Real-time insight generation and post-operative analysis for surgical devices

Abstract

Examples described herein provide a computer-implemented method that includes monitoring a plurality of performance parameters of a surgical device during a surgical procedure and providing the performance parameters to one or more models trained to detect one or more conditions based on at least a subset of the performance parameters. An insight is generated based on detection of at least one of the one or more conditions, and an alert associated with the insight is output. The one or more conditions can be associated with a technique or interaction during usage of the surgical device or an outcome of using the surgical device.

Description

A0013614WO01 (MD80180PCT) REAL-TIME INSIGHT GENERATION AND POST-OPERATIVE ANALYSIS FOR SURGICAL DEVICES BACKGROUND

[0001] The present disclosure relates in general to computing technology and relates more particularly to computing technology for generation of real-time insights and post-operative analysis for surgical devices.

[0002] Various types of data can be captured by computer-assisted systems, particularly computer-assisted surgery systems (CASs), during surgical procedures. The data can include video from one or more cameras and / or data from various sensors and effectors. The data can be stored and / or transmitted for several purposes, such as archival, training, post-surgery analysis, and / or patient consultation. The video data can be displayed on one or more monitors during surgery to assist a surgeon in guiding surgical instruments, particularly in the context of laparoscopic surgery.

[0003] Portions of surgical instruments may be obstructed from view within the video data due to anatomical structures or other viewing constraints. Further, some surgical devices may have limited feedback to assist surgeons in making decisions and detecting potential issues while in use. This can present challenges while using surgical devices during surgeries. SUMMARY

[0004] According to an aspect, a computer-implemented method is provided. The method includes monitoring a plurality of performance parameters of an electrosurgical energy device during a surgical procedure and providing the performance parameters to one or more models trained to detect one or more conditions based on at least a subset of the performance parameters. The one or more conditions are associated a technique or tissue interaction during usage of the electrosurgical energy device. An insight is generated based on detection of at least one of the one or more conditions. An alert associated with the insight is output during the surgical procedure.

[0005] According to another aspect, a system includes a memory system and a processing system. The processing system is coupled to the memory system and configured to execute instructions to perform a plurality of operations. The operations include monitoring a plurality ofA0013614WO01 (MD80180PCT) performance parameters of a surgical device during a surgical procedure and providing the performance parameters to one or more models trained to detect one or more conditions based on at least a subset of the performance parameters. The one or more conditions are associated with a technique or an interaction during usage of the surgical device or an outcome of using the surgical device. The operations further include generating an insight based on detection of at least one of the one or more conditions and outputting an alert associated with the insight.

[0006] According to a further aspect, a computer-implemented method is provided. The computer-implemented method includes accessing alert data associated with a surgical video. The alert data includes an insight associated with activation of an electrosurgical energy device. The computer-implemented method also includes displaying the alert data with the surgical video through a first user interface of a surgical data insight viewer and analyzing surgical data associated with a plurality of surgical videos including the alert data associated with one or more of the surgical videos. The computer-implemented method further includes displaying a usage analysis through a second user interface of the surgical data insight viewer that summarizes a plurality of performance parameters of activation of the electrosurgical energy device corresponding to the surgical videos and the alert data.

[0007] The above features and advantages, and other features and advantages, of the disclosure are readily apparent from the following detailed description when taken in connection with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The specifics of the exclusive rights described herein are particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other features and advantages of the aspects of the disclosure are apparent from the following detailed description taken in conjunction with the accompanying drawings in which:

[0009] FIG.1 depicts a computer-assisted surgery (CAS) system according to one or more aspects;

[0010] FIG.2 depicts a surgical procedure system according to one or more aspects;

[0011] FIG.3 depicts a system for analyzing data according to one or more aspects;

[0012] FIG.4 depicts a perspective view of an electrosurgical energy device according to one or more aspects;A0013614WO01 (MD80180PCT)

[0013] FIG.5 depicts a block diagram of a generator of the electrosurgical energy device of FIG.4 according to one or more aspects;

[0014] FIG.6 depicts a block diagram of parameter processing and models according to one or more aspects;

[0015] FIGS.7A, 7B, 7C, and 7D depicts a user interface with alerts according to one or more aspects;

[0016] FIG.8 depicts a flowchart of a method of insight generation according to one or more aspects;

[0017] FIG.9 depicts a flowchart of a method of training models for insight generation according to one or more aspects;

[0018] FIG.10 depicts a block diagram of a computer system according to one or more aspects;

[0019] FIG.11 depicts a flow diagram of a model for predicting operating conditions associated with usage of an electrosurgical energy device according to one or more aspects;

[0020] FIGS.12A, 12B, and 12C depict system configuration examples according to one or more aspects;

[0021] FIG.13 depicts a user interface of a surgical data insight viewer that displays surgical videos and associated data according to one or more aspects;

[0022] FIG.14 depicts a user interface of a surgical data insight viewer that displays usage analysis for a plurality of surgical videos according to one or more aspects; and

[0023] FIG.15 depicts a flowchart of a method of analyzing and displaying surgical data and alert data associated with surgical videos according to one or more aspects.

[0024] The diagrams depicted herein are illustrative. There can be many variations to the diagrams and / or the operations described herein without departing from the spirit of the described aspects. For instance, the actions can be performed in a differing order, or actions can be added, deleted, or modified. Also, the term “coupled” and variations thereof describe having a communications path between two elements and do not imply a direct connection between the elements with no intervening elements / connections between them. All of these variations are considered a part of the specification.A0013614WO01 (MD80180PCT) DETAILED DESCRIPTION

[0025] Exemplary aspects of the technical solutions described herein include systems and methods for generation of real-time insights for surgical devices and outputting of alerts based on the insights during surgical procedures.

[0026] Aspects can generate clinically relevant surgeon alerts for better patient outcomes during a procedure and post-operatively using device data from surgical devices. Sub-optimal techniques of using surgical devices can impact surgical outcomes and quality. For example, decreased seal quality can result in seal failure and decreased surgeon confidence in the use of a vessel sealing device. Running one or more models, such as artificial intelligence / machine- learning models during use of a surgical device can trigger alerts with insights to warn or guide surgeons of potential issues before completion of a surgical procedure. Further, models can confirm that normal / expected conditions are observed, which may be helpful for training users. Additionally, models can provide contextual information prior to, during, or after use of a surgical device. This can result in preventing and / or correcting the potential issues. The models can use performance parameters which can be directly sensed or derived, along with device operating mode information, to determine one or more conditions and generate insights to alert the surgeon about the one or more conditions. In some aspects, a group of models can be trained, where each of the models is associated with detection of specific conditions. Device operating mode information can be used to assist in determining when specific models should be run to reduce processing resource utilization and associated latency for real-time insight generation.

[0027] Aspects of the technical solutions herein are rooted in computing technology, particularly artificial intelligence, and more particularly to neural networks and other machine- learning methods. Aspects of the technical solutions herein provide improvements to such computing technology. For example, aspects of the technical solutions herein can train models to identify sets of conditions at a device level using parameters that may not otherwise be observable through video-based observation. In some aspects, the models can be trained to execute with greater computational efficiency by determining which performance parameters have a greater impact on the models and providing a subset of the performance parameters having the greater impact to the one or more models for real-time detection of one or more conditions and generation of an insight.

[0028] Turning now to FIG.1, an example computer-assisted surgery (CAS) system 100 is generally shown in accordance with one or more aspects. The CAS system 100 includes at least a computing system 102, a video recording system 104, and a surgical instrumentation systemA0013614WO01 (MD80180PCT) 106. As illustrated in FIG.1, an actor 112 can be medical personnel that uses the CAS system 100 to perform a surgical procedure on a patient 110. Medical personnel can be a surgeon, assistant, nurse, administrator, or any other actor that interacts with the CAS system 100 in a surgical environment. The surgical procedure can be any type of surgery. In other examples, actor 112 can be a technician, an administrator, an engineer, or any other such personnel that interacts with the CAS system 100. For example, actor 112 can record data from the CAS system 100, configure / update one or more attributes of the CAS system 100, review past performance of the CAS system 100, repair the CAS system 100, and / or the like including combinations and / or multiples thereof.

[0029] A surgical procedure can include multiple phases, and each phase can include one or more surgical actions. A “surgical action” can include an incision, a compression, a stapling, a clipping, a suturing, a cauterization, a sealing, or any other such actions performed to complete a phase in the surgical procedure. A “phase” represents a surgical event that is composed of a series of steps (e.g., closure). A “step” refers to the completion of a named surgical objective (e.g., hemostasis). During each step, certain surgical instruments 108 (e.g., forceps) are used to achieve a specific objective by performing one or more surgical actions. In addition, a particular anatomical structure of the patient may be the target of the surgical action(s).

[0030] The video recording system 104 includes one or more cameras 105, such as operating room cameras, endoscopic cameras, and / or the like including combinations and / or multiples thereof. The cameras 105 capture video data of the surgical procedure being performed. The video recording system 104 includes one or more video capture devices that can include cameras 105 placed in the surgical room to capture events surrounding (i.e., outside) the patient being operated upon. The video recording system 104 further includes cameras 105 that are passed inside (e.g., endoscopic cameras) the patient 110 to capture endoscopic data. The endoscopic data provides video and images of the surgical procedure.

[0031] The computing system 102 includes one or more memory devices, one or more processors, a user interface device, among other components. All or a portion of the computing system 102 shown in FIG.1 can be implemented for example, by all or a portion of computer system 800 of FIG.10. Computing system 102 can execute one or more computer-executable instructions. The execution of the instructions facilitates the computing system 102 to perform one or more methods, including those described herein. The computing system 102 can communicate with other computing systems via a wired and / or a wireless network.A0013614WO01 (MD80180PCT)

[0032] A data collection system 150 can be employed to store the surgical data, including the video(s) captured during the surgical procedures and / or device data. The data collection system 150 includes one or more storage devices 152. The data collection system 150 can be a local storage system, a cloud-based storage system, or a combination thereof. Further, the data collection system 150 can use any type of cloud-based storage architecture, for example, public cloud, private cloud, hybrid cloud, and / or the like including combinations and / or multiples thereof. In some examples, the data collection system can use a distributed storage, i.e., the storage devices 152 are located at different geographic locations. The storage devices 152 can include any type of electronic data storage media used for recording machine-readable data, such as semiconductor-based, magnetic-based, optical-based storage media, and / or the like including combinations and / or multiples thereof. For example, the data storage media can include flash- based solid-state drives (SSDs), magnetic-based hard disk drives, magnetic tape, optical discs, and / or the like including combinations and / or multiples thereof.

[0033] In one or more examples, the data collection system 150 can be part of the video recording system 104, or vice-versa. In some examples, the data collection system 150, the video recording system 104, and the computing system 102, can communicate with each other via a communication network, which can be wired, wireless, or a combination thereof. The communication between the systems can include the transfer of data (e.g., video data, instrumentation data, and / or the like including combinations and / or multiples thereof), data manipulation commands (e.g., browse, copy, paste, move, delete, create, compress, and / or the like including combinations and / or multiples thereof), data manipulation results, and / or the like including combinations and / or multiples thereof. In one or more examples, the computing system 102 can manipulate the data already stored / being stored in the data collection system 150. Alternatively, or in addition, the computing system 102 can manipulate the data already stored / being stored in the data collection system 150 based on information from the surgical instrumentation system 106.

[0034] In one or more examples, the video captured by the video recording system 104 is stored on the data collection system 150. In some examples, the computing system 102 curates parts of the video data being stored on the data collection system 150. In some examples, the computing system 102 filters the video captured by the video recording system 104 before it is stored on the data collection system 150. Alternatively, or in addition, the computing system 102 filters the video captured by the video recording system 104 after it is stored on the data collection system 150.A0013614WO01 (MD80180PCT)

[0035] A surgical data management system 160 can provide access to portions of data captured in the data collection system 150, as well as data and records stored in other systems. The surgical data management system 160 can establish user access permissions to patient and surgical data. The surgical data management system 160 can also control access through an interface based on the user access permissions. Access to the surgical data management system 160 can be provided through one or more applications or secure web pages. The surgical data management system 160 can be a stand-alone application, module, and / or an extension of another system. Additional aspects of the surgical data management system 160 can include accessing artificial intelligence (AI)-powered surgical video, insights, and analytics. Further aspects of the surgical data management system 160 can include accessing simulation materials that can assist surgeons to prepare, practice, and teach surgical procedures. Further aspects of the surgical data management system 160 can include integrating aspects of equipment in an operating room, surgery planning, rating surgeon performance, and other such features.

[0036] Turning now to FIG.2, a surgical procedure system 200 is generally shown according to one or more aspects. The example of FIG.2 depicts a surgical procedure support system 202 that can include or may be coupled to the CAS system 100 of FIG.1. The surgical procedure support system 202 can acquire image or video data using one or more cameras 204. The surgical procedure support system 202 can also interface with one or more sensors 206 and / or one or more effectors 208. The sensors 206 may be associated with surgical support equipment and / or patient monitoring. The effectors 208 can be robotic components or other equipment controllable through the surgical procedure support system 202. The surgical procedure support system 202 can also interact with one or more user interfaces 210, such as various input and / or output devices. The surgical procedure support system 202 can store, access, and / or update surgical data 214 associated with a training dataset and / or live data as a surgical procedure is being performed on patient 110 of FIG.1. The surgical procedure support system 202 can store, access, and / or update surgical objectives 216 to assist in training and guidance for one or more surgical procedures. User configurations 218 can track and store user preferences.

[0037] The surgical procedure support system 202 can also communicate with other systems through a network 230. For example, the surgical procedure support system 202 can communicate with a surgical data insight viewer 240 and a surgical data post-processing system 250 through the network 230. Other types of devices, such as a computing device 234 (e.g., a mobile phone, laptop, personal computer, or tablet computer), can communicate directly with the surgical procedure support system 202 or through the network 230. As one example, user interfaces 210 may be connected to or integrated with the surgical procedure support system 202A0013614WO01 (MD80180PCT) by a wired connection while the computing device 234 connects to the surgical procedure support system 202 via a wireless connection. In some aspects, the computing device 234 can execute or link to another computer system that executes the surgical data management system 160 of FIG. 1 to access various data sources through the network 230.

[0038] The surgical data post-processing system 250 can receive surgical data and associated data generated by the surgical procedure support system 202 and may be separately stored and secured through other data storage. Access to specific data or portions of data through the surgical data post-processing system 250 may be limited by associated permissions. The surgical data post-processing system 250 may include features such as video viewing, video sharing, data analytics, event data, and selective data extraction.

[0039] The surgical data insight viewer 240 can provide viewing access to various data sources, such as surgical data 214, data collected in the one or more storage devices 152 of FIG. 1, and post-processed data generated by the surgical data post-processing system 250. For example, surgical instrument data, video data, and artificial intelligence generated data can be accessed for viewing through the surgical data insight viewer 240. The surgical data post- processing system 250 may generate surgical performance metrics and comparison data across data sets collected at multiple locations, making analytics data available to the surgical data insight viewer 240. The surgical data insight viewer 240 can load case data for more than one case of a user, for example, when the user performs a login or otherwise activates the surgical data insight viewer 240. In some aspects, the surgical data insight viewer 240 and / or surgical data post-processing system 250 can be components of the surgical data management system 160 of FIG.1.

[0040] One or more computing device 264 (e.g., a mobile phone, laptop, personal computer, or tablet computer), can execute the surgical data management system 160 of FIG.1 to access various data sources through a network 260. The network 230 may be within a facility or multiple facilities maintained within a private network. The network 260 may be a wider area network, such as the internet. Accordingly, the networks 230 and 260 may have access to different files and data sets along with shared access to select files and data sets. In some aspects, networks 230 and 260 can be combined.

[0041] According to aspects, the surgical data management system 160 of FIG.1 can provide multiple user interfaces and functions through the surgical data insight viewer 240. The user interfaces can include case selection, video playback, surgical phase information, and other such data with supporting analytics.A0013614WO01 (MD80180PCT)

[0042] Turning now to FIG.3, a system 300 for analyzing data is generally shown according to one or more aspects. In accordance with aspects, video can be captured from video recording system 104 of FIG.1. Data can be captured by the surgical instrumentation system 106 of FIG. 1. The analysis can result in predicting features that include surgical phases and structures (e.g., instruments, anatomical structures, and / or the like including combinations and / or multiples thereof) associated with the data using machine learning. Other models can be trained to identify conditions associated with surgical devices and need not use video or image data. System 300 can be the computing system 102 of FIG.1, or a part thereof in one or more examples. System 300 uses data streams in the surgical data to identify procedural states according to some aspects. Further, the system 300 can be implemented as part of the surgical data post-processing system 250 of FIG.2 for post-processing analysis of surgical data. Additionally, some machine learning aspects can be implemented as real-time analysis while other machine learning aspects can be performed as part of post-operative analysis.

[0043] System 300 includes a data reception system 305 that collects surgical data, including surgical instrumentation data. The data reception system 305 can include one or more devices (e.g., one or more user devices and / or servers) located within and / or associated with a surgical operating room and / or control center. The data reception system 305 can receive surgical data in real-time, i.e., as the surgical procedure is being performed. Alternatively, or in addition, the data reception system 305 can receive or access surgical data in an offline manner, for example, by accessing data that is stored in the data collection system 150 of FIG.1.

[0044] System 300 further includes a machine learning processing system 310 that processes the surgical data using one or more machine learning models to identify one or more features, such as instrument usage, anatomical structure interaction, surgical phase, and / or the like including combinations and / or multiples thereof, in the surgical data. It will be appreciated that machine learning processing system 310 can include one or more devices (e.g., one or more servers), each of which can be configured to include part or all of one or more of the depicted components of the machine learning processing system 310. In some instances, a part or all of the machine learning processing system 310 is cloud-based and / or remote from an operating room and / or physical location corresponding to a part or all of data reception system 305. It will be appreciated that several components of the machine learning processing system 310 are depicted and described herein. However, the components are just one example structure of the machine learning processing system 310, and that in other examples, the machine learning processing system 310 can be structured using a different combination of the components. SuchA0013614WO01 (MD80180PCT) variations in the combination of the components are encompassed by the technical solutions described herein.

[0045] The machine learning processing system 310 includes a machine learning training system 325, which can be a separate device (e.g., server) that stores its output as one or more trained machine learning models 330. The machine learning models 330 are accessible by a machine learning execution system 340. The machine learning execution system 340 can be separate from the machine learning training system 325 in some examples. In other words, in some aspects, devices that “train” the models are separate from devices that “infer,” i.e., perform real-time processing of surgical data using the trained machine learning models 330. In some aspects, outputs of the machine learning execution system 340 can be captured in the data store 320 to provide additional data for use by the machine learning training system 325 to revise and update the trained machine learning models 330.

[0046] Machine learning processing system 310, in some examples, further includes a data generator 315 to generate simulated surgical data, such as a set of synthetic device data, in combination with real device data from the data collection system 150 of FIG.1, as a set of training data used to generate trained machine learning models 330. Data generator 315 can access (read / write) a data store 320 to record data including multiple data sets. The data sets can be collected during one or more procedures (e.g., one or more surgical procedures). For example, the device data may have been collected during previous surgeries performed by the actor 112 of FIG.1 (e.g., surgeon), and the device data can be correlated with recorded video data, for instance, from an endoscopic camera inserted inside the patient 110 of FIG.1. The data store 320 is separate from the data collection system 150 of FIG.1 in some examples. In other examples, the data store 320 is part of the data collection system 150.

[0047] Each data set in the data store 320 used as a set of training data for performing training (e.g., generating the machine learning models 330) can be defined as a set of conditions and can be associated with other data that characterizes an associated portion of a surgical procedure. For example, the other data can identify a type of procedure, devices used in the procedure, surgical objectives, and / or an outcome of the procedure. Alternatively, or in addition, the other data can indicate a stage of the procedure with which the device data corresponds and device settings. Further, the other data can include data that identifies and / or characterizes one or more objects (e.g., tools, anatomical objects, and / or the like including combinations and / or multiples thereof) with which the device interacts. The characterization can indicate the position, orientation, or usage parameters. For example, the characterization can indicate a set of data that corresponds to a portion of a surgical tool and / or a state of the surgical tool resulting from a past or current userA0013614WO01 (MD80180PCT) handling. Localization can be performed using a variety of techniques for identifying features in one or more coordinate systems.

[0048] The machine learning training system 325 can use the recorded data in the data store 320, which can include the simulated surgical data (e.g., set of synthetic device performance parameters) and / or actual surgical data to generate the trained machine learning models 330. The trained machine learning models 330 can be defined based on a type of model and a set of hyperparameters (e.g., defined based on input from a client device). The trained machine learning models 330 can be configured based on a set of parameters that can be dynamically defined based on (e.g., continuous or repeated) training (i.e., learning, parameter tuning). Machine learning training system 325 can use one or more optimization algorithms to define the set of parameters to minimize or maximize one or more loss functions. The set of (learned) parameters can be stored as part of the trained machine learning models 330 using a specific data structure for a particular trained machine learning model of the trained machine learning models 330. The data structure can also include one or more non-learnable variables (e.g., hyperparameters and / or model definitions).

[0049] Machine learning execution system 340 can access the data structure(s) of the trained machine learning models 330 and accordingly configure the trained machine learning models 330 for inference (e.g., prediction, classification, and / or the like including combinations and / or multiples thereof). The trained machine learning models 330 can include, for example, a fully convolutional network adaptation, an adversarial network model, an encoder, a decoder, or other types of machine learning models. Further examples of the trained machine learning models 330 can include regression-based models, decision trees, and / or other such machine-learning approaches. The type of the trained machine learning models 330 can be indicated in the corresponding data structures. The trained machine learning models 330 can be configured in accordance with one or more hyperparameters and the set of learned parameters.

[0050] While some techniques for predicting a surgical phase (“phase”) in the surgical procedure are described herein, it should be understood that any other technique for phase prediction can be used without affecting the aspects of the technical solutions described herein. In some examples, the machine learning processing system 310 includes a detector 350 that uses the trained machine learning models 330 to identify various items or states within the surgical procedure (“procedure”). The detector 350 can use a particular procedural tracking data structure 355 from a list of procedural tracking data structures. The detector 350 can select the procedural tracking data structure 355 based on the type of surgical procedure that is being performed. In one or more examples, the type of surgical procedure can be predetermined or input by actor 112.A0013614WO01 (MD80180PCT) For instance, the procedural tracking data structure 355 can identify a set of potential phases that can correspond to a part of the specific type of procedure as “phase predictions”, where the detector 350 may perform phase detection.

[0051] In some examples, the procedural tracking data structure 355 can be a graph that includes a set of nodes and a set of edges, with each node corresponding to a potential phase. The edges can provide directional connections between nodes that indicate (via the direction) an expected order during which the phases will be encountered throughout an iteration of the procedure. The procedural tracking data structure 355 may include one or more branching nodes that feed to multiple next nodes and / or can include one or more points of divergence and / or convergence between the nodes. In some instances, a phase indicates a procedural action (e.g., surgical action) that is being performed or has been performed and / or indicates a combination of actions that have been performed. In some instances, a phase relates to a biological state of a patient undergoing a surgical procedure. For example, the biological state can indicate a complication (e.g., blood clots, clogged arteries / veins, and / or the like including combinations and / or multiples thereof), pre-condition (e.g., lesions, polyps, and / or the like including combinations and / or multiples thereof).

[0052] Each node within the procedural tracking data structure 355 can identify one or more characteristics of the phase corresponding to that node. The characteristics can include device characteristics. In some instances, the node identifies one or more techniques that are typically performed during the phase. The node can also identify a typical type of movement of a surgical tool. Thus, detector 350 can use the segmented data generated by machine learning execution system 340 that indicates the presence and / or characteristics of particular objects in relation to a surgical tool to identify an estimated node to which the real data relates. Identification of the node (i.e., phase) can further be based upon previously detected phases for a given procedural iteration and / or other detected input.

[0053] The detector 350 can output predictions, such as insights associated with a portion of the data that is analyzed by the machine learning processing system 310. The insights are associated with the portion of the data that is analyzed by the machine learning execution system 340. The insights associated with surgical devices can be output as alerts to overlay on video or otherwise notify the actor 112. Further, the insights, in one or more examples, can include additional data dimensions, such as, but not limited to, identities of the structures (e.g., instrument, anatomy, and / or the like including combinations and / or multiples thereof) that are identified by the machine learning execution system 340 in the portion of the data that is analyzed. Further, other types of outputs of the detector 350 can include state information orA0013614WO01 (MD80180PCT) other information used to generate audio output, visual output, and / or commands. For instance, the output can trigger an alert, an augmented visualization, identify a predicted current condition, identify a predicted future condition, command control of equipment, and / or result in other such data / commands being transmitted to a support system component, e.g., through surgical procedure support system 202 of FIG.2.

[0054] Turning now to FIG.4, a schematic illustration of an electrosurgical energy device 1. The electrosurgical energy device 1 includes an electrosurgical forceps 10 for treating patient tissue. Electrosurgical radio frequency (RF) energy is supplied to the forceps 10 by a generator 2 via a cable 18, thus allowing the actor 112 of FIG.1 to selectively coagulate and / or seal tissue.

[0055] As shown in FIG.1, the forceps 10 is an endoscopic version of a vessel sealing bipolar forceps. The forceps 10 is configured to support an effector assembly 85 and generally includes a housing 20, a handle assembly 30, a rotating assembly 80, and a trigger assembly 70 that mutually cooperate with the end effector assembly 85 to grasp, seal and, if required, divide tissue. Forceps 10 also includes a shaft 12 that has a distal end 14 which mechanically engages the end effector assembly 85 and a proximal end 16 which mechanically engages the housing 20 proximate the rotating assembly 80.

[0056] The forceps 10 can also include a plug (not shown) that connects the forceps 10 to a source of electrosurgical energy, e.g., generator 2, via cable 18. Handle assembly 30 includes a fixed handle 50 and a movable handle 40. Handle 40 moves relative to the fixed handle 50 to actuate the end effector assembly 85 and enable a user to selectively grasp and manipulate tissue. Forceps 10 may also include an identification module (not explicitly shown) such as a resistor or computer memory readable by the generator 2 to identify the forceps 10.

[0057] The end effector assembly 85 can include a pair of opposing jaw members 92 and 96 each having an electrically conductive sealing plate 94 and 98, respectively, attached thereto for conducting electrosurgical energy through tissue held therebetween. More particularly, the jaw members 92 and 96 move in response to movement of handle 40 from an open position to a closed position. In open position, the sealing plates 94 and 98 are disposed in spaced relation relative to one another. In a clamping or closed position, the sealing plates 94 and 98 cooperate to grasp tissue and apply electrosurgical energy thereto. In aspects, end effector assembly 85 can include a jaw angle sensor that is adapted to sense an included angle between opposing jaw members 92 and 96 and is configured to operably couple to generator 2.A0013614WO01 (MD80180PCT)

[0058] Jaw members 92 and 96 are activated using a drive assembly enclosed within the housing 20. The drive assembly cooperates with the movable handle 40 to impart movement of the jaw members 92 and 96 from the open position to the clamping or closed position. Jaw members 92 and 96 can also include outer housings on insulators which together with the dimension of the conductive plates of the jaw members 92 and 96 are configured to limit and / or reduce many of the known undesirable effects related to tissue sealing, e.g., flashover, thermal spread and stray current dissipation. The forceps 10 also includes a rotating assembly 80 mechanically associated with the shaft 12 and the drive assembly. Movement of the rotating assembly 80 imparts similar rotational movement to the shaft 12 which, in turn, rotates the end effector assembly 85.

[0059] The forceps 10 may be designed such that it is fully or partially disposable depending upon a particular purpose or to achieve a particular result. For example, end effector assembly 85 may be selectively and releasably engageable with the distal end 14 of the shaft 12 and / or the proximal end 16 of the shaft 12 may be selectively and releasably engageable with the housing 20 and handle assembly 30. In either of these two instances, the forceps 10 may be either partially disposable or replaceable, such as where a new or different end effector assembly 85 or end effector assembly 85 and shaft 12 are used to selectively replace an old end effector assembly 85 as needed.

[0060] The generator 2 includes input controls (e.g., buttons, activators, switches, touch screen, etc.) for controlling the generator 2. In addition, the generator 2 can include one or more display screens for providing the surgeon with variety of output information (e.g., intensity settings, treatment complete indicators, etc.). The controls can allow the surgeon to adjust power of the RF energy, waveform, and other parameters to achieve the desired waveform suitable for a particular task (e.g., coagulating, tissue sealing, division with hemostatis, etc.). The forceps 10 may include a plurality of input controls which may be redundant with certain input controls of the generator 2. Placing the input controls at the forceps 10 can allow for easier and faster modification of RF energy parameters during the surgical procedure without requiring interaction with the generator 2.

[0061] FIG.5 depicts a schematic block diagram of the generator 2 having a controller 4, a high voltage power supply 7 (“HVPS”), a radio frequency (RF) output stage 8, and a sensor circuitry 11. The power supply 7 provides power to an RF output stage 8 which then converts power into RF energy and delivers the RF energy to the forceps 10. The controller 4 includes a processing system 5 (e.g., one or more processors) operably connected to a memory system 6 (e.g., one or more memory devices) which may include volatile type memory (e.g., RAM) and / orA0013614WO01 (MD80180PCT) non-volatile type memory (e.g., flash media, disk media, etc.). The processing system 5 can include an output port which is operably connected to the HVPS 7 and / or RF output stage 8, allowing the processing system 5 to control the output of the generator 2 according to either open and / or closed control loop schemes. A closed loop control scheme may be a feedback control loop where the sensor circuitry 11 provides feedback to the controller 4 (i.e., information obtained from one ore more of sensing mechanisms for sensing various tissue parameters such as tissue impedance, tissue temperature, fluid presence, output current and / or voltage, etc.). The controller 4 then signals the HVPS 7 and / or RF output stage 8, which then adjusts power and / or RF output, respectively. The controller 4 also receives input signals from the input controls of the generator 2 and / or forceps 10. The controller 4 utilizes the input signals to adjust the power output of the generator 2 and / or instructs the generator 2 to perform other control functions.

[0062] The electrosurgical energy device 1, according to the aspects, regulates application of energy and pressure to achieve an effective seal capable of withstanding high burst pressures. The generator 2 can apply energy to tissue at constant current based on a current control curve. Energy application can be regulated by the controller 4 pursuant to an algorithm stored within the memory system 6. The algorithm can maintain energy supplied to the tissue at constant voltage. The algorithm can vary output based on the type of tissue being sealed. For instance, thicker tissue typically requires more power, whereas thinner tissue requires less power. Therefore, the algorithm adjusts the output based on tissue type by modifying specific variables (e.g., voltage being maintained, duration of power application etc.). In aspects, the algorithm can adjust the output based on jaw angle.

[0063] Various conditions can be detected as parameters. For example, the controller 4 can sense tissue impedance with an interrogatory impedance sensing pulse. Tissue impedance can be determined without appreciably changing the tissue. The cumulative (i.e., net amount) of energy delivered to the tissue during the sealing procedure may be determined. Further performance parameters can be determined, for example, that correspond to the maximum energy delivery rate, minimum energy delivery rate, and an average energy delivery rate. Thermal properties related to the tissue may also be sensed, recorded and / or computed during a sealing process. Such properties may include, without limitation, total thermal energy sensed, which may be expressed as the sensed temperature integrated over the time of the procedure, maximum tissue temperature, minimum tissue temperature, and average tissue temperature. Fluid properties, e.g., a total quantity of fluid, may be expressed as a sensed quantity of fluid integrated over the time of the procedure, a maximum fluid quantity, a minimum fluid quantity, an average fluid quantity of fluid.A0013614WO01 (MD80180PCT)

[0064] Application of RF energy can be initiated by delivering current linearly over time to heat the tissue. RF energy may be delivered in a non-linear or in a time-independent step manner from zero to an “on” state. Delivery may be controlled through other parameters such as voltage and / or power and / or energy. Once initiated, the ramping of energy can continues until one of two events occurs: 1) the maximum allowable value is reached or 2) the tissue “reacts.” The term “tissue reaction” is a point at which intracellular and / or extra-cellular fluid begins to boil and / or vaporize, resulting in an increase in tissue impedance. In the case when the maximum allowable value is reached, the maximum value is maintained until the tissue “reacts.” In the event that the tissue reacts prior to reaching the maximum value, the energy required to initiate a tissue “reaction” has been attained and the controller 4 can transition to an impedance control state. Tissue reaction during heating may be indicated as a change in impedance with respect to time.

[0065] Rather than relying on specific limits and fixed algorithms to detect specific conditions, aspects can use machine learning to identify conditions and map the conditions to insights to be provided to the actor 112 of FIG.1, as further described herein.

[0066] FIG.6 depicts a block diagram 400 of parameter processing and models according to one or more aspects. One or more models 402 can include insight models 402A, 402B, 402C, … 402N (where N represents an arbitrary number). The insight models 402A, 402B, 402C, … 402N can be trained to generate respective insights 404A, 404B, 404C, … 404N (where N represents an arbitrary number) based on detecting conditions in performance parameters 405. The performance parameters 405 can include a combination of sensed and derived values based on parameter processing 410 performed on a plurality of parameters 412. For example, parameters 412 can be sensed impedance, voltage, current, temperature, energy, power, position / angle, and other such values observed by sensor circuitry 11 of FIG.5 or otherwise determined by controller 4 of FIG.5. The parameter processing 410 can include various calculations which may blend / filter values, identify maximum / minimum values, decompose complex values into real and imaginary components, and / or other such analysis. For example, the parameter processing 410 can determine one or more characteristics of energy output of the RF output stage 8 of FIG.5 as one or more of: a root mean square (RMS) value 420, an average value 422, a peak value 424, a magnitude value 426, and a phase value 428. In some aspects a mode 414 can also be used to determine how the parameter processing 410 should generate and / or pass the performance parameters 405 to the models 402. The mode 414 can also be used to select specific instances of the models 402 to run in real-time operation. For example, some of the insights 404A-404N may be relevant in a spray mode while others may be relevant in a vesselA0013614WO01 (MD80180PCT) sealing mode. Other such constraints can also be used to limit which of subset of the performance parameters 405 should be passed to specific instances of the models 402 and when the specific instances of the models 402 should be run reduce processor and memory utilization and reduce the chance of generating an insight at the wrong time.

[0067] In aspects, the parameter processing 410 and models 402 can be computed by the processing system 5 of FIG.5. In other aspects, portions of the parameter processing 410 and / or models 402 can be computed by another system, such as computing system 102 of FIG.1 or surgical procedure support system 202 of FIG.2.

[0068] FIG.7A depicts a user interface 500 with an alert according to one or more aspects. In the example of FIG.7A, the user interface 500 depicts a camera view of a surgical procedure, such as video captured by camera 105 or 204 of FIGS.1 and 2. The user interface 500 is an example of a laparoscopic video viewing interface and can depict interactions occurring between a surgical device 502 (such as forceps 10 of FIG.4) and tissue 503. As the models 402 receive the performance parameters 405 of FIG.6, one or more insights 404A-404N may be generated and sent for display on the user interface 500 as an alert 504. The models 402 can use device data observed through control and interaction with the surgical device 502 to generate one or more insights 404A-404N. This approach can be less computationally intensive than attempting to perform video-based analysis. In some aspects, video-based analysis can also be performed to determine which one of multiple insights 404A-404N has a highest confidence score if uncertainty exists between multiple possible insights 404A-404N.

[0069] The example of FIG.7A depicts a first example of an alert 504 based on detecting one or more conditions associated with suboptimal seal techniques in relation to tissue interaction during usage of an electrosurgical energy device. The alert 504 can include guidance in the form of a suggestion, such as, “Tissue Tension. Consider Repositioning”. Alternate tissue tension wording can be used, such as, “Tension Seal – Decrease Tension” or “Tissue tension. Consider repositioning before sealing.” As a further example, an alert may state, “Tissue under Tension Consider Repositioning” or simply, "Tissue under Tension”. FIGS.7B, 7C, and 7D depict further examples of detected conditions and associated alerts. While the examples and associated description of FIGS.7A-7D provide several specific examples, it will be understood that many variations in wording as well as types of alerts are contemplated beyond these examples.

[0070] FIG.7B depicts a user interface 510 as an example of a laparoscopic video viewing interface with interactions occurring between a surgical device 512 (such as a cutting tool) and tissue 513. Alert 514 is an example alert for jaws overfilled, where a smaller bite should beA0013614WO01 (MD80180PCT) considered. Other variations for too much tissue in jaws of the surgical device 512 can be included in the alert 514. For example, “Jaws Overstuffed”, “Jaws Overfilled”, or other similar variants can be incorporated into the alert 514.

[0071] FIG.7C depicts a user interface 520 as an example of a laparoscopic video viewing interface with interactions occurring between one or more surgical devices 522A, 522B (such as forceps and a cutting tool) and tissue 523. Alert 524 is an example alert for metal in jaws, such as metal 525. For instance, if the tissue 523 has been stapled, it may be preferable to perform certain actions, such as cutting or sealing, on a portion of the tissue 523 that does not include metal 525. Other variations for metal 525 in the jaws of one or more of the surgical devices 522A, 522B can be included in the alert 524. For example, “Short Circuit, Verify Seal” can be included in the alert 524, for instance, for an edge cut.

[0072] FIG.7D depicts a user interface 530 as an example of a laparoscopic video viewing interface with interactions occurring between one or more surgical devices 532A, 532B (such as forceps and a cutting tool) and tissue 533. Alert 534 is an example alert for a double seal with inadequate overlap. For instance, the tissue 533 proximate to one or more of surgical devices 532A, 532B may be detected as inadequate for sealing based on one or more detected conditions. Other variations for resealing can be included in the alert 534. For example, “Reseal, Check Tissue Overlap” can be included in the alert 534.

[0073] Turning now to FIG.8, a flowchart of a method 600 for insight generation is generally shown in accordance with one or more aspects. All or a portion of method 600 can be implemented, for example, by the system 300 of FIG.3, controller 4 of FIG.5, and / or computer system 800 of FIG.10, using aspects of the CAS system 100 of FIG.1 and / or surgical procedure system 200 of FIG.2. For example, the machine learning training system 325 of FIG.3 can be used to train the models 402 of FIG.6.

[0074] At block 602, monitoring a plurality of performance parameters 405 of an electrosurgical energy device 1 can be performed during a surgical procedure. At block 604, the performance parameters 405 can be provided to one or more models 402, such as insight models 402A-402N, trained to detect one or more conditions based on at least a subset of the performance parameters 405. The one or more conditions can be associated with a technique or tissue interaction during usage of the electrosurgical energy device 1. Further, the one or more conditions can be associated with an outcome of using the electrosurgical energy device 1. For example, machine learning models can detect conditions other than a suboptimal seal, such as contextual labels (e.g., tissue thickness, blood vessels, critical structures proximity), seal outcomeA0013614WO01 (MD80180PCT) information (e.g., seal quality) and / or standard technique labels (e.g., jaw position, instrument orientation, tip sealing). At block 606, an insight, such as insight 404A-404N, can be generated based on detection of at least one of the one or more conditions. At block 608, an alert, such as alert 504, associated with the insight can be output during the surgical procedure.

[0075] According to some aspects, the method 600 can include tracking an occurrence of the one or more conditions as an event for post-operative review and populating an electronic medical record with an indication of the event. For instance, the event may be captured as part of the data collection system 150 of FIG.1 for subsequent use in combination with other events observed during a surgical procedure. Event data can be summarized and tracked through the surgical data post-processing system 250 of FIG.2. Insights generated by insight models 402A- 402N can be viewed and tracked through the surgical data insight viewer 240 of FIG.2, which may collect insights from multiple sources in addition to the insight models 402A-402N.

[0076] In some aspects, the alert can be output as a visual indicator on a display. For instance, the visual indicator can include a text overlay with the insight on a laparoscopic video viewing interface. Further, the visual indicator can be transmitted to a remote system in a live stream.

[0077] In some aspects, the electrosurgical energy device 1 can include a generator 2 and a vessel sealing device, such as forceps 10, powered by an energy output of the generator 2. The performance parameters 405 can be associated with one or more characteristics of the energy output and operation of the vessel sealing device. As an example, the one or more conditions can be indicative of one or more of: applying tension during a seal using the vessel sealing device, overstuffing jaws of the vessel sealing device, resealing (e.g., double / triple sealing) of tissue with overlap below a threshold level (e.g., insufficient overlap), and / or sealing with metal in jaws of the vessel sealing device. A further example is an edge cutting condition. Additional examples can include thermal-based properties, such as overheating of instruments leading to a risk of tissue burns and / or surgical fires. Further, the one or more characteristics of the energy output can include one or more of: an RMS value 420, an average value 422, a peak value 424, a magnitude value 426, and a phase value 428. While multiple examples have been listed herein for purposes of explanation, it will be understood that further additions, modifications, combinations, and / or subdivisions of conditions are contemplated for corresponding alerts beyond the examples specifically listed above or below.

[0078] In some aspects, a mode 414 of the electrosurgical energy device 1 can be determined. At least one of the one or more models 402 for insight determination can be selected based on the mode 414.A0013614WO01 (MD80180PCT)

[0079] The processing shown in FIG.8 is not intended to indicate that the operations are to be executed in any particular order or that all of the operations shown in FIG.8 are to be included in every case. Additionally, the processing shown in FIG.8 can include any suitable number of additional operations.

[0080] In some aspects, a system, such as controller 4 of FIG.5 can include a memory system, such as memory system 6, and a processing system, such as processing system 5. The processing system can be coupled to the memory system and configured to execute instructions to perform a plurality of operations. The operations can include monitoring a plurality of performance parameters 405 of a surgical device during a surgical procedure and providing the performance parameters 405 to one or more models 402 trained to detect one or more conditions based on at least a subset of the performance parameters 405. The one or more conditions can be associated with a technique or interaction during usage of the surgical device. Further, the one or more conditions can be associated with an outcome of using the surgical device. For example. The operations can further include generating an insight, such as insights 404A-404N, based on detection of at least one of the one or more conditions and outputting an alert, such as alert 504, associated with the insight.

[0081] In some aspects, the surgical device can be an electrosurgical energy device 1 including a generator 2 and a vessel sealing device, such as forceps 10, powered by an energy output of the generator 2. The processing system 5 can be within the controller 4 of the generator 2. In some aspects, the generator 2 can include a power supply 7, a RF output stage 8 configured to generate the energy output based on the power supply 7, and sensor circuitry 11 configured to detect one or more parameters 412 used to determine the performance parameters 405.

[0082] In some aspects, the alert can include one or more of: a visual indicator, an audio indicator, and / or a haptic feedback indicator. Where a visual indicator is used, the alert can be transmitted, for example, to a laparoscopic video viewing interface for display in real-time during a surgical procedure. The alert can be provided to one or more of: a surgical data post-processing system 250 and / or a surgical data insight viewer 240 of FIG.2.

[0083] Turning now to FIG.9, a flowchart of a method 700 for training models for insight generation is generally shown in accordance with one or more aspects. All or a portion of method 600 can be implemented, for example, by the system 300 of FIG.3, controller 4 of FIG. 5, and / or computer system 800 of FIG.10, using aspects of the CAS system 100 of FIG.1 and / or surgical procedure system 200 of FIG.2. For example, the machine learning training system 325 of FIG.3 can be used to train the models 402 of FIG.6.A0013614WO01 (MD80180PCT)

[0084] At block 702, processing a plurality of performance parameters 405 of an electrosurgical energy device 1 can be performed to generate a set of training data, for instance, as part of the data generator 315 populating data store 320. At block 704, one or more models 402 can be trained, for instance as trained machine learning models 330, to detect one or more conditions based on the set of training data. At block 706, the machine learning training system 325 can determine which of the performance parameters 405 have a greater impact on the one or more models 402. At block 708, a subset of the performance parameters 405 having the greater impact can be provided to the one or more models 402 for real-time detection of the one or more conditions and generation of an insight. For instance, there may be dozens of performance parameters 405 generated by parameter processing 410, and the training process can identify a subset of relevant performance parameters on a per-model basis to prevent each of the insight models 402A-402N from attempting to process all of the performance parameters 405 in real time.

[0085] According to some aspects, determining which of the performance parameters 405 have the greater impact on the one or more models 402 can include training the one or more models 402 with two or more combinations of the performance parameters 405 and testing an accuracy of the trained versions of the one or more models 402 to identify which of the two or more combinations results in a higher accuracy.

[0086] In some aspects, determining which of the performance parameters 405 have the greater impact on the one or more models 402 can include determining an association between the mode 414 of the electrosurgical energy device 1 and the one or more conditions and selecting the subset of the performance parameters 405 based on the mode 414.

[0087] In some aspects, the electrosurgical energy device 1 can include a generator 2 and a vessel sealing device, such as forceps 10, powered by an energy output of the generator 2, and the performance parameters 405 can be associated with one or more characteristics of the energy output and operation of the vessel sealing device. In some aspects, the one or more conditions are indicative of one or more of: applying tension during a seal using the vessel sealing device, overstuffing jaws of the vessel sealing device, resealing (e.g., double / triple sealing) of tissue with insufficient overlap, and sealing with metal in jaws of the vessel sealing device.

[0088] The processing shown in FIG.9 is not intended to indicate that the operations are to be executed in any particular order or that all of the operations shown in FIG.9 are to be included in every case. Additionally, the processing shown in FIG.9 can include any suitable number of additional operations.A0013614WO01 (MD80180PCT)

[0089] Turning now to FIG.10, a computer system 800 is generally shown in accordance with an aspect. The computer system 800 can be an electronic computer framework comprising and / or employing any number and combination of computing devices and networks utilizing various communication technologies, as described herein. The computer system 800 can be easily scalable, extensible, and modular, with the ability to change to different services or reconfigure some features independently of others. The computer system 800 may be, for example, a server, desktop computer, laptop computer, tablet computer, or smartphone. In some examples, computer system 800 may be a server that is administered by a 3rdparty, a cloud computing node, or other such computing resources. Computer system 800 may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, and so on that perform particular tasks or implement particular abstract data types. Computer system 800 may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media, including memory storage devices.

[0090] As shown in FIG.10, the computer system 800 has one or more central processing units (CPU(s)) 801a, 801b, 801c, etc. (collectively or generically referred to as processor(s) 801). The processors 801 can be a single-core processor, multi-core processor, computing cluster, or any number of other configurations. The processors 801 can be any type of circuitry capable of executing instructions. The processors 801, also referred to as processing circuits, are coupled via a system bus 802 to a system memory 803 and various other components. The system memory 803 can include one or more memory devices, such as read-only memory (ROM) 804 and a random-access memory (RAM) 805. The ROM 804 is coupled to the system bus 802 and may include a basic input / output system (BIOS), which controls certain basic functions of the computer system 800. The RAM is read-write memory coupled to the system bus 802 for use by the processors 801. The system memory 803 provides temporary memory space for operations of said instructions during operation. The system memory 803 can include random access memory (RAM), read-only memory, flash memory, or any other suitable memory systems.

[0091] The computer system 800 comprises an input / output (I / O) adapter 806 and a communications adapter 807 coupled to the system bus 802. The I / O adapter 806 may be a small computer system interface (SCSI) adapter that communicates with a hard disk 808 and / or anyA0013614WO01 (MD80180PCT) other similar component. The I / O adapter 806 and the hard disk 808 are collectively referred to herein as a mass storage 810.

[0092] Software 811 for execution on the computer system 800 may be stored in the mass storage 810. The mass storage 810 is an example of a tangible storage medium readable by the processors 801, where the software 811 is stored as instructions for execution by the processors 801 to cause the computer system 800 to operate, such as is described hereinbelow with respect to the various Figures. Examples of computer program product and the execution of such instruction is discussed herein in more detail. The communications adapter 807 interconnects the system bus 802 with a network 812, which may be an outside network, enabling the computer system 800 to communicate with other such systems. In one aspect, a portion of the system memory 803 and the mass storage 810 collectively store an operating system, which may be any appropriate operating system to coordinate the functions of the various components shown in FIG.10.

[0093] Additional input / output devices are shown as connected to the system bus 802 via a display adapter 815 and an interface adapter 816 and. In one aspect, the adapters 806, 807, 815, and 816 may be connected to one or more I / O buses that are connected to the system bus 802 via an intermediate bus bridge (not shown). A display 819 (e.g., a screen or a display monitor) is connected to the system bus 802 by a display adapter 815, which may include a graphics controller to improve the performance of graphics-intensive applications and a video controller. A keyboard, a mouse, a touchscreen, one or more buttons, a speaker, etc., can be interconnected to the system bus 802 via the interface adapter 816, which may include, for example, a Super I / O chip integrating multiple device adapters into a single integrated circuit. Suitable I / O buses for connecting peripheral devices such as hard disk controllers, network adapters, and graphics adapters typically include common protocols, such as the Peripheral Component Interconnect (PCI). Thus, as configured in FIG.10, the computer system 800 includes processing capability in the form of the processors 801, and storage capability including the system memory 803 and the mass storage 810, input means such as the buttons, touchscreen, and output capability including the speaker 823 and the display 819.

[0094] In some aspects, the communications adapter 807 can transmit data using any suitable interface or protocol, such as the internet small computer system interface, among others. The network 812 may be a cellular network, a radio network, a wide area network (WAN), a local area network (LAN), or the Internet, among others. An external computing device may connect to the computer system 800 through the network 812. In some examples, an external computing device may be an external web server or a cloud computing node.A0013614WO01 (MD80180PCT)

[0095] It is to be understood that the block diagram of FIG.10 is not intended to indicate that the computer system 800 is to include all of the components shown in FIG.10. Rather, the computer system 800 can include any appropriate fewer or additional components not illustrated in FIG.10 (e.g., additional memory components, embedded controllers, modules, additional network interfaces, etc.). Further, the aspects described herein with respect to computer system 800 may be implemented with any appropriate logic, wherein the logic, as referred to herein, can include any suitable hardware (e.g., a processor, an embedded controller, or an application- specific integrated circuit, among others), software (e.g., an application, among others), firmware, or any suitable combination of hardware, software, and firmware, in various aspects. Various aspects can be combined to include two or more of the aspects described herein.

[0096] Various advantages can be captured through identification of seal conditions and types created using an electrosurgical energy device. Seal types and conditions can include, but are not limited to, baseline conditions, overstuffing of jaws of the electrosurgical energy device, a reseal / double seal with overlap below a threshold level (i.e., inadequate overlap), and a high tension seal. Identifying seal conditions and types without use of machine learning models would require complex rules created from extensive analysis of data sets. In contrast, a machine learning model can be trained to determine an optimal set of boundaries that can more quickly and reliably distinguish among conditions and types.

[0097] FIG.11 depicts a flow diagram of a model 1100 for predicting operating conditions associated with usage of an electrosurgical energy device according to one or more aspects. The model 1100 is an example of one of the one or more models 402 of FIG.6. In the example of FIG.11, the model 1100 is a machine learning model (e.g., machine learning model 330 of FIG. 3), such as a neural network. The machine learning model can be trained using training data that may be labeled or partially labeled. Resulting weights from the training can be applied to nodes of the model 1100 to produce a combination of predictions, such as whether an overstuff, reseal with insufficient overlap, or tension condition is likely occurring based on input data 1102. As one example, the input data 1102 can be groups of time samples for impedance and multiple phases of applying power to an electrosurgical energy device, such as the electrosurgical energy device 1 of FIG.4. As one example, groups of about 20 time samples per input can be pre- processed to produce flattened and normalized features 1104. As one example, 4 groups of 20 time samples can be flattened and normalized into 80 features. Principal component analysis can be applied to identify principal components 1106 of the flattened and normalized features 1104. Principal component analysis can reduce the dimensions of the data, such as reducing the flattened and normalized features 1104 from 80 features down to about 30 components.A0013614WO01 (MD80180PCT) Principal component analysis may include, for instance, mean subtraction, covariance matrix computation, eigenvector and eigenvalue computation, principal component selection from eigenvectors and eigenvalues, dimension reduction through variance projection, for example. The principal components 1106 can be provided to a neural network of the model 1100, passing through a plurality of hidden layers 1108, an encoding layer 1110, and a classifier 1112. The classifier 1112 can use logistic regression for example, to classify whether the input data 1102 is likely indicating an overstuff condition, a reseal with insufficient overlap condition, a tension condition, or none of the conditions. Output of the classifier 1112 can be as scaled probabilities or prediction values, for instance, ranging between 0 and 1, where a higher value indicates a higher likelihood of an association condition being identified. For instance, a value greater than 0.5 indicates a likelihood of a condition being identified, while a higher value (e.g., > 0.7) indicates a greater likelihood of the condition being identified. Through training with ground truth data, such as clinical data with thousands of activations, the weights of the model 1100 can be tuned to minimize a cost function, or maximize an objective function, which may take the form of a metric that describes errors of binary classification (e.g., precision, recall, accuracy), or it may take the form of a metric that describes the error in estimating a continuous variable (e.g., Mean-squared error, log-likelihood, etc.).. For instance, a portion of clinical data can be used for training (e.g., about 80%) and a smaller portion of unlabeled clinical data (e.g., about 20%) can be used to test the performance of the model 1100. The same data can also be tested against rules / thresholds to compare performance for detecting various conditions and to select a best performing approach.

[0098] Some aspects may be trained through a separate model that is tuned to different parameters, such as metal-in-jaws seals, which may have a resulting signature short circuit. Once trained, a model for metal-in-jaws may identify such conditions and issue an alert earlier in a procedure, which may prevent subsequent problems that would not otherwise be identified until later in the activation / cooking process. For instance, signature features may include a current above a threshold level, a low (e.g., near-zero) impedance, and power below a target power (e.g., a negative power value). The sampling and detection rate of various models can differ depending on data availability, processing capacity, and response time to detect specific conditions. Various models can be implemented using one or more processing resources depending on capacity, inputs needed, and latency requirements.

[0099] Machine learning models can be trained to generate a variety of annotations that may be available depending on model input availability. Examples of model inputs can include energy platform settings, radio frequency data, video features, robot logs, robot control inputs,A0013614WO01 (MD80180PCT) robot kinematics, energy platform sensors (e.g., tension, temperature, hyperspectral, jaw aperture, jaw force, and gyros for device position, location, and movement, etc.), operator voice, voice controls, and / or other such inputs. Models developed can be calibrated using model parameters optimized for characteristics, such as instrument type, patient parameters (e.g., vessels in relation to fat or anatomical structures), instrument orientation, environment type, and tissue type. In some aspects, datasets used for training and testing can include forward RF data (e.g., RF energy) simulation with finite element modeling and / or Monte Carlo modelling. RF data used for training and testing may also be augmented using cluster infilling, for example. RF data featurization approaches can include, for instance, raw time samples, selective sampling, feature engineering, non-linear warping, and / or decomposition using principal component analysis, functional principal component analysis, auto-encoders, etc. Machine learning techniques can include, for example, long short-term memory, gated recurrent units, transformers, convolutional neural networks on RF spectrograms, multi-branch encodings, supervised shallow learning, decision trees, logistic classification, support vector machines, and / or other such techniques. The models can run continuously, at key points in a cycle (e.g., when power rises above a threshold level, before the end of a cycle, before cutting, etc.), in a predetermined surgical phase, and / or at the end of a cycle.

[0100] In some aspects, annotations produced by models can be directed to various techniques or events. Examples include overstuffed jaws, tension, upward tension, sideways tension, metal in jaw, foreign object in jaw, out of view activation, hinge seal (e.g., tissue in jaw hinge), partial vessel bite (e.g., jaw misses part of vessel during seal), tissue sticking, eschar build up, reseal (e.g., double, triple seal) with overlap below a threshold level (i.e., inadequate overlap), seal with small gap, device overheating, mismatched seal type with tissue type, etc. Models can be used to confirm that a standard technique is being used, such as performing a tip seal, jaw positioning of tissue, instrument orientation, etc. Model annotations can be trained to identify context, such as tissue thickness, environment type (e.g., bloody, saline, etc.), tissue type, vessel visible in activation, proximity to critical structures, and / or other such context. Models may also be trained to generate annotations related to seal outcomes and complications, such as major post-activation bleeding, minor post-activation bleeding, edge cut, smoke detection from overheating, instrument glow, surgical fire, accidental cutting of foreign objects (e.g., plastics, implants, etc.), seal burst, accidental dissection of critical anatomy, seal quality indication, and / or other such annotations.

[0101] FIGS.12A, 12B, and 12C depict system configuration examples according to one or more aspects. In the example of FIG.12A, system 1200 includes an energy platform 1202 (e.g., generator 2 of FIG.4) including one or more processing resources 1204 (e.g., processor / A0013614WO01 (MD80180PCT) processing circuitry / CPU) that can locally execute one or more models (e.g., AI / machine- learning models). As alert conditions are identified by the processing resources 1204 executing one or more models, corresponding alerts 1206 can be output, such as an audio or visual alert.

[0102] In the example of FIG.12B, a system 1220 can include the energy platform 1202 with processing resources 1204 that can locally execute one or more models. The energy platform 1202 can interface with a display 1222 to visually indicate alerts. The display 1222 can be a robotic display or a laparoscopic display, for example, and may also support audio alerts. The energy platform 1202 can also interface with an external computer 1224 to provide alerts and associated data. The external computer 1224 may combine data from multiple sources, such as a surgical robot 1226, electronic medical records 1228, and a video feed 1230 of a surgical procedure. Data collected by the external computer 1224 can be sent to cloud-based processing resources 1232, which may apply one or more AI models trained to generate insights from the combination of data sources (e.g., data from the energy platform 1202 surgical robot 1226, electronic medical records 1228, and / or video feed 1230) and provide portions of the data sources and associated insights to web and / or mobile platforms 1234 (e.g., computing devices 234, 264 of FIG.2). Insights generated by the external computer 1224 may be non-real-time insights used for time delayed or post-operative analysis.

[0103] In the example of FIG.12C, a system 1240 can include the energy platform 1202 with processing resources 1204 that can perform signal preprocessing, such as flattening and normalization and / or principal component analysis but may not execute a complete model. The energy platform 1202 can interface with an external computer 1224 that may execute one or more models to provide alerts and associated data. The external computer 1224 can interface with a display 1222 to visually indicate alerts and / or visually output data from various sources. The display 1222 can be a robotic display or a laparoscopic display, for example, and may also support audio alerts. The external computer 1224 may combine data from multiple sources, such as a surgical robot 1226, electronic medical records 1228, and a video feed 1230 of a surgical procedure. Data collected by the external computer 1224 can be sent to cloud-based processing resources 1232, which may apply one or more AI models trained to generate insights from the combination of data sources (e.g., data from the energy platform 1202 surgical robot 1226, electronic medical records 1228, and / or video feed 1230) and provide portions of the data sources and associated insights to web and / or mobile platforms 1234 (e.g., computing devices 234, 264 of FIG.2). Insights generated by the external computer 1224 may be non-real-time insights used for time delayed or post-operative analysis.A0013614WO01 (MD80180PCT)

[0104] In some aspects, the data received by the web and / or mobile platforms 1234 can be in real-time or near real-time such that remote participants can interact with users of the energy platform 1202 through live streaming video. The live streaming video can allow remote users to view the video feed 1230 and other content that may be visible on the display 1222. For example, alerts, such energy device activation, device settings, energy and activation time at seal completion, technique warnings and recommendations, warnings based on likelihood of accidental dissection / surgical fire, recommendations on how to proceed based on environment and / or patient, warnings based on seal quality or edge cuts, and / or other such warnings can appear both as an inter-operative screen on the display 1222 and be visible on a remote display of the web and / or mobile platforms 1234. For example, a proctor using the web and / or mobile platforms 1234 can use the model provided feedback with the video feed 1230 to provide real- time suggestions and feedback to a user of the energy platform 1202 using audio, video, telestration, and / or text-based chat. In some aspects, alerts and information may only be visible on the display 1222 or may only be displayed to a user of the web and / or mobile platforms 1234. For instance, insights generated by cloud-based processing resources 1232 may be displayed to a user of the web and / or mobile platforms 1234, and the user of the web and / or mobile platforms 1234 can selective share insights back to a user of the energy platform 1202 to minimize distractions during the surgical procedure. Where live streaming is used, a summary of events may be recorded during the surgical procedure and made available for review upon a new user joining a live stream. When used for teaching, the insights generated by cloud-based processing resources 1232 may be displayed along with related data to illustrate how the surgical procedure in progress compares with previous procedures or best practices. Real-time details related to device settings, techniques, and outcomes can be shown to enhance learning experience and personalize feedback. Trainee views through the web and / or mobile platforms 1234 may differ from proctor views. For example, a trainee view may include techniques, explanations, and recommendations displayed in real-time to provide educational insights that may not be sent to the display 1222.

[0105] FIG.13 depicts a user interface 1300 of a surgical data insight viewer, such as the surgical data insight viewer 240 of FIG.2, that displays surgical videos and associated data according to one or more aspects. The user interface 1300 for viewing a surgical case video and performance data analytics can be generated by the surgical data insight viewer 240. Performance data analytics can be determined by the surgical data insight viewer 240, surgical data post-processing system 250, and / or other components of the surgical procedure support system 202 of FIG.2. In some aspects, the surgical data insight viewer 240 can display a representative frame of a surgical case video in a video viewing region 1302 of the user interfaceA0013614WO01 (MD80180PCT) 1300 based on receiving a selection of the surgical case video. The surgical data insight viewer 240 can display a performance region 1304 in the user interface 1300, where the performance region 1304 is configured to display performance data associated with one or more surgical cases. The performance region 1304 can include a selection control 1310 to toggle between views, such as activations and alarms, for example. The activations can be summarized in records that can identify a timestamp in a corresponding surgical video in the video viewing region 1302 along with data such as an activation time, duration, channel, mode, tissue thickness, total energy, surgical phase, and / or other such information. Selection of a particular activation record can result in playback of the video in the video viewing region 1302 jumping to the associated timestamp. Alarms can summarize when one or more models detect conditions, such as metal-in-jaws, overstuffed jaws, high seal tension, and / or double-seal events with insufficient overlap. The user interface 1300 can also include other information and interactive controls. For example, a summary region 1320 can document a procedure name, surgeons active in the case, a date, sharing, download, and timelines 1324. The timelines 1324 can include an auto-phase that identifies portions of the surgical case video where particular surgical phases have been identified to occur, surgical tools, anatomy, activations, alarms, and other such information. A slider 1326 can be user selectable to move the current play time of the surgical case video displayed in the video viewing region 1302 forward or backward in time. Performance summary information can be displayed through the user interface 1300 and more detailed performance summaries can be displayed through a separate user interface.

[0106] In some aspects, the user interface 1300 can allow users to explore activation events to view associated data, video, and event timelines. Users can jump to desired events by selecting an event listing from the performance region 1304. Further, users can move the slider 1326 to fast-forward, rewind, or jump to a portion of the surgical video of interest. Clicking on the timelines 1324 can also allow a user to jump to a corresponding portion of the surgical video. Aspects of the performance region 1304, such as highlighting, may change to illustrate that a portion of the surgical video currently being displayed in the video viewing region 1302 corresponds to an event record in the performance region 1304.

[0107] Video clips can be extracted from surgical videos that illustrate events or alerts. The video clips can be managed as part of a training video library to allow users to search for and view video clips identified as best practices, sub-optimal practices, or cases for review by experts. Viewers of videos and / or video clips can record comments and provide feedback as text associated with particular events, timestamps, video clips, or complete videos. Further, reviewers can add recommendations as text or links of relevant training materials to be viewed.A0013614WO01 (MD80180PCT) Training materials can also include simulations, documentation guides, proctored videos / clips that illustrate best practice / optimal seal techniques, for example. Recommendations can be based on similar case parameters, such as procedure type, patient, environment, equipment, and the like.

[0108] FIG.14 depicts a user interface 1400 of a surgical data insight viewer that displays usage analysis for a plurality of surgical videos according to one or more aspects. The user interface 1400 for viewing usage analysis can be generated by the surgical data insight viewer 240 of FIG.2, for example. In the example of FIG.14, the user interface 1400 can display energy platform analysis associated with activations and alarms observed over multiple surgical procedures using an electrosurgical energy device, such as the electrosurgical energy device 1 of FIG.4. Various user interactive charts can be displayed as part of the user interface 1400, such as a chart of total seals 1402 (e.g., a percentage or fraction of successful vs. total seals), a phase breakdown chart 1404 that identifies surgical phases where seals were performed, a total energy chart 1406 that displays energy usage with respect to time / procedures, an alarm chart 1408 that indicates a number and type of sub-optimal seals identified by one or more models, a trend chart 1410 that summarizes procedure time vs. time, and insights 1412. The insights 1412 may be generated, for example, using generative artificial intelligence to write summary information into natural language sentences. The insights 1412 can identify strengths and areas of improvement as compared to the performance of others or expected performance thresholds. The summary data can be filtered for various parameters, such as procedure type, date ranges, users, groups of users, and other such information. Although one example of various charts is depicted in FIG. 14, it will be understood that many variations are possible. Further, the various charts and information displayed in user interface 1400 can be user selectable to add, remove, resize, and / or reformat the appearance of the charts and information displayed (e.g., table format vs. plot). Interactivity can include an option to select case data associated with specific events or conditions, such as opening case data and video where a selected alert type was observed. Such a selection can open the user interface 1300 with the surgical video and associated data corresponding to the selected case. Further, summary data can be output in report files in various formats.

[0109] In some aspects, analytics can include case level analytics, aggregate analytics over a group of cases, usage patterns, learning curves / error rate trends, correlations of energy device usage with patient outcomes, metrics adjusted for case complexity, and / or other such information. Benchmark analytics can be selected to perform comparisons relative to peers, experts, or geographic regions (e.g., global). Furthermore, the user interface 1300 or 1400 canA0013614WO01 (MD80180PCT) support replay of analytics alongside of corresponding video or video segments. Personalized insights and recommendations can be incorporated into the insights 1412 and can be adjusted over time as new results are added through performance of subsequent surgical procedures.

[0110] FIG.15 depicts a flowchart of a method 1500 of analyzing and displaying surgical data and alert data associated with surgical videos according to one or more aspects. All or a portion of method 1500 can be implemented, for example, by the system 300 of FIG.3, controller 4 of FIG.5, computer system 800 of FIG.10 and / or systems 1200, 1220, 1240 of FIGS.12A-12C, using aspects of the CAS system 100 of FIG.1, surgical procedure system 200 of FIG.2, and / or model 1100 of FIG.11.

[0111] At block 1502, alert data associated with a surgical video can be accessed, where the alert data includes an insight associated with activation of an electrosurgical energy device, such as the electrosurgical energy device 1. The alert data can include records of one or more alarm conditions identified during a surgical procedure, for instance, by model 1100. At block 1504, the alert data with the surgical video can be displayed through a first user interface of a surgical data insight viewer, such as in video viewing region 1302 of the user interface 1300 and alarm information displayed in the performance region 1304 and / or timelines 1324. At block 1506, surgical data associated with a plurality of surgical videos can be analyzed including the alert data associated with one or more of the surgical videos, for instance by the surgical data insight viewer 240. At block 1508, a usage analysis can be displayed through a second user interface (e.g., user interface 1400) of the surgical data insight viewer that summarizes a plurality of performance parameters of activation of the electrosurgical energy device corresponding to the surgical videos and the alert data.

[0112] According to some aspects, the method 1500 can include where the alert data is determined by a model during a surgical procedure and timelines indicative of alerts and activation of the electrosurgical energy device are displayed with the surgical video in the first user interface.

[0113] According to some aspects, the method 1500 can include where the electrosurgical energy device includes a generator and a vessel sealing device powered by energy output of the generator and the surgical data is associated with one or more characteristics of the energy output and operation of the vessel sealing device. At least one of the one or more models can be executed by a processing resource of the generator or an external computer coupled to a display and the generator, such as external computer 1224.A0013614WO01 (MD80180PCT)

[0114] According to some aspects, the method 1500 can include where the one or more conditions are indicative of one or more of: applying tension during a seal using the vessel sealing device, overstuffing jaws of the vessel sealing device, resealing of tissue with insufficient overlap, and sealing with metal in jaws of the vessel sealing device.

[0115] According to some aspects, the method 1500 can include where the second user interface summarizes alerts associated with applying tension during a seal using the vessel sealing device, overstuffing jaws of the vessel sealing device, resealing of tissue with overlap below a threshold level (i.e., insufficient overlap), and sealing with metal in jaws of the vessel sealing device in the second user interface.

[0116] According to some aspects, the method 1500 can include populating electronic medical records (e.g., electronic medical records 1228) with automated notes associated with usage of an electrosurgical energy device, such as the electrosurgical energy device 1 of FIG.1. Examples of automated operative notes can include text indicating field conditions, patient parameters, and / or settings of the electrosurgical energy device. Further examples can include text describing complications related to usage of the electrosurgical energy device. Additional examples, can include video clips showing complications related to usage of the electrosurgical energy device. For instance, the external computer 1224 and / or the cloud-based processing resources 1232 can execute one or more models trained to identify complications associated with activation and use of the energy platform 1202 and write the results back to the electronic medical records 1228. In some aspects, a generative artificial intelligence model can be used to generate natural language text to summarize detected conditions for documenting in the electronic medical records 1228.

[0117] The processing shown in FIG.15 is not intended to indicate that the operations are to be executed in any particular order or that all of the operations shown in FIG.15 are to be included in every case. Additionally, the processing shown in FIG.15 can include any suitable number of additional operations.

[0118] Aspects disclosed herein may be a system, a method, and / or a computer program product at any possible technical detail level of integration. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions thereon for causing a processor to carry out various aspects.

[0119] According to an aspect, a computer-implemented method is provided. The method includes monitoring a plurality of performance parameters of an electrosurgical energy device during a surgical procedure and providing the performance parameters to one or more modelsA0013614WO01 (MD80180PCT) trained to detect one or more conditions based on at least a subset of the performance parameters. The one or more conditions are associated a technique or tissue interaction during usage of the electrosurgical energy device. An insight is generated based on detection of at least one of the one or more conditions. An alert associated with the insight is output during the surgical procedure.

[0120] According to another aspect, a system includes a memory system and a processing system. The processing system is coupled to the memory system and configured to execute instructions to perform a plurality of operations. The operations include monitoring a plurality of performance parameters of a surgical device during a surgical procedure and providing the performance parameters to one or more models trained to detect one or more conditions based on at least a subset of the performance parameters. The one or more conditions are associated with a technique or an interaction during usage of the surgical device or an outcome of using the surgical device. The operations further include generating an insight based on detection of at least one of the one or more conditions and outputting an alert associated with the insight.

[0121] According to a further aspect, a computer program product is provided. The computer program product includes a memory device having computer executable instructions stored thereon, which when executed by one or more processors cause the one or more processors of a computing system to perform a plurality of operations. The operations can include accessing alert data associated with a surgical video. The alert data includes an insight associated with activation of an electrosurgical energy device. The computer-implemented method also includes displaying the alert data with the surgical video through a first user interface of a surgical data insight viewer and analyzing surgical data associated with a plurality of surgical videos including the alert data associated with one or more of the surgical videos. The computer-implemented method further includes displaying a usage analysis through a second user interface of the surgical data insight viewer that summarizes a plurality of performance parameters of activation of the electrosurgical energy device corresponding to the surgical videos and the alert data.

[0122] The computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer-readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer-readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random accessA0013614WO01 (MD80180PCT) memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device, such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer-readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0123] Computer-readable program instructions described herein can be downloaded to respective computing / processing devices from a computer-readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network, and / or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer- readable storage medium within the respective computing / processing device.

[0124] Computer-readable program instructions for carrying out operations of the present disclosure may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuitry, or either source-code or object code written in any combination of one or more programming languages, including an object-oriented programming language, such as Smalltalk, C++, high-level languages such as Python, or the like, and procedural programming languages, such as the “C” programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some aspects, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer-readable program instruction byA0013614WO01 (MD80180PCT) utilizing state information of the computer-readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0125] Aspects are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to aspects of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0126] These computer-readable program instructions may be provided to a processor of a computer system, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer-readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flowchart and / or block diagram block or blocks.

[0127] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer-implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0128] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various aspects. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchartA0013614WO01 (MD80180PCT) illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

[0129] The descriptions of the various aspects have been presented for purposes of illustration but are not intended to be exhaustive or limited to the aspects disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described aspects. The terminology used herein was chosen to best explain the principles of the aspects, the practical application or technical improvement over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the aspects described herein.

[0130] Various aspects are described herein with reference to the related drawings. Alternative aspects can be devised without departing from the scope of this disclosure. Various connections and positional relationships (e.g., over, below, adjacent, etc.) are set forth between elements in the following description and in the drawings. These connections and / or positional relationships, unless specified otherwise, can be direct or indirect, and the present disclosure is not intended to be limiting in this respect. Accordingly, a coupling of entities can refer to either a direct or an indirect coupling, and a positional relationship between entities can be a direct or indirect positional relationship. Moreover, the various tasks and process steps described herein can be incorporated into a more comprehensive procedure or process having additional steps or functionality not described in detail herein.

[0131] The following definitions and abbreviations are to be used for the interpretation of the claims and the specification. As used herein, the terms “comprises,” “comprising,” “includes,” “including,” “has,” “having,” “contains,” or “containing,” or any other variation thereof are intended to cover a non-exclusive inclusion. For example, a composition, a mixture, process, method, article, or apparatus that comprises a list of elements is not necessarily limited to only those elements but can include other elements not expressly listed or inherent to such composition, mixture, process, method, article, or apparatus.

[0132] Additionally, the term “exemplary” is used herein to mean “serving as an example, instance or illustration.” Any aspect or design described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other aspects or designs. The terms “at least one” and “one or more” may be understood to include any integer number greater than or equal to one, i.e., one, two, three, four, etc. The terms “a plurality” may be understood to include anyA0013614WO01 (MD80180PCT) integer number greater than or equal to two, i.e., two, three, four, five, etc. The term “connection” may include both an indirect “connection” and a direct “connection.”

[0133] The terms “about,” “substantially,” “approximately,” and variations thereof are intended to include the degree of error associated with measurement of the particular quantity based upon the equipment available at the time of filing the application. For example, “about” can include a range of ± 8% or 5%, or 2% of a given value.

[0134] For the sake of brevity, conventional techniques related to making and using aspects may or may not be described in detail herein. In particular, various aspects of computing systems and specific computer programs to implement the various technical features described herein are well known. Accordingly, in the interest of brevity, many conventional implementation details are only mentioned briefly herein or are omitted entirely without providing the well-known system and / or process details.

[0135] It should be understood that various aspects disclosed herein may be combined in different combinations than the combinations specifically presented in the description and accompanying drawings. It should also be understood that, depending on the example, certain acts or events of any of the processes or methods described herein may be performed in a different sequence, may be added, merged, or left out altogether (e.g., all described acts or events may not be necessary to carry out the techniques). In addition, while certain aspects of this disclosure are described as being performed by a single module or unit for purposes of clarity, it should be understood that the techniques of this disclosure may be performed by a combination of units or modules associated with, for example, a medical device.

[0136] In one or more examples, the described techniques may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media may include non-transitory computer- readable media, which corresponds to a tangible medium, such as data storage media (e.g., RAM, ROM, EEPROM, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer).

[0137] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), graphics processing units (GPUs), microprocessors, application- specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Accordingly, the term “processor” as used hereinA0013614WO01 (MD80180PCT) may refer to any of the foregoing structure or any other physical structure suitable for implementation of the described techniques. Also, the techniques could be fully implemented in one or more circuits or logic elements.

Claims

A0013614WO01 (MD80180PCT) CLAIMS What is claimed is:

1. A computer-implemented method comprising: monitoring a plurality of performance parameters (405) of an electrosurgical energy device (1) during a surgical procedure; providing the performance parameters (405) to one or more models (402) trained to detect one or more conditions based on at least a subset of the performance parameters (405), wherein the one or more conditions are associated with a technique or tissue interaction during usage of the electrosurgical energy device (1); generating an insight (404A-404N) based on detection of at least one of the one or more conditions; and outputting an alert (504, 514, 524, 534) associated with the insight (404A-404N) during the surgical procedure.

2. The computer-implemented method of claim 1, further comprising tracking an occurrence of the one or more conditions as an event for post-operative review and populating an electronic medical record with an indication of the event.

3. The computer-implemented method of claims 1 or 2, wherein the alert (504, 514, 524, 534) is output as a visual indicator on a display (819, 1222), and optionally wherein the visual indicator comprises a text overlay including the insight (404A-404N) on a laparoscopic video viewing interface, and the visual indicator is transmitted to a remote system in a live stream.

4. The computer-implemented method of any of claims 1 to 3, wherein the electrosurgical energy device (1) comprises a generator (2) and a vessel sealing device powered by an energy output of the generator (2); optionally wherein the performance parameters (405) are associated with one or more characteristics of the energy output and operation of the vessel sealing device, and at least one of the one or more models (402) is executed by a processing resource of the generator (2) or an external computer (1224) coupled to a display (819, 1222) and the generator (2); optionally, wherein the one or more conditions are indicative of one or more of: applying tension during a seal using the vessel sealing device, overstuffing jaws of the vessel sealingA0013614WO01 (MD80180PCT) device, resealing of tissue with overlap below a threshold level, and sealing with metal in jaws of the vessel sealing device; and optionally, wherein the one or more characteristics of the energy output comprise one or more of: a root mean square value, an average value (422), a peak value (424), a magnitude value (426), and a phase value (428).

5. The computer-implemented method of any of claims 1 to 4, further comprising: determining a mode (414) of the electrosurgical energy device (1); and selecting at least one of the one or more models (402) for insight determination based on the mode (414).

6. A system comprising: a memory system (6); and a processing system (5) coupled to the memory system and configured to execute instructions to perform a plurality of operations comprising: monitoring a plurality of performance parameters (405) of a surgical device (502, 512, 522A, 522B, 532A, 532B) during a surgical procedure; providing the performance parameters (405) to one or more models (402) trained to detect one or more conditions based on at least a subset of the performance parameters (405), wherein the one or more conditions are associated with a technique or an interaction during usage of the surgical device (502, 512, 522A, 522B, 532A, 532B) or an outcome of using the surgical device (502, 512, 522A, 522B, 532A, 532B); generating an insight (404A-404N) based on detection of at least one of the one or more conditions; and outputting an alert (504, 514, 524, 534) associated with the insight (404A-404N).

7. The system of claim 6, wherein the surgical device (502, 512, 522A, 522B, 532A, 532B) is an electrosurgical energy device (1) comprising a generator (2) and a vessel sealing device powered by an energy output of the generator (2), and the processing system (5) is within a controller (4) of the generator (2); and optionally wherein the generator (2) comprises a power supply (7), a radio frequency output stage (8) configured to generate the energy output based onA0013614WO01 (MD80180PCT) the power supply (7), and sensor circuitry (11) configured to detect one or more parameters (412) used to determine the performance parameters (405).

8. The system of claims 6 or 7, wherein the alert (504, 514, 524, 534) comprises one or more of: a visual indicator, an audio indicator, and a haptic feedback indicator.

9. The system of any of claims 6 to 8, wherein the alert (504, 514, 524, 534) is transmitted to a laparoscopic video viewing interface for display in real-time during the surgical procedure.

10. The system of any of claims 6 to 9, wherein the alert (504, 514, 524, 534) is provided to one or more of: a surgical data post-processing system (250), a surgical data insight viewer (240), and a remote system as a live stream.

11. A computer program product comprising a memory device having computer executable instructions stored thereon, which when executed by one or more processors (801) cause the one or more processors (801) of a computing system to perform a plurality of operations comprising: accessing alert data associated with a surgical video, wherein the alert data includes an insight (404A-404N) associated with activation of an electrosurgical energy device (1); displaying the alert data with the surgical video through a first user interface (1300) of a surgical data insight viewer (240); analyzing surgical data associated with a plurality of surgical videos including the alert data associated with one or more of the surgical videos; and displaying a usage analysis through a second user interface (1400) of the surgical data insight viewer (240) that summarizes a plurality of performance parameters (405) of activation of the electrosurgical energy device (1) corresponding to the surgical videos and the alert data.

12. The computer program product of claim 11, wherein the alert data is determined by a model (402) during a surgical procedure and timelines (1324) indicative of alerts (504, 514, 524, 534) and activation of the electrosurgical energy device (1) are displayed with the surgical video in the first user interface (1300).

13. The computer program product of claims 11 or 12, wherein the electrosurgical energy device (1) comprises a generator (2) and a vessel sealing device powered by an energy output of the generator (2) and the surgical data is associated with one or more characteristics of the energy output and operation of the vessel sealing device.A0013614WO01 (MD80180PCT) 14. The computer program product of claim 13, wherein the insight (404A-404N) is associated with of one or more of: applying tension during a seal using the vessel sealing device, overstuffing jaws of the vessel sealing device, resealing of tissue with overlap below a threshold level, and sealing with metal in jaws of the vessel sealing device.

15. The computer program product of claim 13, wherein the second user interface (1400) summarizes two or more alerts (504, 514, 524, 534) associated with applying tension during a seal using the vessel sealing device, overstuffing jaws of the vessel sealing device, resealing of tissue with overlap below a threshold level, and sealing with metal in jaws of the vessel sealing device in the second user interface (1400).

Images