide high-energy, life-saving therapies. In one instance, IMD 6 may malfunction to the point that its temperature or migration data cannot be determined, such that when a potential anomaly is detected based on an image, the processing circuitry 20 can determine, independently of the data received from IMD 6, the likelihood that the anomaly is an actual anomaly based on an adjusted sensitivity level.

[0231] In another instance, when the processing circuitry 20 determines that, for example, the stimulator (not shown) and leads (not shown) are from different manufacturers but are combined into a single IMD 6, the processing circuitry 20 can determine a higher (e.g., more conservative) sensitivity level relative to other, less conservative sensitivity levels. That is, in the case of combining items from different manufacturers into a single device, the likelihood of potential anomalies may be higher, and therefore, the processing circuitry 20 can adjust the sensitivity level to be at a higher sensitivity level in this situation. In some instances, the processing circuitry 20 can adjust the sensitivity level used to identify specific anomalies based on the duration the IMD 6 has been implanted (e.g., built-in calculation bias). This is because certain anomalies (e.g., pocket infection) may be most common during, for example, the first year after implantation, and therefore, a higher sensitivity level can be used in a specific timeframe (e.g., the first year), and / or a lower sensitivity level can be used in another timeframe (e.g., after the first year).

[0232] In another instance, medical device 17 (e.g., IMD 6) may include LINQ. TM ICM. In this case, the processing circuitry 20 can employ a sensitivity level for LINQ compared to that used for other medical devices 17 (e.g., pacemaker implants). TM ICMs employ detection algorithms with varying sensitivity levels. Specifically, the detection algorithm can use medical device information to indicate a specific sensitivity level at which the medical device is implanted as part of a particular type of surgery (e.g., outpatient surgery). Additionally, the processing circuitry system 20 can determine, based on IMD information, that the schedule for virtual registration or other types of registration is arranged at specific intervals (e.g., regular intervals, irregular intervals, frequent intervals, infrequent intervals, etc.). In another example, the processing circuitry system 20 can determine the frequency at which the virtual monitoring service receives and / or monitors medical device diagnoses, such as those from medical device 17 (e.g., IMD 6, wearable heart rate monitor, and / or activity monitor, etc.).

[0233] In illustrative and non-limiting examples, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, may employ a first sensitivity level when determining an abnormality in a first type of implant (e.g., a pacemaker implant), and conversely, a second sensitivity level when determining an abnormality in a second type of implant (e.g., an ICM). In one example, the first sensitivity level may be higher than the second sensitivity level because processing circuitry system 20 may have determined that: the implantation procedure for the second type of implant was performed outside the office or in an outpatient setting; there are one or more periodically scheduled patient follow-ups via system 100 and / or system 300; and processing circuitry system 20 continuously or at least semi-continuously monitors diagnostic device data from the medical device, such as the result of periodic data transmissions from medical device 17 to other devices (e.g., edge device 12, etc.) of computing device 2 and / or system 300.

[0234] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine parameters of the imaging procedure for camera 32, including thresholds for anomaly detection, based on factors such as whether the implantation site has a first implant or a replaced implant, IMD type (e.g., CIED type), skin color, and the age of the monitored patient 4. In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine parameters of the imaging procedure based on information regarding various anomaly control procedures. In an illustrative example, anomaly control procedures may include the use of Medtronic's TYRX by the HCP (e.g., a surgeon or implantation clinician) during implantation of the medical device. TM It can absorb information from antibacterial coatings or other similar elements. It will be understood that TYRX TM It is a mesh capsule that houses implantable cardiac devices, implantable neurostimulators, or other IMDs. The processing circuitry 20 can determine bias factors based on the presence of such control procedures. This is because TYRX TM Designed to stabilize the device after implantation, while releasing antimicrobial agents, minocycline, and rifampin for at least seven days, and therefore, less likely to cause abnormalities during that period compared to implants without such control procedures. In other words, TYRX... TM Patients with the capsule as part of the implant typically have lower rates of TYRX than those without it. TMPatients with a capsule have a low chance of infection. In any case, with TYRX... TM Compared to the imaging procedure parameters used by the patient, the various anomaly detection algorithms of this disclosure can be configured to detect non-TYRX anomalies. TM Patients are more sensitive and / or have lower specificity (e.g., imaging procedure parameters).

[0235] In some instances, AI engines and / or ML models, such as AI engine 28 of computing device 2, AI engine 44 of medical device 17, ML model 30 of computing device 2, or ML model 46 of medical device 17, can determine sensitivity levels based on training the AI ​​engines and / or ML models. In one instance, to determine sensitivity levels, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can train the AI ​​engines and / or ML models based on a dataset containing prevalence data (e.g., infection rate of a specific type of medical device 17), severity data, data on the probability of anomalies, the potential or actual impact of specific types of anomalies (e.g., device malfunction and infection anomalies), IMD information (e.g., device manufacturing information, implantation surgery information), etc. After training based on such data, the AI ​​engines and / or ML models can determine sensitivity levels corresponding to each individual monitoring event (e.g., device environment) or a class of monitoring events for patient 4.

[0236] The advantages of applying such sensitivity levels include allowing monitoring system 100 to efficiently allocate processing, memory, and / or power resources by scaling the sensitivity level according to individual needs. Additionally, the sensitivity level can manage the rate at which computing device 2 receives data from other devices (e.g., transmission rate, etc.). In this way, computing device 2 can, for example, receive more data in situations where the probability of anomalies is high, and less data in other situations. This selective use of sensitivity levels also facilitates bandwidth considerations, such as by limiting the amount of communication data that might otherwise consume significant bandwidth of system 100 and / or system 300.

[0237] In some instances, the site inspection sub-session, including AI engine 28 and / or ML model 30, can be trained based on multiple images / videos that have been labeled to correspond to whether an abnormality exists (e.g., whether an infection is present). In one instance, the video can provide evidence of the patient's four-gait. In such instances, the processing circuitry system 20 may include a site inspection sub-session performed by AI engine 28 and / or ML model 30. AI engine 28 and / or ML model 30 can be trained using data that has been labeled based on improvement or deterioration of the implantation site. In one instance, AI engine 28 and / or ML model 30 can detect implantation site "improvement" or "no improvement" over time as an implantation state.

[0238] In some instances, the processing circuitry system 20 can acquire images of the implantation site from multiple site examination sub-sessions over time after implantation. The processing circuitry system 20 can analyze the temporal aging of implantation sites with different thresholds in a chronological order through the site examination sub-sessions to detect improvement or no improvement at the implantation site. Prescribing physicians can use the system to follow up only patients whose implantation sites do not show signs of healing. In some instances, the processing circuitry system 20 can operate according to a time-lapse pattern. During the time-lapse period, the processing circuitry system 20 can collect images, for example, in a chronological order (e.g., by a daily schedule) and merge these images together over 2–12 weeks post-implantation. This allows for time-series presentation and analysis of the images. In such instances, the processing circuitry system 20 can train the AI ​​engine 28 and / or ML model 30 based on the rate of change in implantation site healing (e.g., infection spread or growth). In some instances, the AI ​​engine 28 and / or ML model 30 can alternatively analyze the progress of implantation site healing rather than assessing the implantation site itself (e.g., the incremental changes between records tracking differences between images over multi-week periods and the superimposed successive images). In some cases, the AI ​​engine 28 and / or ML model 30 can track differences between still images to determine the increment of the implantation site over time (e.g., the increment of healing at the implantation site over time). The processing circuitry system 20 can then determine anomalies based on the analysis of the increment of time at the implantation site.

[0239] In some instances, the processing circuitry system 20 can determine the presence of a potential anomaly based on an image (1616). In one instance, the backend system can route various images to a computing device 2 of an expert technician trained to identify anomalies based on images of the implantation site. In another instance, the backend system can route various images to a second computing device in a computing device 2 with a specific configuration of an AI engine 28 and / or ML model 46 trained to identify anomalies based on images of the implantation site. In some instances, when an anomaly is identified, the processing circuitry system 20 can determine the likelihood (e.g., severity) of the anomaly based on an image of the implantation site (e.g., a captured image of the implantation site). In some cases, the processing circuitry system 20 can deploy a probabilistic model to determine the likelihood of the anomaly. In one instance, the processing circuitry system 20 can determine the potential severity of a potential anomaly based on analysis of the captured images.

[0240] In some instances, the processing circuitry system 20 may output a summary of the implant's status, including information on potential anomalies (1618). In one instance, the back-end system may transmit a report back to a first computing device in computing device 2 indicating the results of image analysis performed by the back-end system. In an illustrative example, the processing circuitry system 20 may generate a summary report identifying an anomaly based on the probability of the anomaly, wherein the summary may include information about the identified potential infection. In some instances, the processing circuitry system 20 may store all image data and markers (e.g., expert markers) in a database and computing system to continuously improve and deploy an automated anomaly detection system (e.g., AI engine 28 and / or ML model 30). In any case, the processing circuitry system 20 may output a summary report. In some instances, the summary report contains one or more frames of image data. In such instances, the processing circuitry system 20 may generate a summary report (e.g., a post-implantation report) containing one or more frames of image data, wherein the image data is received prior to anomaly determination and is at least partially used to determine the anomaly. In some cases, the report contains frames corresponding to one or more camera angles (e.g., left relative to right) from which the potential anomaly was identified. In some instances, when an anomaly is detected, the processing circuitry system 20 can output one or more various images from the implantation site of the sub-session for review by human experts.

[0241] In some instances, computing device 2 can determine whether to configure the interactive session to include a pass-through mode, in which patient 4 does not need to enter for consultation (e.g., for post-implantation infection consultation). In such instances, computing device 2 can provide HCP with access to various images (e.g., still images). Thus, in some instances, HCP can determine whether the implantation site is healing as expected or whether in-person follow-up is necessary.

[0242] In some instances, the HCP may have already programmed the interactive session program and transferred it to an application database (e.g., a program data store). In another instance, the HCP may have directly uploaded the interactive session program to computing device 2. That is, computing device 2 can access the interactive session program from the application database. In one instance, the interactive session program may contain an imaging program for performing a part-of-body examination sub-session. That is, the imaging program may be part of the interactive session program, while in some cases, the imaging program performing the part-of-body examination sub-session may be separate from the interactive session program. Furthermore, some aspects of the part-of-body examination sub-session program may be controlled by a separate programming application, such as a camera application native to the operating software of one of the computing devices 2 (e.g., an OEM camera application), while other aspects may be controlled by an interactive session programming application, such as enhanced overlay, camera parameter control (e.g., zoom, contrast, focus, etc.), enabling the interactive session software to work in conjunction with other software applications (e.g., camera applications, augmented reality applications, etc.) or devices running such software applications (e.g., augmented reality headsets, etc.).

[0243] HCP can be configured to operate in a pass-through mode, where the patient can completely waive post-implantation consultation until the execution of the interactive session leads to the identification of potential abnormalities, such as those meeting predefined thresholds. In such instances, HCP can access images to determine the presence of an abnormality regardless of whether the processing circuitry 20 determines the presence of a potential abnormality. In this way, HCP (e.g., physician, nurse, etc.) can independently adjudicate images, independent of automated image analysis of the site examination sub-session, to independently determine the state of the implant, including the healing status of the implantation site.

[0244] Figure 17 This is a UI visualization of an example site inspection interface 1702 according to one or more techniques of this disclosure. The site inspection interface 1702 includes a photo icon 608, which is configured to cause the camera 32 to capture an image of the implantation site 1704.

[0245] In some cases, the user can point the camera at the implantation site 1704. In this situation, the processing circuitry 20 can automatically perform anomaly detection, regardless of whether an image capture command has been received. Alternatively, when the processing circuitry 20 detects an anomaly, it can cause the camera 32 to automatically capture an image of the implantation site. Once an image is captured, an implant status indicator 1706 appears, indicating the status of the implant, including the implantation site 1704. Figure 17In some instances, the implantation site is indicated as "normal." In other instances, the processing circuitry 20 can perform this detection by comparing a first image (captured automatically or manually) with one or more baseline images (e.g., a set of first images captured over a predetermined time period, measured from the start of implantation or from the time the first image was taken). In one instance, the processing circuitry 20 can apply a sliding window to a historical set of images captured over time to filter images (e.g., older images) from one or more baseline images and compare the first image with one or more filtered baseline images. Additionally, the processing circuitry 20 can determine a projection based on one or more filtered baseline images and determine, at a predetermined time, a reference (e.g., a reference change characteristic) that can be compared with the first image to determine the presence of an anomaly at the image site.

[0246] In some instances, the processing circuitry system 20 may implement a region comparison zone (e.g., Dx) for differential diagnosis. The processing circuitry system 20 may perform gradient analysis on the implantation site 1704 and, for example, sternal regions of different skin colors to determine the differential diagnosis. The processing circuitry system 20 may refer to the differential diagnosis to determine if there is a potential abnormality at the implantation site 1704. The AI ​​engine 28 and / or ML model 30 also use various measurements from user-provided images to determine whether the implantation site is within a threshold of a “normal” state. In some cases, the processing circuitry system 20 may overlay a ruler or other enhancements or overlays on the image to help the user capture images useful for the measurements. That is, the processing circuitry system 20 may provide enhancements or another frame that the user can use to obtain the correct distance and / or perspective of the implantation site. In illustrative examples, the processing circuitry system 20 may guide the user to image the implantation site at a target distance from the camera 32, and in some cases, a second target distance from the implantation site. The processing circuitry system 20 may further guide the user to image the implantation site at a target angle relative to the implantation site or relative to a reference plane of the camera 32 (e.g., the starting position of the computing device 2). In such instances, the processing circuitry system 20 may use overlays, augmented scales, etc., as in augmented reality implementations, to capture images at a specific angle (e.g., a specific view of the implantation site), where the implantation site has a specific relative size in the image data frame, etc.

[0247] In some instances, the processing circuitry system 20 can train the AI ​​engine 28 and / or ML model 30 to distinguish relative measurements of color and markings. In this way, the processing circuitry system 20 can compensate for the different appearances of wounds on different skin tones, across different patient demographic groups, etc. In some instances, the image processing AI can use region comparisons within the same image to distinguish the implantation site from unaffected areas of the patient's skin (e.g., to derive relative or incremental information). The image processing AI can also be trained to compensate for differences between systemic infections and infections caused by implantation sites such as pockets or incisions. In some instances, the processing circuitry system 20 can deploy the AI ​​engine 28 and / or ML model 30 to determine red, green, and blue (RGB) image details based on captured images. Other color schemes. Additionally, the AI ​​engine 28 and / or ML model 30 determine the shape of the wound closure at the implantation site, whether the image includes gloss, etc., based on the captured image. The processing circuitry system 20 can determine, based on various image processing techniques, whether the image of the implantation site contains potential abnormalities or whether the implantation site otherwise meets predefined thresholds for a "normal" state.

[0248] Figure 18 The UI visualization of the interface 1802 is an example part of the inspection interface based on one or more techniques of this disclosure. Figure 18 The example site inspection interface 1802 displays abnormal implantation site results. When an abnormality is detected, the processing circuitry system 20 can provide a visual alert 1806. The processing circuitry system can include descriptive information about the potential abnormality in the visual alert 1806. In some instances, the processing circuitry system can include the visual alert 1806 as a medical intervention instruction for the user to perform some action (e.g., contact a clinic, etc.).

[0249] In some instances, the processing circuitry system 20 may provide an augmented reality overlay 1804 (e.g., an image overlay) on the interface 1802. The processing circuitry system 20 may do this to help the user capture images of the implantation site from a specific angle, using size references, etc. Additionally, the AI ​​engine 28 and / or ML model 30 may adjust the corresponding algorithms based on the trend that postoperative images will change as the implantation site changes (e.g., gradual healing, diminishing healing, etc.). In some instances, the processing circuitry system 20 may train the AI ​​engine 28 and / or ML model 30 to detect deviations from a "healthy" state in some examples. A healthy state may include characteristics of the implantation site from previously undetected abnormality inspection sub-sessions.

[0250] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can identify image overlays to enhance the set of preview frames and guide the user to capture images in a specific manner. In one instance, processing circuitry system 20 can determine patient data corresponding to a patient. Processing circuitry system 20 can then determine image overlay data based at least in part on the patient data. As discussed herein, patient data contains various information about the IMD patient, including any one or more of the following: image data of the implantation site (e.g., removal site), implantation site characteristics, patient identification data (e.g., patient name, authentication data, login information, etc.), patient input data (e.g., input via UI 22), or other information about the IMD 6, including implantation or removal date, IMD component details (e.g., leads, wiring routes, etc.). Image data may include current images or previously captured images, such as images captured shortly after implantation or before the implantation procedure. In such instances, image overlay data may correspond to an IMD and / or other components of the IMD. As used herein, a preview frame generally refers to an image data frame displayed to the user before and / or during image capture. A preview frame represents what the user observes on a display screen, for example, computing device 2. In any case, the image overlay data definition is configured to enhance the image overlay of the preview frame set. In some cases, the image overlay may contain a wireframe resembling the body contour of a subject, such as patient 4 or a generic contour.

[0251] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can acquire images of a patient's body, where the images correspond to one or more locations in the body where one or more components of an IMD (e.g., IMD 6, the leads of IMD 6) overlap. In one instance, the image may represent the right or left pectoral muscle region of the body, where IMD 6 includes an implant configured to be implanted in the pectoral muscle region of the body. In another instance, the image may represent a portion of the neck of patient 4, where the user's task is to image the portion of the neck where the leads of IMD 6 overlap, such as leads routed from IMD 6 to brain regions of patient 4. Processing circuitry system 20 can determine abnormalities (e.g., infection, discharge, etc.) at one or more locations in the body where one or more components of an IMD overlap based on the image.

[0252] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine that image overlay data includes a hollow outline of the body with an outline of the region of interest (e.g., implantation site), allowing the user to properly align the image to capture the region of interest at a specific angle, size, orientation, etc. In one instance, processing circuitry system 20 can determine that image overlay data includes a first portion of an outline comprising at least a portion of the body of patient 4, wherein the body portion corresponds to an implantation site of one or more IMD components, and determine a second portion of image overlay data, wherein the second portion is included within the outline and represents internal overlay of the region of interest (e.g., implantation site).

[0253] In illustrative and non-limiting examples, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine, at least partially, that the IMD coincides with a specific side of the pectoral muscle region of the body based on patient data. In one example, processing circuitry system 20 can determine a first portion of image overlay data to represent a specific side of the pectoral muscle region of the body. In some examples, processing circuitry system 20 can determine a second portion of the image overlay. In such examples, processing circuitry system 20 can determine, at least partially, based on patient data, a specific incision angle comprising the contour of the implantation site 1704 relative to at least a portion of the patient 4's body. That is, the image overlay data can be dynamic and based on the specific environment of the imaging of patient 4, such as based on the type of medical device 17, the location of medical device 17, etc. In any case, processing circuitry system 20 can determine the second portion to represent the implantation site including the specific incision angle.

[0254] Additionally, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can acquire one or more images of the body based on image coverage. In one example, processing circuitry system 20 can acquire an image of the body by determining from a set of preview frames that a second portion of the image coverage coincides with the implantation site of one or more IMD components. In response to determining the coverage, processing circuitry system 20 initiates automatic capture of an image of the patient 4's body. As used herein, "automatically" or "automatically" generally means without user intervention or control.

[0255] In another example, a processing circuitry system, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine image overlay data from an image overlay library. In one example, processing circuitry system 20 can determine static image overlays configured to provide boundaries for aligning the implantation site within the static image overlay. In an illustrative example, the boundaries may include a dashed box shape, similar to... Figure 18 The example shown is overlay 1804. In such instances, processing circuitry system 20 can retrieve static image overlays from an overlay library containing at least one image overlay. In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine customized image overlays, as image overlays customized for patient 4, based at least in part on patient data, IMD information, and / or template overlays (e.g., static image overlays). In an illustrative example, processing circuitry system 20 can obtain an image of the body by detecting movement of computing device 2 (e.g., via accelerometer data) and compensating for the movement by maintaining a specific orientation of the image overlay relative to the set of preview frames and one or more positions of the patient 4's body.

[0256] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine image coverage data by receiving a subset of preview frames via camera processor 38 and determining image coverage data based on the subset of preview frames. In such instances, AI engine 28 and / or ML model 30 can determine initial estimates of what the scar / implantation site looks like and what the patient's body looks like (shoulder frame, body shape, etc.) based on patient data, IMD information, etc. Then, when camera 32 is pointed at the implantation site, AI engine 28 and / or ML model 30 can fine-tune or deform the image coverage in real time to better frame the wound site with reference to other characteristics of the patient 4's body. In this way, the user can be guided by the image coverage to precisely align the implantation site within the coverage outline in a manner that allows computing device 2 to analyze image captures of the implantation site and know the angle of the wound site on the body, the size of the wound site, etc. Additionally, image overlay data can be used to train AI to determine image overlay for future imaging sessions. In another instance, the processing circuitry 20 can use a template overlay as an initial guess or it can use a modified template, and then modify the template in real time once the camera processor 38 receives the actual image data. In such instances, in addition to other features in the image that may be present at the implantation site (e.g., the clavicle for a chest implant, the hairline for a DBS implant, etc.), the processing circuitry 20 can customize the image overlay to fit or conform to the body shape / frame of the patient 4.

[0257] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can determine image coverage data based on the determination of a specific camera configuration of camera 32. In such instances, processing circuitry system 20 can determine whether a front or rear camera of the mobile computing device is being used to capture an image of the patient 4's body, or whether camera 32 is a separate camera unit where a user can stand nearby so that camera 32 can capture an image of the patient 4's body. In illustrative examples, when the camera used is a rear camera of the mobile computing device instead of a front camera, processing circuitry system 20 may require a corresponding mirror for image coverage. Additionally, camera configurations can include the number of cameras (e.g., dual cameras, triple cameras) and lens types (wide-angle, 360° lens, etc.), which will require different image coverage depending on the cameras used. In such instances, processing circuitry system 20 can determine image coverage data at least in part based on camera configuration. When an image overlay defined by image overlay data overlaps with the implantation site of interest or other body part of patient 4, the processing circuitry system 20 can automatically capture an image of the implantation site. As used herein, “overlay” may not include complete overlap, but may involve at least substantial overlap, such that a specific percentage of the body part overlaps with the image overlay. In one instance, when 80-90% of the implantation site is within the boundaries of a specific portion of the image overlay, the processing circuitry system 20 can determine that an overlap exists, such that the portion of the image overlay substantially overlaps with the body part.

[0258] In such instances, image overlay data can be configured to guide image capture of patient 4's body relative to a specific distance from one or more computing devices to the body surface. In some instances, processing circuitry 20 can determine image overlay data by creating wireframes (e.g., custom wireframes, template wireframes, etc.) via an overlay generator (e.g., AI engine 28 and / or ML model 30), where the overlay generator is trained to generate wireframes based on patient data. Wireframes generally refer to enhancements containing contours such as hollow outlines used to align objects in the scene captured within the wireframe. Users can fully perceive objects in the scene through the wireframes in the foreground, and can also perceive the wireframes in the foreground, thereby increasing the number of image data frames as understood in the art. In some instances, obtaining an image of patient 4's body may comprise one or more frames of image data received via communication circuitry 26, wherein one or more frames contain an image of patient 4's body. In another instance, obtaining an image of patient 4's body comprises video data capturing one or more locations of the patient's body (e.g., with the aid of image overlay). In this case, processing circuitry 20 can determine anomalies, including identifying anomalies from the video data and determining a post-implantation report based on the identification of the anomalies.

[0259] Figure 19This is a flowchart illustrating an example method of capturing images of the body according to one or more techniques of this disclosure. In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can create a personalized baseline for patient 4 and allow AI engine 28 (e.g., inference engine) and / or ML model 30 to provide trend-based analysis. In one instance, processing circuitry system 20 may deploy AI engine 28 (e.g., inference engine) and / or ML model 30, configured to evaluate images based on historical frames of image data to fit a trend line, rather than based on snapshots (e.g., a single still image) or even on consecutive snapshots of mutual evaluation rather than evaluation of the baseline characteristics of patient 4. In any case, such evaluation can inform patient 4 and / or HCP how the implantation site (e.g., removal site) changes (e.g., develops) over time toward healing or an abnormality (e.g., rapidly worsening infection or slowly developing infection). In one example, the processing circuitry system 20 enables the preprocessing algorithm to automatically adjust the scale and orientation of the captured images, allowing users reviewing delayed images to obtain a consistent view while reviewing successive images over time. Furthermore, due to the presence of contextual data available at inference points, the processing circuitry system 20 can achieve higher predictive confidence in image analysis, such as by utilizing an inference AI engine that reviews images from specific body part examination sub-sessions in addition to other data items from the interactive session, to determine a fully integrated post-implantation report.

[0260] In some instances, the AI ​​engine 28 and / or ML model 30 can be trained on multiple images that have been labeled as corresponding to whether an abnormality exists (e.g., whether an infection exists). In such instances, the AI ​​engine 28 and / or ML model 30 can be trained on data that has been labeled based on improvements at the implantation site. In one instance, the AI ​​engine 28 and / or ML model 30 can detect "improvement" or "no improvement" at the implantation site over time as an implantation status.

[0261] In some instances, the processing circuitry system 20 can acquire images of the implantation site from multiple interactive sessions over time. The processing circuitry system 20 can maintain an image chronology to detect improvement or lack of improvement at the implantation site. In one instance, the processing circuitry system 20 can collect images at a predetermined schedule and align the images over a period of time post-implantation. In such instances, the processing circuitry system 20 can train the AI ​​engine 28 and / or ML model 30 based on how much the characteristics of the implantation site change over time. In some instances, the AI ​​engine 28 and / or ML model 30 can determine post-implantation reports based on changes between consecutive images that identify differences between images over time.

[0262] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can identify a first set of images (1902) representing a specific location of the patient 4's body. In one instance, processing circuitry system 20 can identify a first set of images representing a specific location of the body where at least one component of IMD 6 (e.g., IMD 6, lead wire, etc.) overlaps. In some instances, the first set of images may contain a single image, while in other instances, the first set of images may contain multiple images.

[0263] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can determine the projection of altered characteristics, such as healing characteristics (1904). In one instance, processing circuitry system 20 can determine a trend line or model representing the projection of altered characteristics over time. That is, the projection typically represents the altered characteristics projected over time at a specific location on the patient 4's body. The specific location on the body may include the implantation site of IMD 6 or other body parts of the patient 4 that overlap with other components of IMD 6. In some instances, processing circuitry system 20 can determine the projection of altered characteristics based on images of other IMD recipients, such as recipients aligned with a specific group of patients 4.

[0264] In illustrative examples, processing circuitry 20 can determine the projection of altered characteristics from a first image set. In such examples, processing circuitry 20 can determine a common alignment reference for aligning the first image set in a delayed representation of the first image set. In some examples, processing circuitry 20 can align multiple images from the first image set according to the common alignment reference to determine the delayed representation. In some examples, processing circuitry 20 can determine the projection of altered characteristics based on multiple aligned images. In some examples, each image in the first image set can be verified to determine whether an image should be included in multiple images. In one example, processing circuitry 20 can verify the quality (e.g., blurriness), orientation (e.g., portrait only) of an image, and can discard images that fail the verification test.

[0265] As described herein, in various instances, a specific location on the body may contain an implantation site for at least one component of the IMD 6. In such instances, a common alignment reference includes alignment truths utilizing one or more of the following: the relative angle of the implantation site, the relative size of the implantation site, to determine and implement alignment truths, for example, to align an image in a time-delay configuration. In some instances, the common alignment reference may further include: image illumination characteristics, skin pigmentation characteristics, the relative orientation of the implantation site, or the relative position of the implantation site in a corresponding image data frame representing a first set of images.

[0266] In an illustrative example, the processing circuitry system 20 can align multiple images from a first image set. In one example, the processing circuitry system 20 can provide an image overlay configured to enhance a set of preview frames during image capture. The processing circuitry system 20 can determine the overlap between an image of a specific location of the body from the set of preview frames and the image overlay. The processing circuitry system 20 can obtain a first image from the first image set, at least partially based on the overlap, wherein the first image represents a specific location of the body according to a common alignment reference. The processing circuitry system 20 can align an image of the implantation site with the common alignment reference using multiple images.

[0267] In some instances, the processing circuitry system 20 can determine a set of pre-implantation images representing a specific location on the body prior to implantation. In one instance, the set of pre-implantation images may include images captured before the implantation surgery, such that the pre-implantation images represent the baseline of patient 4, to which patient 4 will return after healing, sometimes inevitably with added surgical artifacts (e.g., scars, etc.). In such instances, a physician or physician's assistant may capture the set of pre-implantation images while placing a white balance card (e.g., representing pure white) next to patient 4's body. In illustrative and non-limiting instances, a nurse or image acquisition representative may capture one or more skin tone baseline images of the implantation site (e.g., the intended implantation site) of patient 4 via camera 32 prior to implantation of the IMD 6, while image acquisition simultaneously or in parallel captures images of color references, such as a white balance reference card held within a frame.

[0268] The processing circuitry system 20 can determine a set of pre-implantation images with color reference to allow it to identify the color truth of patient 4's pigmentation and / or skin type. The processing circuitry system 20 can store the set of pre-implantation images to a storage device (e.g., cloud storage or storage device 24), where the AI ​​engine 28 and / or ML model 30 can (e.g., via a cloud solution) determine the color truth of patient 4. As described herein, the color truth can be used to determine baseline characteristics of patient 4 and to project the healing characteristics of patient 4 over time based on images captured post-implantation. In this way, taking into account the diversity of skin color and body type worldwide, the processing circuitry system 20 can acquire images of the implantation site immediately before and after implantation to accurately identify abnormalities (e.g., excessive or abnormal bruising) at the implantation site across various groups.

[0269] In some instances, the pre-implantation image set includes a single image or multiple images representing a specific location of the patient 4's body captured from a specific vantage point relative to a set of potential vantage points representing various different views of the implantation site, under specific lighting conditions. In an illustrative example, the processing circuitry system 20 can determine baseline characteristics of the patient 4's body before implantation based on the pre-implantation image set. In some instances, baseline characteristics may include pigmentation, skin type, etc.

[0270] In some instances, AI engine 28 and / or ML model 30 can automatically determine microgroups of patient 4 based on a pre-implantation image set, such as microgroups based on skin pigmentation. In some instances, users can manually self-identify user-defined groups via UI 22, such as based on skin type or pigmentation. In another instance, processing circuitry system 20 can automatically identify microgroups of patient 4 using manually entered information and baseline characteristic data, which use the manually entered information as hypothetical input to AI engine 28 and / or ML model 30, configured, for example, to automatically or at least semi-automatically identify microgroups for further image processing and / or training purposes as described herein. In some instances, AI engine 28 and / or ML model 30 can automatically infer the groups of patient 4 that will align best for analyzing patient 4's images based on preprocessing when the first image of patient 4 is captured.

[0271] In an illustrative example, processing circuitry 20 can transmit pre-implantation images via communication circuitry 26 to a device (e.g., another computing device in computing device 2) configured to operate a skin color classification algorithm for preprocessing. In another example, processing circuitry 20 can operate a skin color classification algorithm, in which case the pre-implantation images can be stored only in storage device 24. The algorithm can be trained on thousands of skin photographs and uses color scales such as Von Luschan's chromatic scale, Fitzpatrick scale, or combinations thereof. Processing circuitry systems, such as processing circuitry 20 of computing device 2, processing circuitry 64 of edge device 12, processing circuitry 98 of server 94, or processing circuitry 40 of medical device 17, can classify the patient 4's skin type into various skin type categories using color scales, enabling ML model 28 and / or AI engine 30 to accurately identify skin abnormalities after implantation in one of medical devices 17 (e.g., IMD 6). Skin type classification may involve categorizing or organizing the patient 4's skin type into subsets, such as various subsets corresponding to specific color scales, for example, the von Luchamp scale and / or the Fischer scale. In any case, the processing circuitry system 20 may automatically group the patient 4 into microgroups, for example, based on skin type classification. That is, the processing circuitry system 20 may automatically determine the group of the patient 4 based on one or more pre-implantation images. In another instance, the processing circuitry system 20 may automatically determine the group of the patient 4 based on one or more post-implantation images (e.g., a first image set and / or a second image set).

[0272] In such instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can apply specially defined implantation site analysis algorithms for each group to produce optimal results for specific groups, such as automatically determined groups, by taking into account differences in skin type. Additionally, during application loading, processing circuitry system 20 can provide patient 4 with the option to self-identify their race, age, weight, biological sex, and body type via UI 22. As described herein, if provided, processing circuitry system 20 can use these inputs to fine-tune the results of AI engine 28 and / or ML model 30.

[0273] The processing circuitry system 20 can determine the projection of the altered characteristics based at least in part on baseline characteristics. In such instances, the altered characteristics from the projection are configured to approximate the patient's baseline characteristics over time. That is, the processing circuitry system 20 can determine a trajectory back to the patient 4's baseline based on post-implantation images, such as a return to the state of a fully healed scar at the implantation site containing IMD 6.

[0274] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can identify a second set of images (1906). In one instance, processing circuitry system 20 can identify a second set of images representing a specific location of the body at time intervals following the progression of a first set of images. Similar to the first set of images, the second set of images may contain a single image, while in other instances, it may contain multiple images. Similarly, processing circuitry system 20 can perform similar verification on the images in the second set of images and can discard images that fail the verification test. In one instance, processing circuitry system 20 can determine whether an image was captured according to a specific orientation (e.g., portrait, angle, etc.) and can prompt the user via UI 22 to capture the image according to the specific orientation when an image is identified as captured in an incorrect orientation. In another instance, processing circuitry system 20 can identify objects through object recognition and notify the user via UI 22 when an image represents an incorrect object, such as an object that does not appear to represent the relevant implantation site.

[0275] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can determine the second set of altered characteristics (1908). In one instance, processing circuitry system 20 can determine the second set of altered characteristics based on a second set of images.

[0276] In an illustrative example, the processing circuitry 20 may determine a first image set to include at least one first post-implantation image and at least one second post-implantation image, wherein these images are captured at consecutive time intervals. The consecutive time intervals may be temporally spaced apart by a first duration. In one example, the duration may comprise a relatively short period of time, such as one hour or one day. In such an example, the second image set may include at least one third post-implantation image captured at a registration time following the time the first image set was captured.

[0277] In such instances, the second duration may be longer than the first duration, such as one week after the last capture of the first image set. That is, the first image set may be captured at frequent intervals, such as hourly or every hour of the first day, immediately after implantation or at least immediately after bandage removal from the implantation site. The first image set is captured at frequent intervals to determine how the characteristics of the images change over time (e.g., healing indicators). In such instances, the second image set includes consecutive fourth images captured at a second registration time for a third duration after the first registration time, such as two or three weeks after capturing the first images of the baseline set. In such instances, the second set of altered characteristics includes the healing trend of relative altered characteristics between consecutive images of the second image set. That is, the second set of altered characteristics may be based on healing progress between at least two images of the second image set, where healing progress can be compared to the first set of altered characteristics determined based on the first image set and / or the pre-implantation image set. The processing circuitry system 20 may further determine the second set of altered characteristics based on the pre-implantation image set and / or the first image set to track trajectories from the first image set to the second image set, from the second image set to the patient 4 based on a baseline from the pre-implantation images, and / or combinations of such trajectories.

[0278] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can compare the second set of altered characteristics with a projection of the altered characteristics (1910). In one instance, processing circuitry system 20 can compare the second set of altered characteristics with a projection. In an illustrative example, in order to compare the second set of altered characteristics with a projection, processing circuitry system 20 can determine the amount of difference between the second set of altered characteristics and the projection. In some instances, processing circuitry system 20 can determine the amount of difference between the second set of altered characteristics and the projection (e.g., the time when the second set of images is identified, such as when the second set of images is acquired, captured, received, timestamped, transmitted from another device, and / or obtained), wherein the projection time is based on an interval or point in time corresponding at least partially to a historical set of images (e.g., a first set of images, pre-implantation images, a first set of images and pre-implantation images, etc.).

[0279] In a non-limiting example, the processing circuitry system 20 can determine a projection based on a historical set of images that indicates a specific change should occur relative to the implantation site of patient 4 at a specific future time (e.g., projection time). In some cases, the processing circuitry system 20 can prompt patient 4 to capture a second set of images (e.g., one or more images) at the projection time and can compare the characteristics of the second set of images with the projection to determine the degree of cure of patient 4 tracked on the projection. If the difference between the projection and the second set of characteristics exceeds a certain threshold, the processing circuitry system 20 can determine that further analysis is needed or that additional images of the implantation site should be captured for supplementary or enhanced analysis. In another example, the processing circuitry system 20 can identify the second set of images and, based on the projection, determine a specific portion of the projection that overlaps with the second set of images (e.g., overlaps in terms of time intervals), rather than prompting patient 4 for images. In any case, the processing circuitry system can compare the second set of images with the projection to determine the presence of anomalies, such as when the comparison indicates a specific deviation exceeding a predetermined threshold.

[0280] In some cases, the processing circuitry system 20 can determine, based on a set of historical images, how much the implantation site of patient 4 should change over time at a specific future time (e.g., an expected time). In this case, the processing circuitry system 20 can compare a second set of change characteristics with the projection to identify potential abnormalities, the likelihood of potential abnormalities, or whether further analysis, such as by an HCP, technician, etc., is required. In another example, the processing circuitry system 20 can determine, based on a second set of images and, in some cases, a first set of images, how much the implantation site of patient 4 has changed or appears to have changed over time at a time corresponding to the second set of images. The processing circuitry system 20 can determine a second set of change characteristics based on the determination of how much the implantation site of patient 4 has changed or appears to have changed over time, and the processing circuitry system 20 can compare the second set of change characteristics with an expected projection, wherein the expected projection indicates how much the processing circuitry system 20 expects the implantation site of patient 4 to change over time at a specific time in the projection, said projection being aligned with or at least approximating the time corresponding to one or more images from the second set of images (e.g., the time the second set of images was obtained).

[0281] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can output estimates via UI 22 regarding the time it takes for one or more milestone changes at a specific location on the body, as projected. In one instance, the milestone estimate may include indications about the time it takes for redness to subside, the time it takes for soreness to subside to below a predefined threshold relative to the patient 4's pain threshold, the time it takes for the likelihood of infection to decrease to below a predefined threshold, and the time it takes for the implantation site to heal beyond a predefined healing threshold. Additionally, processing circuitry system 20 may determine the milestone estimate based on a comparison of a second set of change characteristics with the projection. In such instances, the comparison indicates the amount of deviation that processing circuitry system 20 can utilize to determine the estimate notified by the current image of patient 4 and past images of patient 4. Furthermore, processing circuitry system 20 may determine the estimate based on (e.g., notified by) images and / or healing trends of other IMD patients (e.g., patients in the same microgroup as patient 4). In any case, the deviation amount can indicate the degree to which patient 4's healing deviates from the projection (e.g., a projection based on historical images of patient 4 and / or other IMD patients), as notified by the determination of the second set of altered characteristics. Thus, the processing circuitry system 20 can provide notified estimates of the timeframe at which patient 4 can be expected to reach various altered milestones in patient 4's healing process.

[0282] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can identify potential abnormalities based on comparison (1912). In one instance, processing circuitry system 20 can identify potential abnormalities at specific locations on the body, at least in part, based on comparison. In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can identify potential abnormalities by determining an abnormality trend indicating expected progress toward or toward a worsening abnormality relative to the potential abnormality. In any case, in response to determining a potential abnormality, processing circuitry system 20 can transmit a first image set and a second image set (e.g., via communication circuitry system 26) to one or more devices of the HCP via network 10. In another instance, the processing circuitry system 20 may use anomaly detection to determine a post-implantation report, which in some instances includes a basis of physiological parameter data, device query data, etc.

[0283] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can identify (e.g., via an inference engine) at least one component corresponding to the IMD (e.g., gauze, TYRX). TM This could be a user inputting information (e.g., medication, etc.) or one or more anomaly control procedures corresponding to patient 4 (e.g., medication, etc.). In one instance, the processing circuitry 20 can determine such information based on patient input during a patient input sub-session. That is, the user (e.g., patient 4) can input medication information, gauze information, etc., and the processing circuitry 20 can refer to said information via an AI inference engine to determine projection data at least in part based on one or more anomaly control procedures. In such instances, the projection of the healing timeline and the healing trend may differ, as when using TYRX. TM In cases of control procedures or the use of specific drugs.

[0284] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of data server 94, or processing circuitry system 40 of medical device 17, can output the results of the comparison to storage devices (e.g., storage devices 24, 65, 96, and / or 50). In one instance, as part of outputting a second set of images to one or more HCPs, processing circuitry system 20 can transmit anomalous data items configured to visually represent potential anomalies identified in the second set of images. In an illustrative example, where processing circuitry system 20 marks the results of images as including “potential infection,” processing circuitry system 20 can generate an alert and (e.g., via UI 22) provide an alert indication to one or more HCPs. The alert indication may include a summary of the results, a post-implantation report, one or more images, and in some cases, highlight the images to indicate characteristics of the potential anomaly. Additionally, the alert indication may include a delay in the image created according to one or more of the various techniques of this disclosure. In any case, the processing circuitry, such as the processing circuitry 20 of the computing device 2, the processing circuitry 64 of the edge device 12, the processing circuitry 98 of the data server 94, or the processing circuitry 40 of the medical device 17, can (e.g., via a corresponding storage device) maintain the chronology of the first image set.

[0285] In some instances, the projection techniques of this disclosure allow the processing circuitry system 20 to personalize the algorithm and make the feedback most useful to the patient 4 and the clinician. This is because images of the implantation site can be captured at a high frequency immediately after implantation, thus allowing the processing circuitry system 20 to generate time-series (e.g., time-lapse) datasets. The processing circuitry system 20 can then use the time series to create a personalized baseline for the patient and allow the model to generate trend analysis, as described herein. In another instance, the processing circuitry system 20 can utilize preprocessing algorithms to automatically adjust the scale and orientation of all images so that the physician viewing the time series has a consistent view when the HCP appears to review historical images over time. In such instances, the processing circuitry system 20 can provide predetermined reminders to prompt the user to capture specific images at a first frequency (e.g., with a specific zoom level, lighting, angle, etc.) to determine a first set of reference images (e.g., a first set of post-implantation images), and can provide predetermined reminders to prompt the user to capture specific images at a second frequency, where the second frequency may include variable frequencies, but typically may include frequencies less than the first frequency, to determine a second set of continuously registered images (e.g., a second set of post-implantation images). Based on at least two image sets, the processing circuitry system 20 can accurately determine the presence of an anomaly and / or determine post-implantation reports indicating an anomaly notified by other sets of data items (e.g., physiological parameters, etc.). It should be noted that, as described herein, various techniques of this disclosure (e.g., projection techniques, sub-session techniques, overlay techniques, etc.) are applicable to “cloud” implementations (e.g., Medtronic). Both network and "edge" implementations (e.g., regarding mobile applications, tablet applications, IoT applications, etc.).

[0286] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can later synchronize image analysis data and results for ease of access and / or algorithm tuning. In one instance, processing circuitry system 20 can coordinate with other processors in the processing system to synchronize image analysis data and results between the edge network (e.g., computing device 2, edge device 12, medical device 17, etc.) and the cloud network (e.g., server 94).

[0287] Figure 20This is a flowchart illustrating an example method of a set of UI interfaces for navigating a virtual registration process (e.g., an interactive session) according to one or more technologies of this disclosure. Processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine data items including image data representing the body of patient 4 based on a site examination sub-session (2002). In another example, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine data items including physiological parameters based on a physiological parameter sub-session (2004). In an optional example, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine data items including patient input based on a patient status sub-session (2006). As described herein, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine data items including device query data based on device inspection sub-sessions (2008). It should be understood that sub-sessions can be executed in various different orders and may have additional sub-sessions or not have one or more of the sub-sessions described herein. In any case, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine anomalies based on a combination and / or synthesis of image data and one or more other data items described herein (2010).

[0288] Figure 21 This is a UI visualization of a complete registration interface 2102, an example of one or more technologies according to this disclosure. The complete registration interface 2102 demonstrates the UI that the processing circuitry system 20 can display after completing one or more virtual registration sub-sessions (e.g., device inspection sub-session, site inspection process, etc.). In some cases, the processing circuitry system 20 can output the complete registration interface 2102 to be forwarded to HCP / clinicians, etc., after information submission. Figure 21 This demonstrates the UI that computing device 2 can generate and render for indicating corresponding... Figure 7The completion of an interactive session for all four tiles shown. As described herein, in some instances, the full registration interface 2102 may involve fewer or more tiles, where the computing device 2 utilizes additional or fewer interfaces to obtain data about the patient 4 and / or the medical device 17. The full registration interface 2102 may further include a graphical icon 2104 indicating the completion of, for example, a site examination sub-session.

[0289] In some instances, the images can be determined by a remote dermatology service. In this case, the remote dermatology service can be configured to generate reports based on the images (e.g., summary reports, post-implantation reports, etc.). Additionally, computing device 2 can receive reports from the remote dermatology service and provide them for review via UI 22. In such instances, computing device 2 can engage with the remote dermatology service via network 10 and / or via a medium, such as one of edge devices 12. As described herein, edge device 2 may include one of computing devices 2, wherein computing device 2 is configured to engage with and / or operate the remote dermatology service to generate summary reports based on various images.

[0290] In some cases, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can generate summary reports that match the user's proficiency level. In one example, processing circuitry system 20 can identify a user's specific proficiency level and generate a summary report for the user based on that proficiency level. In this case, proficiency level can represent the user's level of expertise in reviewing reports such as remote dermatology reports. Processing circuitry system 20 can automatically determine this proficiency level based on user data and / or can receive user input indicating this proficiency level, such as requesting such information from the user through questionnaires or other input mechanisms.

[0291] In an illustrative example, processing circuitry system 20 may receive a single report data file. Processing circuitry system 20 may then transform the data in the data file to generate a user-oriented summary report (e.g., a post-implantation report). Processing circuitry system 20 may transform the data in different ways, for example, after determining that the report is to be presented to a “novice” user (e.g., an elderly patient taking their own photo) rather than to another user, such as an “expert” user (e.g., a specific HCP, nursing home staff, etc.). The summary report may include images, physiological parameters, patient status updates, device query data (e.g., device diagnostics), and / or the results of automated image analysis of an interactive reporting session, reflecting the HCP's decision.

[0292] In some instances, the full registration interface 2102 may provide options for scheduling on-site outpatient follow-ups. This option may be presented via UI 22 when a potential anomaly is detected or when the processing circuitry 20 cannot rule out anomalies from the evaluation of the camera images.

[0293] Additionally, the complete registration interface 2102 may include a "Generate Report" icon 2106 and / or a "Send Report to Clinic" icon 2108. Among other information, the report may include images captured by the processing circuitry system 20. Furthermore, the report may include synthesized data containing failure criteria based on failure severity (e.g., criteria for detecting anomalies), the number of failed tests, the number of failed attempts, the number of failed patches, etc. Additionally, the processing circuitry system 20 may generate the report based on physician preferences (e.g., report type, details of data weighting, etc.). Furthermore, the processing circuitry system 20 may transmit the report based on the physician's preferences for notifications and / or notification frequency. The processing circuitry system 20 may further synthesize data based on the characteristics of the patient 4 and / or the type of medical device 17 (e.g., IMD 6).

[0294] In an illustrative example, the processing circuitry system 20 may employ various anomaly scoring algorithms based on the severity of potential anomalies detected in one or more images. The anomaly scoring algorithm may determine an anomaly score mapped to an actionable response (e.g., transmitting a report to the HCP, automatically scheduling a clinician visit, etc.) based on factors such as IMD type. Sensitivity may define a threshold whose range can vary conservatively based on a response to a determination of failure in any sub-session, resulting in a specific output (e.g., failure determination, transmitting a report to the HCP, etc.). In another example, sensitivity may define a complex threshold utilizing a weighted composite score, in a non-limiting example, which takes into account the severity of failure across sub-sessions related to any potential medical condition of patient 4 and the underlying algorithm defining each sub-session (whether failed or not) to determine, for example, whether a failure requiring a specific response has been determined based on the mapping from anomaly score to a specific response output. Additionally, sensitivity may be further defined as a threshold that takes into account physician-programmable limitations of the medical device 17.

[0295] In some instances, the processing circuitry system 20 can provide feedback to the patient 4 via simplified graphical icons. In another instance, the processing circuitry system 20 can obtain indications from the HCP (Heat-Chip Response Center) instead of simplified icons to provide a preference for complex outcomes. In this case, the processing circuitry system 20 can provide feedback to the patient 4 as a complex outcome.

[0296] Figure 22This is a UI visualization of an example complete registration interface 2202 according to one or more techniques of this disclosure. In one instance, the complete registration interface 2202 indicates a receipt confirmation 2204 from the HCP office or an intermediate system responsible for submitting to the HCP office. That is, the processing circuitry system 20 can receive confirmation from the intermediate system (e.g., edge device 12) and, consequently, can provide the receipt confirmation 2204. The receipt confirmation 2204 may indicate that a post-implantation report has been received at the HCP office of patient 4. In another instance, the receipt confirmation 2204 may indicate confirmation that the post-implantation report has been successfully saved to a database (e.g., one of servers 94, multiple servers 94 including a cloud storage database, server 94 including a cloud storage database, and edge device 12, etc.). In such instances, an authorized HCP can access the report from the database via the HCP's computing device 2. In an illustrative example, the receipt confirmation may further include uploading a summary report to an EMR database. As described herein, the techniques of this disclosure are applicable to "cloud" implementations (e.g., Medtronic). Both network and / or "edge" implementations (e.g., regarding mobile applications). Thus, post-implantation reports can be uploaded and stored in any number of different locations and accessed from those locations in any number of different ways.

[0297] Figure 23 This is a flowchart illustrating an example method for determining instructions for medical intervention regarding an IMD patient according to one or more techniques of this disclosure. In some instances, a processing circuitry system, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine the health status of at least one medical device in medical device 17 (e.g., IMD 6) and / or patient 4 (2302) based on a post-implantation report. The health status may include indications that processing circuitry system 20 has determined abnormalities at the implantation site of IMD 6 and / or abnormalities in the performance of one or more medical devices 17 (e.g., IMD 6), abnormal physiological parameters, and / or abnormalities in patient status input. In some cases, processing circuitry system 20 may determine the health status based on the synthesis (e.g., combination) of data items obtained through multiple sub-sessions of an interactive registration session (e.g., site check sub-session and physiological parameter sub-session). In some instances, processing circuitry system 20 determines the health status based on images received through UI 22. Although described as typically performed by computing device 2, Figure 23 The example method can be performed by any one or more of, for example, edge device 12, medical device 17, or server 94, such as by the processing circuitry system of any one or more of these devices.

[0298] Processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can determine instructions (2304) for medical intervention based on the health status of patient 4. For example, if processing circuitry system 20 determines that an abnormality exists at the implantation site of IMD 6, processing circuitry system 20 can determine instructions for medical intervention based on the abnormality. In another instance, when processing circuitry system 20 determines that an abnormality exists at the implantation site of IMD 6 and that the physiological parameters of patient 4 are abnormal, processing circuitry system 20 can determine instructions for medical intervention based on post-implantation reports generated at least in part based on multiple abnormalities. In some instances, processing circuitry system 20 can determine different instructions for different severity levels or abnormality classifications. For example, processing circuitry system 20 can determine a first set of instructions for an abnormality that processing circuitry system 20 determines may not be as severe as another abnormality. In some instances, processing circuitry system 20 can not determine intervention instructions if processing circuitry system 20 determines that the abnormality level does not meet a predefined threshold. In some instances, the processing circuitry 20 can provide alerts, such as text- or graphic-based notifications, visual notifications, etc. In some instances, the processing circuitry 20 can trigger an audible alarm or a tactile alarm to alert the patient 4 to a identified abnormality. In other instances, the computing device 2 can provide visible light indications, such as emitting red light for high severity or yellow light for moderate severity. Alerts can indicate potential, possible, or predicted abnormal events (e.g., potential infection).

[0299] In some instances, processing circuitry systems, such as processing circuitry system 20 of computing device 2, processing circuitry system 64 of edge device 12, processing circuitry system 98 of server 94, or processing circuitry system 40 of medical device 17, can transmit instructions (2306) for medical intervention to be displayed via a user interface such as UI 22. In some instances, processing circuitry system 20 can transmit instructions to a device of the HCP (e.g., a caregiver), such as an HCP pager. In instances where processing circuitry system 64 generates instructions, processing circuitry system 20 can transmit instructions for medical intervention to a user interface, such as UI 22. Instructions may include post-implantation reports and / or indications of individual abnormalities (e.g., abnormal ECG values, etc.). In some instances, edge device 12, medical device 17 (e.g., IMD 6), server 94, and / or computing device 2 can use collected data to employ integrated diagnostic methods to predict adverse health events (e.g., worsening infection). In other words, computing device 2 can use anomaly determinations, including probability or severity determinations, as evidence nodes for a probabilistic model deployed, for example by AI engine 28 and / or ML model 30, to determine the probability score indicating the likelihood of infection at the implantation site of patient 4, the likelihood of infection within a predetermined time period, the likelihood that one of the medical devices 17 (e.g., IMD 6) may experience functional abnormalities (e.g., malfunctions), etc. In some instances, processing circuitry, such as processing circuitry 20 of computing device 2, processing circuitry 64 of edge device 12, processing circuitry 98 of server 94, or processing circuitry 40 of medical device 17, may further include failure criteria based on failure severity (e.g., criteria for detecting anomalies), the number of failed tests, the number of failed attempts, the number of failed tiles or sub-sessions, patient characteristics, the type of medical device 17 (e.g., IMD 6), physician preferences, etc., as evidence nodes for probabilistic determinations (e.g., anomaly prediction).

[0300] Although described from the perspective of a user computing device 2 implementing the technology of this disclosure, it should be noted that the system of this disclosure supports bidirectional communication between a user (e.g., patient 4) and the HCP. Bidirectional communication can operate using similar UIs at both ends of the communication line. In such an example, the HCP can access images, physiological parameter data items, medical device information, patient information, etc., uploaded by the user through the user's computing device 2. Furthermore, the HCP can determine the presence or absence of anomalies based on the uploaded data using the HCP's computing device 2 and transmit a summary report back to the user's (e.g., patient 4's) computing device 2, for example, containing one or more indications of the anomaly.

[0301] Illustrative examples of this disclosure include:

[0302] Example 1: A method for monitoring a patient with an intramural disorder (IMD), the method comprising: providing an interactive session via a computing device, the interactive session being configured to allow a user to navigate multiple sub-sessions, the multiple sub-sessions including at least a first sub-session and a second sub-session different from the first sub-session, wherein the first sub-session includes capturing image data via one or more cameras; determining, via the computing device, a first set of data items based on the first sub-session of the interactive session, the first set of data items containing the image data; determining, via the computing device, a second set of data items based on the second sub-session of the interactive session, the second set of data items being different from the first set of data items and including one or more of: data obtained from the IMD, at least one physiological parameter of the patient, or user input data; determining, at least in part, an abnormality corresponding to at least one of the patient or the IMD based on the first set of data items and the second set of data items; and outputting a post-implantation report of the interactive session via the computing device, wherein the post-implantation report includes an indication of the abnormality and an indication of the amount of time that has occurred since the date of implantation of the IMD.

[0303] Example 2: According to the method of Example 1, determining the post-implantation report includes: determining the anomaly based on the second set of data items; and determining the post-implantation report based at least in part on the anomaly and the first set of data items.

[0304] Example 3: The method according to any one of Examples 1 or 2, wherein providing the interactive session comprises: training a session generator by the computing device according to one or more of the following: group parameters or IMD information; deploying the session generator by the computing device to generate the interactive session; and providing an interactive session by the session generator that is at least partially personalized for the user as a result of the training.

[0305] Example 4: The method according to any one of Examples 1 to 3, wherein the IMD information includes query data, and wherein the method further comprises: performing a pairing process via the computing device, the pairing process being configured to pair the computing device with the IMD; receiving the query data about the IMD via the pairing process; and storing the query data as historical query data for reference via the computing device.

[0306] Example 5: The method according to any one of Examples 1 to 4, wherein providing the interactive session includes: identifying the patient's follow-up schedule, the follow-up schedule being defined by one or more time periods, during which the computing device is configured to prompt the user to engage in the interactive session; and providing the interactive session according to the follow-up schedule.

[0307] Example 6: According to the method in Example 5, identifying the follow-up schedule includes: receiving a push notification through the communication circuitry of the computing device; and determining a first time period of the follow-up schedule based on the push notification.

[0308] Example 7: According to the method of any one of Examples 5 or 6, the one or more time periods include at least one time period corresponding to a predetermined amount of time from the date of implantation of the IMD.

[0309] Example 8: The method according to any one of Examples 1 to 7, wherein the image data includes one or more frames of an image representing the patient's body.

[0310] Example 9: According to the method of Example 8, wherein a part of the patient's body includes the implantation site of the IMD, and wherein the one or more frames represent an image of the implantation site.

[0311] Example 10: The method according to any one of Examples 1 to 9, wherein providing the interactive session includes: providing a top-level interface containing a first interface tile, wherein the first interface tile corresponds to the first sub-session, and wherein the first sub-session includes a first sub-interface level that is at a lower level relative to the level of the top-level interface.

[0312] Example 11: According to the method of Example 10, wherein the first data item set includes an image overlay, and wherein the method further includes: outputting the image overlay at the first sub-interface level through the computing device.

[0313] Example 12: The method according to any one of Examples 10 or 11, wherein providing the first sub-session includes: detecting the selection of the first interface tile via the computing device; and providing the first sub-session of the interactive session via the computing device.

[0314] Example 13: According to the method of Example 12, determining the first set of data items includes: providing the user with a prompt via the computing device to capture image data using one or more cameras; and determining at least a portion of the first set of data items after the prompt.

[0315] Example 14: The method according to any one of Examples 10 to 13, wherein providing the second sub-session includes: detecting the selection of a second interface tile via the computing device, wherein the first interface tile and the second interface tile are different from each other; and providing the second sub-session of the interactive session in response to the selection of the second interface tile.

[0316] Example 15: According to the method described in Example 14, the highest-level interface includes the second interface tile.

[0317] Example 16: The method according to any one of Examples 14 or 15 further includes: providing a second sub-session of the interactive session via a second sub-session interface; modifying a second interface tile to indicate completion of the second sub-session; providing a first sub-session of the interactive session after the second sub-session; modifying a first interface tile to indicate completion of the first sub-session; providing a third sub-session of the interactive session after the first sub-session or the second sub-session; and determining a third set of data items, different from the first set of data items, based on the third sub-session of the interactive session using the computing device.

[0318] Example 17: According to the method of Example 16, determining the third data item set includes: receiving physiological parameter signals; and determining the third data item set based on the physiological parameter signals.

[0319] Example 18: The method according to any one of Examples 1 to 17, wherein the anomaly includes a first anomaly, and wherein determining the post-implantation report comprises: outputting a second set of data items to another device via a communication circuitry of the computing device; receiving, via the communication circuitry of the computing device, an analysis result of the third set of data items, the result indicating that the second set of data items does not indicate the presence of a second anomaly; and determining the post-implantation report based at least in part on the first anomaly and the second set of data items.

[0320] Example 19: The method according to any one of Examples 1 to 15, wherein the second sub-session includes a physiological parameter sub-session, wherein determining the second data item set includes: receiving at least one physiological parameter corresponding to the patient according to the second sub-session; and determining the second data item set according to the at least one physiological parameter.

[0321] Example 20: According to the method of Example 19, receiving the at least one physiological parameter includes: receiving the at least one physiological parameter from a plurality of medical devices via the communication circuitry system of the computing device.

[0322] Example 21: The method according to any one of Examples 19 or 20, wherein the at least one physiological parameter includes at least one of the following: electrocardiogram (ECG) parameter, respiratory parameter, impedance parameter, activity parameter, or pressure parameter.

[0323] Example 22: According to the method of Example 21, wherein the ECG parameter represents an abnormal ECG, and wherein determining the abnormality includes: determining the abnormality at least in part based on the abnormal ECG.

[0324] Example 23: The method according to any one of Examples 1 to 15, wherein the second sub-session includes a device checking sub-session, wherein determining the second set of data items includes: performing an inquiry to one or more medical devices corresponding to the patient via the communication circuitry system of the computing device, wherein the one or more medical devices include the IMD; and determining the second set of data items based on the inquiry.

[0325] Example 24: The method according to any one of Example 23, wherein performing the query includes: receiving the second set of data items via a computing network.

[0326] Example 25: The method according to any one of Examples 23 or 24, wherein determining the post-implantation report comprises: determining, based on the second set of data items, that the one or more medical devices meet one or more performance thresholds; and determining the post-implantation report based at least in part on the second set of data items.

[0327] Example 26: The method according to any one of Examples 1 to 3, wherein the second sub-session includes a patient status sub-session, wherein determining the second set of data items includes: receiving user input data according ...

Claims

1. A system for monitoring a patient with an implantable medical device (IMD), the system comprising: A memory configured to store image data; as well as One or more processors communicating with the memory, the one or more processors being configured to: An interactive session is provided that is configured to allow a user to navigate multiple sub-sessions, the multiple sub-sessions including at least a first sub-session and a second sub-session different from the first sub-session, wherein the first sub-session includes capturing the image data through one or more cameras; A first set of data items is determined based on the first sub-session of the interactive session, the first set of data items containing the image data; A second set of data items is determined based on the second sub-session of the interactive session. The second set of data items is different from the first set of data items and includes one or more of the following: data obtained from the IMD, at least one physiological parameter of the patient, or user input data. An anomaly corresponding to at least one of the patient or the IMD is determined, at least in part, based on the first set of data items and the second set of data items. and Output a post-implantation report for the interactive session, wherein the post-implantation report includes an indication of the anomaly and an indication of the amount of time that has occurred since the IMD was implanted.

2. The system of claim 1, wherein the second sub-session includes a physiological parameter sub-session, wherein, in order to determine the second set of data items, the one or more processors are configured to: Receive at least one physiological parameter corresponding to the patient according to the second sub-session; and The second set of data items is determined based on the at least one physiological parameter.

3. The system of claim 1 or 2, wherein the second sub-session includes a device inspecting the sub-session, wherein, in order to determine the second set of data items, the one or more processors are configured to: Perform an inquiry into one or more medical devices corresponding to the patient, wherein the one or more medical devices include the IMD; and The second set of data items is determined based on the query.

4. The system of claim 1 or 2, wherein the interactive session includes a third sub-session and a fourth sub-session, wherein the third sub-session includes a physiological parameter sub-session and the fourth sub-session includes a device checking sub-session, wherein, in order to determine the anomaly, the one or more processors are configured to: Determine user input data based on the second sub-session; The patient's at least one physiological parameter is determined based on the third sub-session; The query data is determined based on the fourth sub-session; and The anomaly is determined at least in part based on the user input data, the at least one physiological parameter, or the query data.

5. The system according to claim 1 or 2, wherein the system includes a computing device, wherein the computing device includes at least one of the processors and at least one of the cameras, wherein the at least one processor is configured to: The first set of data items is determined by receiving the image data from the at least one camera; The anomaly is determined at least in part based on the first set of data items and the second set of data items.

6. A non-transitory computer-readable storage medium having instructions stored thereon, the instructions causing one or more processors to: An interactive session is provided to a user, the interactive session being configured to allow the user to navigate multiple sub-sessions, the multiple sub-sessions including at least a first sub-session and a second sub-session different from the first sub-session, wherein the first sub-session includes capturing image data through one or more cameras; A first set of data items is determined based on the first sub-session of the interactive session, the first set of data items containing the image data; A second set of data items is determined based on the second sub-session of the interactive session. The second set of data items is different from the first set of data items and includes one or more of the following: data obtained from an implantable medical device (IMD), at least one physiological parameter of the patient, or user input data. An anomaly corresponding to at least one of the patient or the IMD is determined, at least in part, based on the first set of data items and the second set of data items. and Output a post-implantation report for the interactive session, wherein the post-implantation report contains an indication of the anomaly.

7. A method for monitoring a patient with an implantable medical device (IMD), the method comprising: An interactive session is provided via a computing device, the interactive session being configured to allow a user to navigate multiple sub-sessions, the multiple sub-sessions including at least a first sub-session and a second sub-session different from the first sub-session, wherein the first sub-session includes capturing image data via one or more cameras; Based on the first sub-session of the interactive session, the computing device determines a first set of data items, the first set of data items containing the image data; Based on the second sub-session of the interactive session, the computing device determines a second set of data items, which is different from the first set of data items and includes one or more of the following: data obtained from the IMD, at least one physiological parameter of the patient, or user input data. An anomaly corresponding to at least one of the patient or the IMD is determined, at least in part, based on the first set of data items and the second set of data items. as well as The computing device outputs a post-implantation report of the interactive session, wherein the post-implantation report includes an indication of the anomaly and an indication of the amount of time that has occurred since the IMD was implanted.

Images