Automated management of procedure cards maintained for healthcare professionals by a collaborative medical platform

Abstract

A collaborative medical platform facilitates remote collaboration related to medical procedures during the stages of a medical case. The collaborative medical platform receives telemetry or video data from a location that does not identify the medical worker or medical procedure. Using the characteristics of the medical worker and the telemetry or video data maintained by the collaborative medical platform, the platform selects the medical worker connected to the telemetry or video data. The collaborative medical platform stores the connection between the selected medical worker and the telemetry or video data. Subsequently, the collaborative medical platform selects procedure cards maintained for the selected medical worker for the corresponding type of medical procedure and can identify deviations between one or more of the selected procedure cards and the telemetry or video data. The interface allows the selected medical worker to modify the procedure card where the deviation has been identified.

Description

Technology Field

[0001] Cross-reference of related applications

[0002] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 605,879 filed December 4, 2023; U.S. Provisional Patent Application No. 63 / 641,754 filed May 2, 2024; U.S. Provisional Patent Application No. 63 / 661,015 filed June 17, 2024; U.S. Provisional Patent Application No. 63 / 661,858 filed June 19, 2024; U.S. Provisional Patent Application No. 63 / 717,950 filed November 8, 2024; U.S. Provisional Patent Application No. 63 / 718,000 filed November 8, 2024; and U.S. Provisional Patent Application No. 63 / 719,015 filed November 11, 2024, the contents of which are respectively incorporated herein by reference It is included.

[0003] Technology field

[0004] The described embodiment relates to a system and method for managing procedure cards maintained by a collaborative medical platform for medical professionals. Background Technology

[0005] A healthcare worker performs a medical procedure on a patient at a medical facility. When the medical procedure is performed, sensors capture telemetry data describing the operation or settings of one or more medical devices during the procedure. Additionally, one or more cameras or image capture devices capture video data describing the performance of the medical procedure. The captured telemetry and video data may be analyzed later to evaluate the performance of the medical procedure. This evaluation identifies changes to one or more techniques for performing the medical procedure, identifies educational content regarding the medical procedure to assist in its subsequent performance, or identifies the techniques performed during the medical procedure to present to other healthcare workers performing that type of medical procedure.

[0006] Different medical professionals may possess specific methods, skills, or preferences when performing different types of medical procedures, and medical facilities maintain procedure cards specific to various professionals to assign professional-specific information regarding different types of medical procedures. Medical facilities may maintain sets of procedure cards for medical professionals, and different sets of procedure cards correspond to different types of medical procedures. Different procedure cards within a set may be associated with different steps of the corresponding medical procedure, and the order of the procedure cards within the set specifies the sequence in which the steps of that medical procedure are performed. This enables medical facilities to simplify the performance of different types of medical procedures by different medical professionals.

[0007] Additionally, after completing a medical procedure, the healthcare worker prepares a post-procedure summary describing the performance of the procedure. The post-procedure summary can identify modifications to one or more techniques when performing that type of medical procedure in the future. Furthermore, the post-procedure summary may include specific information that influences the performance of that type of medical procedure. Traditionally, healthcare workers have not had access to telemetry or video data captured during the performance of the medical procedure when preparing post-procedure summaries, which limits the amount of detail included in the summaries prepared by many healthcare workers. Similarly, reviewing procedure cards associated with the healthcare worker and the type of medical procedure performed can be helpful when the healthcare worker prepares the post-procedure summary. However, conventional procedure cards are physical documents that may not be easily accessible to the healthcare worker when preparing the post-procedure summary.

[0008] Locations, such as medical facilities, may provide captured telemetry or video data to external systems for the analysis of telemetry or video data or for subsequent retrieval when preparing post-procedure summaries. However, data privacy restrictions often limit the information a location can distribute outside the location where the medical procedure was performed. For example, many medical facilities are prohibited from providing information to external systems that can uniquely identify the patient on whom the medical procedure was performed. To comply with such data privacy restrictions, a location cannot include information identifying the medical procedure or one or more healthcare personnel associated with the procedure in the telemetry or video data captured during the procedure provided to systems outside of that location. Similarly, compliance with data privacy restrictions prevents the location where the medical procedure was performed from providing external systems with access to scheduling information regarding the medical procedure performed at that location.

[0009] Unless an external system receives or accesses information from a location (e.g., a medical facility) identifying the medical personnel associated with a medical procedure, it cannot correlate the received telemetry or video data regarding the medical procedure with the medical personnel performing the procedure or associated with the procedure. To correlate telemetry or video data captured during a medical procedure with a medical personnel, conventional external systems manually review the received telemetry or video data to identify the medical procedure and the medical personnel associated with the telemetry or video data. Since locations such as medical facilities often perform a large number of medical procedures daily, the volume of information regarding the telemetry or video data, medical personnel, and medical procedures that must be reviewed to correlate them with medical personnel is impractical and difficult to handle for manual review. Therefore, compliance with data privacy restrictions often hinders external systems from providing medical personnel with subsequent access to telemetry or video data captured during a medical procedure, as the external system is often unable to identify one or more medical personnel associated with the telemetry or video data. Brief explanation of the drawing

[0010] FIG. 1 is an exemplary embodiment of a computing environment for electronically assisted medical procedures. Figure 2 is a block diagram of an exemplary architecture for a collaborative medical platform. FIG. 3a illustrates a first view of an exemplary worker dashboard associated with a collaborative medical platform. FIG. 3b illustrates a second view of an exemplary worker dashboard associated with a collaborative medical platform. Figure 4 illustrates an exemplary worker dashboard that displays educational content items to medical workers associated with a collaborative medical platform. FIG. 5 is an exemplary embodiment of a case sharing interface associated with sharing medical cases in a collaborative medical platform. FIG. 6 is an exemplary embodiment of a case dashboard associated with a case set in a collaborative medical platform. Figure 7 is an exemplary telepresence interface associated with a collaborative medical platform. Figure 8 is another example of a telepresence interface associated with a collaborative medical platform. Figure 9 is an exemplary analysis dashboard associated with a collaborative medical platform. Figure 10 is an exemplary video interface associated with a collaborative medical platform. Figure 11 is an exemplary prompt for a healthcare worker to verify a connection to telemetry data or video data associated with a collaborative healthcare platform. FIG. 12 is an exemplary request for supplementary information regarding telemetry data or video data connected to a medical worker associated with a collaborative medical platform. Figure 13 is an exemplary procedure card interface associated with a collaborative medical platform. FIG. 14 is a flowchart of an exemplary embodiment of a process in which a collaborative medical platform provides a prompt to a medical worker based on one or more procedure cards maintained for the medical worker and received telemetry data or video data. Specific details for implementing the invention

[0011] The drawings and the following description describe specific embodiments merely by way of example. Those skilled in the art will readily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be adopted without departing from the principles described herein. Hereinafter, reference will be made to the various embodiments illustrated in the accompanying drawings. Where feasible, similar or identical reference numerals may be used in the drawings and may indicate similar or identical functions.

[0012] A collaborative healthcare platform facilitates the exchange of data between telemedicines during the pre-procedure, intra-procedure, and post-procedure phases in relation to a medical case. The collaborative healthcare platform receives telemetry data or video data captured from a medical facility during the performance of a medical procedure. Telemetry data describes the movement or operation of one or more medical devices during the medical procedure, and video data captures the actions of one or more healthcare workers during the medical procedure. However, to comply with one or more data privacy restrictions, the collaborative healthcare platform does not receive data from the location where the telemetry data or video data was captured that identifies the healthcare worker performing the medical procedure or the patient on whom the medical procedure was performed.

[0013] A collaborative healthcare platform selects healthcare workers connected to received telemetry or video data by utilizing information received from client devices associated with healthcare workers, as well as locally stored information regarding healthcare workers. For example, the collaborative healthcare platform receives telemetry or video data along with the characteristics of healthcare workers and trains a worker prediction model to generate a probability that a healthcare worker will be connected to the telemetry or video data. Based on the probability generated for at least a set of healthcare workers, the collaborative healthcare platform selects a healthcare worker and stores the connection between the selected healthcare worker and the telemetry or video data. This enables the collaborative healthcare platform to connect a healthcare worker to received telemetry or video data that does not contain data or metadata identifying the healthcare worker.

[0014] Additionally, the collaborative medical platform maintains procedure cards for various medical professionals. A set of procedure cards may be associated with a type of medical procedure and a medical professional, and the set of procedure cards identifies the medical professional's skills, configuration, methods, or preferences for performing that type of medical procedure. In various embodiments, the collaborative medical platform selects a set of procedure cards associated with a medical professional connected to telemetry data or video data. The collaborative medical platform generates information describing the performance of that type of medical procedure by comparing the telemetry data or video data connected to the medical professional with the selected set of procedure cards associated with the medical professional and the type of medical procedure for which the telemetry data or video data was captured. Additionally, information from one or more procedure cards can be utilized by the collaborative medical platform to assist the medical professional in generating a post-procedure summary for the medical procedure. For example, the collaborative medical platform generates a prompt that identifies deviations between the telemetry data or video data and the procedure cards within the selected set of procedure cards. Prompts may be presented to healthcare professionals through an interface for generating post-procedure summaries to reduce the amount of input provided by healthcare professionals to generate post-procedure summaries or to identify specific information to include in the post-procedure summary. Furthermore, the collaborative healthcare platform may provide a prompt to healthcare professionals to modify one or more procedure cards in a set in response to identifying one or more deviations between telemetry data or video data and one or more procedure cards in a set. Providing such a prompt in response to identifying deviations from one or more procedure cards simplifies the modification of one or more procedure cards for a type of medical procedure based on changes made in the performance of that type of medical procedure by the healthcare professional.

[0015] FIG. 1 illustrates an exemplary embodiment of a computing environment (100) for a collaborative medical platform (140). The collaborative medical platform (140) may include one or more servers coupled by a network (130) to a client device (150) associated with a user (155) of the collaborative medical platform (140), medical equipment (160), and various third-party servers (170). The collaborative medical platform (140) facilitates the exchange of collaborative data between medical professionals, patients, administrators, or other users (155) through the client device (150) to support the pre-procedure, in-procedure, and post-procedure phases of a medical case. The collaborative medical platform (140) may also facilitate access to telemetry data (e.g., real-time video, images, biometric detection data, equipment control and / or status signals, etc.) from medical equipment (160) that can be utilized in conjunction with performing medical procedures and managing patient cases. Furthermore, the collaborative medical platform (140) can facilitate access to various third-party servers (170) that provide external services such as electronic healthcare record (EHR) services, medical telepresence services, operating room scheduling, and data analysis services.

[0016] To further support the pre-procedure phase of a medical case, the collaborative medical platform (140) may select one or more reference content items to present to a medical professional before performing a medical procedure. In various embodiments, the collaborative medical platform (140) maintains a repository or library of reference content items from which reference content items for the medical professional are selected. Alternatively or additionally, one or more third-party servers (170) maintain reference content items, and the collaborative medical platform (140) selects one or more reference content items from the third-party servers (170). Reference content items for the medical professional may be retrieved from a combination of one or more third-party servers (170) and the collaborative medical platform (140). The collaborative medical platform (140) selects one or more reference content items for the medical professional by utilizing data in the medical professional's user profile.

[0017] To support the in-procedure phase of a medical case, the collaborative medical platform (140) can facilitate the presentation of various information to support the procedure, such as pre-procedure images, models, patient data, equipment information, or other data. The collaborative medical platform (140) can also facilitate telepresence sessions that allow one or more remote contributors to access videos, images, 3D models, equipment telemetry data, or other data streams captured during the medical procedure in progress. The collaborative medical platform (140) can also enable remote practitioners to provide annotations or other comments related to real-time videos, images, or 3D models associated with the procedure. The collaborative medical platform (140) tracks and stores all data from the procedure (including videos, medical equipment telemetry, and collaborative comments) in association with a case identifier to enable subsequent access.

[0018] During the procedure phase, the collaborative medical platform (140) may present educational content regarding the medical procedure being performed to one or more medical personnel performing the medical procedure. The educational content describes the performance of the medical procedure, such as the techniques to be used, the movement of medical devices or medical equipment, information on the settings for the medical equipment, or other information. During the procedure phase, the collaborative medical platform (140) compares the telemetry data or video data of the medical procedure with a baseline reference associated with the educational content and selects the educational content associated with the baseline reference where a deviation occurs from the telemetry data or video data. The educational content may include commands to modify one or more settings of the medical equipment based on the educational content when executed by the medical equipment (160), thereby simplifying the adjustment of the operation of the medical equipment (160).

[0019] To support the post-procedure phase of a medical procedure, the collaborative medical platform (140) enables medical professionals associated with a case to collaboratively monitor data related to the patient's recovery. For example, the collaborative medical platform (140) can provide an interface for viewing health records related to the patient's recovery and facilitate collaborative exchanges among medical professionals through case-specific content feeds. The collaborative medical platform (140) can also perform various analyses related to the medical procedure performed based on data aggregation. The analyses may be useful for supporting patient recovery, improving future procedures, and tracking the performance of medical professionals.

[0020] Educational content related to medical procedures may be selected by the collaborative medical platform (140) and presented to a medical professional who performed the medical procedure during the post-procedure phase. For example, an indicator or analysis determined for the medical procedure by the collaborative medical platform (140) is compared to a baseline standard for various educational content. In various embodiments, the collaborative medical platform (140) selects educational content associated with the indicator and the baseline standard where deviation occurs and presents the selected educational content to the medical professional. For example, the collaborative medical platform (140) simplifies access to educational information related to medical procedures by including information identifying the selected educational content in one or more interfaces created to present it to the medical professional.

[0021] The collaborative medical platform (140) can intelligently utilize data collected during the pre-procedure, in-procedure, and / or post-procedure phases of a case during different phases of the same case or different cases. For example, annotations of images or 3D models, practitioner comments from content feeds, or other information obtained during the pre-procedure phase may be made available during the in-procedure phase to assist practitioners during the procedure being performed. Analytical data related to post-procedure data may be utilized to generate recommendations for future procedures, such as educational content, to improve efficiency and / or results.

[0022] The collaborative medical platform (140) can also facilitate functions such as managing clinical trials, facilitating training and performance tracking, facilitating the broadcasting of medical-related presentations, and facilitating procedure scheduling. Beneficially, the collaborative medical platform (140) stores a complete record of medical cases (including video and telemetry from procedures) on a centralized, standardized platform that naturally enables collaboration in an online environment where practitioners can interact from different remote locations. The collaborative medical platform (140) can maintain data in a manner that complies with the data privacy and compliance obligations of medical practitioners and organizations.

[0023] The collaborative medical platform (140) may also employ various machine learning techniques to infer recommendations, insights, or other artificially generated contributions based on data collected by the collaborative medical platform (140). For example, the collaborative medical platform (140) may generate recommendations for a medical professional to review educational content related to the medical professional based on data captured by the collaborative medical platform (140) during the performance of a medical procedure. For example, the collaborative medical platform (140) selects educational content for the medical professional based on telemetry data captured during a medical procedure performed by the medical professional. As another example, the collaborative medical platform selects educational content for the medical professional based on video data captured during a medical procedure performed by the medical professional. The educational content selected by the collaborative medical platform may be video, audio, text, or other data describing the performance of the medical procedure. Additionally or alternatively, it may be educational content configuration commands or configuration data for one or more medical devices (160).

[0024] The collaborative medical platform (140) may generate and present other recommendations to the medical worker based on information stored for the medical worker. For example, the collaborative medical platform (140) generates recommendations for the medical worker based on the type of procedure scheduled to be performed by the medical worker. In various embodiments, the recommendations include case records associated with one or more past cases captured in the collaborative medical platform (140) regarding the previous performance of the type of procedure for a patient in a similar situation. If appropriate authorization is granted, the worker may review the entire case record, including pre-procedure information, video or other data from the procedure itself, and post-procedure result data, through the collaborative medical platform (140). As another example, the collaborative medical platform (140) may intelligently generate recommendations inviting a specific medical worker to collaborate on the case based on the relevant worker who possesses relevant expertise, experience, and / or availability. Then, an invitation may be generated to the medical worker to enable access to and collaboration on the case during at least one of the pre-procedure, in-procedure, and post-procedure phases. Additionally, the collaborative medical platform (140) can intelligently identify and present patient risk factors related to the performance, planning, and post-procedure management of procedures. The collaborative medical platform (140) can also intelligently recommend educational content for training medical personnel based on individual tracked performance and various comparative analyses.

[0025] The collaborative medical platform (140) may be implemented using an on-site computing or storage system, a cloud computing or storage system, or a combination thereof, and may be implemented by utilizing a local or cloud-based server that may include a physical machine or a virtual machine or a combination thereof. The cloud-based server may include a private cloud system, a public cloud system, a hybrid public / private cloud system, or a combination thereof. Accordingly, the collaborative medical platform (140) may be local, remote, and / or distributed with respect to the medical environment where the procedure is performed and the client device (150) providing user access. Furthermore, different parts of the collaborative medical platform (140) may run on different remote servers, and various system elements of the collaborative medical platform (140) may be coupled to communicate via a network (130).

[0026] A client device (150) may include, for example, a mobile phone, tablet, laptop or desktop computer, other computing device, or an application running thereon to access the collaborative medical platform (140) via a network (130). The client device (150) may enable access to various user interfaces (which may include a web-based interface accessed via a browser or an application interface accessed via an application) for viewing / viewing or editing information associated with the collaborative medical platform (140). The client device (150) may include conventional computer hardware such as a display, an input device (e.g., a touch screen), memory, a processor, and a non-transient computer-readable storage medium that stores instructions for execution by the processor to perform the functions described herein. Examples of user interfaces are described in more detail below in connection with FIGS. 3 through 13.

[0027] A third-party server (170) can facilitate various services utilized by the collaborative medical platform (140). For example, the third-party server (170) may include various EHR systems for managing patient records, a robot control platform for controlling surgical robots or other medical equipment, a telepresence server for facilitating telepresence services, a patient scheduling system, a hospital information system (HIS), or other servers. As another example, one or more third-party servers (170) may include educational content regarding various medical procedures, such as papers on various medical procedures, audio data related to medical procedures, video data related to medical procedures, settings or configuration details for medical equipment (160) used in medical procedures, or other descriptive information regarding medical procedures. The third-party server (170) may be implemented using a cloud computing or storage system, such as various on-site computing or storage systems, private cloud systems, public cloud systems, hybrid public / private cloud systems, or a combination thereof.

[0028] Medical equipment (160) may include various sensors, such as cameras or other imaging equipment, biometric monitors, or other sensing devices that collect data associated with the medical procedure being performed. Sensor data may include physiological or biological signals (e.g., heart rate, blood pressure, body temperature, etc.), video, electrical signals indicating the status of a medical prescription, or other information. The camera or image sensor may include a still image camera, a video camera, a three-dimensional (3D) imaging device, or a combination thereof. The camera may include a fixed camera within a medical environment (e.g., an operating room) or a camera integrated into a medical device, such as an endoscope camera. The imaging system may include a computed tomography (CT) imaging system, a magnetic resonance imaging (MRI) system, an X-ray system, or other imaging equipment. Medical equipment may also include a robotic device that facilitates robot-assisted medical procedures. The robotic device may include, for example, a robotic arm or other computer-controlled mechanical device that performs or assists in the medical procedure. The robotic device may be pre-programmed to perform a series of specific steps or tasks, or may be manually controlled by an operator. Telemetry data associated with the robotic device may include force data, position data or other sensor data, control signals, error conditions, or other data related to the operation of the robotic device during the procedure. Medical equipment data may be streamed in real time to the collaborative medical platform (140) or stored on a third-party server (170) and then uploaded to the collaborative medical platform (140) later.

[0029] The network (130) includes a communication path for communication between a collaborative medical platform (140), medical equipment (160), a client device (150), and a third-party server (170). The network (130) may include one or more local area networks and / or one or more wide area networks (including the Internet). The network (130) may also include one or more direct wired or wireless connections (e.g., Ethernet, WiFi, cellular protocol, WiFi Direct, Bluetooth, Universal Serial Bus (USB), or other communication links).

[0030] FIG. 2 is a block diagram illustrating an exemplary architecture of one embodiment of a collaborative medical platform (140). In the embodiment of FIG. 2, the collaborative medical platform (140) includes a data collection module (205), an entity management module (210), an interface management module (215), a medical intelligence module (220), a telepresence module (225), an analysis module (230), a staff training module (235), a presentation module (240), an application integration module (245), a video library (250), a connection graph repository (255), a user profile repository (260), and a patient data repository (265). In other embodiments, the collaborative medical platform (140) includes functional blocks that are different from or additional to those shown in FIG. 2. Furthermore, in some embodiments, a single functional block provides the functions of multiple functional blocks shown in FIG. 2.

[0031] In one embodiment, the illustrated function block may be executed entirely within the collaborative medical platform (140), but alternative embodiments may include various modules or individual functions of modules executed by one or more third-party servers (170). Here, the collaborative medical platform (140) may interact with the third-party server (170) via an application programming interface (API) to enable the collaborative medical platform (140) to request and utilize services provided by the third-party server (170) to facilitate any of the functions described herein. For example, in one embodiment, electronic medical records may be provided by the third-party server (170). Here, the collaborative medical platform (140) may query the third-party server (170) for relevant data but does not necessarily store complete patient records locally. Furthermore, the third-party server (170) may facilitate services such as telepresence sessions, presentation creation, access to video resources, 3D model creation, or other aspects of the functions of the collaborative medical platform (140) described herein.

[0032] The data collection module (205) collects various medical data used by the collaborative medical platform (140). The data collection module (205) may be electronically coupled to one or more external servers, databases, or other data sources that supply medical data. The medical data may include, for example, profile data about patients (e.g., demographic information, health records, etc.), medical professionals (e.g., expertise, experience, etc.), or facilities; information about medical conditions, procedures, and medications; information about robotic systems, imaging systems, intervention tools, or other medical equipment; information about post-procedure outcomes; or other medical information discussed herein.

[0033] The data collection module (205) can aggregate data from various input data sources. For example, the data collection module (205) can acquire medical data from a conventional electronic medical record (EHR) system. Here, the data collection module (205) can perform various preprocessing to normalize the data into a standardized format used by the collaborative medical platform (140). For example, the medical record may be composed of a database structure containing values ​​(strings, numeric values, binary values, or other data types) assigned to each of the predefined sets of information fields.

[0034] The data collection module (205) may also interface with one or more imaging systems to collect images, videos, or three-dimensional models associated with the patient before, during, or after the procedure. For example, the data collection module (205) may acquire and store X-ray images, magnetic resonance imaging (MRI) images, computed tomography (CT) scan images, visible light images, near-infrared fluorescence (NIRF) images, or other medical images, videos, or three-dimensional models derived therefrom. Image data may also include image or video data from one or more cameras present in the medical environment where the medical procedure is being performed, such as one or more overhead cameras and / or one or more endoscopic cameras. Imaging data may include telemetry data from one or more medical devices used to perform the medical procedure, annotations or comments associated with the video received from one or more medical personnel associated with the medical procedure, segmentation data or images associated with dividing the video into segments associated with different stages of the procedure, or other information associated with the video data.

[0035] To simplify subsequent search and review of medical procedure videos and associated metadata, the data collection module (205) can perform various preprocessing and indexing on the content and associated metadata. For example, the data collection module (205) indexes the video of a medical procedure with associated metadata to correlate different metadata with different parts of the video, synchronizes videos associated with the same medical procedure, or performs various encoding or reformatting of the video data. The video can also be automatically divided and indexed into video segments corresponding to different stages of the procedure.

[0036] The data collection module (205) can also be integrated with various robot platforms or other medical equipment to acquire telemetry data associated with the procedure. For example, the data collection module (205) can acquire various sensor data from sensors utilized during the medical procedure to identify information associated with the medical equipment, control data associated with controlling the robot platform or other medical equipment, or other data generated from the medical equipment in association with the medical procedure performed.

[0037] The data collection module (205) may also provide an interface accessible through a client device (150) to collect data that is directly input into the collaborative medical platform (140). For example, the data collection module (205) may present various forms or free-form input elements to enable the input of medical information related to operation.

[0038] In one embodiment, the data collection module (205) may manage data in a manner consistent with various compliance and privacy policies. For example, the data collection module (205) may enable the removal or correction of parts of the received data to protect patient privacy when the data is used for purposes where patient identification is not required.

[0039] The entity management module (210) manages the presentation of entity pages associated with different entities linked to the collaborative medical platform (140) and manages connections between entities. Entities may include, for example, users (155) (which may include medical professionals, patients, administrators, etc.), medical cases associated with procedures, facilities, medical equipment (160), files or media content, events (e.g., conferences), presentations, training modules, or other data objects. Entity pages may include web pages accessible through a web browser of a client device (150) or pages of a desktop or mobile application installed on the client device (150).

[0040] Each entity page for an entity may allow viewing of information associated with the entity and / or interactions with the entity. For example, each user (155) of the collaborative medical platform may have a dedicated page providing information about the user (155), such as identification information, role (e.g., surgeon, nurse, executive, manager, patient, etc.), profile information (e.g., history, credentials, etc.), assigned cases, procedure history, connections with other users or cases, scheduling information, or other user-specific data. An entity page for a patient (regardless of whether the patient is a user (155) of the collaborative medical platform (140) may include patient profile information, health history, planned procedures, risk factors, or medical information associated with the patient. An entity page for a medical case may include information about the patient associated with the case, descriptive information about the medical procedure associated with the case (e.g., a type of medical procedure), the medical environment in which the medical procedure will be performed, other descriptive information about the medical procedure, the status of the procedure (e.g., pre-procedure, in-procedure, or post-procedure phases), or other information related to the medical case. The page may also include various interactive elements (e.g., content feeds) that allow users to share and interact with data associated with the entity, as described in more detail below.

[0041] The entity management module (210) also organizes pages and associated data received by the collaborative medical platform (140) into a connection graph (stored in the connection graph repository (255)) that captures the relationships between data associated with different entities. Some connections may be configured as default connections, while others may be created based on specific actions by a user (155). For example, a user (155) may be connected by default with another user (155) within the same organization (at least having view permissions). Alternatively, a connection may be created only when the user (155) explicitly invites another user (155) to connect and the receiving user (155) accepts the connection request. Connections between medical practitioners and medical cases may similarly be created by default or in response to an invitation to create a connection. For example, a default connection may be created between an entity for a planned medical procedure and a medical practitioner assigned responsibility for the procedure. Alternatively, all medical practitioners within an organization or related department may be connected to the planned procedure by default. In another scenario, the user may create a connection request to invite other medical professionals to collaborate on the medical case by sharing the medical case with one or more other medical professionals. Then, acceptance of the connection request may create a connection between the invited professionals and the medical case. Additional connections may also be created automatically (e.g., between the procedure owner and the invited contributor). Connections may also be created between the user (155) and individual videos, files, presentations, or other data objects. For example, the user (155) who creates or owns a video may share the video with one or more other users (155) to grant access to the video.

[0042] Connections between entities can have various types and may be governed by different permissions. Generally, pages may only be accessed by users with appropriate access permissions. Different permission levels may dictate distinct levels of access to different pages. For example, depending on user-specific permissions for a particular page, users may be allowed or blocked from accessing data, editing data, commenting on or annotating data, deleting data, or performing other modifications. In one embodiment, a page may have a page owner with the highest level of access permissions. Typically, a medical professional may be the owner of their profile page and pages for procedures for which they have primary responsibility. Pages associated with facilities, medical equipment, or other entities may be variably owned by assigned medical professionals. Non-owners may have distinct levels of access to pages based on configured permissions. Permissions may be granted by other users with appropriate permissions to assign or grant permissions to the page owner or other users.

[0043] Based on different connections available to different users (155), the collaborative medical platform (140) enables a personalized experience for each user (155). For example, when logging into the collaborative medical platform (140), the user (155) may be presented with a personalized interface related to connections to other users (155), medical cases, videos, presentations, or other content hosted by the collaborative medical platform (140).

[0044] The interface management module (215) manages content associated with various interfaces hosted by the collaborative medical platform (140) and accessible through a client device (150). As described above, the interface management module (215) may manage pages associated with various entities managed by the collaborative medical platform (140), including users (155) (which may include medical professionals, patients, administrators, etc.), medical cases associated with procedures, facilities, medical equipment (160), files or media content, events (e.g., conferences), presentations, training modules, or other data objects. Access to different pages by a specific user (155) may depend on the connection and permissions of that user configured in the connection graph repository (255). Additionally, patient data may be pseudonymized for viewing by other specific users (depending on connection type and / or permissions) so that patient data cannot be attributed to a specific individual.

[0045] A medical case page associated with a medical case may contain information organized into pre-procedure, in-procedure, and post-procedure phases. In the pre-procedure phase, the medical case page may contain information about the patient, the procedure being performed, and the medical professional performing the procedure. The interface management module (215) may also provide access to various analytical information (e.g., generated by the analysis module (230) described below), such as risk factors for the patient, the experience / expertise of the medical professional, results for the planned type of procedure, or other data. In the in-procedure phase, the medical case page may provide access to a telepresence session that allows a remote collaborator to collaborate remotely regarding the procedure in progress. In the post-procedure phase, the medical case page may contain information about the patient's treatment plan, risk factors, follow-up visits, or other post-procedure information.

[0046] Some entity pages in the collaborative medical platform (140) may include a content feed to facilitate collaboration among users (155). The content feed may include various content (e.g., posts), such as text-based commentary, images, videos, 3D models, or other multimedia content related to medical cases. Content may be posted directly to pages associated with medical cases, or posts may include links to content stored by the collaborative medical platform (140) or on an external server. Posts may be grouped into conversations that hierarchically track the relationships between posts. For example, posts may be written as original posts (starting a new conversation) or as replies to existing posts (becoming part of a conversation).

[0047] In one exemplary use, a user (155) may invite one or more other users (155) to collaborate on a medical case and access the case page for the medical case. The content feed on the page allows the collaborating users (155) to post to the case page in relation to the medical case. Thus, the content feed may enable discussions on the procedure to be performed, risks, best practices, or other information that may be useful to the practitioner performing the procedure. Additionally, the participating users (155) may post videos or 3D models (or links to content) related to past procedures on patients in similar situations. Furthermore, the participating users (155) may share links to entity pages related to past procedures that may be relevant, allowing the medical practitioner performing the procedure to view past content feeds related to that procedure. Patient data may be optionally pseudonymized when shared with other users (depending on the connection type and / or permissions) so that patient data cannot be attributed to a specific individual.

[0048] The content feed can also be utilized in relation to the procedure in progress during a real-time telepresence session, as discussed in more detail below. Here, the content feed may be presented as a real-time chat window that allows a contributor to comment during the procedure, share videos, images, or other media, provide links to relevant resources, or provide content during the procedure.

[0049] In the post-procedure phase, the content feed may be utilized by contributors to discuss post-procedure treatment, patient recovery, risk management, or other information related to patient recovery. An example of a content feed is provided in Fig. 7, which is described in more detail below.

[0050] The medical intelligence module (220) generates medical intelligence data that may be automatically added to a content feed or otherwise made available in the context of a collaborative medical platform (140). For example, the medical intelligence module (220) may automatically contribute posts to a content feed regarding medical cases that an artificial intelligence agent infers are relevant. Artificially generated posts may mimic posts provided by human contributors and may include text-based commentary, multimedia, links, etc. Medical intelligence data may be generated during the pre-procedure phase, during the procedure, or during the post-procedure phase.

[0051] In one exemplary embodiment, the medical intelligence module (220) may include one or more machine learning models trained to generate content that the model infers is relevant to a specific medical case or, more generally, to the user (155). In one embodiment, the machine learning model generates an embedding for the medical case based on descriptive information about the medical procedure, characteristics of the patient to whom the medical procedure is to be performed, characteristics of the medical professional performing the procedure, posts within the content feed, or other information available on the collaborative medical platform (140). The medical intelligence module (220) determines a measure of similarity (e.g., cosine similarity, inner product) between the embedding for the medical case and the embedding for other content available on the collaborative medical platform (140) and which may be included in the automated posts. Then, the medical intelligence module (220) may generate posts and / or select content for posts based on the similarity of the embeddings. The medical intelligence module (220) may also employ various large-scale language models (LLMs) to analyze text-based content associated with medical cases and artificially generate relevant natural language content for the content feed. The machine learning model may also include one or more neural networks (e.g., convolutional neural networks (CNN), artificial neural networks (ANN), resentential neural networks (ResNet) or recurrent neural networks (RNN)), regression-based models, generative models, or other types of machine learning models capable of achieving the functions described herein.

[0052] In one exemplary use case, the medical intelligence module (220) can identify one or more past medical cases similar to the current medical case and automatically generate a link to a case page for the relevant cases. Then, the medical professional can view videos, models, or other recorded data associated with the relevant medical case to help prepare for the procedure. In another example, the medical intelligence module (220) can automatically respond to questions raised by the user in the content feed. For example, the medical intelligence module (220) can function like a chatbot that intelligently responds to text-based queries. In a further embodiment, the medical intelligence module (220) can generate recommendations inviting specific medical professionals to collaborate on a medical case based on relevant expertise and experience. Then, the user can choose whether to invite the recommended collaborators to collaborate on the medical case based on the artificially generated recommendations.

[0053] The telepresence module (225) facilitates a telepresence session during a procedure. The telepresence session may include one or more collaborators invited to collaborate on a medical case, and allows other users (155) to remotely access video captured during the medical procedure, telemetry data from one or more medical devices, or other real-time data. As described above, a content feed is also displayed in association with the telepresence session, allowing contributors to comment on or share multimedia or links related to the procedure.

[0054] The telepresence module (225) may also enable the contributor to provide real-time annotations on images, videos, 3D models, or other visual content of anatomical structures related to the ongoing procedure. For example, the contributor may mark locations on the visual content in conjunction with provided comments. The telepresence module (225) may also enable the contributor to add overlaid drawings, highlights, or other visual markings during the ongoing telepresence session.

[0055] In one embodiment, the telepresence module (225) may enable a remote contributor to control the medical equipment (160). For example, the remote contributor may access a control interface that provides control elements for controlling the position or orientation of a camera, controlling a robot arm, setting the configuration of a sensing device, or performing other control functions of the medical equipment.

[0056] When the procedure is completed, the telepresence module (225) can store recorded video, telemetry data, content feeds, annotations, and other captured data associated with the procedure. This information may later be accessed by a user (155) of the collaborative medical platform (140) (if appropriate permissions are granted) and / or utilized by the medical intelligence module (220) to further train machine learning models and / or generate inferences.

[0057] The analysis module (230) facilitates the generation of various statistics, indicators, or other analyses associated with information stored in the collaborative medical platform (140). The analysis can generally be generated based on a set of filtering parameters that yield a subset of data records for aggregation, and a combination function that specifies how the filtered data should be combined. The filtering parameters can filter medical procedure data based on data fields such as patient data, medical worker data, facility, type of procedure, medical equipment used, etc. The combination function may include, for example, an average function, a median function, a histogram function, or other functions. A specific analysis function may provide a single output value or a series of values ​​across one or more dimensions. The series of outputs may be visually presented as a table, chart, graph, or other visual output.

[0058] For example, the analysis module (230) may generate an indicator describing the average length of time required to complete a medical procedure for a specific medical worker or group of medical workers. The average time for various procedures performed by the same medical worker or group of medical workers may be presented along with similar indicators for other medical workers for comparison purposes. In another example, the analysis module (230) may generate an indicator describing the number of times a medical worker has performed a specific type of medical procedure in the past. Such counts may be further aggregated to represent a percentage reflecting the number of times a medical worker performed a different type of medical procedure out of the total number of procedures performed.

[0059] In an additional embodiment, the analysis module (230) may generate an analysis based on interactions of medical professionals on the collaborative medical platform (140). For example, statistics may be derived based on the count of posts, comments, or other content contributed by medical professionals to the collaborative medical platform (140). Such an analysis may be expressed in terms of interaction counts, interaction frequency, or other aggregations. Such an analysis may also be aggregated separately based on whether the interaction is related to the pre-procedure, in-procedure, or post-procedure phases.

[0060] In one embodiment, the analysis module (230) may generate an analysis based on a specific filtering and / or combining function specified by a user (155) of the collaborative medical platform (140). Additionally, the analysis module (230) may include various preset analyses that can be generated without necessarily receiving specific user input. Furthermore, in some embodiments, the medical intelligence module (220) may automatically generate an analysis that is inferred to be relevant to a specific user (155).

[0061] In some embodiments, the analysis module (230) may generate an analysis based on any aspect of collective case data including pre-procedure data, telepresence session data (including recorded video, telemetry data, in-session content feed data, etc.), and post-procedure data. The analysis associated with the telepresence session data may include performing various video processing, content recognition, or other advanced image processing techniques to extract useful information from the video. Additionally, the analysis module (230) may generate an analysis by utilizing various medical intelligence data generated from the medical intelligence module (220).

[0062] The analysis module (230) also receives telemetry data from sensors captured during the performance of a medical procedure. The sensors may be included in one or more medical devices (160) used during the medical procedure or may be located outside the medical devices (160). Additionally or alternatively, the analysis module (230) receives video data captured from one or more cameras (or image capture devices) of the medical procedure being performed. Telemetry data describes how the medical devices (160) were used during the medical procedure. For example, the medical devices (160) are robots, and the telemetry data includes configuration information of the robot or data captured by one or more sensors describing the movement or operation of the robot during the medical procedure (e.g., changes in the robot's position at different times, forces applied by the robot at different times, the speed at which the robot changed its position, inputs received by the robot at different times, etc.). Different sensors may capture different types of telemetry data during the medical procedure, or different sensors may capture telemetry data from different medical devices (160).

[0063] One or more cameras or other image capture devices included at the location where a medical procedure is performed capture video data of the medical procedure being performed. For example, cameras are positioned at different locations within the operating room where one or more medical procedures are performed to capture different parts of the operating room. The video data may include one or more medical personnel performing the medical procedure, parts of one or more medical equipment (160) used during the medical procedure, one or more medical devices used during the medical procedure, parts of the patient on whom the medical procedure is being performed, or other information regarding the medical procedure. Multiple cameras may capture different video data of the medical procedure, and different cameras capture different parts of the medical procedure.

[0064] In various embodiments, telemetry data or video data includes metadata identifying the location where the telemetry data or video data was captured as well as the time at which the telemetry data or video data was captured. For example, the telemetry data or video data includes the name of the location where the medical procedure was performed (e.g., the name of the medical facility). Furthermore, the analysis module (230) may generate metadata associated with the telemetry data or video data through the analysis of the telemetry data or video data. For example, the analysis module (230) applies one or more models to the telemetry data or video data to extract features of the telemetry data or video data that are stored as metadata associated with the telemetry data or video data. Exemplary features extracted from the telemetry data or video data include: the location associated with the telemetry data or video data, the type of medical procedure at which the telemetry data or video data was captured, and one or more medical devices (160) associated with the telemetry data or video data.

[0065] However, metadata included in telemetry data or video data often does not include information identifying one or more medical personnel who performed the medical procedure or descriptive information about the medical procedure. Many medical facilities are subject to data privacy restrictions on information transmitted to systems outside the medical facility. Data privacy restrictions prevent (or may complicate) the transmission of data containing information that can uniquely identify the patient on whom the medical procedure was performed to systems (e.g., servers) located at one or more locations outside the medical facility, and thus these data privacy restrictions prevent the inclusion of metadata identifying medical personnel or medical procedures in telemetry data or video data transmitted to the collaborative medical platform (140). Excluding metadata identifying medical personnel or medical procedures from telemetry data or video data transmitted to the collaborative medical platform (140) complies with one or more data privacy restrictions applicable to the medical facility by excluding information that directly and uniquely identifies the patient based on the medical personnel and medical procedures. Omitting metadata identifying medical personnel or medical procedures complies with data privacy restrictions imposed on medical facilities, but such omission prevents the analysis module (230) from directly accessing information that explicitly identifies the medical personnel performing (or associated with) the medical procedure in which telemetry data or video data was captured.

[0066] Without directly receiving information identifying a medical procedure or a medical worker associated with a medical procedure, the analysis module (230) may operate to indirectly infer a connection between the received telemetry data or video data and the medical worker. Inferring such a connection enables the medical worker associated with the medical procedure in which the telemetry data or video data was captured to receive an indicator or analysis of the medical procedure determined by the analysis module (230). Based on this inferred connection, the medical worker may obtain information from the analysis module (230) to improve the subsequent performance of the corresponding type of medical procedure in which the telemetry data or video data was captured.

[0067] To select a medical worker to connect to telemetry data or video data, the analysis module (230) utilizes data from one or more of the user profile repository (260), video library (250), and connection graph repository (255), as well as telemetry data or video data. Exemplary characteristics of a medical worker from the medical worker's user profile include: one or more locations associated with the medical worker (e.g., medical facilities), one or more types of medical procedures associated with the medical worker, information describing the performance of one or more medical procedures by the medical worker, and other information describing the types of medical procedures associated with the medical worker. Video data within the video library (250) connected to the medical worker's user profile via the connection graph repository (255) is, in some embodiments, one or more characteristics of the medical worker.

[0068] Additionally, the user profile stored for a medical worker includes one or more procedure cards associated with the medical worker. The procedure cards associated with the medical worker are characteristics of the medical worker that the analysis module (230) can use to select the medical worker to connect to telemetry data or video data. Each procedure card within the medical worker's user profile is associated with one type of medical procedure. Different procedure cards may be associated with different types of medical procedures. In some embodiments, the user profile repository (260) includes a set of procedure cards associated with one type of medical procedure for the medical worker, and each procedure card in the set is associated with a step that occurs during the performance of that type of medical procedure.

[0069] A procedure card includes preferences, skills, or methods for performing a type of medical procedure associated with a medical professional. For example, a procedure card associated with a type of medical procedure designates one or more specific medical devices that the medical professional uses in a step of that type of medical procedure. The procedure card may also designate the placement of different medical devices or medical equipment (160) within the location where the medical professional performs the medical procedure for a step of that type of medical procedure; thus, the procedure card designates the placement of medical devices or medical equipment (160) when the medical professional performs different steps in that type of medical procedure. Furthermore, a user profile for a medical professional includes a set of procedure cards for that type of medical procedure in an order corresponding to the order in which the medical professional performs different steps of that type of medical procedure. Thus, a procedure card with a higher position in the set corresponds to a step performed at an earlier time in that type of medical procedure.

[0070] In various embodiments, one or more procedure cards in a set of procedure cards contain configuration information for one or more medical devices (160) used during a type of medical procedure associated with the set. In some embodiments, the collaborative medical platform (140) transmits configuration information for one or more medical devices (150) included in the procedure card to the medical devices (150) in response to receiving a selection of a procedure card (or a set of procedure cards including the procedure card) from a medical professional. Including configuration information for one or more medical devices (160) in the procedure card simplifies the configuration of one or more medical devices (160) to take into account the medical professional's preferences or usage patterns when the medical professional performs a type of medical procedure.

[0071] Furthermore, based on previously received telemetry data or video data associated with a medical worker, the analysis module (230) may determine usage patterns for different medical equipment (160) or different medical devices and determine movement patterns of the medical worker from the telemetry data or video data. For example, the analysis module (230) may apply one or more machine learning models to the video data or telemetry data to identify the medical equipment (160) or medical device included in the video data or telemetry data, identify movement patterns of the medical equipment (160) or medical device from the video data or telemetry data, identify value patterns for one or more settings of the medical equipment (160), identify movement patterns of the medical worker or medical equipment (160) from the telemetry data or video data, or identify other descriptive information from the telemetry data. The analysis module (230) may store patterns detected from the telemetry data or video data associated with the medical worker at least at a critical frequency in relation to the type of medical procedure associated with the medical worker and the telemetry data or video data. Associating specific movement patterns of a healthcare worker with a healthcare worker and a type of medical procedure within a user profile allows for the identification of patterns, movements, or usage typical of that type of medical procedure for the healthcare worker.

[0072] Subsequently, the analysis module (230) may apply one or more classification models to the received telemetry data or video data to determine the type of medical procedure in which the telemetry data or video data was captured based on the movement patterns of the medical worker or medical equipment. The classification model may determine the type of medical procedure in which the telemetry data or video data was captured by utilizing the movement patterns of the medical worker or one or more medical equipment from the stored video data or telemetry data associated with one or more medical workers. For example, the video library (250) associates the type of medical procedure with different stored video data or telemetry data, and the classification model determines the type of medical procedure in which the telemetry data or video data was captured based on similarity measures for the stored video data associated with different types of medical procedures, which explains the different movement patterns of the medical equipment (160) or medical worker when performing different types of medical procedures. For example, the classification model is a nearest neighbor model that generates embeddings for the telemetry data or video data and embeddings for the stored video data associated with different types of medical procedures. Such a classification model determines a similarity measure between an embedding for telemetry data or video data and each embedding for the stored video data. The classification model determines the type of medical procedure for the telemetry data or video data as the type of medical procedure associated with the stored video data having an embedding with the maximum similarity measure to the embedding for the telemetry data or video data.In another embodiment, the classification model determines the distance between an embedding for telemetry data or video data and each embedding for stored video data, and determines the type of medical procedure for telemetry data or video data as the type of medical procedure associated with video data having an embedding having a minimum distance to the embedding for telemetry data or video data.

[0073] Applying a classification model to telemetry data or video data and stored video data allows the movement patterns of medical equipment (160) or medical personnel stored in the video library (250) to be utilized to identify the type of medical procedure captured in the telemetry data or video data. The determined type of medical procedure can be stored as metadata associated with the telemetry data or video data and used as input to a probabilistic model of the personnel. The determined type of medical procedure captured in the telemetry data or video data can be used when selecting a medical personnel connected to the telemetry data or video data, so that the type of medical procedure associated with the medical personnel can be compared with the type of medical procedure captured in the telemetry data or video data.

[0074] Additionally, a user profile associated with a medical worker includes a time log of when the medical worker accessed the collaborative medical platform (140) through a client device (150). For example, the log may identify the date and time when the medical worker accessed the collaborative medical platform (140) through the client device (150) and may include an identifier of the client device (150) through which the medical worker accessed the collaborative medical platform (140). The log may also include an identifier of the location (e.g., a medical facility) where the medical worker's client device (150) accessed the collaborative medical platform (140). Furthermore, the user profile associated with the medical worker may include an indication of whether the medical worker is currently accessing the collaborative medical platform (140) through the client device (150).

[0075] In various embodiments, the analysis module (230) trains a worker prediction model to generate a probability that a worker will connect to the telemetry data or video data based on the characteristics of the worker from the telemetry data or video data and the user profile of the worker. Exemplary characteristics of the worker include: one or more medical facilities associated with the worker, one or more types of medical procedures associated with the worker, information describing the performance of one or more medical procedures by the worker (e.g., a procedure card associated with the worker, a pattern of use of medical equipment (160) or medical devices by the worker, a movement pattern of the worker, etc.), the time the worker accessed the collaborative medical platform (140) from the client device (150), the location of the client device (150) used by the worker to access the collaborative medical platform (140), or any combination thereof. Metadata included in or extracted from the telemetry data or video data is received by the worker prediction model in various embodiments. Exemplary metadata from telemetry data or video data includes the time the telemetry data or video data was captured, the location where the telemetry data or video data was captured, the type of medical procedure where the telemetry data or video data was captured, and any combination thereof.

[0076] The worker prediction model includes a set of weights stored on a non-transient computer-readable storage medium. The analysis module (230) trains the worker prediction model by generating a training dataset containing multiple training examples based on previously received telemetry data or video data and connections between one or more medical workers and previously received telemetry data or video data. Different medical workers may be associated with telemetry data or video data included in different training examples. Each training example includes training telemetry data or training telemetry data and characteristics of a training user. Furthermore, each training example has a label indicating whether the training medical worker is connected to the training telemetry data or training video data. For example, the label has a specific value in response to the training medical worker being connected to the training video data or training telemetry data, and an alternative value in response to the training medical worker not being connected to the training telemetry data or training video data.

[0077] To train the worker prediction model, the analysis module (230) initializes a set of weights constituting the worker prediction model and applies the worker prediction model to a number of training examples in the training dataset. Applying the worker prediction model to a number of training examples updates one or more parameters (e.g., weights) constituting the worker prediction model. The parameters constituting the worker prediction model convert input data (telemetry data or video data and characteristics of a medical worker) into predicted probabilities that the telemetry data or video data will be connected to a medical worker. When applied to training examples, the worker prediction model generates predicted probabilities that the training telemetry data or training video data will be connected to a training user based on the training telemetry data or training video data and the characteristics of the training user.

[0078] For each training example to which the worker prediction model is applied, the analysis module (230) generates a score including an error term based on the predicted probability that the training medical worker will be associated with the training video data or training telemetry data and the label applied to the training example. The error term is larger when the difference between the predicted probability that the training medical worker will be associated with the training video data or training telemetry data for the training example and the label applied to the training example is larger, and is smaller when the difference between the predicted probability that the training medical worker will be associated with the training video data or training telemetry data for the training example and the label applied to the training example is smaller. In various embodiments, the analysis module (230) generates the error term using a loss function based on the difference between the predicted probability that the training medical worker will be associated with the training video data or training telemetry data for the training example and the label applied to the training example. Exemplary loss functions include a mean squared error function, a mean absolute error, a hinge loss function, and a cross-entropy loss function.

[0079] The analysis module (230) updates the set of parameters constituting the worker prediction model by backpropagating the error term, and stops backpropagating in response to the error term or loss function meeting one or more criteria. For example, the analysis module (230) updates the parameters of the worker prediction model by backpropagating the error term through the worker prediction model until the error term has a threshold value below a threshold. For example, the analysis module (230) may update the set of parameters by applying gradient descent. After stopping backpropagation, the analysis module (230) stores the set of parameters constituting the worker prediction model in a non-transient computer-readable storage medium.

[0080] Various characteristics of a medical worker influence the probability that telemetry data or video data, determined by the worker prediction module, will be connected to the medical worker. For example, a characteristic indicating that the medical worker did not access the collaborative medical platform (140) using a client device (150) during the period corresponding to the telemetry data or video data increases the probability that the video data or telemetry data will be connected to this medical worker, because the medical worker performing the medical procedure cannot access the collaborative medical platform (140) using a client device (150). Similarly, a location associated with the medical worker that matches the location where the telemetry data or video data was received increases the probability that the video data or telemetry data will be connected to the medical worker. As another example, a characteristic of the medical worker indicating that the location of the medical worker during the time interval corresponding to the telemetry data or video data matched the location where the telemetry data or video data was captured, and indicating that the medical worker did not access the collaborative medical platform (140) using a client device (150) during the period corresponding to the telemetry data or video data, increases the probability that the telemetry data or video data will be connected to the medical worker. As another example, the movement pattern of a medical worker during one or more medical procedures or the usage pattern of medical equipment (160) during a medical procedure stored in the medical worker's user profile has a higher similarity measure to the movement pattern of a medical worker or the usage pattern of medical equipment (160) identified from telemetry data or video data, which increases the probability that the telemetry data or video data is connected to the medical worker.In an additional example, the type of medical procedure associated with a medical worker within a user profile matches the type of medical procedure determined by the analysis module (230) for telemetry data or video data, thereby increasing the probability that the telemetry data or video data is connected to the medical worker. During the training process for the worker prediction model, the relationship between the characteristics of the medical worker and the probability that the telemetry data or video data is connected to the medical worker is refined and presented through the parameters of the worker prediction model.

[0081] In various embodiments, the analysis module (230) applies a trained worker prediction model to each of the telemetry data or video data and the set of medical workers to generate a probability that each medical worker in the set is connected to the telemetry data or video data. Each medical worker in the set has one or more specific characteristics in various embodiments. For example, the analysis module (230) identifies the medical facility where the telemetry data or video data was received from the metadata included in the telemetry data or video data, and selects a set of medical workers as medical workers having a location that matches the identified medical facility. In another example, the analysis module (230) determines, for example, a date corresponding to the telemetry data or video data from the metadata included in the telemetry data or video data, determines the medical facility where the telemetry data or video data was received from the metadata, and the analysis module (230) identifies a set of medical workers as medical workers having a location that matches the medical facility determined on the determined date. Selecting a set of medical workers limits the number of medical workers to which the worker prediction model is applied.

[0082] Alternatively, the analysis module (230) maintains a set of rules applied to the characteristics of a medical worker and the telemetry data or video data to determine the probability that the medical worker will be connected to the telemetry data or video data. In various embodiments, each rule identifies one or more characteristics of the medical worker and a criterion for comparing one or more characteristics with the telemetry data or video data. In response to the result of comparing one or more characteristics of the medical worker within the rule with the telemetry data or video data specified by the rule indicating that one or more characteristics satisfy the rule, the analysis module (230) increases the probability that the medical worker will be connected to the telemetry data or video data. For example, the rule identifies an indication that the medical worker has accessed the collaborative medical platform and a criterion that the indication was negative during the time interval corresponding to the telemetry data or video data and the criterion. In response to the indication that the medical worker has accessed the collaborative medical platform being negative during the time interval corresponding to the telemetry data or video data, the analysis module (230) increases the probability that the medical worker will be connected to the telemetry data or video data. As another example, the rule identifies the location of the medical worker and the criterion that the location of the medical worker matches the location identified by the telemetry data or video data. In response to the medical worker's location matching the location identified by the telemetry data or video data, the analysis module (230) increases the probability that the medical worker is connected to the telemetry data or video data. As another example, the rule increases the probability that the medical worker is connected to the telemetry data or video data in response to the type of medical procedure associated with the telemetry data or video data matching the type of medical procedure associated with the medical worker.As another example, one or more rules compare a movement pattern of a medical worker during one or more medical procedures or a usage pattern of medical equipment (160) during one or more medical procedures stored in a medical worker's user profile with a movement pattern of a medical worker or a usage pattern of medical equipment (160) identified from telemetry data or video data, and if one or more patterns from the user profile have a higher similarity measure with one or more patterns from telemetry data or video data, the probability that the telemetry data or video data is connected to the medical worker is increased.

[0083] Having characteristics that satisfy a greater number of rules leads to a higher probability that a medical worker will have a connection to telemetry data or video data. In some embodiments, the analysis module (230) reduces the probability that a medical worker will have a connection to telemetry data or video data in response to a user's characteristics not meeting one or more criteria within the rules. However, in other embodiments, the analysis module (230) does not modify the probability that a medical worker will have a connection to telemetry data or video data in response to a user's characteristics not meeting one or more criteria within the rules. The analysis module (230) determines the probability that different medical workers will have a connection to telemetry data or video data by applying the rules to characteristics maintained for a majority of medical workers in the set.

[0084] Based on the probability determined for each medical worker in the set, the analysis module (230) selects a medical worker. For example, the analysis module (230) ranks the medical workers in the set based on the probability of being connected to video data or telemetry data and selects a medical worker who has a threshold position, such as the maximum position in the ranking. Alternatively, the analysis module (230) selects a medical worker who has at least a threshold probability or a maximum probability. In various embodiments, the analysis module (230) automatically stores the connection between the selected medical worker and the telemetry data or video data. Alternatively, the analysis module (230) sends a prompt to the client device (150) of the selected medical worker that includes descriptive information about the video data or telemetry data and a request for the selected medical worker to confirm the connection between the selected medical worker and the video data or telemetry data, and stores the connection between the selected medical worker and the telemetry data or video data in response to receiving confirmation.

[0085] The analysis module (230) simplifies the generation of a post-procedure summary by a selected medical professional regarding a medical procedure in which telemetry data or video data was captured by utilizing the stored characteristics of the selected medical professional based on a connection to the telemetry data or video data. The post-procedure summary includes notes or other descriptive information from the selected medical professional regarding the performance of the medical procedure in which the telemetry data or video data was captured. For example, the post-procedure summary includes comments or notes from the medical professional regarding actions taken during the medical procedure, specific skills or observations related to the performance of the medical procedure, descriptions of skills used during the medical procedure, or other information from the medical professional regarding the medical procedure. Conventionally, the medical professional prepares the post-procedure summary based on the medical professional's recollection of the medical procedure, which may lead to the medical professional omitting specific information regarding the performance of the medical procedure if time elapses between the medical professional performing the medical procedure and preparing the post-procedure summary.

[0086] Storing the connection between the selected medical worker and the telemetry data or video data captured during the medical procedure enables the analysis module (230) to present a portion of the telemetry data or video data captured during the medical procedure to the selected medical worker at an interface for generating a post-procedure summary. This enables the selected medical worker to review a portion of the telemetry data or video data when preparing the post-procedure summary. Providing the selected medical worker with access to the telemetry data or video data captured during the medical procedure based on the stored connection between the selected medical worker and the telemetry data or video data enables the selected medical worker to review details regarding the performance of the medical procedure to identify content for the post-procedure summary.

[0087] In various embodiments, to simplify the generation of post-procedure summaries, the analysis module (230) selects a set of procedure cards associated with a selected medical professional based on telemetry data or video data. For example, the analysis module (230) searches for a set of procedure cards associated with a selected medical professional and determines a similarity measure between the telemetry data or video data and each set of procedure cards associated with the medical professional. In various embodiments, the analysis module (230) generates an embedding for each set of procedure cards and an embedding for the telemetry data or video data, and determines a similarity measure (e.g., cosine similarity, inner product) between the embedding for the set of procedure cards and the embedding for the telemetry data or video data. The analysis module (230) selects a set of procedure cards having the maximum similarity measure between the embedding for the set of procedure cards and the embedding for the telemetry data or video data.

[0088] For example, the analysis module (230) applies one or more nearest neighbor models to the embeddings for the procedure card set associated with the selected medical practitioner and to the embeddings for the telemetry data or video data. In some embodiments, the analysis module (230) applies the nearest neighbor models to the embeddings for the procedure card set and to the embeddings for the telemetry data or video data. The nearest neighbor model determines the distance (or similarity measure) in latent space between the embeddings for the various procedure card sets and the embeddings for the telemetry data or video data. For example, the nearest neighbor model determines the Euclidean distance between the embeddings for the procedure card set and the embeddings for the telemetry data or video data. Based on the distance, the nearest neighbor model ranks the procedure card sets so that the procedure card sets with smaller distances have higher positions in the ranking, and selects one or more procedure card sets that have at least a threshold position in the ranking. Thus, the selected one or more procedure card sets have the embeddings closest to the embeddings for the telemetry data or video data. Alternatively, the nearest neighbor model selects one or more procedure card sets having a threshold distance less than the threshold distance from the embeddings for the telemetry data or video data. Alternatively, the nearest neighbor model determines a similarity measure (e.g., cosine similarity, inner product) between the embeddings of various procedure card sets and the embeddings for the telemetry data or video data. Based on the similarity measure, the nearest neighbor model ranks the procedure card sets so that the procedure card sets with larger similarity measures have higher positions in the ranking, and selects one or more procedure card sets having at least a threshold position in the ranking. Thus, the selected one or more procedure card sets have larger similarity measures with the embeddings for the telemetry data or video data.In various embodiments, the analysis module (230) selects the set of procedure cards having the highest position in the ranking.

[0089] Alternatively, the analysis module (230) determines the type of medical procedure captured in the telemetry data or video data by applying one or more classification models to the received telemetry data or video data. As described in more detail above, one or more classification models determine the type of medical procedure captured in the telemetry data or video data by considering the movement patterns of medical personnel or one or more medical devices (160) included in the video data or telemetry data stored in the video library (250). For example, the video library (250) associates the type of medical procedure with different stored video data or telemetry data, and the classification model determines the type of medical procedure captured in the medical procedure based on a similarity measure or distance between the embedding for the received telemetry data or video data and the embedding for the stored telemetry data or video data. In various embodiments, the classification model determines for the received telemetry data or video data the type of medical procedure associated with the stored video data or telemetry data having an embedding having the maximum similarity measure with the embedding for the received telemetry data or video data. Alternatively, the classification model determines for the received telemetry data or video data the type of medical procedure associated with the stored video data or telemetry data having an embedding having a minimum distance from the embedding for the received telemetry data or video data. The analysis module (230) selects a set of procedure cards from a user profile for a selected medical worker associated with the type of medical procedure determined for the received telemetry data or video data.

[0090] The analysis module (230) compares telemetry data or video data with procedure cards in a selected set. For example, the analysis module (230) applies one or more trained models to various procedure cards in the selected set to determine a measure of similarity between different parts of the telemetry data or video data and the selected set. The trained models may be nearest neighbor models, as described in more detail above. In some embodiments, the analysis module (230) identifies individual segments of the telemetry data or video data and compares each segment of the telemetry data or video data with one or more procedure cards in the selected set using a trained model or one or more other methods. This comparison correlates different segments of the telemetry data or video data with different procedure cards in the selected set.

[0091] For a segment of telemetry data or video data, the analysis module (230) compares the segment of telemetry data or video data with a corresponding procedure card in a selected set. In various embodiments, the analysis module (230) applies one or more models to the segment of telemetry data or video data and to the corresponding procedure card in the set to determine whether the telemetry data or video data contains one or more deviations from the corresponding procedure card. In response to determining the deviation between the corresponding procedure card and the segment of telemetry data or video data, the analysis module (230) generates a prompt for a selected medical professional to identify the determined deviation and a part of the corresponding procedure card. For example, the prompt includes a part of the telemetry data or video data segment corresponding to the deviation and a part of the corresponding procedure card corresponding to the deviation. The prompt may include a request for the selected medical professional to explain one or more reasons for the deviation from the corresponding procedure card. As another example, the analysis module (230) generates an interface element that is presented in an interface that is close to a description or part of the corresponding procedure card where the deviation was identified. In response to receiving the selection of interface elements, the analysis module (230) may display additional input elements to provide information explaining the deviation as well as information about the deviation between the selected medical practitioner and the procedure card corresponding to the telemetry data or video data.

[0092] Identifying deviations between a segment of telemetry data or video data and one or more procedure cards in a set corresponding to the medical procedure in which the telemetry data or video data was captured provides specific information about the medical procedure regarding how the selected medical practitioner typically performs the medical procedure in an interface for the selected medical practitioner to generate a post-procedure summary of the medical procedure. Identifying deviations from the procedure card for the selected medical practitioner encourages the selected medical practitioner to include one or more reasons for the deviation between the segment of telemetry data or video data and the corresponding procedure card in the post-procedure summary. Subsequently, the reasons may be stored in association with the selected medical practitioner to increase the amount of data available to the analysis module (230) or to allow the practitioner training module (235) to provide content to the selected medical practitioner. The analysis module (230) may include one or more reasons for the deviation with the selected medical practitioner in the post-procedure summary, or may use one or more reasons as part of a prompt to cause the generating model to generate a summary of one or more reasons for the deviation to be included in the post-procedure summary. In some embodiments, the interface for providing a post-procedure summary includes a group of prompts, each prompt corresponding to a deviation between telemetry data or video data and a corresponding procedure card in a selected set. Presenting a prompt or interface element for an identified deviation between one or more parts of telemetry data or video data and one or more corresponding procedure cards in a selected set allows the analysis module (230) to guide a selected medical professional in the process of generating a post-procedure summary, thereby increasing the amount of detailed information about the medical procedure included in the post-procedure summary.Comparing the stored set of procedure cards with telemetry data or video data provides selected medical professionals with additional information regarding the nature of the medical procedure to be included in the post-procedure summary, based on the captured telemetry data or video data.

[0093] Additionally, the analysis module (230) may provide a selected medical professional with a prompt to modify one or more of the selected set of procedure cards based on identified deviations between telemetry data or video data and one or more of the procedure cards in the selected set of procedure cards. Since conventional procedure cards are physical documents maintained at a medical facility, updating or modifying one or more procedure cards is a time-consuming process, which reduces the frequency with which procedure cards are updated when the preferences or skills of the medical professional performing the medical procedure change. However, storing the set of procedure cards in the user profile for the medical professional allows the analysis module (230) to simplify the modification of one or more procedure cards.

[0094] As described in more detail above, the analysis module (230) compares a segment of telemetry data or video data with a corresponding procedure card in a selected set to determine whether the telemetry data or video data contains one or more deviations from the corresponding procedure card. In response to determining the deviation between the segment of telemetry data or video data and the corresponding procedure card, the analysis module (230) generates a correction prompt for the selected medical practitioner. The correction prompt includes a message to the selected medical practitioner to identify at least some of the procedure cards in the set corresponding to the telemetry data or video data segment in which the deviation was determined, and to determine whether to update the procedure card in the set corresponding to the telemetry data or video data segment in which the deviation was determined. In some embodiments, the analysis module (230) maintains a deviation count of the deviation detected between the telemetry data or video data and the procedure card for each procedure card maintained for the selected medical practitioner. The deviation count for the procedure card enables the analysis module (230) to determine how often the telemetry data or video data from that type of medical procedure deviates from the various procedure cards for the selected medical practitioner over time. In various embodiments, the analysis module (230) determines whether to generate a correction prompt for a procedure card based on a deviation count and present it to a selected medical professional. For example, the analysis module (230) generates a correction prompt for a procedure card in response to the deviation count for the procedure card being equal to or exceeding a threshold. Alternatively, the analysis module (230) generates a correction prompt for a procedure card in response to determining a deviation between the procedure card and telemetry data or video data having at least a threshold frequency.

[0095] In some embodiments, the analysis module (230) generates a procedure card interface that is transmitted to a client device (150) of a selected medical professional based on a comparison of telemetry data or video data with a selected set of procedure cards. In some embodiments, the procedure card interface displays at least a portion of each procedure card among the selected set of procedure cards. One or more interface elements are presented in proximity to one or more procedure cards among the selected set of procedure cards. For a procedure card in which a deviation has occurred between a segment of telemetry data or video data, a deviation interface element is presented in proximity to the procedure card. In response to receiving a selection of a deviation interface element from the selected medical professional, the analysis module (230) provides a prompt to the selected medical professional to provide details or reasons for the deviation between the segment of telemetry data or video data and the procedure card, as described in more detail above.

[0096] Additionally or alternatively, the procedure card interface includes an editing interface element located near the procedure card where the deviation occurred with a segment of telemetry data or video data. For example, the procedure card interface presents an editing interface element located near the procedure card where the deviation occurred with a segment of telemetry data or video data in response to the procedure card having a deviation count equal to or exceeding a threshold count. As another example, in response to the analysis module identifying that the telemetry data or video data has deviated from the procedure card at least at a threshold frequency, the procedure card interface displays an editing interface element located near the procedure card. In response to receiving a selection of an editing interface element by a selected medical practitioner, the analysis module (230) generates one or more interfaces for the selected medical practitioner to modify or edit the procedure card. Interaction with one or more interfaces enables the selected medical practitioner to modify the content of the procedure card, thereby simplifying the modification of the procedure card to reflect changes or modifications to the performance of medical procedures by the selected medical practitioner. One exemplary procedure card interface is described in more detail below in relation to FIG. 13.

[0097] The practitioner training module (235) manages and stores training data for medical practitioners associated with medical procedures. In various embodiments, the training data includes educational content containing descriptive information about a medical procedure or a part of a medical procedure. Exemplary educational content includes training videos related to performing a medical procedure, papers on performing a medical procedure, papers or videos on using one or more medical devices (160) in a medical procedure, papers or videos on using one or more medical devices in a medical procedure, best practices for a medical procedure, training manuals for a medical procedure, educational materials on one or more medical devices used in a medical procedure, digital training modules, webinars, audio data on a medical procedure (e.g., a podcast about a medical procedure), or other information for training medical practitioners in relation to a medical procedure.

[0098] In various embodiments, the training content also includes configuration data or configuration commands for one or more medical devices (160) used in one or more medical procedures. For example, the training content includes a set of configuration commands for configuring or calibrating a robotic arm or other medical devices (160) for use in a medical procedure. The configuration commands may include one or more settings for the medical devices (160). Exemplary settings include: one or more limit values ​​for the amount of force applied by the medical devices (160), one or more limit values ​​for the range of motion of the medical devices (160), one or more limit values ​​for the amount of energy supplied by the medical devices (160), an operating mode identifier for the medical devices (160), or a value for one or more other settings of the medical devices (160). As another example, the training content includes a set of commands that, when executed by the medical devices (160), cause the medical devices (160) to perform a series of actions for calibration. Specific educational content can be executed by medical equipment (160) to modify one or more setting values ​​of medical equipment (160) or the operating mode of medical equipment (160), thereby enabling automatic modification of one or more settings of medical equipment (160) through educational content items without medical personnel having to manually specify the setting values ​​of medical equipment (160).

[0099] The practitioner training module (235) stores training content as different training content items, each training content item containing individual parts of content such as files. Each training content item has one or more attributes that provide descriptive information about the training content item. For example, the attributes of the training content item identify one or more types of medical procedures associated with the training content item, thereby enabling the identification of training content items corresponding to different types of medical procedures. Other exemplary attributes of the training content item include: one or more medical practitioners associated with the training content item (e.g., a medical practitioner who performed the medical procedure associated with the training content item, a medical practitioner who created the training content item), a location associated with the training content item (e.g., a geographical location, a specific medical facility), a time associated with the training content item (e.g., the time the training content item was created), an identifier of one or more medical equipment (160) associated with the training content item, an identifier of one or more medical devices used in the medical procedure associated with the training content item, the format of the training content item (e.g., audio, video, text), or other information describing the training content item. In various embodiments, educational content items may be stored locally by the collaborative medical platform (140) (e.g., in a video library (250) or other storage device) or retrieved from one or more third-party servers (170).

[0100] One or more educational content items may include a reference case, which is a medical case selected by a medical professional who performed a medical procedure completed in a medical case to make available to other medical professionals. For the reference case, the professional training module (235) stores video data, telemetry data from medical equipment (160), or other data captured by the collaborative medical platform (140) during the performance of the medical procedure completed. In various embodiments, the reference case includes a content feed containing comments or other data obtained from contributors by the collaborative medical platform (140) during the medical procedure completed. For the reference case, the professional training module (235) pseudonyms the patient data to prevent the reference case from containing patient data that may be attributed to a specific patient. In some embodiments, the pseudonymized patient data in the reference case identifies a range for one or more open data types to prevent identification of the specific patient for whom the medical procedure completed was performed, while maintaining relevant information about the patient for whom the medical procedure completed was performed for other medical professionals.

[0101] Each educational content item is associated with one or more baseline criteria. Different baseline criteria specify values ​​for indicators from performing a medical procedure, settings of medical equipment (160) used in the medical procedure, movement patterns of medical equipment (160) during the medical procedure, patterns of telemetry data acquired during the medical procedure, movement patterns of medical personnel during the medical procedure, or other descriptive information regarding the performance of the medical procedure. Baseline criteria specify standardized values ​​for indicators, standardized techniques or approaches used in the medical procedure, or other standardized values ​​or techniques associated with the medical procedure. The practitioner training module (235) maintains one or more baseline criteria for different medical procedures, and thus different educational content items correspond to different medical procedures. The attributes of an educational content item include an identifier of a corresponding type of medical procedure to indicate that the educational content item and its associated baseline criteria correspond to a type of procedure. This enables the practitioner training module (235) to identify different baseline criteria for different types of medical procedures.

[0102] In various embodiments, one or more medical professionals input baseline criteria for medical procedures into the professional training module (235). For example, a group of medical professionals reaches an agreement on the value of an indicator, the pattern of telemetry data, the pattern of movement, or the value of other information describing the performance of the medical procedure. The medical professionals in the group input the agreed baseline criteria into the professional training module (235) to store them associated with training content items. The group of medical professionals may be associated with a specific medical facility (e.g., a hospital, a clinic) to provide facility-specific baseline criteria. The professional training module (235) stores the identifier of the medical facility as an attribute of the training content item associated with the facility-specific baseline criteria to indicate the baseline criteria associated with the specific medical facility. Additionally or alternatively, the group of medical professionals who determined the baseline criteria may not be associated with a specific medical facility but may belong to a larger organization or standard body, and thus the baseline criteria for medical procedures may be applicable across various medical facilities. The employee training module (235) may store facility-specific baseline standards and more generally applicable baseline standards as different attributes of training content items in various embodiments. This allows the more generally applicable baseline standards associated with the training content items to be reinforced with facility-specific baseline standards.

[0103] In various embodiments, the practitioner training module (235) applies one or more trained machine learning models to indicators generated by the analysis module (235) for multiple medical cases in which a type of medical procedure is performed, thereby generating one or more baseline criteria associated with educational content items. In various embodiments, one or more trained machine learning models are also applied to telemetry data or video data captured by the telepresence module (225) during the medical cases in which the corresponding type of medical procedure is performed. For example, the machine learning model detects patterns in telemetry data captured during a specific type of medical procedure occurring in a medical case where a specific value of the generated indicator is generated or the value of the generated indicator is within a value range. The specific value of the generated indicator or the value range of the generated indicator may correspond to one or more specific patient outcomes. For example, the specific value or value range identifies successful patient outcomes for the corresponding type of medical procedure. One or more patterns in telemetry data detected at least at a critical frequency in medical procedures occurring in medical cases where the generated indicator has a specific value or a value within a specified range are stored in various embodiments as baseline criteria for educational content items associated with the specific type of medical procedure.

[0104] For example, applying a machine learning model to telemetry data identifies a specific movement sequence of medical equipment (160) detected at least at a critical frequency in a specific type of completed medical procedure performed in a medical case having an indicator corresponding to a positive outcome, which is stored as a baseline reference for an educational content item corresponding to the movement of medical equipment (160) for a specific type of medical procedure. Telemetry data describing the specific movement sequence of medical equipment (160) may be stored in an educational content item to specify limits on the movement of medical equipment (160) during a specific type of medical procedure or limits on the force applied by medical equipment (160) during a specific type of medical procedure. As another example, captured telemetry data includes location data for medical equipment (160) during the occurrence of a corresponding type of medical procedure in a medical case having one or more indicators associated with a positive outcome for a patient. The practitioner training module (235) stores an educational content item associated with the corresponding type of medical procedure having location data in the captured telemetry data as a baseline reference. This simplifies the creation of educational content items for various medical procedures by enabling the worker training module (235) to dynamically generate educational content items and associated baseline criteria for a type of medical procedure based on telemetry data captured during the performance of a type of medical procedure over time.

[0105] In another example of generating an educational content item from telemetry data, telemetry data from medical equipment includes the two-hand manipulation proficiency of a medical worker during a medical procedure, and the two-hand manipulation proficiency information is stored as a baseline reference in the educational content item in response to a determination that the medical procedure has a positive outcome. In various embodiments, the generated educational content item includes data for accessing a simulator for the medical equipment (160) used during the medical procedure (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.), thereby further improving the use of the medical equipment (160) in response to the telemetry data from the medical worker during the medical procedure including two-hand manipulation proficiency information that deviates by at least a threshold amount from the baseline reference of the educational content item. As another example, telemetry data from medical equipment (160) includes tissue tension on a patient during the medical procedure, and the tissue tension is stored as a baseline reference in the educational content item in response to a determination that the medical procedure has a positive outcome by the worker education module (235). The generated educational content item may include data for accessing a simulator for medical equipment (160) used during a medical procedure (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.), thereby further improving the use of the medical equipment (160) in response to telemetry data from a medical worker during a medical procedure containing two-handed operation proficiency information that deviates from the baseline standard of the educational content item by at least a threshold amount.

[0106] Additionally or alternatively, the practitioner training module (235) applies one or more machine learning models to video data captured during the performance of a specific type of medical procedure during a previous medical case to identify different medical equipment (160) used during the specific type of medical procedure, movement of different medical equipment (160) during the specific type of medical procedure, movement of the medical practitioner performing the specific type of medical procedure, or other information regarding the performance of the specific type of medical procedure. As described in more detail above, applying a machine learning model to video data of a previous performance of a specific type of medical procedure detects movement patterns of the medical practitioner or medical equipment (160) during the performance of the specific type of medical procedure. Patterns or movements detected at least at a threshold frequency in video data of a specific type of completed medical procedure performed in a medical case having an indicator corresponding to a positive outcome are stored as baseline criteria for one or more training content items associated with the specific type of medical procedure. Such training content items associated with baseline criteria describing the medical procedure and movement patterns of that type include location data or other data describing the movement or positioning of the medical practitioner or medical equipment (160) during the specific type of medical procedure for subsequent reference. Other information, such as depth perception data, proximity of the medical equipment (160) to the patient's structure, angle of incision of the patient's structure by the medical equipment (160), path length of the medical equipment (160), tissue tension, proficiency of the medical worker's two-hand operation, or other data, can be determined from video data by the worker training module (235) and is stored as a baseline reference in response to being determined from video data of the medical procedure at a threshold frequency or in response to being determined from video data of the medical procedure having an indicator corresponding to a positive result.This allows the worker training module (235) to determine a baseline standard for one type of medical procedure based on video data of one or more medical procedures.

[0107] To select an educational content item for a medical worker, the worker education module (235) compares data describing the performance of a medical procedure performed by a medical worker with baseline criteria associated with various educational content items. In various embodiments, after a medical worker completes a medical procedure, the worker education module (235) identifies an educational content item associated with a type of medical procedure and compares acquired information describing the medical procedure with one or more baseline criteria associated with the identified educational content item. For example, the worker education module (235) compares an indicator generated for the medical procedure by the analysis module (230) from captured telemetry data, video data, or other data with baseline criteria associated with the educational content item associated with that type of medical procedure. In response to the indicator differing by at least a threshold amount from the baseline criteria associated with the educational content item, or failing to meet the baseline criteria, the worker education module (235) selects an educational content item associated with the baseline criteria to present to the medical worker. For example, in response to a determination that the amount of time a medical worker takes to complete a medical procedure exceeds the average time taken to complete that type of medical procedure or exceeds the baseline time taken to complete that type of medical procedure, one or more educational content items are selected that are associated with that type of medical procedure and associated with a baseline standard that specifies the amount of time taken to complete that type of medical procedure. In some embodiments, the worker training module (235) selects one or more educational content items associated with a baseline standard that is associated with a type of medical procedure and where the indicator determined for the medical procedure differs by at least a threshold amount, so that the worker training module (235) can consider a specific amount of difference between the determined indicator and the baseline standard when selecting the educational content items.

[0108] Alternatively or additionally, the practitioner training module (235) compares one or more patterns or data detected within telemetry data captured during the performance of a medical procedure with a baseline reference associated with a training content item. The practitioner training module (235) selects a training content item associated with a baseline reference that specifies a pattern of telemetry data that is associated with the type of medical procedure and differs from the captured telemetry data by at least a threshold amount. For example, the telemetry data includes depth perception data during the medical procedure, and the practitioner training module (235) selects a training content item associated with depth perception data that is associated with the type of medical procedure and differs from the captured depth perception data by at least a threshold amount. In some embodiments, the selected training content item includes information for accessing a simulator for medical equipment (160) to be accessed by a medical practitioner (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.). In another example, telemetry data includes tissue tension data captured during a medical procedure, and the practitioner training module (235) selects a training content item associated with tissue tension data that is associated with the type of medical procedure and differs from the captured tissue tension data by at least a threshold amount. The selected training content item includes information for accessing a simulator for medical equipment (160) to be accessed by a medical practitioner in various embodiments (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.).

[0109] Telemetry data from one or more sensors (e.g., sensors included in medical equipment (160)) may also describe the movement or positioning of medical equipment (160) or medical devices during a medical procedure, and the practitioner training module (235) selects a training content item that includes a baseline criterion in which the movement of medical equipment or the positioning of medical devices in the telemetry data deviates by at least a threshold amount. For example, the telemetry data includes the path length of medical equipment (160) during a medical procedure, and the practitioner training module (235) selects a training content item that includes a baseline criterion in which the path length of medical equipment (160) in the captured telemetry data associated with that type of medical procedure deviates by at least a threshold amount. In another example, telemetry data includes location data of medical equipment (160) during a medical procedure, and the practitioner training module (235) selects an educational content item that includes a baseline criterion specifying the location data of medical equipment (160) in the captured telemetry data associated with the type of medical procedure and the location data of medical equipment (160) that deviates by at least a threshold amount. In one additional example, telemetry data includes two-handed manipulation proficiency data of a medical practitioner during a medical procedure, and the practitioner training module (235) selects an educational content item that includes a baseline criterion specifying the two-handed manipulation proficiency data of medical equipment (160) that deviates by at least a threshold amount from the two-handed manipulation proficiency data in the captured telemetry data associated with the type of medical procedure. In the preceding examples, the educational content item selected based on the telemetry data includes information for accessing a simulator associated with the medical equipment (160) corresponding to the telemetry data (e.g., via a collaborative medical platform (140)), thereby providing the medical practitioner with increased interaction with the medical equipment (160).Furthermore, an educational content item selected based on the deviation from the baseline reference of the location data of the medical equipment (160) may include one or more of the following: a training video associated with the medical equipment (160) and explaining the operation of the medical equipment; audio data explaining the operation of the medical equipment (160); and information for accessing a simulator for the medical equipment (160) (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.). In some embodiments, captured telemetry data describes the usage pattern of the medical equipment (160) during a medical procedure. In response to determining that the usage pattern of the medical equipment (160) deviates from the baseline usage pattern of the medical equipment in the educational content item, the practitioner training module (235) selects an educational content item that may include benchmarking data describing the cost of the medical procedure based on the usage pattern and information on alternative usage patterns of the medical equipment (160) to reduce costs, or information describing the recommended usage pattern of the medical equipment (160) or the use of alternative medical equipment (160) in that type of medical procedure.

[0110] In various embodiments, the practitioner training module (235) compares one or more data identified from video data captured during the performance of a medical procedure with a baseline reference associated with the training content item to select one or more training content items for a medical practitioner. The practitioner training module (235) selects a training content item associated with a baseline reference that specifies specific data associated with the type of medical procedure and differs by at least a threshold amount from the data identified from the captured video. For example, the practitioner training module (235) obtains depth perception data from video data of the medical procedure during the medical procedure and selects a training content item associated with depth perception data associated with the type of medical procedure and differs by at least a threshold amount from the depth perception data determined from video data of the medical procedure. In some embodiments, the selected training content item includes information for accessing a simulator for medical equipment (160) to be accessed by the medical practitioner (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.). As another example, the practitioner training module (235) determines tissue tension data during a medical procedure and selects an educational content item associated with tissue tension data that is associated with the type of medical procedure and differs from the tissue tension data determined from video data by at least a threshold amount. The selected educational content item includes information for accessing a simulator for medical equipment (160) to be accessed by a medical practitioner in various embodiments (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.).

[0111] The worker training module (235) determines the movement or positioning of medical equipment (160) or medical devices during a medical procedure from video data of a medical procedure through one or more computer vision models or other models in various embodiments. Based on the movement or positioning information obtained from the video data, the worker training module (235) selects a training content item that includes a baseline criterion that deviates by at least a threshold amount from the movement or positioning of medical equipment or medical devices in the telemetry data. For example, the worker training module (235) determines the path length of the medical equipment (160) during a medical procedure from the video data of the medical procedure, and the worker training module (235) selects a training content item that includes a baseline criterion that specifies the path length of the medical equipment (160) associated with the type of medical procedure and deviates by at least a threshold amount from the path length in the video data. In another example, the worker training module (235) determines location data of medical equipment (160) during a medical procedure from a video of a medical procedure, and the worker training module (235) selects a training content item that includes a baseline criterion for specifying location data of medical equipment (160) associated with the type of medical procedure and having a deviation of at least a threshold amount from the location data of medical equipment (160) from the video data. In one additional example, the worker training module (235) determines two-handed operation proficiency data of a medical worker during a medical procedure from video data, and the worker training module (235) selects a training content item that includes a baseline criterion for specifying two-handed operation proficiency data of medical equipment (160) associated with the type of medical procedure and having a deviation of at least a threshold amount from the two-handed operation proficiency data determined from the video data.In the preceding examples, the training content item selected based on telemetry data includes information for accessing a simulator associated with the medical equipment (160) corresponding to the telemetry data (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.), thereby providing the medical worker with increased interaction with the medical equipment. Furthermore, the training content item selected based on the deviation of the location data of the medical equipment (160) from a baseline reference may include one or more of the following: a training video associated with the medical equipment (160) and explaining the operation of the medical equipment, audio data explaining the operation of the medical equipment (160), and information for accessing a simulator for the medical equipment (160) (e.g., an identifier of the simulator, one or more exercises or skills to be performed on the identified simulator, etc.).

[0112] In some embodiments, the practitioner training module (235) determines from video data of a medical procedure the angle at which a patient’s structure (e.g., a patient’s organ) is incised by medical equipment (160) (or medical device) during the medical procedure. The practitioner training module (235) selects an educational content item that includes an angle for incising a patient’s structure associated with the type of medical procedure and which has a deviation of at least a threshold amount from the angle determined from the video data of the medical procedure. The educational content item selected based on the determined angle of incision of the patient’s structure from the baseline angle of incision may include content describing the use of medical equipment (160) (or medical device) for incising the patient’s structure during the medical procedure or content describing the correlation between the angle of incision of the patient’s structure and one or more medical procedure outcomes (e.g., information describing the correlation between a specific angle of incision of the patient’s structure and a positive medical procedure outcome or the angle of incision of the patient’s structure and a negative medical procedure outcome). As another example, the practitioner training module (235) determines the proximity of medical equipment (160) (or medical device) to one or more critical structures of a patient (e.g., organs, bones, arteries) during a medical procedure from video data of a medical procedure. The practitioner training module (235) selects a training content item that includes the proximity of medical equipment (160) (or medical device) from video data associated with the type of medical procedure and baseline proximity of medical equipment (160) (or medical device) to critical structures of the patient that have deviated by at least a threshold amount.In various embodiments, an educational content item having baseline proximity to a patient's vital structures includes content explaining the use of an energy device during a medical procedure, which may include interactive content (e.g., content with questions to be answered by a medical professional), video or audio content explaining the use of an energy device during a medical procedure, or other explanatory information regarding the use of an energy device during a medical procedure.

[0113] Furthermore, the practitioner training module (235) can determine the usage pattern of the medical equipment (160) during the medical procedure from video data of the medical procedure. In response to determining that the usage pattern of the medical equipment (160) deviates from the baseline usage pattern of the medical equipment in the training content item, the practitioner training module (235) selects a training content item. The selected training content item may include benchmarking data describing the cost of the medical procedure based on the usage pattern and information on alternative usage patterns of the medical equipment (160) to reduce costs. As another example, the selected training content item may include information describing the recommended usage pattern of the medical equipment (160) or the use of alternative medical equipment (160) in that type of medical procedure.

[0114] As another example, the worker training module (235) compares a pattern of one or more movements (e.g., movement of medical equipment (160), movement of a part of the medical worker) detected within video data captured during a medical procedure with a baseline reference that includes a movement pattern for that type of medical procedure, and selects an educational content item for the medical worker associated with the baseline reference that specifies a movement pattern where the detected movement pattern deviates by at least a threshold amount. Thus, the worker training module (235) can determine when to select an educational content item for the medical worker using data (e.g., telemetry data or video data) captured during the performance of the medical procedure. Different detected patterns within the telemetry data or video data captured during the performance of the medical procedure can be compared with different educational content items associated with different baseline references, respectively. This enables the worker training module (235) to select an educational content item for the medical worker based on the specific part of the medical procedure where a deviation from the corresponding baseline reference occurred, based on the telemetry data or video data captured during the performance of the medical procedure, thereby enabling customization of the selection of educational content items for a specific part of the medical procedure.

[0115] The worker training module (235) may select one or more training content items to present to the medical worker by applying one or more trained machine learning models to attributes of the training content items, such as data describing the performance of a medical procedure performed by the medical worker and training content items associated with a type of medical procedure. Exemplary attributes of the training content items include: the type of medical procedure associated with the reference content item, one or more medical workers associated with the reference content item, the location where the medical procedure was performed (e.g., geographic location, medical facility identifier), the format of the reference content item (e.g., text data, audio data, video data, etc.), feedback on the reference content item from one or more medical workers (e.g., ranking, amount of positive feedback received for the reference content item, etc.), or other descriptive information. In various embodiments, the worker training module (235) trains one or more machine learning models to select one or more training content items for the medical worker based on the attributes of the training content items and the characteristics of the medical worker. Exemplary machine learning models include regression models, support vector machines, naive Bayes, decision trees, k nearest neighbors, random forests, boosting algorithms, k-means, and hierarchical clustering. Machine learning models may also include neural networks such as perceptrons, multilayer perceptrons, convolutional neural networks, recurrent neural networks, sequence-to-sequence models, generative adversarial networks, or transformers, and other types of machine learning models may be additionally or alternatively trained or applied by the practitioner training module (235) in various embodiments.

[0116] For example, to train a machine learning model to select one or more educational content items, the practitioner training module (235) generates a set of training examples, each training example including data describing the performance of a medical procedure performed by a medical practitioner and attributes of an educational content item, and has a label indicating whether the medical practitioner in the training example accessed the educational content item included in the training example (or whether the medical practitioner in the training example provided positive feedback on the educational content item included in the training example).

[0117] Applying a machine learning model to a training example generates a predictability that a healthcare worker in the training example will access an educational content item in the training example (or a predictability that a healthcare worker in the training example will provide positive feedback on an educational content item included in the training example). For each training example to which the worker training module (235) applies the machine learning model, the worker training module (235) generates a score for the machine learning model that includes an error term based on the label applied to the training example and the predictability that a healthcare worker in the training example will access an educational content item in the training example (or a predictability that a healthcare worker in the training example will provide positive feedback on an educational content item included in the training example). The error term and the corresponding score are larger when the difference between the label applied to the training example and the predictability of the healthcare worker in the training example accessing the educational content item in the training example (or the predictability of the healthcare worker in the training example providing positive feedback on the educational content item included in the training example) is larger, and are smaller when the difference between the label applied to the training example and the predictability of the healthcare worker in the training example accessing the educational content item in the training example (or the predictability of the healthcare worker in the training example providing positive feedback on the educational content item included in the training example) is smaller. In various embodiments, the worker training module (235) generates a score for the machine learning model applied to the training example using a loss function based on the difference between the label applied to the training example and the predictability of the healthcare worker in the training example accessing the educational content item in the training example (or the predictability of the healthcare worker in the training example providing positive feedback on the educational content item included in the training example). Exemplary loss functions include a mean squared error function, a mean absolute error function, a hinge loss function, and a cross-entropy loss function.

[0118] The worker training module (235) updates the set of parameters constituting the machine learning model by backpropagating error terms and stops backpropagating in response to the score or loss function meeting one or more criteria. For example, the worker training module (235) updates the parameters of the machine learning model by backpropagating the score to the machine learning model through the layers of the machine learning model until the score has a value smaller than a threshold. For example, the worker training module (235) updates the set of parameters constituting the machine learning model using gradient descent. The worker training module (235) stores machine learning models trained to apply to data describing the performance of medical procedures performed by medical workers and attributes of one or more training content items. In some embodiments, the worker training module (235) trains and maintains different machine learning models using different combinations of attributes of training content items and data describing the performance of medical procedures performed by medical workers, respectively.

[0119] Alternatively or additionally, one or more machine learning models applied by the practitioner training module (235) to select an educational content item are nearest neighbor models applied to the characteristics of a medical practitioner, including embeddings corresponding to the educational content item and data describing the performance of a medical procedure performed by the medical practitioner. As described in more detail above, exemplary attributes of an educational content item include: the type of medical procedure associated with the reference content item, one or more medical practitioners associated with the reference content item, the location where the medical procedure was performed (e.g., geographic location, medical facility identifier), the format of the reference content item (e.g., text data, audio data, video data, etc.), feedback on the reference content item from one or more medical practitioners (e.g., ranking, amount of positive feedback received for the reference content item, etc.), or other descriptive information. Exemplary characteristics of a medical worker include: the medical worker's specialty, the type of previous medical procedure performed by the medical worker, the medical procedure scheduled to be performed by the medical worker, the location where the medical worker performs the medical procedure (e.g., geographic location, medical facility identifier, etc.), collaborators connected to the medical worker via a connection graph, or other descriptive information about the medical worker and the data described above in more detail regarding the performance of the medical procedure by the medical worker.

[0120] In some embodiments, the practitioner training module (235) applies a nearest neighbor model to the medical practitioner embedding to determine the distance (or similarity measure) in a latent space between the medical practitioner embedding and the embeddings for various training content items. For example, the nearest neighbor model determines the Euclidean distance between the medical practitioner embedding and the embeddings for training content items. Based on the distance, the nearest neighbor model ranks the training content items according to the distance (or similarity measure) of the corresponding embeddings to the medical practitioner embeddings, selects one or more training content items that have a threshold position in the rank, and thus the selected one or more training content items have the embedding closest to the medical practitioner embedding. Alternatively, the nearest neighbor model selects one or more training content items that have a distance less than the threshold distance from the medical practitioner embedding. Alternatively, the practitioner training module (235) generates an embedding for a medical procedure performed by a medical practitioner, as described in more detail above, and selects one or more training content items based on the distance between the embedding for the medical procedure and the embedding for the training content item.

[0121] Furthermore, in some embodiments, the worker training module (235) generates embeddings for different medical workers based on the characteristics of the medical worker, as described in more detail above. The worker training module (235) determines the distance between the embedding for the medical worker and the embedding for additional medical workers. For example, the worker training module (235) determines the Euclidean distance between the embedding for the medical worker and the embeddings for a number of additional medical workers. Based on the distance (or similarity measure), the worker training module (235) selects a set of additional medical workers. For example, the worker training module (235) selects additional medical workers that have embeddings within a threshold distance from the embedding of the medical worker. As another example, the worker training module (235) ranks the additional medical workers based on the distance between the embedding of the additional medical workers and the embedding of the medical worker, and selects additional medical workers that have at least a threshold position in the rank. The worker training module (235) selects to present one or more educational content items to the medical worker, which are presented to one or more of the selected additional medical workers. Such an embodiment allows the worker training module (235) to select educational content items to present to the medical worker by utilizing similarities among various medical workers.

[0122] In various embodiments, the practitioner training module (235) determines one or more baseline criteria for educational content items by applying one or more clustering models to one or more attributes of a medical case in which a specific type of medical procedure was performed. The attributes of the medical case include one or more indicators generated for the medical case by the analysis module (230), telemetry data captured during the performance of the medical procedure in the medical case, video data captured during the performance of the medical procedure in the medical case, or other descriptive information about the medical case. Based on the attributes of the medical case, the practitioner training module (235) generates an embedding for the medical case. The practitioner training module (235) generates different clusters of cases in which a specific type of medical procedure was performed by applying a clustering model to the embeddings for different medical cases in which a specific type of medical procedure was performed. Different clusters are presented as different centroids in a latent space containing the embeddings for the medical cases, and the clusters include medical cases having embeddings within a threshold distance from the centroid of the cluster. In some embodiments, the practitioner training module (235) applies a k-means clustering model to embeddings for different medical cases in which a specific type of medical procedure was performed. Using k-means clustering causes medical cases in which a specific type of medical procedure was performed to be included in clusters based on the distance between the embedding for the medical case and the centroids of different clusters. Medical cases in which a specific type of medical procedure was performed are included in clusters that have centroids with the minimum distance from the embedding for the medical case. The centroids of the clusters are iteratively updated based on the embeddings for medical cases in which a specific type of medical procedure was performed that are included in various clusters until one or more criteria are met. This results in a specific number of clusters, each cluster containing medical cases in which a specific type of medical procedure was performed that have similar embeddings.

[0123] The worker training module (235) can identify baseline criteria based on medical cases included in one or more clusters. For example, a cluster of cases where a specific type of medical procedure was performed corresponds to a positive outcome for the specific type of medical procedure, and an alternative cluster corresponds to a negative outcome for the specific type of medical procedure. Based on telemetry data or video data captured during the performance of the specific type of medical procedure in additional cases, the worker training module (235) generates an embedding for the additional cases and determines the cluster containing the additional cases based on the cluster centroid and the embedding for the additional cases. In response to determining that the additional cases are included in an alternative cluster corresponding to a negative outcome, the worker training module (235) selects one or more training content items to present to the medical worker performing the specific type of medical procedure during the additional cases. The worker training module (235) compares telemetry data or video data captured during the performance of a specific type of medical procedure in additional medical cases with telemetry data or video data associated with a baseline standard of an educational content item associated with a specific type of medical procedure, and selects one or more educational contents having a baseline standard that specifies telemetry data or video data associated with a specific type of medical procedure and differs by at least a threshold amount from the telemetry data or video data captured during the performance of a specific type of medical procedure.

[0124] Alternatively, the practitioner training module (235) selects an educational content item for a medical case in response to determining that the embedding for the medical case is not included in a specific cluster. As an example, the practitioner training module (235) selects an educational content item for a medical case in response to determining that the embedding for the medical case is greater than a threshold distance from the center point of a specific medical case cluster. This may indicate that the medical case has characteristics that deviate by at least a threshold amount from the characteristics of other medical cases with positive patient outcomes in which that type of medical procedure was performed. As described in more detail above, the practitioner training module (235) may select an educational content item having a baseline criterion that includes telemetry data or video data that is associated with a specific type of medical procedure performed in the medical case and differs by at least a threshold amount from the telemetry data or video data captured during the performance of the medical procedure in the medical case.

[0125] When creating clusters of medical cases based on corresponding embeddings, the practitioner training module (235) may identify medical cases included in a specific cluster as reference cases for educational content items for the corresponding type of medical procedure. For example, in response to the practitioner training module (235) including a medical case in a specific cluster associated with a positive outcome, the practitioner training module (235) prompts the medical practitioner associated with the medical case to create a reference case based on the medical case. In response to receiving approval from the medical practitioner to create a reference case from the medical case, the practitioner training module (235) pseudonyms the patient data in the medical case and stores the pseudonymized patient data, video data captured during the performance of the medical procedure, telemetry data captured during the performance of the medical procedure, and one or more indicators generated for the medical procedure as educational content items for the corresponding type of medical procedure. One or more patterns determined from the telemetry data or video data, or one or more generated indicators, are stored as baseline criteria associated with the educational content items. This simplifies the creation of educational content items for a type of medical procedure by utilizing data captured by the collaborative medical platform (140) during the performance of the medical procedure to create educational content items for subsequent reference regarding the medical procedure.

[0126] In various embodiments, an educational content item selected for a medical worker based on the performance of a medical procedure by a medical worker is presented to the medical worker during the post-procedure phase. Presenting the educational content item to the medical worker during the post-procedure phase enables the review of the educational content item after the completion of the medical procedure. The worker education module (235) creates one or more interfaces that identify the educational content item selected for the medical worker. For example, the worker education module (235) includes information identifying the educational content item selected on a worker dashboard presented to the medical worker, such as the worker dashboard described in more detail below in relation to FIG. 4. In various embodiments, the information identifying the educational content item selected includes a link to retrieve the educational content item selected for presentation when selected by the medical worker. Alternatively, the worker education module (235) presents the information identifying the educational content item in a different interface or a different format. For example, the worker education module (235) sends a notification message to the medical worker's client device (150) that includes a link to retrieve the educational content item selected for presentation when selected by the medical worker.

[0127] The worker training module (235) may include selected educational content items in one or more interfaces presented to a medical worker when accessing the collaborative medical platform (140) in various embodiments. For example, the worker training module (235) creates an interface containing educational content and presents information describing the selected educational content item through the interface, so that the medical worker can select the information describing the selected educational content item to access the selected educational content item. As another example, the worker training module (235) includes information identifying the selected educational content item on a medical case page created by the interface management module (215) for a medical procedure for which the educational content item is selected. For example, the medical case page includes a section containing notes or feedback for the medical worker regarding the medical case, and one or more educational content items selected by the worker training module (235) are included in the section. Furthermore, the interface management module (215) may generate one or more interfaces containing recommendations for medical personnel based on indicators for medical personnel based on medical procedures, and the recommendation interface includes one or more educational content items selected by the personnel education module for medical personnel based on data describing the performance of one or more medical procedures.

[0128] In some embodiments, the worker training module (235) includes the selected training content item in different interfaces depending on the content of the selected training content item. For example, a training content item describing the use of medical equipment or medical devices is displayed in a recommendations interface. As another example, a training content item containing interactive materials or audio or video data to be presented to a medical worker is presented in a medical case page or a training interface. However, in other embodiments, the worker training module (235) selects an interface for identifying the selected training content item based on other characteristics of the training content item.

[0129] Alternatively or additionally, the worker training module (235) presents selected educational content items to the medical worker during the procedure phase of the medical procedure. This presents selected educational content items to the medical worker while the medical worker is performing the medical procedure. In various embodiments, the worker training module (235) transmits a notification identifying the selected educational content item to a client device (150) or medical equipment (160), which displays or audibly presents the notification to the medical worker. The notification may include specific content from the selected educational content item to simplify the medical worker's access to relevant information from the selected educational content item. In various embodiments, the worker training module (235) transmits a notification identifying the educational content item to the medical equipment (160) associated with the educational content item. For example, the educational content item may include recommended settings for the medical equipment (160) (e.g., force threshold, movement threshold), so transmitting the notification to the medical equipment (160) simplifies the identification of the medical equipment (160) associated with the educational content item. A notification transmitted to the medical equipment (160) may include a link that, when selected by a medical professional, causes the medical equipment (160) to execute one or more commands to modify one or more settings based on the educational content item. Similarly, information identifying an educational content item associated with the medical equipment (160) presented by the client device (150) may include a command that, when selected, transmits a command to modify one or more settings of the medical equipment (160). This simplifies the modification of settings of the medical equipment (160) based on the selected educational content item by reducing the amount of interaction with the medical equipment (160) by the medical professional. Alternatively, the professional training module (235) includes information identifying the selected educational content item in an interface presented to the medical professional through the client device (150).

[0130] In some embodiments, a medical worker authorizes the worker training module (235) to automatically modify one or more settings of medical equipment (160) based on training content items selected for the medical worker. Such authorization may be limited to one or more specific medical equipment (160) that is specific to a specific medical procedure or used during a specific medical procedure. When the medical worker authorizes the worker training module (235) to automatically modify one or more settings of medical equipment (160), the worker training module (235) sends a notification to the medical equipment (160) used for the medical procedure that includes one or more commands corresponding to the selected training content items. The medical equipment (160) executes one or more commands to modify one or more settings of the medical equipment (160) based on the selected training content items. In various embodiments, the medical equipment (160) displays a notification or informs the medical worker that one or more settings have been modified or specified based on the selected training content items. An indication that one or more settings will be modified based on selected educational content items may be presented to the medical worker by the medical equipment (160) or client device (150) to warn the medical worker that one or more settings of the medical equipment (160) are being automatically updated and to provide the medical worker with an option to prevent the modification of one or more settings. Alternatively, the worker training module (235) automatically modifies one or more settings of the medical equipment (160) based on the educational content items selected for the medical worker, as described in more detail above, unless the medical worker indicates that the worker training module (235) has not authorized the medical worker to automatically modify one or more settings of the medical equipment (160).This allows a different embodiment to enable a medical worker to opt in to the worker training module (235) automatically modifying one or more settings of the medical equipment (160) or to opt out to the worker training module (235) automatically modifying one or more settings of the medical equipment (160).

[0131] In another embodiment, presenting an educational content item during the procedure phase of a medical case increases the number of interactions required to modify one or more settings of the medical equipment (160) used during the medical procedure. For example, presenting an educational content item through the medical equipment (160) causes the medical device (160) to request additional confirmation input from the medical worker after receiving input from the medical worker that changes a specific setting of the medical equipment (160) to a value that deviates from the corresponding value in the educational content item, or specifies a specific value for a specific setting of the medical equipment (160) outside the range corresponding to the educational content item. As an example, presenting an educational content item to the medical worker transmits a command to the medical equipment (160) used during the medical procedure, which causes the medical equipment (160) to display one or more warnings requesting input from the medical worker when the medical equipment (160) receives input from the medical worker that changes a setting value of the medical equipment (160) to a value outside the range included in the educational content item. This increases the difficulty for a medical professional who configures medical equipment (160) in a manner that does not match the selected educational content item, thereby increasing the likelihood that the setting value of the medical equipment (160) will match the selected educational content item.

[0132] The presentation module (240) facilitates the creation of presentations for education, research, training, or other purposes by utilizing stored information associated with completed medical procedures. The presentation may take the form of a slide deck, poster, video, animation, or other multimedia content. The presentation may incorporate various multimedia (e.g., video, images, 3D models, and associated metadata), patient record data, medical equipment telemetry data, information from content feeds, and other information generated or stored by the analysis or collaborative medical platform (140).

[0133] In one embodiment, the presentation module (240) may maintain one or more presentation templates for creating presentations. The templates may include pre-formatted content with various information fields that can be automatically populated from a series of records. For example, a practitioner who wishes to prepare a presentation related to a set of recently performed procedures may specify the set of procedures to include in the presentation, and the presentation module (240) may automatically populate the presentation based on data stored in association with the procedures, with each page associated with one or more types of data regarding the completed medical procedures. In some embodiments, the presentation module (240) may apply one or more trained machine learning models to automatically generate and / or recommend presentation content that may be of interest to the practitioner. In additional embodiments, the presentation module (240) may intelligently and automatically de-identify patient data included in the presentation.

[0134] The presentation module (240) may also include various editing tools for creating, viewing, and editing the presentation. For example, the editing tools may enable editing of text, video, images, animations, 3D models, or other content to be included in the presentation.

[0135] In one embodiment, the presentation may be presented directly through the presentation module (240) without the data associated with the presentation being exported outside the collaborative medical platform (140). For example, the presentation module (240) may enable live streaming of the presentation to a series of invited attendees during a telepresence session. The invited attendees may be limited to users (155) of the collaborative medical platform (140) or may include external attendees accessible via an external link. Sharing the presentation in this manner allows the practitioner to maintain data privacy and compliance and avoid potential issues that may arise when exporting medical data externally.

[0136] The application integration module (245) manages the integration of the application with the collaborative medical platform (140). The application can be utilized to add additional optional features to the collaborative medical platform (140). For example, the application can enable integration with a specific EHR system, scheduling system, or other existing medical system. The application can also allow the user to optionally add specific features in addition to the core features of the collaborative medical platform (140). The application integration module (245) can allow third parties to create applications that interface with the collaborative medical platform (140) and to add such applications.

[0137] The application integration module (245) may maintain a catalog of applications that can interface with the collaborative medical platform (140) and provide an interface that allows the user (155) to selectively add applications for integration. In various embodiments, applications identified by the application integration module (245) are approved or authorized by the administrator of the collaborative medical platform (140) for installation, thereby enabling the regulation of applications that can be executed on the collaborative medical platform (140).

[0138] Additionally, the application integration module (245) may include one or more application programming interfaces (APIs) for applications installed through the application integration module (245). The APIs for the applications provide the ability to exchange data between the applications and one or more components of the collaborative medical platform (140), thereby simplifying data exchange between the applications and other parts of the collaborative medical platform (140).

[0139] The video library (250) stores videos of various medical procedures, training presentations, simulations, or other medical videos, as well as metadata associated with the videos. Examples of metadata associated with medical procedure videos may include telemetry data from one or more medical devices received with the video, comments or annotations received from one or more medical personnel via a surgical interface during the medical procedure included in the video, segmentation data dividing the video into temporal segments associated with different procedure steps, profile information associated with the patient in the video (e.g., age, body mass index, gender, etc.), or other information supplementing the video. Various reference content items containing video data may be stored in the video library (250) for retrieval by the personnel training module (235) in various embodiments.

[0140] A video library (250) may store videos in an indexed database that indexes videos based on various metadata. Then, the video library (250) may be navigated or searched through a video library interface to identify related videos. The metadata associated with the videos may include permissions stored in a connection graph store (255) that controls which users (155) can access different videos. For example, videos within the video library (250) may be accessible only to users (155) who have viewing permissions for the videos, or the videos may be explicitly shared.

[0141] The connection graph store (255) includes a database that stores information describing connections between entities or other objects (e.g., video or other multimedia) managed by the collaborative medical platform (140). For example, as described above, the connection graph store (255) stores connections between users (155), connections between users (155) and procedures, connections between users (155) and multimedia content or other objects, or other connections between data entities of the collaborative medical platform (140).

[0142] The user profile repository (260) stores profile data for a user (155) of the collaborative medical platform (140). A user profile for a medical professional includes descriptive information such as the medical professional's name, contact information for the medical professional, credentials or licenses for the medical professional, biographical information for the medical professional, types of medical procedures that can be performed by the medical professional, medical facilities associated with the medical professional, operating room preferences (e.g., patient positioning, equipment settings, preferred devices, typical procedure step sequence, etc.), equipment configuration preferences (e.g., ergonomic settings for a robotic console), or other information describing the medical professional. The characteristics of the user profile may be inferred using machine learning techniques. For example, the medical professional's preferred devices or step sequence may be inferred from the application of a machine learning model trained to infer such preferences based on observed historical data. Additionally, a user profile for a medical professional includes information describing medical procedures as well as medical procedures that have been or will be performed by the medical professional. For example, the user profile may identify different types of medical procedures to be performed or performed by a medical professional and may include characteristics for each medical procedure (e.g., the length of time taken to complete the medical procedure, the number of times the medical professional has performed a type of medical procedure matching the medical procedure, etc.). Furthermore, as described in more detail above, one or more indicators determined for the medical professional by the analysis module (230) may be included in the user profile for the medical professional.

[0143] In various embodiments, additionally, a user profile stored for a medical professional includes one or more procedure cards associated with the medical professional. A procedure card includes preferences, skills, or methods for performing a type of medical procedure associated with the medical professional. For example, a procedure card associated with a type of medical procedure specifies one or more specific medical devices that the medical professional uses in a step of that type of medical procedure. A procedure card may also specify the placement of different medical devices or medical equipment (160) within the location where the medical professional performs the medical procedure for a step of that type of medical procedure, so that the procedure card specifies the placement of medical devices or medical equipment (160) when the medical professional performs different steps in that type of medical procedure. Different procedure cards may be associated with different types of medical procedures. In some embodiments, the user profile repository (260) includes a set of procedure cards associated with a type of medical procedure for the medical professional, and each procedure card in the set is associated with a step that occurs during the performance of that type of medical procedure. The set of procedure cards may specify an order of procedure cards corresponding to the order in which the medical professional performs different steps of that type of medical procedure. Therefore, procedure cards with a higher position in the set correspond to steps performed at an earlier time in that type of medical procedure.

[0144] In various embodiments, one or more procedure cards in a set of procedure cards contain configuration information for one or more medical devices (160) used during a type of medical procedure associated with the set. In some embodiments, the collaborative medical platform (140) transmits configuration information for one or more medical devices (150) included in the procedure card to the medical devices (150) in response to receiving a selection of a procedure card (or a set of procedure cards including the procedure card) from a medical professional. Including configuration information for one or more medical devices (160) in the procedure card simplifies the configuration of one or more medical devices (160) to take into account the medical professional's preferences or usage patterns when the medical professional performs a type of medical procedure.

[0145] The patient data repository (265) includes a patient profile for each patient associated with a medical case. The patient profile includes characteristics of the corresponding patient that may be obtained from electronic medical records for the patient or provided through input from a medical professional. The patient characteristics include demographic information about the patient, the patient's medical status, medical procedures previously performed by the patient, the patient's allergies, contact information about the patient, current or previous prescriptions for the patient, or other medically relevant information about the patient. A patient identifier is associated with the patient profile to uniquely identify the patient profile.

[0146] All data stored in the collaborative medical platform (140) (or made available through the collaborative medical platform (140)) may be stored, presented, and in some cases restricted in a manner that ensures compliance with various data privacy and protection regulations.

[0147] FIGS. 3a and 3b illustrate an exemplary worker dashboard (300). FIG. 3a illustrates the top portion of the dashboard (300), and FIG. 3b illustrates the bottom portion of the dashboard (300) (which may be continuously scrollable). The worker dashboard (300) may function as a home landing page for a medical worker when the medical worker logs into the collaborative medical platform (140). The worker dashboard (300) may include various content sections, at least some of which may be specifically targeted at the worker. A search bar (305) enables the input of a text-based search query to search for content available on the collaborative medical platform (140) (e.g., case pages, other user pages, videos, presentations, etc.). In response to the input of a search query, a list of results may be displayed along with links to content that matches the search query. The video promotion section (310) displays videos recently added by a worker along with user interface tools to allow the worker to promote videos by sharing them with other users, create highlight reels, or view various statistical information about the videos. The performance section (315) presents performance related to the use of the collaborative medical platform (140). In this example, the performance section (315) highlights that the user has recently reached 100 videos and provides a link to view the user's videos and access the video library. Other examples of performance in the performance section (315) may relate to the number of managed cases, the time spent using the platform (140), the number of accesses, the frequency of interactions, or other usage performance. The video library (320) includes video thumbnails, video tags, or other links that allow the medical worker to browse videos selected as potentially relevant.For example, relevant videos related to past or scheduled procedures associated with a medical professional may be selected based on the medical professional's history of watching videos, based on the medical professional's specialty of practice or other profile information, or based on other factors. The webinar promotion section (325) includes promotional banners for scheduled webinars that may be viewed within the collaborative medical platform (140). Webinars may be identified as being of potential interest to the medical professional based, for example, the topic of the webinar, the host of the webinar, or other factors. The shared case section (330) provides summary information and links to case pages shared with the medical professional. Examples of case pages are described in more detail below. The analysis summary (335) includes exemplary analyses associated with the medical professional's use of the collaborative medical platform (140), procedures performed by the medical professional, or other analytical data derived from information stored in the collaborative medical platform (140). The analytical data may be presented in one or more visual representations, such as graphs or charts. The feedback section (340) provides a link that allows medical professionals to send feedback to the administrator of the collaborative medical platform (140).

[0148] FIGS. 3a and 3b illustrate only one example of a worker dashboard (300). The types of content presented on the worker dashboard (300) may vary for different workers and / or may change dynamically over time for the same medical worker. Some sections may be fixed and always appear when accessing the dashboard (300) (e.g., search bar (305), video library (320), shared cases (330), analytics (335), and feedback sections (340)), while other sections (e.g., video promotions (310), achievements (315), webinar promotions (325)) may be dynamically inserted only in specific contexts. For example, webinar promotions (325) may be presented only when a scheduled webinar is scheduled that is considered to be of sufficient interest. Achievements (315) may similarly be displayed only when a relevant achievement has recently been accomplished. Additionally, the dashboard (300) may be customized by the user to display the desired sections in a configured order. Where present, various sections (305, 310, 315, 320, 325, 330, 335, 340) may also be presented in different order in different contexts.

[0149] FIG. 4 illustrates an alternative embodiment of a worker dashboard (400). In the example illustrated in FIG. 4, the worker dashboard (400) includes an educational content item section (405) containing information identifying an educational content item selected for a medical worker based on a previously performed medical procedure. The worker training module (235) selects the identified educational content item based on a stored baseline reference for the educational content item associated with the type of previously performed medical procedure and captured data describing the performance of the previously performed medical procedure, as described in more detail above in relation to FIG. 2. In various embodiments, the educational content item section (405) identifies one or more reasons why the identified educational content item is of potential interest to the medical worker. In the example of FIG. 4, the educational content item section (405) indicates that the identified educational content item includes proposed parameters or settings for medical equipment (160) (e.g., a robotic arm) used in the previously performed medical procedure. The educational content item section (405) in the example of FIG. 4 includes a link (410) for searching for educational content items to be presented to the medical worker through the medical worker's client device (150) when selected by the medical worker.

[0150] For the purpose of illustration, FIG. 4 illustrates an exemplary worker dashboard (400) in which an educational content item section (405) is displayed in proximity to a search bar (305). For example, the educational content item section (405) is displayed below the search bar (305) at a location on the worker dashboard (400), and thus the educational content item section (405) is displayed prominently on the worker dashboard (400) to increase the likelihood that a medical worker will select a link (410) to an identified educational content item. However, in other embodiments, the worker dashboard (400) displays the educational content item section (405) at a different location relative to other sections. Similarly, FIG. 4 illustrates an example in which a performance section (315) and a video library section (320) are displayed together with the educational content item section (405), but in other embodiments, different or additional sections are displayed by the worker dashboard (400) together with the proposed reference content item section (405).

[0151] In various embodiments, the educational content item section (405) is dynamically inserted into the worker dashboard (400) in certain contexts and is not included in the worker dashboard (400) in other contexts. For example, the worker dashboard (400) displays the educational content item section (405) after a medical worker completes a medical procedure. In one example, the worker dashboard (400) displays the educational content item section (405) after a certain amount of time has passed after the medical worker completes a medical procedure, but does not display the educational content section (405) before a certain amount of time has elapsed after the medical procedure is completed. In various embodiments, the worker dashboard (400) displays the educational content item section (405) for a specific time interval after the medical worker completes a medical procedure.

[0152] FIG. 4 illustrates an example in which an educational content item section (405) identifies a single reference content item, but in other embodiments, the educational content item section (405) displays multiple reference content items selected for a medical professional. For example, the educational content item section (405) is a carousel content item having multiple slides, each slide containing information identifying a different selected educational content item and a link to a different selected educational content item. In response to a medical professional performing a specific interaction with the educational content item section (405), the educational content item section (405) is updated to display a different slide containing information identifying a different selected educational content item. For example, the educational item section (405) displays an alternative slide containing information identifying a different selected educational content item in response to a medical professional performing a swipe gesture along an axis perpendicular to the axis including the search bar (305), the educational content item section (405), the performance section (315), and the video library section (320). This allows a single section of the worker dashboard (400) to enable medical workers to identify multiple educational content items.

[0153] In some embodiments, the collaborative medical platform (140) generates one or more educational interfaces, such as an educational dashboard. The educational interface additionally or alternatively displays one or more proposed educational content items to the medical worker, thereby providing the medical worker with an additional way to access the proposed educational content items. The worker dashboard (400) may include interface elements that cause the display of the educational interface when selected by the medical worker. In some embodiments, the educational interface may display information identifying multiple proposed educational content items, thereby enabling the medical worker to more easily access a wider range of proposed educational content items.

[0154] FIG. 5 illustrates an exemplary embodiment of a case sharing interface (500) for sharing a case with one or more contributors. Adding contributors to a case can create a connection between the contributor and the case, and between the contributor and the case owner. The case sharing interface (500) includes a selection element (505) for receiving identification information to identify a desired contributor. For example, the selection element (505) may receive the email address, name, username, or other identifier of a medical professional or other requested contributor. In some embodiments, when identification information for a desired contributor is selected, the case sharing interface (500) displays all or part of the profile data for the requested collaborator so that the requester can verify whether the matching profile data is the intended collaborator. Then, the case sharing interface (500) allows the requester to confirm or reject the selection of the collaborator and to interact with an authority selection element (520) to set the desired authority level for the requested collaborator. Here, the authority level may restrict the invited collaborator's access to data regarding the case and / or restrict the actions the collaborator is allowed to perform in connection with the case. In one exemplary embodiment, the authority level may be selected from the "collaborator" level (525A) and the "delegate" level (525B).

[0155] In response to receiving input to select a requested collaborator and set a desired level of permission (via the permission selection element (520)), the case sharing interface (500) may send an invitation to the requested contributor (e.g. via email, text message, phone call, portal message, or other communication mechanism) so that the requested collaborator may accept or decline the request. If the request is accepted, the case sharing interface (500) may add an identifier or other information about the new collaborator to the linked healthcare worker list (510) that lists contributors added to the case. For example, the illustrated example shows a linked healthcare worker list (510) including a case owner (515) and three additional contributors added to the case.

[0156] The case sharing interface (500) may also allow the case owner to change the authority level of an existing contributor in the linked medical worker list (510). Additionally, the case sharing interface (500) may include a removal element (530) associated with each contributor in the linked medical worker list (510) to allow the contributor to be removed from the case. The selection of the removal element (530) may remove the stored connection between the worker and the case, thereby preventing the worker from accessing the case any longer.

[0157] FIG. 6 is an exemplary embodiment of a case dashboard (600) for a medical professional. The case dashboard (600) enables access to cases owned by the medical professional and cases shared with the medical professional by other users (155), as indicated in the case summary (610). In this example, the case dashboard (600) is composed of a series of case cards (605) each graphically illustrating a summary of the case. Selecting a case card (605) leads to a case page (400) for the case. In an alternative embodiment, the dashboard (600) may be presented in a list view or other view, without necessarily presenting the case cards (605) in the visual form shown in FIG. 6.

[0158] FIG. 7 illustrates an example of a telepresence interface (700) associated with a telepresence session that may occur during an actual procedure or a simulated procedure. Alternatively, the telepresence session may be utilized for live planning purposes without necessarily performing or simulating the procedure. In this example, the telepresence interface (700) displays a three-dimensional model of a target anatomical structure (705) associated with the procedure. The model may include annotated comments that may be acquired during the telepresence session or added during the pre-procedure stage. Alternatively, the telepresence interface (700) may include a real-time video or image view associated with the procedure in progress. In one embodiment, each contributor may switch between different associated views, such as real-time video or image, a three-dimensional model, a pre-procedure image, or other related multimedia.

[0159] The telepresence interface (700) may also include a telepresence content feed (715) for exchanging real-time messages between contributors. For example, the telepresence content feed (715) allows a user to post messages and / or view messages from other participants. Messages may include text, media content (e.g., images, videos, animations, etc.), or links to various media content or other resources (e.g., research papers). The telepresence interface (700) may also allow a participant to provide annotations on a target anatomical structure (presented in the form of an image, video, or model). For example, a participant may pin annotations to a specific location on the depicted anatomical structure, as indicated by an identifier (710).

[0160] Additionally, the telepresence interface (700) may display statistics (720) or other analyses that may be relevant to the procedure. The statistics (720) may include estimated or modeled values ​​or indicators related to anatomical structures based on various detected data from the medical equipment (160). The telepresence interface (700) may dynamically update the statistics (720) over time during the procedure.

[0161] FIG. 8 is another example of a telepresence interface (800) associated with a telepresence session. In this example, the telepresence interface (800) displays a live video of a procedure being performed, along with an annotation tool set (810) that allows a remote contributor to add annotations (805) overlaid on the video. The telepresence interface (800) also includes an alternative set of views (815) that the contributor can switch to during the telepresence session. These alternative views (815) may include one or more different camera views (e.g., a view of the medical environment), one or more three-dimensional models (e.g., as illustrated in FIG. 7), a view of pre-procedure images, or other multimedia associated with the case. In various embodiments, a telepresence interface such as that illustrated in FIG. 7 or FIG. 8 is stored for a medical case and, as described in more detail above in relation to FIG. 2, may be presented later to another medical worker if the medical worker associated with the case approves the creation of a reference case based on the medical case.

[0162] In the example of FIG. 8, the telepresence interface (800) also displays an educational content item (820) to a medical worker, such as a medical worker performing a medical procedure. The educational content item (820) is dynamically selected by the telepresence interface (800) in various embodiments based on telemetry data or video data captured during the medical procedure. The telepresence interface (800) describes the educational content item (820) or includes information extracted from the educational content item (820), enabling the medical worker to capture content from the educational content item (820) through the telepresence interface (800). In various embodiments, the telepresence interface (800) limits the presentation of the educational content item (820) to a specific time interval. For example, the telepresence interface (800) displays the educational content item (820) in response to the collaborative medical platform (140) determining that telemetry data or video data captured during the performance of a medical procedure deviates by at least a threshold amount from the baseline reference associated with the educational content item (820). When the captured telemetry data or video data does not deviate by at least a threshold amount from the corresponding baseline reference for the educational content item (820), the telepresence interface (800) does not present the educational content item (820). For example, a client device (150) displaying the telepresence interface (800) receives a presentation command from the collaborative medical platform (140) to present the educational content item (820) and subsequently receives an alternative command from the collaborative medical platform (140) to stop presenting the educational content item (820).An alternative command may be received in response to the collaborative medical platform (140) determining that the telemetry data or video data received during the performance of a medical procedure meets the baseline criteria associated with the educational content item (820), or in response to the determination that the telemetry data or video data no longer identifies a pattern corresponding to the baseline criteria associated with the educational content item (820).

[0163] To simplify the integration of information from the educational content item (820) into a medical procedure, the telepresence interface (800) presents a modification command (825) associated with the educational content item (820). The modification command (825) includes an identifier of the medical equipment (160) and one or more setting values ​​for the medical equipment (160). In response to a medical professional selecting the modification command (825) through the telepresence interface (800), the collaborative medical platform (140) receives a request to identify the educational content item (820) and the medical equipment (160). In response to receiving the request, the collaborative medical platform (140) transmits the command to the identified medical equipment (160) to modify one or more setting values ​​with values ​​retrieved from the educational content item (820) and included in the command transmitted to the medical equipment (160). In various embodiments, the collaborative medical platform (140) determines the identifier of the medical equipment (160) based on the identifier included in the telemetry data received by the collaborative medical platform (140) or the identification information included in the received video data of the medical procedure. This simplifies the modification of one or more settings of the medical equipment based on the educational content items (820) through interaction with the telepresence interface (800) rather than by manually entering the setting values ​​identified by the educational content items into the medical equipment (160).

[0164] FIG. 9 is an exemplary embodiment of an analysis dashboard (900) for a medical professional. In this example, the analysis dashboard (900) displays a summary of cases managed by the medical professional, including, for example, the total number of cases, the number of cases in the current month, the number of cases in the current week, and the distribution of the types of cases performed by the professional. In the example of FIG. 9, the analysis dashboard (900) also displays an educational content item section (905) to the medical professional. The educational content item section (905) includes information identifying an educational content item selected by the collaborative medical platform (140) for the medical professional based on data describing the performance of medical procedures by the medical professional, as described in more detail above in relation to FIG. 2. In various embodiments, the educational content item section (905) includes a link to retrieve an educational content item from the collaborative medical platform (140) or a third-party server (170) for presentation when accessed. In some embodiments, the educational content item section (905) may identify an educational content item selected based on the medical procedure most recently completed by the medical professional. Alternatively, the analytics dashboard (900) includes a plurality of educational content item sections (905), each of which includes an educational content item selected for a medical procedure previously performed by the medical professional, thereby simplifying access to different educational content items related to various medical procedures performed by the medical professional.

[0165] FIG. 10 is an exemplary embodiment of a case video interface dashboard (1000) for viewing case videos. The case video may be captured during a telepresence session or similarly captured during a procedure without a telepresence session that is live-streamed. The case video interface (1000) includes a video interface (1005) that displays one or more views of a video associated with a medical procedure. The video interface (1005) may include a number of captured views that may originate from a camera within the medical environment, a camera inserted into an anatomical structure (e.g., an endoscope camera), or other cameras. The captured views may also include a 3D model, pre-procedure images, procedure planning documents, or other visual information. The video may be segmented (manually or automatically using video processing and content recognition technologies) to divide the video into segments associated with different stages of the procedure. The video may include annotations provided by a medical professional during a telepresence session or in a post-procedure review. A content feed (1010) may be presented in conjunction with a video that allows a user (155) to post comments, links, media, or other content in connection with the presentation. Reference content items, such as reference cases, may display videos of medical procedures and other information (e.g., content feed (1010)) to medical professionals using the video interface (1000) described in relation to FIG. 10.

[0166] FIG. 11 is an exemplary prompt for a medical worker to confirm a connection to telemetry data or video data captured during a medical procedure. The prompt (1100) is presented to a medical worker selected by the analysis module (230) based on the telemetry data or video data. In various embodiments, the prompt (1100) is presented to the medical worker via a client device (150) after the analysis module (230) selects the medical worker, as described in more detail above in relation to FIG. 2. For example, the collaborative medical platform (140) transmits the prompt (1100) to a client device (150) that receives information identifying the medical worker after the analysis module (230) selects the medical worker. As an example, the prompt (1100) is presented as an overlay on a portion of the worker dashboard (300) described in more detail above in relation to FIG. 3a and FIG. 3b. Alternatively, the prompt (1100) is presented as part of the worker dashboard (300) presented to the medical worker when the medical worker accesses the collaborative medical platform (140).

[0167] The prompt (1100) includes descriptive information (1105) for telemetry data or video data received by the collaborative medical platform (140). As described in more detail above in relation to FIG. 2, in various embodiments, the descriptive information (1105) includes metadata extracted from the telemetry data or video data. In the example illustrated in FIG. 11, the descriptive information (1105) also includes a medical worker identifier (1110) of the medical worker to whom the prompt (1100) is presented. Exemplary metadata determined from the telemetry data or video data includes the type of medical procedure (1115) in which the telemetry data or video data was captured. Exemplary additional metadata extracted from the telemetry data or video data includes timing information (1120) indicating the time when the telemetry data or video data was captured. However, the descriptive information (1105) for the telemetry data or video data may include different or additional types of metadata. Additionally, the prompt includes at least a portion of video data (1125) in some embodiments, as in the example illustrated in FIG. 11. Alternatively, or additionally, the prompt (1100) may include at least a portion of telemetry data in various embodiments.

[0168] The prompt (1100) also includes a confirmation interface element (1130) and a rejection interface element (1135). In response to receiving a selection of the confirmation interface element (1130) from a medical worker, the client device (150) presenting the prompt (1100) transmits a confirmation to the collaborative medical platform (140) that telemetry data or video data is associated with the selected medical worker. Subsequently, the collaborative medical platform (140) stores the connection between the medical worker and the telemetry data or video data. However, in response to receiving a selection of the rejection interface element (1135), the client device (150) presenting the prompt (1100) transmits a rejection to the collaborative medical platform (140), and thus the collaborative medical platform (140) does not store the connection between the medical worker and the telemetry data or video data. In some embodiments, the collaborative medical platform (140), in response to receiving the rejection, selects an alternative medical worker, as described in more detail above with reference to FIG. 2. The collaborative medical platform (140) then modifies the prompt (1100) and presents the modified prompt (1100) to an alternative medical worker.

[0169] FIG. 12 is an exemplary request for supplementary information regarding telemetry data or video data connected to a medical worker. In the example of FIG. 12, the interface (1200) presents a request (1205) determined by the collaborative medical platform (140) to the medical worker. In various embodiments, the collaborative medical platform (140) presents the interface (1200) to the medical worker in response to receiving confirmation from the medical worker that the telemetry data or video data received by the collaborative medical platform (140) is connected to the medical worker. Thus, the interface (1200) enables the collaborative medical platform (140) to receive supplementary information that augments the video data or telemetry data from the medical worker connected to the video data or telemetry data.

[0170] The request (1205) identifies or describes supplementary information to be received from a medical worker regarding telemetry data or video data connected to a medical worker by the collaborative medical platform (140). In various embodiments, the collaborative medical platform (140) generates the request (1205) by applying a generative model, such as an LLM, to the telemetry data or video data and the characteristics of the medical worker. Alternatively, the collaborative medical platform (140) stores a predefined request in which the request (1205) is selected and presented.

[0171] To receive supplementary information based on a request (1205), the interface (1200) includes an input element (1210), such as a text box, that receives input from a medical worker associated with the request (1205). The collaborative medical platform (140) stores the data received from the medical worker through the input element (1210) as supplementary information associated with telemetry data or video data. In some embodiments, the interface (1200) also includes an interface element that, when selected by a medical worker, transmits the data received through the input element (1210) to the collaborative medical platform (140) along with the medical worker's identifier and the telemetry data or video data's identifier.

[0172] FIG. 13 is an exemplary procedure card interface generated by a collaborative medical platform (140) that identifies one or more procedure cards associated with a medical worker. In the example of FIG. 13, the procedure card interface (1300) displays information describing procedure cards (1305), procedure cards (1310), and procedure cards (1315). Procedure cards (1305), procedure cards (1310), and procedure cards (1315) are each procedure cards among a set of procedure cards maintained by the collaborative medical platform (140) for a medical worker. For example, the collaborative medical platform (140) selects a set of procedure cards included in a user profile for a medical worker and associated with a specific type of medical procedure, as described in more detail above in relation to FIG. 2, and thus the procedure card interface (1300) displays information describing procedure cards among the selected set that identify different steps of a specific type of medical procedure. In some embodiments, the description of the procedure card displayed by the procedure card interface (1300) includes a portion of the procedure card, such as a subset of text data or image data included in the procedure card. Alternatively, the description of the procedure card displayed by the procedure card interface (1300) includes a summary of the procedure card, but in other embodiments, the description of the procedure card may be other information that enables a medical professional to uniquely identify the corresponding procedure card.

[0173] In various embodiments, the procedure card interface (1300) displays one or more interface elements in proximity to a description of one or more of the procedure card (1305), the procedure card (1310), and the procedure card (1315). In the example of FIG. 13, the procedure card interface (1300) displays a deviation interface element (1320) and an editing interface element (1325) in proximity to a description of the procedure card (1305). In various embodiments, the collaborative medical platform (140) displays the deviation interface element (1320) in response to identifying a deviation between a segment of received telemetry data or video data connected to a medical worker and the procedure card (1305). Identifying a deviation between a segment of telemetry data or video data connected to a medical worker and the procedure card maintained for the medical worker has been described in more detail above in relation to FIG. 2. In response to receiving a selection of a deviation interface element (1320) from a medical professional, the collaborative medical platform (140) provides a prompt to the medical professional to provide details or reasons for the deviation between a segment of telemetry data or video data and a procedure card, as described in more detail above. For example, in response to receiving a selection of a deviation interface element (1320), the collaborative medical platform (140) displays another interface that provides the medical professional with a request for supplementary information, as described in more detail above in relation to FIG. 12, or a prompt for information explaining the identified discrepancy between a segment of telemetry data or video data connected to the medical professional and a procedure card (1305). In various embodiments, the deviation interface element (1320) is not displayed unless the collaborative medical platform (140) identifies a deviation between the procedure card and the corresponding segment of telemetry data or video data.

[0174] Additionally, the exemplary procedure card interface (1300) illustrated in FIG. 13 presents an editing interface element (1325) in proximity to the procedure card (1305). In various embodiments, the collaborative medical platform (140) displays the editing interface element (1325) in proximity to the procedure card (1305) in response to one or more criteria being met. For example, the collaborative medical platform (140) displays the editing interface element (1325) in proximity to the procedure card (1305) in response to the deviation count associated with the procedure card (1305) being equal to or exceeding a threshold deviation count, as described in more detail above in relation to FIG. 2. In another example, in response to the collaborative medical platform (140) identifying that telemetry data or video data has deviated from the procedure card (1305) at least at a threshold frequency, the procedure card interface (1300) displays the editing interface element (1325) in proximity to the procedure card (1305). However, in another embodiment, the collaborative medical platform (140) displays an editing interface element (1325) in close proximity to the procedure card (1305) in response to an identified deviation between the procedure card (1305) and a corresponding segment of telemetry data or video data meeting one or more criteria.

[0175] In response to receiving a selection of an editing interface element (1325) by a medical professional, the collaborative medical platform (140) creates one or more additional interfaces for the medical professional to modify or edit the procedure card (1305). For example, the interface displays the content constituting the procedure card (1305) so that the medical professional can modify the content constituting the procedure card (1305), delete the content constituting the procedure card (1305), or add additional content to the procedure card (1305). In some embodiments, the additional interface presented by the collaborative medical platform (140) in response to receiving a selection of an editing interface element (1325) presents a portion of telemetry data received from medical equipment (160) corresponding to the procedure card (1305) and allows the medical professional to select a set of telemetry data as configuration information for the medical equipment (160). Thus, selecting the editing interface element (1325) simplifies the modification of the content of the procedure card by the medical professional.

[0176] For the purpose of illustration, FIG. 13 illustrates an exemplary procedure card interface (1300) in which a deviation interface element (1330) is displayed in proximity to the procedure card (1310), but an editing interface element is not displayed in proximity to the procedure card (1310). For example, the collaborative medical platform (140) identifies that the deviation between a segment of telemetry data or video data and the procedure card (1310) does not identify at least a threshold number of deviations between a segment of telemetry data or video data and the procedure card (1310), or at least a threshold frequency of deviations between a segment of telemetry data or video data and the procedure card (1310). In the example illustrated in FIG. 13, the procedure card interface (1300) limits the presentation of an editing interface element in proximity to the procedure card where at least a threshold number of deviations from the telemetry data or video data have been cumulatively identified, or where the deviation from the telemetry data or video data meets one or more criteria. However, in another embodiment, the procedure card interface (1300) displays an editing interface element near each description of the procedure card to simplify modification of one or more procedure cards by a medical professional.

[0177] In some embodiments, the procedure card interface (1300) displays procedure cards (1305), procedure cards (1310), and procedure cards (1315) in order based on a set of procedure cards, so that the procedure card interface (1300) presents the procedure cards (1305) in the order in which steps corresponding to different procedure cards are performed during a medical procedure. The procedure card interface (1300) enables a medical professional to rearrange procedure cards in a set relative to one another by selecting procedure cards and providing specific input to the collaborative medical platform (140) through the procedure card interface (1300). For example, the medical professional selects a procedure card and rearranges the selected procedure card relative to one or more other procedure cards in the procedure card interface (1300). The collaborative medical platform (140) updates the stored set of procedure cards from the procedure card interface (1300) to reflect the rearranged order of procedure cards relative to one another. Accordingly, the procedure card interface (1300) simplifies not only the change in the way a medical professional performs a medical procedure but also the modification of the content comprising one or more procedure cards.

[0178] FIG. 14 is an exemplary embodiment of a process in which a collaborative medical platform provides a prompt to a medical worker based on one or more procedure cards maintained for the medical worker and received telemetry data or video data. The collaborative medical platform (140) receives telemetry data or video data from a location such as a medical facility (1402). The telemetry data or video data was captured during the performance of a medical procedure at that location. As described in more detail above in relation to FIG. 2, the telemetry data describes setting values ​​for one or more medical devices (160) used during the medical procedure, configuration data for one or more medical devices (160), or other information describing the operation or function of one or more medical devices (160). The video data includes parts of one or more medical workers associated with the medical procedure, parts of one or more medical devices (160) (or medical devices) during the medical procedure, parts of the patient on whom the medical procedure was performed, or other parts of the location where the medical procedure was performed.

[0179] However, telemetry data or video data does not contain information that identifies the medical procedure in which it was captured or identifies one or more medical personnel associated with the medical procedure in which the telemetry data or video data was captured. Various locations, such as medical facilities, are subject to data privacy restrictions that prevent the transmission of information that can uniquely identify the patient treated by a medical personnel to a system outside of that location. For example, a hospital may transmit telemetry data or video data to a collaborative medical platform (140), but is also prevented from providing the collaborative medical platform with information that identifies the medical procedure in which the telemetry data or video data was captured or identifies one or more medical personnel associated with the medical procedure. Similarly, the collaborative medical platform (140) may be prevented from accessing scheduling information regarding one or more medical personnel at a location such as a medical facility, because such access could allow the collaborative medical platform (140) to infer the patient on whom the medical personnel performed the medical procedure.

[0180] Receiving telemetry data or video data (1402) without information identifying a medical worker prevents the collaborative medical platform (140) from providing information generated from the telemetry data or video data to the medical worker connected to the telemetry data or video data. For example, one or more indicators describing the performance of a medical procedure captured in the telemetry data or video data cannot be provided to the medical worker performing the medical procedure if the collaborative medical platform (140) cannot identify the medical worker connected to the telemetry data or video data. Similarly, educational content that the collaborative medical platform (140) can determine for a medical worker based on the telemetry data or video data cannot be provided to the medical worker associated with the medical procedure captured in the telemetry data or video data. Since the location often performs multiple medical procedures during time intervals, the collaborative medical platform (140) may receive a large amount of telemetry data or video data from the location (1402), which makes it impractical and difficult to identify the connection between the medical worker and the received telemetry data or video data by manually reviewing the telemetry data or video data and the information about the medical worker maintained by the collaborative medical platform (140).

[0181] To identify medical workers associated with telemetry data or video data, the collaborative medical platform (140) determines the probability that each of one or more medical workers will be connected to the telemetry data or video data (1404). In various embodiments, the collaborative medical platform determines the probability that a medical worker will be connected to the telemetry data or video data based on the characteristics of the medical worker and the telemetry data or video data (1404). For example, the collaborative medical platform (140) applies a trained worker prediction model to various medical workers and telemetry data or video data, and the worker prediction model determines the probability that a medical worker will be connected to the telemetry data or video data, as described in more detail above with reference to FIG. 2 (1404). In some embodiments, the collaborative medical platform (140) identifies a set of medical workers each having one or more common characteristics and determines the probability that each medical worker in the set will be connected to the telemetry data or video data (1404). For example, the collaborative medical platform (140) identifies a set of medical workers associated with a location where telemetry data or video data is received (1402), and determines the probability that each medical worker in the set will be connected to the telemetry data or video data (1404). Based on the determined probability, the collaborative medical platform (140) selects a medical worker from the set (1406). For example, the collaborative medical platform (140) selects a medical worker from the set who has the determined maximum probability (1406).

[0182] In various embodiments, the collaborative medical platform (140) stores a connection between a selected medical worker and telemetry data or video data (1408). For example, the collaborative medical platform (140) automatically stores a connection between a selected medical worker and telemetry data or video data (1408). Alternatively, the collaborative medical platform (140) sends a prompt to the selected medical worker's client device (150) containing descriptive information about the telemetry data or video data, including a request for the selected medical worker to confirm the connection to the telemetry data or video data. In response to receiving confirmation from the selected medical worker, the collaborative medical platform (140) stores a connection between the selected medical worker and the telemetry data or video data (1408).

[0183] The collaborative medical platform (140) may transmit a request for supplementary information regarding telemetry data or video data to the client device (150) of the selected medical worker in response to storing a connection between the selected medical worker and the telemetry data or video data (1408). For example, the collaborative medical platform (140) generates a request for supplementary information by applying a generative model, such as a large-scale language model, to the telemetry data or video data and one or more characteristics of the selected medical worker (e.g., characteristics from the user profile of the selected medical worker). The generative model then generates one or more requests presented to the selected medical worker. Alternatively, the collaborative medical platform (140) maintains one or more predefined requests and presents one or more of the predefined requests in response to storing a connection between the selected medical worker and the telemetry data or video data (1408). The collaborative medical platform (140) stores the supplementary data received in association with the selected medical worker and the telemetry data or video data, as described in more detail above with reference to FIG. 2.

[0184] Additionally, the collaborative medical platform (140) maintains one or more sets of procedure cards for one or more medical practitioners. As described in more detail above with reference to FIG. 2, the set of procedure cards is associated with a type of medical procedure for the medical practitioner, and each procedure card in the set is associated with a step that occurs during the performance of that type of medical procedure. The procedure cards include preferences, skills, or methods for performing a type of medical procedure associated with the medical practitioner. For example, a procedure card associated with a type of medical procedure may specify one or more specific medical devices that the medical practitioner uses in a step of that type of medical procedure, and may specify the positioning of different medical devices or medical equipment (160) relative to each other. Thus, the procedure cards maintained for the medical practitioner identify the medical practitioner's preferences or skills for performing steps of various types of medical procedures.

[0185] A collaborative medical platform (140) utilizes one or more sets of procedure cards maintained for a selected medical worker and received telemetry data or video data to enable the selected medical worker to prepare a post-procedure summary describing the medical procedure in which the telemetry data or video data was captured, or to modify one or more maintained procedure cards. In various embodiments, the collaborative medical platform (140) selects a set of procedure cards maintained for a selected medical worker based on the telemetry data or video data (1410). For example, the collaborative medical platform (140) determines the type of medical procedure in which the telemetry data or video data was captured and selects a set of procedure cards from a user profile for a selected medical worker associated with the determined type (1410). In another example, the collaborative medical platform (140) determines a similarity measure (or distance) between an embedding for the telemetry data or video data and an embedding for a set of procedure cards and selects a set of procedure cards based on the similarity measure (or distance) (1410).

[0186] For each procedure card in a selected set, the collaborative medical platform (140) determines whether one or more segments of telemetry data or video data deviate from the procedure card in the selected set. In various embodiments, the collaborative medical platform (140) determines the procedure card in the selected set corresponding to each segment of telemetry data or video data through the application of one or more models. Subsequently, the collaborative medical platform (140) applies one or more additional models to the procedure card corresponding to the segment of telemetry data or video data to identify one or more deviations between the segment of telemetry data or video data and the procedure card corresponding to it. The procedure card includes a preference or technique used by the selected medical practitioner when performing the corresponding type of medical procedure in which the telemetry data or video data is captured. This enables the collaborative medical platform (140) to identify the segment of the medical procedure in which deviations have occurred from the way the selected medical practitioner typically performs the corresponding type of medical procedure associated with the selected set of procedure cards in which the telemetry data or video data is associated.

[0187] In response to identifying a deviation between a segment of telemetry data or video data and a corresponding procedure card in a selected set (1412), the collaborative medical platform (140) generates an interface for identifying the deviation (1414). In some embodiments, the interface is for generating a post-procedure summary of a medical procedure in which telemetry data or video data is captured. For example, the interface identifies a segment of telemetry data or video data and a procedure card in a selected set in which a deviation has occurred, and indicates that a deviation from the procedure card has been identified (1412). Then, a selected medical professional may provide information describing or explaining the identified deviation to be included in the post-procedure summary. In various embodiments, the interface presents the content of the segment of telemetry data or video data and the corresponding procedure card, thereby providing additional information about the medical procedure to the selected medical professional to increase the amount of detail included in the post-procedure summary.

[0188] Alternatively, the interface is a procedure card interface that identifies a procedure card in a selected set and identifies the procedure card in which a deviation has occurred with respect to the corresponding segment of telemetry data or video data, as described in more detail above with respect to FIG. 13. Through interaction with the procedure card interface, the selected medical practitioner may modify one or more procedure cards in the set based on one or more identified deviations, or provide details regarding one or more identified deviations to the collaborative medical platform (140). As described in more detail above with respect to FIG. 13, the procedure card interface may also allow the selected medical practitioner to modify the relative positioning of procedure cards within the set relative to each other, thereby further simplifying the modification of procedure cards maintained by the collaborative medical platform (140) for the selected medical practitioner.

[0189] The described embodiments incorporate a number of technical improvements that enhance the capabilities of computer systems, machine learning techniques, data management systems (particularly related to medical data management), computer-based user interfaces, robotic and / or other medical device systems, and other technologies and technical fields. For example, the disclosed embodiments improve data availability by predicting information (e.g., the identity of a healthcare worker) that might otherwise be restricted in a medical system due to compliance with data privacy restrictions.

[0190] The described embodiments also include improvements in machine learning methods in that they improve predictive capabilities compared to traditional machine learning techniques by combining information from heterogeneous data sources, including medical equipment telemetry data, video data, and mobile device data. Furthermore, by connecting telemetry data and video associated with medical procedures to a healthcare professional, the described system can generate various personalized alerts, recommendations, or other content that enable a specific healthcare professional to improve their care, thereby providing better patient outcomes based on connecting the telemetry data or video data to the specific healthcare professional.

[0191] Furthermore, the described embodiment includes technical improvements in the field of robot-assisted surgery in that the connection between medical telemetry data learned by the robot system and the medical worker enables the system to learn the nuances of how a specific worker operates and interacts with such a system, and consequently allows such a system to be configured in a manner specifically customized to that medical worker (e.g., by automatically controlling one or more settings of the surgical robot based on the learned behavior of the medical worker). This worker-specific information can be more easily stored as one or more worker cards for a specific medical worker, which can later be utilized to configure one or more medical devices for use by the medical worker in a specific type of medical procedure. This, consequently, improves patient outcomes and represents a technical improvement in the medical field.

[0192] The foregoing description of the embodiments is provided for illustrative purposes only and is not intended to encompass all embodiments or limit them to the exact form disclosed. Those skilled in the art will understand that many modifications and changes are possible in light of the foregoing disclosure.

[0193] Some parts of this description describe embodiments in terms of algorithms and symbolic representations of operations on information. These operations are described functionally, computationally, or logically, but are understood to be implemented by computer programs or equivalent electrical circuits, microcode, etc. Furthermore, it has been found convenient from time to time to refer to such arrangements of operations as modules without loss of generality. The described operations and their associated modules may be implemented in software, firmware, hardware, or a combination thereof.

[0194] Any step, operation, or process described herein may be performed or implemented by one or more hardware or software modules, either alone or in combination with other devices. Embodiments may also relate to devices for performing the operations of the present invention. Such devices may include general-purpose computing devices that are specifically configured for the required purpose and / or are optionally activated or reconfigured by a computer program stored in a computer. Such computer programs may be stored on a non-transient computer-readable storage medium of a tangible form or on any type of medium suitable for storing electronic instructions and may be coupled to a computer system bus. Additionally, any computing system mentioned herein may include a single processor or may include an architecture employing a multi-processor design for increased computing power.

[0195] Unless explicitly stated otherwise, the use of “or” herein refers to an inclusive “or” rather than an exclusive “or.” For example, the condition “A or B” is satisfied by any one of the following: when A is true (or exists) and B is false (or absent); when A is false (or absent) and B is true (or exists); and when both A and B are true (or exist). Similarly, the condition “A, B or C” is satisfied by any combination of A, B, and C being true (or exist). As a non-limiting example, the condition “A, B or C” is satisfied when A and B are true (or exist) and C is false (or absent). Similarly, as another non-limiting example, the condition “A, B or C” is satisfied when A is true (or exists) and B and C are false (or absent).

[0196] Finally, the language used in this specification has been chosen primarily for readability and educational purposes and may not have been chosen to describe or limit the essence of the invention. Therefore, the scope is not intended to be limited by this detailed description, but rather by any claims derived therefrom for an application based herein. Accordingly, the disclosure of the embodiments is intended to exemplify, rather than limit, the scope of the invention as defined in the following claims.

Claims

Claim 1 A method for an online collaborative medical platform to create an interface for a medical professional based on a medical procedure in which telemetry data or video data is received, comprising: receiving telemetry data or video data captured during the performance of said medical procedure on the collaborative medical platform; determining a probability that each set of medical professionals has a connection to said telemetry data or video data, wherein the probability that a medical professional in said set will be connected to said telemetry data or video data is based on the characteristics of said medical professional in said set from a user profile maintained by said collaborative medical platform and said telemetry data or video data; selecting a medical professional based on said probability; storing a connection between said medical professional and said telemetry data or video data on the collaborative medical platform; selecting a set of procedure cards maintained by said collaborative medical platform and associated with said medical professional, wherein said set of procedure cards describes the preference of said selected medical professional when performing a type of said medical procedure; and identifying a deviation between a procedure card in said set of procedure cards and a segment of said telemetry data or video data. A method comprising the step of creating the interface for presenting to the selected medical professional, wherein the interface identifies the deviation and the description of the procedure card among the selected set of procedure cards. Claim 2 The method of claim 1, wherein the step of selecting the set of procedure cards maintained by the collaborative medical platform and associated with the selected medical practitioner comprises: determining the type of the medical procedure in which the telemetry data or video data is captured; retrieving the set of procedure cards from the user profile of the selected medical practitioner among the user profiles maintained by the collaborative medical platform for the selected medical practitioner—different sets of procedure cards are associated with different types of medical procedures—; and selecting the set of procedure cards from the user profile associated with the type of the medical procedure. Claim 3 In paragraph 2, the step of determining the type of medical procedure in which the telemetry data or video data is captured comprises: applying one or more classification models to the telemetry data or video data and to the stored video data or telemetry data—each stored video data or telemetry data is associated with a medical procedure of a corresponding type, and the one or more classification models determine a similarity measure between the telemetry data or video data and the stored different telemetry data or video data—; and determining the type of medical procedure as a type of medical procedure associated with the stored video data or telemetry data based on the determined similarity measure. Claim 4 A method according to claim 1, wherein the step of selecting the set of procedure cards maintained by the collaborative medical platform and associated with the selected medical worker comprises: determining a similarity measure between the embedding for the telemetry data or video data and the embedding for each of one or more sets of procedure cards stored in the user profile of the selected medical worker by the collaborative medical platform; and selecting the set of procedure cards having an embedding having a maximum similarity measure for the embedding for the telemetry data or video data. Claim 5 In claim 1, the step of determining the probability that each of the sets of medical workers has the connection to the telemetry data or video data comprises the step of applying a worker prediction model to each of the medical workers in the set and to the telemetry data or video data, wherein the worker prediction model determines the probability of the medical workers in the set, and the worker prediction model, A step of acquiring a training dataset containing multiple training examples—each training example includes training telemetry data or characteristics of training telemetry data and a training user and has a label indicating whether said training medical worker is connected to said training telemetry data or said training video data—; A step of applying the above worker prediction model to each training example of the above training dataset to generate a predicted probability that the training medical worker will be connected to the training telemetry data or the training video data; A step of scoring the practitioner prediction model using a loss function, a predicted probability that the training medical practitioner will be connected to the training telemetry data or the training video data, and a label of the training example; and A method trained by updating one or more parameters of the worker prediction model through backpropagation based on the scoring step until one or more criteria are met. Claim 6 The method of claim 1, wherein the step of creating the interface for presenting to the selected medical practitioner—the interface identifies the deviation and a description of a procedure card among the selected procedure card set—includes the step of creating an interface for the selected medical practitioner to create a post-procedure summary to receive information describing the performance of the medical procedure by the selected medical practitioner, and wherein the interface includes interface elements for the selected medical practitioner to select the deviation and provide one or more reasons for the deviation. Claim 7 A method according to claim 1, wherein the step of creating the interface for presenting to the selected medical practitioner—the interface identifies the deviation and the description of the procedure card in the selected set of procedure cards—includes the step of creating a procedure card interface comprising information describing one or more procedure cards in the selected set, wherein the procedure card interface displays an indication of a deviation from a procedure card in the selected set of procedure cards along with a description of a procedure card in the selected set of procedure cards. Claim 8 In claim 7, the method wherein the procedure card interface displays deviation description elements in close proximity to the description of a procedure card among the selected set of procedure cards. Claim 9 In claim 8, the method wherein the procedure card interface displays an editing interface element in proximity to each description of a procedure card among the selected set of procedure cards. Claim 10 In claim 7, the method wherein the procedure card interface displays an editing interface element in close proximity to a description of a procedure card in the selected procedure card set in response to a deviation count between telemetry data or video data and a procedure card in the selected procedure card set being equal to or exceeding a threshold value. Claim 11 An online collaborative medical platform is a non-transient computer-readable storage medium having instructions encoded to create an interface for a medical professional based on a medical procedure in which telemetry data or video data is received, wherein the instructions, when executed by one or more processors, cause the one or more processors to receive telemetry data or video data captured during the performance of the medical procedure from the collaborative medical platform; determine the probability that each set of medical professionals has a connection to the telemetry data or video data, wherein the probability that a medical professional in the set will be connected to the telemetry data or video data is based on the characteristics of the medical professional in the set from a user profile maintained by the collaborative medical platform and the telemetry data or video data; select a medical professional based on the determined probability; store the connection between the selected medical professional and the telemetry data or video data in the collaborative medical platform; select a set of procedure cards maintained by the collaborative medical platform and associated with the selected medical professional, wherein the set of procedure cards describes the preference of the selected medical professional when performing a type of the medical procedure; and the procedure cards in the selected set of procedure cards and the A non-transient computer-readable storage medium that enables the performance of steps including: identifying deviations between segments of telemetry data or video data; and creating an interface for presenting to the selected medical practitioner, wherein the interface identifies the deviations and descriptions of procedure cards among the selected set of procedure cards. Claim 12 In claim 11, selecting the set of procedure cards maintained by the collaborative medical platform and associated with the selected medical practitioner comprises: determining the type of the medical procedure in which the telemetry data or video data is captured; retrieving the set of procedure cards from the user profile of the selected medical practitioner among the user profiles maintained by the collaborative medical platform for the selected medical practitioner—different sets of procedure cards are associated with different types of medical procedures—; and selecting the set of procedure cards from the user profile associated with the type of the medical procedure, a non-transient computer-readable storage medium. Claim 13 A non-transient computer-readable storage medium according to claim 12, wherein determining the type of medical procedure in which the telemetry data or video data is captured comprises applying one or more classification models to the telemetry data or video data and to the stored video data or telemetry data—each stored video data or telemetry data is associated with a medical procedure of a corresponding type, and the one or more classification models determine a similarity measure between the telemetry data or video data and the stored different telemetry data or video data—; and determining the type of medical procedure as a type of medical procedure associated with the stored video data or telemetry data based on the determined similarity measure. Claim 14 A non-transient computer-readable storage medium, wherein, in claim 11, selecting the set of procedure cards maintained by the collaborative medical platform and associated with the selected medical worker comprises: determining a similarity measure between an embedding for the telemetry data or video data and an embedding for each of one or more sets of procedure cards stored in the user profile of the selected medical worker by the collaborative medical platform; and selecting a set of procedure cards having an embedding having a maximum similarity measure for the embedding for the telemetry data or video data. Claim 15 In paragraph 11, determining the probability that each of the said set of medical workers has the said connection to the said telemetry data or video data comprises applying a worker prediction model to each of the said set of medical workers and to the said telemetry data or video data, wherein the worker prediction model determines the said probability of the said medical workers among the said set, and the worker prediction model, Acquiring a training dataset containing multiple training examples—each training example includes training telemetry data or characteristics of training telemetry data and a training user and has a label indicating whether said training medical worker is connected to said training telemetry data or said training video data—; Applying the above worker prediction model to each training example of the above training dataset to generate a predicted probability that the training medical worker will be connected to the training telemetry data or the training video data; Scoring the practitioner prediction model using a loss function, a predicted probability that the training medical practitioner will be connected to the training telemetry data or the training video data, and labels of the training examples; and A non-transient computer-readable storage medium trained by updating one or more parameters of the worker prediction model through backpropagation based on the scoring step until one or more criteria are met. Claim 16 In paragraph 11, creating the interface for presenting to the selected medical practitioner—the interface identifies the deviation and the description of the procedure card among the selected procedure card set—includes creating an interface for the selected medical practitioner to generate a post-procedure summary in order to receive information describing the performance of the medical procedure by the selected medical practitioner, wherein the interface comprises interface elements for the selected medical practitioner to select the deviation and provide one or more reasons for the deviation, a non-transient computer-readable storage medium. Claim 17 In claim 11, creating the interface for presenting to the selected medical practitioner—the interface identifies the deviation and the description of the procedure card in the selected set of procedure cards—includes creating a procedure card interface comprising information describing one or more procedure cards in the selected set, wherein the procedure card interface displays a description of the procedure card in the selected set of procedure cards along with a notation of the deviation from the procedure card in the selected set of procedure cards, a non-transient computer-readable storage medium. Claim 18 In paragraph 17, the procedure card interface is a non-transient computer-readable storage medium that displays deviation description elements in close proximity to a description of a procedure card among the selected set of procedure cards. Claim 19 In paragraph 18, the procedure card interface is a non-transient computer-readable storage medium that displays editing interface elements in proximity to each description of a procedure card among the selected set of procedure cards. Claim 20 In claim 17, the procedure card interface is a non-transient computer-readable storage medium that displays an editing interface element in close proximity to a description of a procedure card in the selected set of procedure cards in response to a deviation count of a deviation between telemetry data or video data and a procedure card in the selected set of procedure cards being equal to or exceeding a threshold.

Images